From ca33bb71158a5a6804c61157d6fa47429afadcdd Mon Sep 17 00:00:00 2001 From: Isaac Mutie Date: Tue, 22 Jan 2019 11:08:15 +0300 Subject: [PATCH 01/43] add .gitignore list --- .gitignore | 1 + .idea/Python4ds_cohort-1.iml | 13 +++ .idea/misc.xml | 4 + .idea/modules.xml | 8 ++ .idea/vcs.xml | 6 ++ .idea/workspace.xml | 164 +++++++++++++++++++++++++++++++++++ notes.txt | 0 7 files changed, 196 insertions(+) create mode 100644 .gitignore create mode 100644 .idea/Python4ds_cohort-1.iml create mode 100644 .idea/misc.xml create mode 100644 .idea/modules.xml create mode 100644 .idea/vcs.xml create mode 100644 .idea/workspace.xml create mode 100644 notes.txt diff --git a/.gitignore b/.gitignore new file mode 100644 index 0000000..ae412d6 --- /dev/null +++ b/.gitignore @@ -0,0 +1 @@ +env/ \ No newline at end of file diff --git a/.idea/Python4ds_cohort-1.iml b/.idea/Python4ds_cohort-1.iml new file mode 100644 index 0000000..825118f --- /dev/null +++ b/.idea/Python4ds_cohort-1.iml @@ -0,0 +1,13 @@ + + + + + + + + + + + + \ No newline at end of file diff --git a/.idea/misc.xml b/.idea/misc.xml new file mode 100644 index 0000000..22be2d5 --- /dev/null +++ b/.idea/misc.xml @@ -0,0 +1,4 @@ + + + + \ No newline at end of file diff --git a/.idea/modules.xml b/.idea/modules.xml new file mode 100644 index 0000000..548426a --- /dev/null +++ b/.idea/modules.xml @@ -0,0 +1,8 @@ + + + + + + + + \ No newline at end of file diff --git a/.idea/vcs.xml b/.idea/vcs.xml new file mode 100644 index 0000000..94a25f7 --- /dev/null +++ b/.idea/vcs.xml @@ -0,0 +1,6 @@ + + + + + + \ No newline at end of file diff --git a/.idea/workspace.xml b/.idea/workspace.xml new file mode 100644 index 0000000..ddedad1 --- /dev/null +++ b/.idea/workspace.xml @@ -0,0 +1,164 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + @@ -93,7 +104,7 @@ - + @@ -124,13 +135,9 @@ - - + - - - - + @@ -138,6 +145,10 @@ + + + + @@ -162,10 +173,17 @@ + + + + + + + - - + + diff --git a/notebooks/.ipynb_checkpoints/Introduction-Ipython-checkpoint.ipynb b/notebooks/.ipynb_checkpoints/Introduction-Ipython-checkpoint.ipynb index abd761e..2e00b7f 100644 --- a/notebooks/.ipynb_checkpoints/Introduction-Ipython-checkpoint.ipynb +++ b/notebooks/.ipynb_checkpoints/Introduction-Ipython-checkpoint.ipynb @@ -38,7 +38,7 @@ }, { "cell_type": "code", - "execution_count": 3, + "execution_count": 5, "metadata": {}, "outputs": [], "source": [ @@ -56,6 +56,97 @@ "add??" ] }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## Error Handling and Debugging \n", + "This involves using Exception mode and python debugger to trace errors" + ] + }, + { + "cell_type": "code", + "execution_count": 1, + "metadata": {}, + "outputs": [], + "source": [ + "# A test function aimed at raising an exception\n", + "def calculate(x, y):\n", + " \"\"\" Return the quotient of x and y \"\"\"\n", + " return eval(x / y)" + ] + }, + { + "cell_type": "code", + "execution_count": 3, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Exception reporting mode: Plain\n", + "Automatic pdb calling has been turned ON\n" + ] + }, + { + "ename": "ZeroDivisionError", + "evalue": "division by zero", + "output_type": "error", + "traceback": [ + "Traceback \u001b[1;36m(most recent call last)\u001b[0m:\n", + " File \u001b[0;32m\"\"\u001b[0m, line \u001b[0;32m4\u001b[0m, in \u001b[0;35m\u001b[0m\n calculate(1, 0)\n", + "\u001b[1;36m File \u001b[1;32m\"\"\u001b[1;36m, line \u001b[1;32m4\u001b[1;36m, in \u001b[1;35mcalculate\u001b[1;36m\u001b[0m\n\u001b[1;33m return eval(x / y)\u001b[0m\n", + "\u001b[1;31mZeroDivisionError\u001b[0m\u001b[1;31m:\u001b[0m division by zero\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "> \u001b[1;32m\u001b[0m(4)\u001b[0;36mcalculate\u001b[1;34m()\u001b[0m\n", + "\u001b[1;32m 1 \u001b[1;33m\u001b[1;31m# A test function aimed at raising an exception\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", + "\u001b[0m\u001b[1;32m 2 \u001b[1;33m\u001b[1;32mdef\u001b[0m \u001b[0mcalculate\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mx\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0my\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", + "\u001b[0m\u001b[1;32m 3 \u001b[1;33m \u001b[1;34m\"\"\" Return the quotient of x and y \"\"\"\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", + "\u001b[0m\u001b[1;32m----> 4 \u001b[1;33m \u001b[1;32mreturn\u001b[0m \u001b[0meval\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mx\u001b[0m \u001b[1;33m/\u001b[0m \u001b[0my\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", + "\u001b[0m\n", + "ipdb> quit\n" + ] + } + ], + "source": [ + "# Turn Exception mode on to Plain and debugger then call the function\n", + "%xmode Plain\n", + "%pdb on\n", + "calculate(1, 0)" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## Timing and Profiling \n", + "`%timeit` and `%%timeit` to show execution time" + ] + }, + { + "cell_type": "code", + "execution_count": 6, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "3.71 µs ± 29.7 ns per loop (mean ± std. dev. of 7 runs, 100000 loops each)\n", + "range(0, 100)\n" + ] + } + ], + "source": [ + "%timeit sum(range(100))" + ] + }, { "cell_type": "code", "execution_count": null, diff --git a/notebooks/Introduction-Ipython.ipynb b/notebooks/Introduction-Ipython.ipynb index 7bfa89a..7672819 100644 --- a/notebooks/Introduction-Ipython.ipynb +++ b/notebooks/Introduction-Ipython.ipynb @@ -56,6 +56,96 @@ "add??" ] }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## Error Handling and Debugging \n", + "This involves using Exception mode and python debugger to trace errors" + ] + }, + { + "cell_type": "code", + "execution_count": 1, + "metadata": {}, + "outputs": [], + "source": [ + "# A test function aimed at raising an exception\n", + "def calculate(x, y):\n", + " \"\"\" Return the quotient of x and y \"\"\"\n", + " return eval(x / y)" + ] + }, + { + "cell_type": "code", + "execution_count": 3, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Exception reporting mode: Plain\n", + "Automatic pdb calling has been turned ON\n" + ] + }, + { + "ename": "ZeroDivisionError", + "evalue": "division by zero", + "output_type": "error", + "traceback": [ + "Traceback \u001b[1;36m(most recent call last)\u001b[0m:\n", + " File \u001b[0;32m\"\"\u001b[0m, line \u001b[0;32m4\u001b[0m, in \u001b[0;35m\u001b[0m\n calculate(1, 0)\n", + "\u001b[1;36m File \u001b[1;32m\"\"\u001b[1;36m, line \u001b[1;32m4\u001b[1;36m, in \u001b[1;35mcalculate\u001b[1;36m\u001b[0m\n\u001b[1;33m return eval(x / y)\u001b[0m\n", + "\u001b[1;31mZeroDivisionError\u001b[0m\u001b[1;31m:\u001b[0m division by zero\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "> \u001b[1;32m\u001b[0m(4)\u001b[0;36mcalculate\u001b[1;34m()\u001b[0m\n", + "\u001b[1;32m 1 \u001b[1;33m\u001b[1;31m# A test function aimed at raising an exception\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", + "\u001b[0m\u001b[1;32m 2 \u001b[1;33m\u001b[1;32mdef\u001b[0m \u001b[0mcalculate\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mx\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0my\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", + "\u001b[0m\u001b[1;32m 3 \u001b[1;33m \u001b[1;34m\"\"\" Return the quotient of x and y \"\"\"\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", + "\u001b[0m\u001b[1;32m----> 4 \u001b[1;33m \u001b[1;32mreturn\u001b[0m \u001b[0meval\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mx\u001b[0m \u001b[1;33m/\u001b[0m \u001b[0my\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", + "\u001b[0m\n", + "ipdb> quit\n" + ] + } + ], + "source": [ + "# Turn Exception mode on to Plain and debugger then call the function\n", + "%xmode Plain\n", + "%pdb on\n", + "calculate(1, 0)" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## Timing and Profiling \n", + "`%timeit` and `%%timeit` to show execution time" + ] + }, + { + "cell_type": "code", + "execution_count": 11, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "4.13 µs ± 452 ns per loop (mean ± std. dev. of 7 runs, 100000 loops each)\n" + ] + } + ], + "source": [ + "%timeit sum(range(100))" + ] + }, { "cell_type": "code", "execution_count": null, diff --git a/notes.txt b/notes.txt index c67a6a7..29e4514 100644 --- a/notes.txt +++ b/notes.txt @@ -1,8 +1,18 @@ - ### Magical commands ### -- Preceded by %(for single-line commands) or %%(For multiline) -# %paste - -- Paste copied code on Ipython without syntax errors -# %cpaste - -- Paste multiple copied codes. '--' alone or Ctrl-D to stop. -# %run - -- Run s python script in Ipython shell. The run script will be available for use in the cells. \ No newline at end of file +### Magical commands ### + - Preceded by %(for single-line commands) or %%(For multiline) + # %paste + -- Paste copied code on Ipython without syntax errors + # %cpaste + -- Paste multiple copied codes. '--' alone or Ctrl-D to stop. + # %run + -- Run s python script in Ipython shell. The run script will be available for use in the cells. + + +### ERROR DEBUGGING ### + %xmode will switch to Exception mode. It can either be Plain, Context(default) and Verbose.(In order of detailness) + %debug to launch debug mode + E.g + %xmode Plain + %pdb on + func(args) + From 6ff31e3df2d1503658ca427025b182a9ff33701f Mon Sep 17 00:00:00 2001 From: Isaac Mutie Date: Tue, 22 Jan 2019 16:51:29 +0300 Subject: [PATCH 04/43] Edit log.md --- .idea/workspace.xml | 51 +++++++++++++++++++++++---------------------- log.md | 7 +++---- 2 files changed, 29 insertions(+), 29 deletions(-) diff --git a/.idea/workspace.xml b/.idea/workspace.xml index 48966e2..864a679 100644 --- a/.idea/workspace.xml +++ b/.idea/workspace.xml @@ -2,10 +2,7 @@ - - - - + @@ -92,11 +95,6 @@ - - - - - @@ -164,13 +169,6 @@ - - - - - - - @@ -181,12 +179,19 @@ - - + + + + + + + + + \ No newline at end of file diff --git a/notebooks/Introduction-Ipython.ipynb b/notebooks/Introduction-Ipython.ipynb index 7672819..2fb4f22 100644 --- a/notebooks/Introduction-Ipython.ipynb +++ b/notebooks/Introduction-Ipython.ipynb @@ -73,7 +73,7 @@ "# A test function aimed at raising an exception\n", "def calculate(x, y):\n", " \"\"\" Return the quotient of x and y \"\"\"\n", - " return eval(x / y)" + " return eval(x / y)\n" ] }, { @@ -92,13 +92,13 @@ { "ename": "ZeroDivisionError", "evalue": "division by zero", - "output_type": "error", "traceback": [ "Traceback \u001b[1;36m(most recent call last)\u001b[0m:\n", " File \u001b[0;32m\"\"\u001b[0m, line \u001b[0;32m4\u001b[0m, in \u001b[0;35m\u001b[0m\n calculate(1, 0)\n", "\u001b[1;36m File \u001b[1;32m\"\"\u001b[1;36m, line \u001b[1;32m4\u001b[1;36m, in \u001b[1;35mcalculate\u001b[1;36m\u001b[0m\n\u001b[1;33m return eval(x / y)\u001b[0m\n", "\u001b[1;31mZeroDivisionError\u001b[0m\u001b[1;31m:\u001b[0m division by zero\n" - ] + ], + "output_type": "error" }, { "name": "stdout", @@ -118,7 +118,7 @@ "# Turn Exception mode on to Plain and debugger then call the function\n", "%xmode Plain\n", "%pdb on\n", - "calculate(1, 0)" + "calculate(1, 0)\n" ] }, { From a052745c4744a497828ef469e5075580d41b45dd Mon Sep 17 00:00:00 2001 From: Isaac Mutie Date: Tue, 22 Jan 2019 16:57:18 +0300 Subject: [PATCH 06/43] fix typos in markdown --- .idea/workspace.xml | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-) diff --git a/.idea/workspace.xml b/.idea/workspace.xml index b6ae175..1f4cb27 100644 --- a/.idea/workspace.xml +++ b/.idea/workspace.xml @@ -1,9 +1,7 @@ - - - + - + - - + + @@ -90,6 +91,7 @@ + @@ -101,7 +103,6 @@ + @@ -155,7 +163,6 @@ - @@ -204,10 +211,13 @@ + + + - - + + diff --git a/notebooks/.ipynb_checkpoints/Numpy-checkpoint.ipynb b/notebooks/.ipynb_checkpoints/Numpy-checkpoint.ipynb index 0079c22..bcc6a8d 100644 --- a/notebooks/.ipynb_checkpoints/Numpy-checkpoint.ipynb +++ b/notebooks/.ipynb_checkpoints/Numpy-checkpoint.ipynb @@ -53,7 +53,7 @@ }, { "cell_type": "code", - "execution_count": 4, + "execution_count": 2, "metadata": {}, "outputs": [ { @@ -62,7 +62,7 @@ "array([1., 2., 3., 4.], dtype=float32)" ] }, - "execution_count": 4, + "execution_count": 2, "metadata": {}, "output_type": "execute_result" } @@ -73,7 +73,7 @@ }, { "cell_type": "code", - "execution_count": 6, + "execution_count": 3, "metadata": {}, "outputs": [ { @@ -84,7 +84,7 @@ " [4, 5, 6]])" ] }, - "execution_count": 6, + "execution_count": 3, "metadata": {}, "output_type": "execute_result" } @@ -103,7 +103,7 @@ }, { "cell_type": "code", - "execution_count": 18, + "execution_count": 4, "metadata": {}, "outputs": [ { @@ -114,7 +114,7 @@ " [0, 0, 1]])" ] }, - "execution_count": 18, + "execution_count": 4, "metadata": {}, "output_type": "execute_result" } @@ -159,7 +159,7 @@ }, { "cell_type": "code", - "execution_count": 20, + "execution_count": 5, "metadata": {}, "outputs": [ { @@ -195,6 +195,216 @@ "print(\"Array2 size: \", array2.size)\n", "print(\"Array2 dtype: \", array2.dtype)" ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## Array Indexing - Accessing single array elements" + ] + }, + { + "cell_type": "code", + "execution_count": 6, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "[5 0 3 3 7 9]\n", + "Array 1 irst element: 5\n", + "[[3 5 2 4]\n", + " [7 6 8 8]\n", + " [1 6 7 7]]\n", + "3\n" + ] + } + ], + "source": [ + "# Access the first element in array 1\n", + "print(array1)\n", + "first_array1_element = array1[0]\n", + "print(\"Array 1 first element: \", first_array1_element)\n", + "\n", + "# Access the first element in second row of array 2\n", + "print(array2)\n", + "array2_element = array2[0, 0]\n", + "print(array2_element)" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## Array Slicing: Accesing sub-arrays" + ] + }, + { + "cell_type": "code", + "execution_count": 9, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "[0 1 2 3 4 5 6 7 8 9]\n", + "First five elements: [0 1 2 3 4]\n", + "Last five: [5 6 7 8 9]\n", + "[4 5 6]\n" + ] + } + ], + "source": [ + "\"\"\"\n", + " uses slice notation ':'.\n", + " format: x[start, stop, step]\n", + "\"\"\"\n", + "# Initialize a 1-dim array\n", + "x = np.arange(10)\n", + "print(x)\n", + "\n", + "# Select first five elements\n", + "print(\"First five elements: \", x[:5])\n", + "\n", + "# Elements after index 5\n", + "print(\"Last five: \", x[5:])\n", + "\n", + "# Middle sub-array\n", + "print(x[4:7])" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## Array copies" + ] + }, + { + "cell_type": "code", + "execution_count": 14, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Array 2: \n", + " [[9 5 2 4]\n", + " [7 6 8 8]\n", + " [1 6 7 7]]\n", + "Sub array: \n", + " [[9 5]\n", + " [7 6]]\n", + "New Sub array: \n", + " [[9 5]\n", + " [7 6]]\n", + "New main array: \n", + " [[9 5 2 4]\n", + " [7 6 8 8]\n", + " [1 6 7 7]]\n" + ] + } + ], + "source": [ + "# When a sub array is created, it is not a copy of the original array, \n", + "# its its view, meaning that any change made on the sub array refelects on the main array.\n", + "\n", + "print(\"Array 2: \\n\", array2)\n", + "\n", + "# Create a 2x2 sub array\n", + "sub_array2 = array2[:2, :2]\n", + "print(\"Sub array: \\n\", sub_array2)\n", + "\n", + "# Change any value in sub array\n", + "sub_array2[0, 0] = 9\n", + "print(\"New Sub array: \\n\", sub_array2)\n", + "print(\"New main array: \\n\", array2)\n", + "\n", + "# To make an array copy which is not affected by any changes in the sub array, use the copy() fn.\n", + "sub_array_copy = array2[:2, :2].copy()" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## Basic Ufuncs" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "# Functions that enable vectorization - A faster way than python loops\n", + "\"\"\"\n", + " \n", + "Operator\tEquivalent ufunc\tDescription\n", + "+\tnp.add\tAddition (e.g., 1 + 1 = 2)\n", + "-\tnp.subtract\tSubtraction (e.g., 3 - 2 = 1)\n", + "-\tnp.negative\tUnary negation (e.g., -2)\n", + "*\tnp.multiply\tMultiplication (e.g., 2 * 3 = 6)\n", + "/\tnp.divide\tDivision (e.g., 3 / 2 = 1.5)\n", + "//\tnp.floor_divide\tFloor division (e.g., 3 // 2 = 1)\n", + "**\tnp.power\tExponentiation (e.g., 2 ** 3 = 8)\n", + "%\tnp.mod\tModulus/remainder (e.g., 9 % 4 = 1)\n", + "\"\"\"\n", + "\n", + "# More Ufuncs found on docs" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## Aggregations" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "\"\"\"\n", + " Aggregations are used to compute operations. This include sum, min, max, percentiles, median, standard deviation, \n", + " quartiles, etc.\n", + "\"\"\"" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## Broadcasting: \n", + "### Computations on arrays of different sizes and dimensions" + ] + }, + { + "cell_type": "code", + "execution_count": 7, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "array a: \n", + " [[1 1 1]\n", + " [1 1 1]\n", + " [1 1 1]]\n" + ] + } + ], + "source": [ + "# A 1-dim array of integers\n", + "a = np.ones(shape=(3, 3), dtype=np.int)\n", + "print(\"array a: \\n\", a)" + ] } ], "metadata": { diff --git a/notebooks/Numpy.ipynb b/notebooks/Numpy.ipynb index 0a6c6e3..e45463b 100644 --- a/notebooks/Numpy.ipynb +++ b/notebooks/Numpy.ipynb @@ -53,7 +53,7 @@ }, { "cell_type": "code", - "execution_count": 4, + "execution_count": 2, "metadata": {}, "outputs": [ { @@ -62,7 +62,7 @@ "array([1., 2., 3., 4.], dtype=float32)" ] }, - "execution_count": 4, + "execution_count": 2, "metadata": {}, "output_type": "execute_result" } @@ -73,7 +73,7 @@ }, { "cell_type": "code", - "execution_count": 6, + "execution_count": 3, "metadata": {}, "outputs": [ { @@ -84,7 +84,7 @@ " [4, 5, 6]])" ] }, - "execution_count": 6, + "execution_count": 3, "metadata": {}, "output_type": "execute_result" } @@ -103,7 +103,7 @@ }, { "cell_type": "code", - "execution_count": 18, + "execution_count": 4, "metadata": {}, "outputs": [ { @@ -114,7 +114,7 @@ " [0, 0, 1]])" ] }, - "execution_count": 18, + "execution_count": 4, "metadata": {}, "output_type": "execute_result" } @@ -159,7 +159,7 @@ }, { "cell_type": "code", - "execution_count": 20, + "execution_count": 5, "metadata": {}, "outputs": [ { @@ -205,7 +205,7 @@ }, { "cell_type": "code", - "execution_count": 24, + "execution_count": 6, "metadata": {}, "outputs": [ { @@ -213,7 +213,7 @@ "output_type": "stream", "text": [ "[5 0 3 3 7 9]\n", - "5\n", + "Array 1 irst element: 5\n", "[[3 5 2 4]\n", " [7 6 8 8]\n", " [1 6 7 7]]\n", @@ -225,13 +225,205 @@ "# Access the first element in array 1\n", "print(array1)\n", "first_array1_element = array1[0]\n", - "print(first_array1_element)\n", + "print(\"Array 1 first element: \", first_array1_element)\n", "\n", "# Access the first element in second row of array 2\n", "print(array2)\n", "array2_element = array2[0, 0]\n", "print(array2_element)" ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## Array Slicing: Accesing sub-arrays" + ] + }, + { + "cell_type": "code", + "execution_count": 9, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "[0 1 2 3 4 5 6 7 8 9]\n", + "First five elements: [0 1 2 3 4]\n", + "Last five: [5 6 7 8 9]\n", + "[4 5 6]\n" + ] + } + ], + "source": [ + "\"\"\"\n", + " uses slice notation ':'.\n", + " format: x[start, stop, step]\n", + "\"\"\"\n", + "# Initialize a 1-dim array\n", + "x = np.arange(10)\n", + "print(x)\n", + "\n", + "# Select first five elements\n", + "print(\"First five elements: \", x[:5])\n", + "\n", + "# Elements after index 5\n", + "print(\"Last five: \", x[5:])\n", + "\n", + "# Middle sub-array\n", + "print(x[4:7])" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## Array copies" + ] + }, + { + "cell_type": "code", + "execution_count": 14, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Array 2: \n", + " [[9 5 2 4]\n", + " [7 6 8 8]\n", + " [1 6 7 7]]\n", + "Sub array: \n", + " [[9 5]\n", + " [7 6]]\n", + "New Sub array: \n", + " [[9 5]\n", + " [7 6]]\n", + "New main array: \n", + " [[9 5 2 4]\n", + " [7 6 8 8]\n", + " [1 6 7 7]]\n" + ] + } + ], + "source": [ + "# When a sub array is created, it is not a copy of the original array, \n", + "# its its view, meaning that any change made on the sub array refelects on the main array.\n", + "\n", + "print(\"Array 2: \\n\", array2)\n", + "\n", + "# Create a 2x2 sub array\n", + "sub_array2 = array2[:2, :2]\n", + "print(\"Sub array: \\n\", sub_array2)\n", + "\n", + "# Change any value in sub array\n", + "sub_array2[0, 0] = 9\n", + "print(\"New Sub array: \\n\", sub_array2)\n", + "print(\"New main array: \\n\", array2)\n", + "\n", + "# To make an array copy which is not affected by any changes in the sub array, use the copy() fn.\n", + "sub_array_copy = array2[:2, :2].copy()" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## Basic Ufuncs" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "# Functions that enable vectorization - A faster way than python loops\n", + "\"\"\"\n", + " \n", + "Operator\tEquivalent ufunc\tDescription\n", + "+\tnp.add\tAddition (e.g., 1 + 1 = 2)\n", + "-\tnp.subtract\tSubtraction (e.g., 3 - 2 = 1)\n", + "-\tnp.negative\tUnary negation (e.g., -2)\n", + "*\tnp.multiply\tMultiplication (e.g., 2 * 3 = 6)\n", + "/\tnp.divide\tDivision (e.g., 3 / 2 = 1.5)\n", + "//\tnp.floor_divide\tFloor division (e.g., 3 // 2 = 1)\n", + "**\tnp.power\tExponentiation (e.g., 2 ** 3 = 8)\n", + "%\tnp.mod\tModulus/remainder (e.g., 9 % 4 = 1)\n", + "\"\"\"\n", + "\n", + "# More Ufuncs found on docs" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## Aggregations" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "\"\"\"\n", + " Aggregations are used to compute operations. This include sum, min, max, percentiles, median, standard deviation, \n", + " quartiles, etc.\n", + "\"\"\"" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## Broadcasting: \n", + "### Computations on arrays of different sizes and dimensions" + ] + }, + { + "cell_type": "code", + "execution_count": 10, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "array a: \n", + " [[1 1 1]\n", + " [1 1 1]\n", + " [1 1 1]]\n", + "array b: \n", + " [1 2 3]\n", + "b + 5 = [6 7 8]\n", + "a + b: \n", + " [[2 3 4]\n", + " [2 3 4]\n", + " [2 3 4]]\n" + ] + } + ], + "source": [ + "# A 3-dim array of integers an\n", + "a = np.ones(shape=(3, 3), dtype=np.int)\n", + "\n", + "# 1-dim array\n", + "b = np.array([1, 2, 3])\n", + "\n", + "print(\"array a: \\n\", a)\n", + "print(\"array b: \\n\", b)\n", + "\n", + "# Adding array b to a scalar(0-dim array)\n", + "print(\"b + 5 = \", b + 5)\n", + "\n", + "# Adding a to b\n", + "ab = a + b\n", + "print(\"a + b: \\n\", ab)" + ] } ], "metadata": { diff --git a/notebooks/tests.ipynb b/notebooks/tests.ipynb index c696b66..836f038 100644 --- a/notebooks/tests.ipynb +++ b/notebooks/tests.ipynb @@ -9,7 +9,7 @@ }, { "cell_type": "code", - "execution_count": 7, + "execution_count": 4, "metadata": {}, "outputs": [], "source": [ @@ -18,7 +18,7 @@ "np.__version__\n", "\n", "# numpy namespace and docs\n", - "np.random.randint?" + "np.arange?" ] }, { @@ -30,20 +30,9 @@ }, { "cell_type": "code", - "execution_count": 3, + "execution_count": null, "metadata": {}, - "outputs": [ - { - "data": { - "text/plain": [ - "array('i', [0, 1, 2, 3, 4, 5, 6, 7, 8, 9])" - ] - }, - "execution_count": 3, - "metadata": {}, - "output_type": "execute_result" - } - ], + "outputs": [], "source": [ "import array\n", "\n", @@ -58,40 +47,9 @@ }, { "cell_type": "code", - "execution_count": 5, + "execution_count": null, "metadata": {}, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "[[[1 1 4 1 2]\n", - " [9 2 1 6 0]\n", - " [5 6 9 9 2]\n", - " [7 4 4 0 5]]\n", - "\n", - " [[3 1 0 6 3]\n", - " [5 3 5 6 5]\n", - " [8 9 5 4 1]\n", - " [6 6 2 7 9]]\n", - "\n", - " [[2 8 0 1 8]\n", - " [1 5 9 1 7]\n", - " [5 9 6 7 5]\n", - " [6 3 9 3 0]]]\n" - ] - }, - { - "data": { - "text/plain": [ - "array([0, 6, 7, 6, 8, 1])" - ] - }, - "execution_count": 5, - "metadata": {}, - "output_type": "execute_result" - } - ], + "outputs": [], "source": [ "print(np.random.randint(10, size=(3, 4, 5)))\n", "x1 = np.random.randint(10, size=6)\n", diff --git a/notes.txt b/notes.txt index 2f568ff..73a672a 100644 --- a/notes.txt +++ b/notes.txt @@ -20,4 +20,5 @@ ### NUMPY ### - The difference between python list arrays and numpy arrays is that for python each item can be of different type, while numpy is restricted to a certain data type. + - Numpy uses vectorization in repeated operations, which is way faster than python loops. From d189e7c1b15097d115478936cae51c7136fb2f9f Mon Sep 17 00:00:00 2001 From: Isaac Mutie Date: Thu, 31 Jan 2019 14:33:53 +0300 Subject: [PATCH 12/43] Finish on Numpy arrays --- .idea/workspace.xml | 15 +- .../.ipynb_checkpoints/Numpy-checkpoint.ipynb | 255 +++++++++--------- .../.ipynb_checkpoints/tests-checkpoint.ipynb | 30 +-- notebooks/Numpy.ipynb | 246 ++++++++--------- notebooks/tests.ipynb | 4 +- 5 files changed, 250 insertions(+), 300 deletions(-) diff --git a/.idea/workspace.xml b/.idea/workspace.xml index ebd5ba4..5dd8ad6 100644 --- a/.idea/workspace.xml +++ b/.idea/workspace.xml @@ -6,7 +6,6 @@ - - + @@ -74,6 +71,18 @@ + + + + + + + + + + + + @@ -83,9 +92,9 @@ @@ -162,6 +171,7 @@ + @@ -193,16 +203,6 @@ - - - - - - - - - - @@ -220,5 +220,15 @@ + + + + + + + + + + \ No newline at end of file diff --git a/log.md b/log.md index 0c63797..a490556 100644 --- a/log.md +++ b/log.md @@ -10,11 +10,12 @@ ## Week 2: Chapter 2: Introduction to Numpy -**This week's Progress**: +**This week's Progress**: Finished going through introduction to Numpy. -**Thoughts**: +**Thoughts**: Numpy arrays are very interesting. Not only do they provide an efficient way of manipulating Datasets but also make it easier and faster. + No blockers so far and having learnt the basis of dataset manipulation I'm more than eager to move to Pandas. -**Link to work**: +**Link to work**: [Numpy Arrays](https://github.com/Kasre96/Python4ds_cohort-1/blob/Isaac/notebooks/Numpy.ipynb) ## Week 3: Chapter 3: Data Manipulation with Pandas From 37f7c763e732a90b3e027c190cf6f68d93272df3 Mon Sep 17 00:00:00 2001 From: yokasre <37965744+Kasre96@users.noreply.github.com> Date: Thu, 31 Jan 2019 14:47:40 +0300 Subject: [PATCH 14/43] Update README.md --- README.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/README.md b/README.md index 61b5afe..cb30eb0 100644 --- a/README.md +++ b/README.md @@ -1,10 +1,10 @@ -# Cohort-1 Python for Data Science Nairobi +# Cohort-1 Python for Data Science Nairobi - Isaac ## Contents * [Rules](https://github.com/Python-4-DS/Python4ds_cohort-1/blob/master/rules.md) -* [Log - click here to see my progress](https://github.com/Python-4-DS/Python4ds_cohort-1/blob/master/log.md) +* [Log - click here to see my progress](https://github.com/Kasre96/Python4ds_cohort-1/blob/Isaac/log.md) * [Resources](https://github.com/Python-4-DS/Python4ds_cohort-1/blob/master/resources.md) From 92b560356c43fc2cb1285aafc201bc89e342fa3e Mon Sep 17 00:00:00 2001 From: kasre96 Date: Thu, 7 Feb 2019 09:06:03 +0300 Subject: [PATCH 15/43] install pandas library --- .gitignore | 4 +- .idea/encodings.xml | 4 ++ .idea/workspace.xml | 111 ++++++++++---------------------------------- 3 files changed, 31 insertions(+), 88 deletions(-) create mode 100644 .idea/encodings.xml diff --git a/.gitignore b/.gitignore index ae412d6..c5d561e 100644 --- a/.gitignore +++ b/.gitignore @@ -1 +1,3 @@ -env/ \ No newline at end of file +env/ +venv/ +myvenv/ \ No newline at end of file diff --git a/.idea/encodings.xml b/.idea/encodings.xml new file mode 100644 index 0000000..15a15b2 --- /dev/null +++ b/.idea/encodings.xml @@ -0,0 +1,4 @@ + + + + \ No newline at end of file diff --git a/.idea/workspace.xml b/.idea/workspace.xml index 4316ee7..81afe76 100644 --- a/.idea/workspace.xml +++ b/.idea/workspace.xml @@ -1,8 +1,10 @@ - - + + + + - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - + - - - - - - - + + + + @@ -91,10 +31,10 @@ @@ -122,7 +62,7 @@ - + @@ -170,10 +110,10 @@ - + - + @@ -184,7 +124,7 @@ - + @@ -192,17 +132,7 @@ - - - - - - - - - @@ -210,9 +140,6 @@ - - - @@ -230,5 +157,15 @@ + + + + + + + + + + \ No newline at end of file From 1a8ec91784d44967c4bcb4c311e9a0cf1edf6965 Mon Sep 17 00:00:00 2001 From: kasre96 Date: Fri, 8 Feb 2019 13:43:48 +0300 Subject: [PATCH 16/43] go through dataframe indexing --- .idea/Python4ds_cohort-1.iml | 2 + .idea/libraries/R_User_Library.xml | 6 + .idea/workspace.xml | 40 +- .../Pandas in General-checkpoint.ipynb | 377 ++++++++++++++++++ notebooks/Pandas in General.ipynb | 377 ++++++++++++++++++ 5 files changed, 782 insertions(+), 20 deletions(-) create mode 100644 .idea/libraries/R_User_Library.xml create mode 100644 notebooks/.ipynb_checkpoints/Pandas in General-checkpoint.ipynb create mode 100644 notebooks/Pandas in General.ipynb diff --git a/.idea/Python4ds_cohort-1.iml b/.idea/Python4ds_cohort-1.iml index 825118f..c597cfb 100644 --- a/.idea/Python4ds_cohort-1.iml +++ b/.idea/Python4ds_cohort-1.iml @@ -6,6 +6,8 @@ + + - + @@ -101,7 +100,7 @@ - + 1548144056464 - - + - + @@ -124,12 +122,14 @@ - + + + @@ -140,13 +140,6 @@ - - - - - - - @@ -167,5 +160,12 @@ + + + + + + + \ No newline at end of file diff --git a/notebooks/.ipynb_checkpoints/Pandas in General-checkpoint.ipynb b/notebooks/.ipynb_checkpoints/Pandas in General-checkpoint.ipynb new file mode 100644 index 0000000..a1f3730 --- /dev/null +++ b/notebooks/.ipynb_checkpoints/Pandas in General-checkpoint.ipynb @@ -0,0 +1,377 @@ +{ + "cells": [ + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "# Pandas\n", + "Pandas are used together with numpy. They form an extension of the numpy ndarray object.\n", + "It consists of Series and Dataframe as its key objects" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## Pandas Series object\n", + "A 1-D array of indexed data" + ] + }, + { + "cell_type": "code", + "execution_count": 1, + "metadata": {}, + "outputs": [], + "source": [ + "# import the packages\n", + "import numpy as np\n", + "import pandas as pd" + ] + }, + { + "cell_type": "code", + "execution_count": 6, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "data:\n", + " 0 0.10\n", + "1 6.35\n", + "2 7.00\n", + "3 13.70\n", + "4 8.00\n", + "dtype: float64\n", + "values: [ 0.1 6.35 7. 13.7 8. ]\n", + "indices: RangeIndex(start=0, stop=5, step=1)\n", + "data at index 3: 13.7\n" + ] + } + ], + "source": [ + "# Create a Series from a list or array\n", + "data = pd.Series([0.1, 6.35, 7.0, 13.7, 8.0])\n", + "# display the data\n", + "print(\"data:\\n\", data)\n", + "\n", + "# display the values only\n", + "print(\"values: \", data.values)\n", + "\n", + "# display the indices(as a range)\n", + "print(\"indices: \", data.index)\n", + "\n", + "# access a value\n", + "print(\"data at index 3: \", data[3])" + ] + }, + { + "cell_type": "code", + "execution_count": 7, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "a 1\n", + "b 2\n", + "c 3\n", + "d 4\n", + "e 5\n", + "dtype: int64" + ] + }, + "execution_count": 7, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# Series with custom indices\n", + "custom_data = pd.Series([1, 2, 3, 4, 5], index=['a', 'b', 'c', 'd', 'e'])\n", + "custom_data" + ] + }, + { + "cell_type": "code", + "execution_count": 8, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "kasee 22\n", + "Ken 27\n", + "Kashee 19\n", + "Miro 21\n", + "Phoebe 20\n", + "dtype: int64" + ] + }, + "execution_count": 8, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# A series object can also be created from a dictionary. The indices will be the dict keys.\n", + "ages = {\n", + " 'kasee': 22,\n", + " 'Ken': 27,\n", + " 'Kashee': 19,\n", + " 'Miro': 21,\n", + " 'Phoebe': 20\n", + "}\n", + "\n", + "age_data = pd.Series(ages)\n", + "age_data" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## The DataFrame Object\n", + "Can be created from an array or a dict\n", + "format: pd.DataFrame(data, columns='', index='')" + ] + }, + { + "cell_type": "code", + "execution_count": 2, + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
populationarea
Atlanta74598437589347
Connecticut124765759874
Kansas124765985904384
Seattle124765475398475
Viginia124765509438
\n", + "
" + ], + "text/plain": [ + " population area\n", + "Atlanta 7459843 7589347\n", + "Connecticut 124765 759874\n", + "Kansas 124765 985904384\n", + "Seattle 124765 475398475\n", + "Viginia 124765 509438" + ] + }, + "execution_count": 2, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# States data\n", + "population = {\n", + " 'Seattle': 124765,\n", + " 'Atlanta': 7459843,\n", + " 'Kansas': 124765,\n", + " 'Connecticut': 124765,\n", + " 'Viginia': 124765,\n", + "}\n", + "\n", + "# State areas\n", + "area = {\n", + " 'Seattle': 475398475,\n", + " 'Atlanta': 7589347,\n", + " 'Kansas': 985904384,\n", + " 'Connecticut': 759874,\n", + " 'Viginia': 509438\n", + "}\n", + "\n", + "# create a dataframe\n", + "states = pd.DataFrame({\n", + " 'population': population,\n", + " 'area': area\n", + "})\n", + "\n", + "states" + ] + }, + { + "cell_type": "code", + "execution_count": 4, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "Atlanta 7459843\n", + "Connecticut 124765\n", + "Kansas 124765\n", + "Seattle 124765\n", + "Viginia 124765\n", + "Name: population, dtype: int64" + ] + }, + "execution_count": 4, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# Accessing individual data\n", + "popn = states['population'] # or states.population\n", + "popn" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## Data Indexing and Selection\n", + "Normal slicing and indexing brings confusion, hence `iloc` and `loc` attribs are used for implicit(normal python list-style) and explicit indexing, respectively" + ] + }, + { + "cell_type": "code", + "execution_count": 5, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "1 a\n", + "2 b\n", + "3 c\n", + "dtype: object" + ] + }, + "execution_count": 5, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "data = pd.Series(['a', 'b', 'c'], index=[1, 2, 3])\n", + "data" + ] + }, + { + "cell_type": "code", + "execution_count": 7, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "a\n", + "2 b\n", + "3 c\n", + "dtype: object\n" + ] + } + ], + "source": [ + "# Trying to access the data locally\n", + "print(data[1]) # explicit index when indexing\n", + "print(data[1:3]) # implicit index when slicing" + ] + }, + { + "cell_type": "code", + "execution_count": 9, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "a\n", + "1 a\n", + "2 b\n", + "3 c\n", + "dtype: object\n", + "b\n", + "2 b\n", + "3 c\n", + "dtype: object\n" + ] + } + ], + "source": [ + "# To solve this, loc and iloc are used\n", + "# Explicit indexing\n", + "print(data.loc[1])\n", + "print(data.loc[1:3])\n", + "\n", + "# implicit indexing\n", + "print(data.iloc[1])\n", + "print(data.iloc[1:3])" + ] + } + ], + "metadata": { + "kernelspec": { + "display_name": "Python 3", + "language": "python", + "name": "python3" + }, + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 3 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython3", + "version": "3.7.2" + } + }, + "nbformat": 4, + "nbformat_minor": 2 +} diff --git a/notebooks/Pandas in General.ipynb b/notebooks/Pandas in General.ipynb new file mode 100644 index 0000000..a1f3730 --- /dev/null +++ b/notebooks/Pandas in General.ipynb @@ -0,0 +1,377 @@ +{ + "cells": [ + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "# Pandas\n", + "Pandas are used together with numpy. They form an extension of the numpy ndarray object.\n", + "It consists of Series and Dataframe as its key objects" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## Pandas Series object\n", + "A 1-D array of indexed data" + ] + }, + { + "cell_type": "code", + "execution_count": 1, + "metadata": {}, + "outputs": [], + "source": [ + "# import the packages\n", + "import numpy as np\n", + "import pandas as pd" + ] + }, + { + "cell_type": "code", + "execution_count": 6, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "data:\n", + " 0 0.10\n", + "1 6.35\n", + "2 7.00\n", + "3 13.70\n", + "4 8.00\n", + "dtype: float64\n", + "values: [ 0.1 6.35 7. 13.7 8. ]\n", + "indices: RangeIndex(start=0, stop=5, step=1)\n", + "data at index 3: 13.7\n" + ] + } + ], + "source": [ + "# Create a Series from a list or array\n", + "data = pd.Series([0.1, 6.35, 7.0, 13.7, 8.0])\n", + "# display the data\n", + "print(\"data:\\n\", data)\n", + "\n", + "# display the values only\n", + "print(\"values: \", data.values)\n", + "\n", + "# display the indices(as a range)\n", + "print(\"indices: \", data.index)\n", + "\n", + "# access a value\n", + "print(\"data at index 3: \", data[3])" + ] + }, + { + "cell_type": "code", + "execution_count": 7, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "a 1\n", + "b 2\n", + "c 3\n", + "d 4\n", + "e 5\n", + "dtype: int64" + ] + }, + "execution_count": 7, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# Series with custom indices\n", + "custom_data = pd.Series([1, 2, 3, 4, 5], index=['a', 'b', 'c', 'd', 'e'])\n", + "custom_data" + ] + }, + { + "cell_type": "code", + "execution_count": 8, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "kasee 22\n", + "Ken 27\n", + "Kashee 19\n", + "Miro 21\n", + "Phoebe 20\n", + "dtype: int64" + ] + }, + "execution_count": 8, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# A series object can also be created from a dictionary. The indices will be the dict keys.\n", + "ages = {\n", + " 'kasee': 22,\n", + " 'Ken': 27,\n", + " 'Kashee': 19,\n", + " 'Miro': 21,\n", + " 'Phoebe': 20\n", + "}\n", + "\n", + "age_data = pd.Series(ages)\n", + "age_data" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## The DataFrame Object\n", + "Can be created from an array or a dict\n", + "format: pd.DataFrame(data, columns='', index='')" + ] + }, + { + "cell_type": "code", + "execution_count": 2, + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
populationarea
Atlanta74598437589347
Connecticut124765759874
Kansas124765985904384
Seattle124765475398475
Viginia124765509438
\n", + "
" + ], + "text/plain": [ + " population area\n", + "Atlanta 7459843 7589347\n", + "Connecticut 124765 759874\n", + "Kansas 124765 985904384\n", + "Seattle 124765 475398475\n", + "Viginia 124765 509438" + ] + }, + "execution_count": 2, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# States data\n", + "population = {\n", + " 'Seattle': 124765,\n", + " 'Atlanta': 7459843,\n", + " 'Kansas': 124765,\n", + " 'Connecticut': 124765,\n", + " 'Viginia': 124765,\n", + "}\n", + "\n", + "# State areas\n", + "area = {\n", + " 'Seattle': 475398475,\n", + " 'Atlanta': 7589347,\n", + " 'Kansas': 985904384,\n", + " 'Connecticut': 759874,\n", + " 'Viginia': 509438\n", + "}\n", + "\n", + "# create a dataframe\n", + "states = pd.DataFrame({\n", + " 'population': population,\n", + " 'area': area\n", + "})\n", + "\n", + "states" + ] + }, + { + "cell_type": "code", + "execution_count": 4, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "Atlanta 7459843\n", + "Connecticut 124765\n", + "Kansas 124765\n", + "Seattle 124765\n", + "Viginia 124765\n", + "Name: population, dtype: int64" + ] + }, + "execution_count": 4, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# Accessing individual data\n", + "popn = states['population'] # or states.population\n", + "popn" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## Data Indexing and Selection\n", + "Normal slicing and indexing brings confusion, hence `iloc` and `loc` attribs are used for implicit(normal python list-style) and explicit indexing, respectively" + ] + }, + { + "cell_type": "code", + "execution_count": 5, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "1 a\n", + "2 b\n", + "3 c\n", + "dtype: object" + ] + }, + "execution_count": 5, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "data = pd.Series(['a', 'b', 'c'], index=[1, 2, 3])\n", + "data" + ] + }, + { + "cell_type": "code", + "execution_count": 7, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "a\n", + "2 b\n", + "3 c\n", + "dtype: object\n" + ] + } + ], + "source": [ + "# Trying to access the data locally\n", + "print(data[1]) # explicit index when indexing\n", + "print(data[1:3]) # implicit index when slicing" + ] + }, + { + "cell_type": "code", + "execution_count": 9, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "a\n", + "1 a\n", + "2 b\n", + "3 c\n", + "dtype: object\n", + "b\n", + "2 b\n", + "3 c\n", + "dtype: object\n" + ] + } + ], + "source": [ + "# To solve this, loc and iloc are used\n", + "# Explicit indexing\n", + "print(data.loc[1])\n", + "print(data.loc[1:3])\n", + "\n", + "# implicit indexing\n", + "print(data.iloc[1])\n", + "print(data.iloc[1:3])" + ] + } + ], + "metadata": { + "kernelspec": { + "display_name": "Python 3", + "language": "python", + "name": "python3" + }, + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 3 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython3", + "version": "3.7.2" + } + }, + "nbformat": 4, + "nbformat_minor": 2 +} From f82599b214d1bc8de8981af183dcddba696bfb44 Mon Sep 17 00:00:00 2001 From: Kasre96 Date: Tue, 12 Feb 2019 10:52:00 +0300 Subject: [PATCH 17/43] Finish up on pandas --- .idea/workspace.xml | 29 +- data/births.csv | 15548 ++++++++++++++++ data/births.csv.txt | 15548 ++++++++++++++++ .../Pandas in General-checkpoint.ipynb | 14 + notebooks/Pandas in General.ipynb | 369 + notebooks/births.csv | 15548 ++++++++++++++++ notebooks/tests.ipynb | 349 +- 7 files changed, 47397 insertions(+), 8 deletions(-) create mode 100644 data/births.csv create mode 100644 data/births.csv.txt create mode 100644 notebooks/births.csv diff --git a/.idea/workspace.xml b/.idea/workspace.xml index 30ae354..8abf373 100644 --- a/.idea/workspace.xml +++ b/.idea/workspace.xml @@ -2,8 +2,10 @@ - + + + - + @@ -22,6 +24,11 @@ + + + + + @@ -37,7 +44,7 @@ - + @@ -46,6 +53,7 @@ + @@ -53,11 +61,15 @@ + + + + + + @@ -126,9 +101,8 @@ - - + @@ -139,7 +113,7 @@ - + @@ -170,22 +144,22 @@ - - - - - - - - + + + + + + + + \ No newline at end of file diff --git a/notebooks/.ipynb_checkpoints/kiva_analytics-checkpoint.ipynb b/notebooks/.ipynb_checkpoints/kiva_analytics-checkpoint.ipynb new file mode 100644 index 0000000..3b059bc --- /dev/null +++ b/notebooks/.ipynb_checkpoints/kiva_analytics-checkpoint.ipynb @@ -0,0 +1,52 @@ +{ + "cells": [ + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "# KIVA ANALYTICS\n", + "The kiva datasets contain data on money funded to borrowers from different countries.\n", + "A lot of information can be deduced from the datasets." + ] + }, + { + "cell_type": "code", + "execution_count": 1, + "metadata": {}, + "outputs": [], + "source": [ + "# Importing the packages\n", + "import numpy as np\n", + "import pandas as pd" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] + } + ], + "metadata": { + "kernelspec": { + "display_name": "Python 3", + "language": "python", + "name": "python3" + }, + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 3 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython3", + "version": "3.7.2" + } + }, + "nbformat": 4, + "nbformat_minor": 2 +} diff --git a/notebooks/.ipynb_checkpoints/tests-checkpoint.ipynb b/notebooks/.ipynb_checkpoints/tests-checkpoint.ipynb index 381a656..436f48c 100644 --- a/notebooks/.ipynb_checkpoints/tests-checkpoint.ipynb +++ b/notebooks/.ipynb_checkpoints/tests-checkpoint.ipynb @@ -9,51 +9,5514 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 8, "metadata": {}, "outputs": [], "source": [ - "# Numpy version\n", - "import numpy as np\n", - "np.__version__\n", - "\n", - "# numpy namespace and docs\n", - "np.random.RandomState?" + "import pandas as pd\n", + "import numpy as np" ] }, { - "cell_type": "markdown", + "cell_type": "code", + "execution_count": 3, "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
idfunded_amountloan_amountactivitysectorusecountry_codecountryregioncurrencypartner_idposted_timedisbursed_timefunded_timeterm_in_monthslender_counttagsborrower_gendersrepayment_intervaldate
0653051300.0300.0Fruits & VegetablesFoodTo buy seasonal, fresh fruits to sell.PKPakistanLahorePKR247.02014-01-01 06:12:39+00:002013-12-17 08:00:00+00:002014-01-02 10:06:32+00:0012.012NaNfemaleirregular2014-01-01
1653053575.0575.0RickshawTransportationto repair and maintain the auto rickshaw used ...PKPakistanLahorePKR247.02014-01-01 06:51:08+00:002013-12-17 08:00:00+00:002014-01-02 09:17:23+00:0011.014NaNfemale, femaleirregular2014-01-01
2653068150.0150.0TransportationTransportationTo repair their old cycle-van and buy another ...INIndiaMaynaguriINR334.02014-01-01 09:58:07+00:002013-12-17 08:00:00+00:002014-01-01 16:01:36+00:0043.06user_favorite, user_favoritefemalebullet2014-01-01
3653063200.0200.0EmbroideryArtsto purchase an embroidery machine and a variet...PKPakistanLahorePKR247.02014-01-01 08:03:11+00:002013-12-24 08:00:00+00:002014-01-01 13:00:00+00:0011.08NaNfemaleirregular2014-01-01
4653084400.0400.0Milk SalesFoodto purchase one buffalo.PKPakistanAbdul HakeemPKR245.02014-01-01 11:53:19+00:002013-12-17 08:00:00+00:002014-01-01 19:18:51+00:0014.016NaNfemalemonthly2014-01-01
\n", + "
" + ], + "text/plain": [ + " id funded_amount loan_amount activity sector \\\n", + "0 653051 300.0 300.0 Fruits & Vegetables Food \n", + "1 653053 575.0 575.0 Rickshaw Transportation \n", + "2 653068 150.0 150.0 Transportation Transportation \n", + "3 653063 200.0 200.0 Embroidery Arts \n", + "4 653084 400.0 400.0 Milk Sales Food \n", + "\n", + " use country_code country \\\n", + "0 To buy seasonal, fresh fruits to sell. PK Pakistan \n", + "1 to repair and maintain the auto rickshaw used ... PK Pakistan \n", + "2 To repair their old cycle-van and buy another ... IN India \n", + "3 to purchase an embroidery machine and a variet... PK Pakistan \n", + "4 to purchase one buffalo. PK Pakistan \n", + "\n", + " region currency partner_id posted_time \\\n", + "0 Lahore PKR 247.0 2014-01-01 06:12:39+00:00 \n", + "1 Lahore PKR 247.0 2014-01-01 06:51:08+00:00 \n", + "2 Maynaguri INR 334.0 2014-01-01 09:58:07+00:00 \n", + "3 Lahore PKR 247.0 2014-01-01 08:03:11+00:00 \n", + "4 Abdul Hakeem PKR 245.0 2014-01-01 11:53:19+00:00 \n", + "\n", + " disbursed_time funded_time term_in_months \\\n", + "0 2013-12-17 08:00:00+00:00 2014-01-02 10:06:32+00:00 12.0 \n", + "1 2013-12-17 08:00:00+00:00 2014-01-02 09:17:23+00:00 11.0 \n", + "2 2013-12-17 08:00:00+00:00 2014-01-01 16:01:36+00:00 43.0 \n", + "3 2013-12-24 08:00:00+00:00 2014-01-01 13:00:00+00:00 11.0 \n", + "4 2013-12-17 08:00:00+00:00 2014-01-01 19:18:51+00:00 14.0 \n", + "\n", + " lender_count tags borrower_genders \\\n", + "0 12 NaN female \n", + "1 14 NaN female, female \n", + "2 6 user_favorite, user_favorite female \n", + "3 8 NaN female \n", + "4 16 NaN female \n", + "\n", + " repayment_interval date \n", + "0 irregular 2014-01-01 \n", + "1 irregular 2014-01-01 \n", + "2 bullet 2014-01-01 \n", + "3 irregular 2014-01-01 \n", + "4 monthly 2014-01-01 " + ] + }, + "execution_count": 3, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ - "## Python arrays" + "data = pd.read_csv('C:/Users/user/Desktop/kasee/kiva/kiva_loans.csv')\n", + "data.head(5)" ] }, { "cell_type": "code", - "execution_count": null, + "execution_count": 5, "metadata": {}, - "outputs": [], + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
idfunded_amountloan_amountpartner_idterm_in_monthslender_count
count6.712050e+05671205.000000671205.000000657698.000000671205.000000671205.000000
mean9.932486e+05785.995061842.397107178.19961613.73902220.590922
std1.966113e+051130.3989411198.66007394.2475818.59891928.459551
min6.530470e+050.00000025.0000009.0000001.0000000.000000
25%8.230720e+05250.000000275.000000126.0000008.0000007.000000
50%9.927800e+05450.000000500.000000145.00000013.00000013.000000
75%1.163653e+06900.0000001000.000000204.00000014.00000024.000000
max1.340339e+06100000.000000100000.000000536.000000158.0000002986.000000
\n", + "
" + ], + "text/plain": [ + " id funded_amount loan_amount partner_id \\\n", + "count 6.712050e+05 671205.000000 671205.000000 657698.000000 \n", + "mean 9.932486e+05 785.995061 842.397107 178.199616 \n", + "std 1.966113e+05 1130.398941 1198.660073 94.247581 \n", + "min 6.530470e+05 0.000000 25.000000 9.000000 \n", + "25% 8.230720e+05 250.000000 275.000000 126.000000 \n", + "50% 9.927800e+05 450.000000 500.000000 145.000000 \n", + "75% 1.163653e+06 900.000000 1000.000000 204.000000 \n", + "max 1.340339e+06 100000.000000 100000.000000 536.000000 \n", + "\n", + " term_in_months lender_count \n", + "count 671205.000000 671205.000000 \n", + "mean 13.739022 20.590922 \n", + "std 8.598919 28.459551 \n", + "min 1.000000 0.000000 \n", + "25% 8.000000 7.000000 \n", + "50% 13.000000 13.000000 \n", + "75% 14.000000 24.000000 \n", + "max 158.000000 2986.000000 " + ] + }, + "execution_count": 5, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ - "import array\n", - "\n", - "# create a list of 10 items\n", - "my_list = list(range(10))\n", - "\n", - "# Create an array\n", - "# The 'i' is a type code indicating all the contents are integers\n", - "my_array = array.array('i', my_list)\n", - "my_array" + "data.describe()" ] }, { "cell_type": "code", - "execution_count": null, + "execution_count": 21, "metadata": {}, - "outputs": [], + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
sum
funded_amountloan_amount
countrysector
AfghanistanArts14000.014000.0
AlbaniaAgriculture976925.01005350.0
Arts8375.08375.0
Clothing153925.0162050.0
Construction35325.037975.0
Education117075.0118025.0
Entertainment5225.05225.0
Food107375.0123400.0
Health329400.0342550.0
Housing436175.0500900.0
Manufacturing33675.033675.0
Personal Use87550.0108400.0
Retail52250.059875.0
Services83100.090225.0
Transportation50875.057725.0
Wholesale12750.012750.0
ArmeniaAgriculture6607450.07587550.0
Arts63225.063225.0
Clothing288725.0360025.0
Construction146725.0162475.0
\n", + "
" + ], + "text/plain": [ + " sum \n", + " funded_amount loan_amount\n", + "country sector \n", + "Afghanistan Arts 14000.0 14000.0\n", + "Albania Agriculture 976925.0 1005350.0\n", + " Arts 8375.0 8375.0\n", + " Clothing 153925.0 162050.0\n", + " Construction 35325.0 37975.0\n", + " Education 117075.0 118025.0\n", + " Entertainment 5225.0 5225.0\n", + " Food 107375.0 123400.0\n", + " Health 329400.0 342550.0\n", + " Housing 436175.0 500900.0\n", + " Manufacturing 33675.0 33675.0\n", + " Personal Use 87550.0 108400.0\n", + " Retail 52250.0 59875.0\n", + " Services 83100.0 90225.0\n", + " Transportation 50875.0 57725.0\n", + " Wholesale 12750.0 12750.0\n", + "Armenia Agriculture 6607450.0 7587550.0\n", + " Arts 63225.0 63225.0\n", + " Clothing 288725.0 360025.0\n", + " Construction 146725.0 162475.0" + ] + }, + "execution_count": 21, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "data.pivot_table(index=['country', 'sector'], aggfunc=[np.sum], values=['funded_amount', 'loan_amount']).head(20)" + ] + }, + { + "cell_type": "code", + "execution_count": 22, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "0 female\n", + "1 female, female\n", + "2 female\n", + "3 female\n", + "4 female\n", + "5 female\n", + "6 female\n", + "7 female\n", + "8 female\n", + "9 female\n", + "10 female\n", + "11 female\n", + "12 female\n", + "13 female\n", + "14 female\n", + "15 female\n", + "16 female\n", + "17 female, female, female\n", + "18 female\n", + "19 female\n", + "20 female\n", + "21 female\n", + "22 female, female\n", + "23 female\n", + "24 female\n", + "25 female\n", + "26 female\n", + "27 female\n", + "28 female\n", + "29 female\n", + "Name: borrower_genders, dtype: object" + ] + }, + "execution_count": 22, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "data['borrower_genders'].head(30)" + ] + }, + { + "cell_type": "code", + "execution_count": 32, + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
idfunded_amountloan_amountactivitysectorusecountry_codecountryregioncurrencypartner_idposted_timedisbursed_timefunded_timeterm_in_monthslender_counttagsborrower_gendersrepayment_intervaldate
0NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
1NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
2NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
3NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
4NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
5NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
6NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
7NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
8NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
9NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
10NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
11NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
12NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
13NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
14NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
15NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
16NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
17NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
18NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
19NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
20NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
21NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
22NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
23NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
24NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
25NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
26NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
27NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
28NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
29NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
...............................................................
671175NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671176NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671177NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671178NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671179NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671180NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671181NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671182NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671183NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671184NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671185NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671186NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671187NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671188NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671189NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671190NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671191NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671192NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671193NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671194NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671195NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671196NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671197NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671198NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671199NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671200NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671201NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671202NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671203NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671204NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
\n", + "

671205 rows × 20 columns

\n", + "
" + ], + "text/plain": [ + " id funded_amount loan_amount activity sector use country_code \\\n", + "0 NaN NaN NaN NaN NaN NaN NaN \n", + "1 NaN NaN NaN NaN NaN NaN NaN \n", + "2 NaN NaN NaN NaN NaN NaN NaN \n", + "3 NaN NaN NaN NaN NaN NaN NaN \n", + "4 NaN NaN NaN NaN NaN NaN NaN \n", + "5 NaN NaN NaN NaN NaN NaN NaN \n", + "6 NaN NaN NaN NaN NaN NaN NaN \n", + "7 NaN NaN NaN NaN NaN NaN NaN \n", + "8 NaN NaN NaN NaN NaN NaN NaN \n", + "9 NaN NaN NaN NaN NaN NaN NaN \n", + "10 NaN NaN NaN NaN NaN NaN NaN \n", + "11 NaN NaN NaN NaN NaN NaN NaN \n", + "12 NaN NaN NaN NaN NaN NaN NaN \n", + "13 NaN NaN NaN NaN NaN NaN NaN \n", + "14 NaN NaN NaN NaN NaN NaN NaN \n", + "15 NaN NaN NaN NaN NaN NaN NaN \n", + "16 NaN NaN NaN NaN NaN NaN NaN \n", + "17 NaN NaN NaN NaN NaN NaN NaN \n", + "18 NaN NaN NaN NaN NaN NaN NaN \n", + "19 NaN NaN NaN NaN NaN NaN NaN \n", + "20 NaN NaN NaN NaN NaN NaN NaN \n", + "21 NaN NaN NaN NaN NaN NaN NaN \n", + "22 NaN NaN NaN NaN NaN NaN NaN \n", + "23 NaN NaN NaN NaN NaN NaN NaN \n", + "24 NaN NaN NaN NaN NaN NaN NaN \n", + "25 NaN NaN NaN NaN NaN NaN NaN \n", + "26 NaN NaN NaN NaN NaN NaN NaN \n", + "27 NaN NaN NaN NaN NaN NaN NaN \n", + "28 NaN NaN NaN NaN NaN NaN NaN \n", + "29 NaN NaN NaN NaN NaN NaN NaN \n", + "... .. ... ... ... ... ... ... \n", + "671175 NaN NaN NaN NaN NaN NaN NaN \n", + "671176 NaN NaN NaN NaN NaN NaN NaN \n", + "671177 NaN NaN NaN NaN NaN NaN NaN \n", + "671178 NaN NaN NaN NaN NaN NaN NaN \n", + "671179 NaN NaN NaN NaN NaN NaN NaN \n", + "671180 NaN NaN NaN NaN NaN NaN NaN \n", + "671181 NaN NaN NaN NaN NaN NaN NaN \n", + "671182 NaN NaN NaN NaN NaN NaN NaN \n", + "671183 NaN NaN NaN NaN NaN NaN NaN \n", + "671184 NaN NaN NaN NaN NaN NaN NaN \n", + "671185 NaN NaN NaN NaN NaN NaN NaN \n", + "671186 NaN NaN NaN NaN NaN NaN NaN \n", + "671187 NaN NaN NaN NaN NaN NaN NaN \n", + "671188 NaN NaN NaN NaN NaN NaN NaN \n", + "671189 NaN NaN NaN NaN NaN NaN NaN \n", + "671190 NaN NaN NaN NaN NaN NaN NaN \n", + "671191 NaN NaN NaN NaN NaN NaN NaN \n", + "671192 NaN NaN NaN NaN NaN NaN NaN \n", + "671193 NaN NaN NaN NaN NaN NaN NaN \n", + "671194 NaN NaN NaN NaN NaN NaN NaN \n", + "671195 NaN NaN NaN NaN NaN NaN NaN \n", + "671196 NaN NaN NaN NaN NaN NaN NaN \n", + "671197 NaN NaN NaN NaN NaN NaN NaN \n", + "671198 NaN NaN NaN NaN NaN NaN NaN \n", + "671199 NaN NaN NaN NaN NaN NaN NaN \n", + "671200 NaN NaN NaN NaN NaN NaN NaN \n", + "671201 NaN NaN NaN NaN NaN NaN NaN \n", + "671202 NaN NaN NaN NaN NaN NaN NaN \n", + "671203 NaN NaN NaN NaN NaN NaN NaN \n", + "671204 NaN NaN NaN NaN NaN NaN NaN \n", + "\n", + " country region currency partner_id posted_time disbursed_time \\\n", + "0 NaN NaN NaN NaN NaN NaN \n", + "1 NaN NaN NaN NaN NaN NaN \n", + "2 NaN NaN NaN NaN NaN NaN \n", + "3 NaN NaN NaN NaN NaN NaN \n", + "4 NaN NaN NaN NaN NaN NaN \n", + "5 NaN NaN NaN NaN NaN NaN \n", + "6 NaN NaN NaN NaN NaN NaN \n", + "7 NaN NaN NaN NaN NaN NaN \n", + "8 NaN NaN NaN NaN NaN NaN \n", + "9 NaN NaN NaN NaN NaN NaN \n", + "10 NaN NaN NaN NaN NaN NaN \n", + "11 NaN NaN NaN NaN NaN NaN \n", + "12 NaN NaN NaN NaN NaN NaN \n", + "13 NaN NaN NaN NaN NaN NaN \n", + "14 NaN NaN NaN NaN NaN NaN \n", + "15 NaN NaN NaN NaN NaN NaN \n", + "16 NaN NaN NaN NaN NaN NaN \n", + "17 NaN NaN NaN NaN NaN NaN \n", + "18 NaN NaN NaN NaN NaN NaN \n", + "19 NaN NaN NaN NaN NaN NaN \n", + "20 NaN NaN NaN NaN NaN NaN \n", + "21 NaN NaN NaN NaN NaN NaN \n", + "22 NaN NaN NaN NaN NaN NaN \n", + "23 NaN NaN NaN NaN NaN NaN \n", + "24 NaN NaN NaN NaN NaN NaN \n", + "25 NaN NaN NaN NaN NaN NaN \n", + "26 NaN NaN NaN NaN NaN NaN \n", + "27 NaN NaN NaN NaN NaN NaN \n", + "28 NaN NaN NaN NaN NaN NaN \n", + "29 NaN NaN NaN NaN NaN NaN \n", + "... ... ... ... ... ... ... \n", + "671175 NaN NaN NaN NaN NaN NaN \n", + "671176 NaN NaN NaN NaN NaN NaN \n", + "671177 NaN NaN NaN NaN NaN NaN \n", + "671178 NaN NaN NaN NaN NaN NaN \n", + "671179 NaN NaN NaN NaN NaN NaN \n", + "671180 NaN NaN NaN NaN NaN NaN \n", + "671181 NaN NaN NaN NaN NaN NaN \n", + "671182 NaN NaN NaN NaN NaN NaN \n", + "671183 NaN NaN NaN NaN NaN NaN \n", + "671184 NaN NaN NaN NaN NaN NaN \n", + "671185 NaN NaN NaN NaN NaN NaN \n", + "671186 NaN NaN NaN NaN NaN NaN \n", + "671187 NaN NaN NaN NaN NaN NaN \n", + "671188 NaN NaN NaN NaN NaN NaN \n", + "671189 NaN NaN NaN NaN NaN NaN \n", + "671190 NaN NaN NaN NaN NaN NaN \n", + "671191 NaN NaN NaN NaN NaN NaN \n", + "671192 NaN NaN NaN NaN NaN NaN \n", + "671193 NaN NaN NaN NaN NaN NaN \n", + "671194 NaN NaN NaN NaN NaN NaN \n", + "671195 NaN NaN NaN NaN NaN NaN \n", + "671196 NaN NaN NaN NaN NaN NaN \n", + "671197 NaN NaN NaN NaN NaN NaN \n", + "671198 NaN NaN NaN NaN NaN NaN \n", + "671199 NaN NaN NaN NaN NaN NaN \n", + "671200 NaN NaN NaN NaN NaN NaN \n", + "671201 NaN NaN NaN NaN NaN NaN \n", + "671202 NaN NaN NaN NaN NaN NaN \n", + "671203 NaN NaN NaN NaN NaN NaN \n", + "671204 NaN NaN NaN NaN NaN NaN \n", + "\n", + " funded_time term_in_months lender_count tags borrower_genders \\\n", + "0 NaN NaN NaN NaN NaN \n", + "1 NaN NaN NaN NaN NaN \n", + "2 NaN NaN NaN NaN NaN \n", + "3 NaN NaN NaN NaN NaN \n", + "4 NaN NaN NaN NaN NaN \n", + "5 NaN NaN NaN NaN NaN \n", + "6 NaN NaN NaN NaN NaN \n", + "7 NaN NaN NaN NaN NaN \n", + "8 NaN NaN NaN NaN NaN \n", + "9 NaN NaN NaN NaN NaN \n", + "10 NaN NaN NaN NaN NaN \n", + "11 NaN NaN NaN NaN NaN \n", + "12 NaN NaN NaN NaN NaN \n", + "13 NaN NaN NaN NaN NaN \n", + "14 NaN NaN NaN NaN NaN \n", + "15 NaN NaN NaN NaN NaN \n", + "16 NaN NaN NaN NaN NaN \n", + "17 NaN NaN NaN NaN NaN \n", + "18 NaN NaN NaN NaN NaN \n", + "19 NaN NaN NaN NaN NaN \n", + "20 NaN NaN NaN NaN NaN \n", + "21 NaN NaN NaN NaN NaN \n", + "22 NaN NaN NaN NaN NaN \n", + "23 NaN NaN NaN NaN NaN \n", + "24 NaN NaN NaN NaN NaN \n", + "25 NaN NaN NaN NaN NaN \n", + "26 NaN NaN NaN NaN NaN \n", + "27 NaN NaN NaN NaN NaN \n", + "28 NaN NaN NaN NaN NaN \n", + "29 NaN NaN NaN NaN NaN \n", + "... ... ... ... ... ... \n", + "671175 NaN NaN NaN NaN NaN \n", + "671176 NaN NaN NaN NaN NaN \n", + "671177 NaN NaN NaN NaN NaN \n", + "671178 NaN NaN NaN NaN NaN \n", + "671179 NaN NaN NaN NaN NaN \n", + "671180 NaN NaN NaN NaN NaN \n", + "671181 NaN NaN NaN NaN NaN \n", + "671182 NaN NaN NaN NaN NaN \n", + "671183 NaN NaN NaN NaN NaN \n", + "671184 NaN NaN NaN NaN NaN \n", + "671185 NaN NaN NaN NaN NaN \n", + "671186 NaN NaN NaN NaN NaN \n", + "671187 NaN NaN NaN NaN NaN \n", + "671188 NaN NaN NaN NaN NaN \n", + "671189 NaN NaN NaN NaN NaN \n", + "671190 NaN NaN NaN NaN NaN \n", + "671191 NaN NaN NaN NaN NaN \n", + "671192 NaN NaN NaN NaN NaN \n", + "671193 NaN NaN NaN NaN NaN \n", + "671194 NaN NaN NaN NaN NaN \n", + "671195 NaN NaN NaN NaN NaN \n", + "671196 NaN NaN NaN NaN NaN \n", + "671197 NaN NaN NaN NaN NaN \n", + "671198 NaN NaN NaN NaN NaN \n", + "671199 NaN NaN NaN NaN NaN \n", + "671200 NaN NaN NaN NaN NaN \n", + "671201 NaN NaN NaN NaN NaN \n", + "671202 NaN NaN NaN NaN NaN \n", + "671203 NaN NaN NaN NaN NaN \n", + "671204 NaN NaN NaN NaN NaN \n", + "\n", + " repayment_interval date \n", + "0 NaN NaN \n", + "1 NaN NaN \n", + "2 NaN NaN \n", + "3 NaN NaN \n", + "4 NaN NaN \n", + "5 NaN NaN \n", + "6 NaN NaN \n", + "7 NaN NaN \n", + "8 NaN NaN \n", + "9 NaN NaN \n", + "10 NaN NaN \n", + "11 NaN NaN \n", + "12 NaN NaN \n", + "13 NaN NaN \n", + "14 NaN NaN \n", + "15 NaN NaN \n", + "16 NaN NaN \n", + "17 NaN NaN \n", + "18 NaN NaN \n", + "19 NaN NaN \n", + "20 NaN NaN \n", + "21 NaN NaN \n", + "22 NaN NaN \n", + "23 NaN NaN \n", + "24 NaN NaN \n", + "25 NaN NaN \n", + "26 NaN NaN \n", + "27 NaN NaN \n", + "28 NaN NaN \n", + "29 NaN NaN \n", + "... ... ... \n", + "671175 NaN NaN \n", + "671176 NaN NaN \n", + "671177 NaN NaN \n", + "671178 NaN NaN \n", + "671179 NaN NaN \n", + "671180 NaN NaN \n", + "671181 NaN NaN \n", + "671182 NaN NaN \n", + "671183 NaN NaN \n", + "671184 NaN NaN \n", + "671185 NaN NaN \n", + "671186 NaN NaN \n", + "671187 NaN NaN \n", + "671188 NaN NaN \n", + "671189 NaN NaN \n", + "671190 NaN NaN \n", + "671191 NaN NaN \n", + "671192 NaN NaN \n", + "671193 NaN NaN \n", + "671194 NaN NaN \n", + "671195 NaN NaN \n", + "671196 NaN NaN \n", + "671197 NaN NaN \n", + "671198 NaN NaN \n", + "671199 NaN NaN \n", + "671200 NaN NaN \n", + "671201 NaN NaN \n", + "671202 NaN NaN \n", + "671203 NaN NaN \n", + "671204 NaN NaN \n", + "\n", + "[671205 rows x 20 columns]" + ] + }, + "execution_count": 32, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "data[data.isnull()]" + ] + }, + { + "cell_type": "code", + "execution_count": 28, + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
idfunded_amountloan_amountactivitysectorusecountry_codecountryregioncurrencypartner_idposted_timedisbursed_timefunded_timeterm_in_monthslender_counttagsborrower_gendersrepayment_intervaldate
0653051300.0300.0Fruits & VegetablesFoodTo buy seasonal, fresh fruits to sell.PKPakistanLahorePKR247.02014-01-01 06:12:39+00:002013-12-17 08:00:00+00:002014-01-02 10:06:32+00:0012.012NaNfemaleirregular2014-01-01
1653053575.0575.0RickshawTransportationto repair and maintain the auto rickshaw used ...PKPakistanLahorePKR247.02014-01-01 06:51:08+00:002013-12-17 08:00:00+00:002014-01-02 09:17:23+00:0011.014NaNfemale, femaleirregular2014-01-01
2653068150.0150.0TransportationTransportationTo repair their old cycle-van and buy another ...INIndiaMaynaguriINR334.02014-01-01 09:58:07+00:002013-12-17 08:00:00+00:002014-01-01 16:01:36+00:0043.06user_favorite, user_favoritefemalebullet2014-01-01
3653063200.0200.0EmbroideryArtsto purchase an embroidery machine and a variet...PKPakistanLahorePKR247.02014-01-01 08:03:11+00:002013-12-24 08:00:00+00:002014-01-01 13:00:00+00:0011.08NaNfemaleirregular2014-01-01
4653084400.0400.0Milk SalesFoodto purchase one buffalo.PKPakistanAbdul HakeemPKR245.02014-01-01 11:53:19+00:002013-12-17 08:00:00+00:002014-01-01 19:18:51+00:0014.016NaNfemalemonthly2014-01-01
51080148250.0250.0ServicesServicespurchase leather for my business using ksh 20000.KEKenyaNaNKESNaN2014-01-01 10:06:19+00:002014-01-30 01:42:48+00:002014-01-29 14:14:57+00:004.06NaNfemaleirregular2014-01-01
6653067200.0200.0DairyAgricultureTo purchase a dairy cow and start a milk produ...INIndiaMaynaguriINR334.02014-01-01 09:51:02+00:002013-12-16 08:00:00+00:002014-01-01 17:18:09+00:0043.08user_favorite, user_favoritefemalebullet2014-01-01
7653078400.0400.0Beauty SalonServicesto buy more hair and skin care products.PKPakistanEllahabadPKR245.02014-01-01 11:46:01+00:002013-12-20 08:00:00+00:002014-01-10 18:18:44+00:0014.08#Elderly, #Woman Owned Bizfemalemonthly2014-01-01
8653082475.0475.0ManufacturingManufacturingto purchase leather, plastic soles and heels i...PKPakistanLahorePKR245.02014-01-01 11:49:43+00:002013-12-20 08:00:00+00:002014-01-01 18:47:21+00:0014.019user_favoritefemalemonthly2014-01-01
9653048625.0625.0Food Production/SalesFoodto buy a stall, gram flour, ketchup, and coal ...PKPakistanLahorePKR247.02014-01-01 05:41:03+00:002013-12-17 08:00:00+00:002014-01-03 15:45:04+00:0011.024NaNfemaleirregular2014-01-01
10653060200.0200.0RickshawTransportationto cover the cost of repairing rickshawPKPakistanLahorePKR247.02014-01-01 07:32:39+00:002013-12-24 08:00:00+00:002014-01-01 12:18:55+00:0011.03NaNfemaleirregular2014-01-01
11653088400.0400.0WholesaleWholesaleto purchase biscuits, sweets and juices in bulk.PKPakistanFaisalabadPKR245.02014-01-01 12:03:43+00:002013-12-16 08:00:00+00:002014-01-03 09:19:26+00:0014.016NaNfemalemonthly2014-01-01
12653089400.0400.0General StoreRetailto buy stock of rice, sugar and flour .PKPakistanFaisalabadPKR245.02014-01-01 12:04:57+00:002013-12-24 08:00:00+00:002014-01-08 00:35:14+00:0014.016#Repeat Borrower, #Woman Owned Bizfemalemonthly2014-01-01
13653062400.0400.0Clothing SalesClothingto purchase variety of winter clothes to sell.PKPakistanLahorePKR247.02014-01-01 07:57:58+00:002013-12-24 08:00:00+00:002014-01-02 15:47:37+00:0012.010NaNfemaleirregular2014-01-01
14653075225.0225.0PoultryAgricultureto expand her existing poultry farm business.INIndiaDhupguriINR334.02014-01-01 11:24:40+00:002013-12-20 08:00:00+00:002014-01-01 18:58:18+00:0043.07user_favoritefemalebullet2014-01-01
15653054300.0300.0RickshawTransportationto buy a three-wheeled rickshaw.PKPakistanLahorePKR247.02014-01-01 06:58:07+00:002013-12-17 08:00:00+00:002014-01-02 00:04:08+00:0011.09NaNfemaleirregular2014-01-01
16653091400.0400.0General StoreRetailto buy packs of salts, biscuits and beverages.PKPakistanFaisalabadPKR245.02014-01-01 12:09:10+00:002013-12-09 08:00:00+00:002014-01-14 15:57:05+00:0014.011#Woman Owned Biz, #Parentfemalemonthly2014-01-01
17653052875.0875.0TailoringServicesTo buy a sewing machine, lace, zippers and but...PKPakistanLahorePKR247.02014-01-01 06:25:41+00:002013-12-17 08:00:00+00:002014-01-01 18:07:34+00:0011.025NaNfemale, female, femaleirregular2014-01-01
18653066250.0250.0SewingServicesto purchase a sewing machine.INIndiaMaynaguriINR334.02014-01-01 09:48:35+00:002013-12-13 08:00:00+00:002014-01-01 17:18:09+00:0043.04user_favorite, user_favoritefemalebullet2014-01-01
19653080475.0475.0Beauty SalonServicesto buy more cosmetics products for her beauty ...PKPakistanLahorePKR245.02014-01-01 11:48:08+00:002013-12-19 08:00:00+00:002014-01-10 03:22:29+00:0014.018#Woman Owned Bizfemalemonthly2014-01-01
\n", + "
" + ], + "text/plain": [ + " id funded_amount loan_amount activity \\\n", + "0 653051 300.0 300.0 Fruits & Vegetables \n", + "1 653053 575.0 575.0 Rickshaw \n", + "2 653068 150.0 150.0 Transportation \n", + "3 653063 200.0 200.0 Embroidery \n", + "4 653084 400.0 400.0 Milk Sales \n", + "5 1080148 250.0 250.0 Services \n", + "6 653067 200.0 200.0 Dairy \n", + "7 653078 400.0 400.0 Beauty Salon \n", + "8 653082 475.0 475.0 Manufacturing \n", + "9 653048 625.0 625.0 Food Production/Sales \n", + "10 653060 200.0 200.0 Rickshaw \n", + "11 653088 400.0 400.0 Wholesale \n", + "12 653089 400.0 400.0 General Store \n", + "13 653062 400.0 400.0 Clothing Sales \n", + "14 653075 225.0 225.0 Poultry \n", + "15 653054 300.0 300.0 Rickshaw \n", + "16 653091 400.0 400.0 General Store \n", + "17 653052 875.0 875.0 Tailoring \n", + "18 653066 250.0 250.0 Sewing \n", + "19 653080 475.0 475.0 Beauty Salon \n", + "\n", + " sector use \\\n", + "0 Food To buy seasonal, fresh fruits to sell. \n", + "1 Transportation to repair and maintain the auto rickshaw used ... \n", + "2 Transportation To repair their old cycle-van and buy another ... \n", + "3 Arts to purchase an embroidery machine and a variet... \n", + "4 Food to purchase one buffalo. \n", + "5 Services purchase leather for my business using ksh 20000. \n", + "6 Agriculture To purchase a dairy cow and start a milk produ... \n", + "7 Services to buy more hair and skin care products. \n", + "8 Manufacturing to purchase leather, plastic soles and heels i... \n", + "9 Food to buy a stall, gram flour, ketchup, and coal ... \n", + "10 Transportation to cover the cost of repairing rickshaw \n", + "11 Wholesale to purchase biscuits, sweets and juices in bulk. \n", + "12 Retail to buy stock of rice, sugar and flour . \n", + "13 Clothing to purchase variety of winter clothes to sell. \n", + "14 Agriculture to expand her existing poultry farm business. \n", + "15 Transportation to buy a three-wheeled rickshaw. \n", + "16 Retail to buy packs of salts, biscuits and beverages. \n", + "17 Services To buy a sewing machine, lace, zippers and but... \n", + "18 Services to purchase a sewing machine. \n", + "19 Services to buy more cosmetics products for her beauty ... \n", + "\n", + " country_code country region currency partner_id \\\n", + "0 PK Pakistan Lahore PKR 247.0 \n", + "1 PK Pakistan Lahore PKR 247.0 \n", + "2 IN India Maynaguri INR 334.0 \n", + "3 PK Pakistan Lahore PKR 247.0 \n", + "4 PK Pakistan Abdul Hakeem PKR 245.0 \n", + "5 KE Kenya NaN KES NaN \n", + "6 IN India Maynaguri INR 334.0 \n", + "7 PK Pakistan Ellahabad PKR 245.0 \n", + "8 PK Pakistan Lahore PKR 245.0 \n", + "9 PK Pakistan Lahore PKR 247.0 \n", + "10 PK Pakistan Lahore PKR 247.0 \n", + "11 PK Pakistan Faisalabad PKR 245.0 \n", + "12 PK Pakistan Faisalabad PKR 245.0 \n", + "13 PK Pakistan Lahore PKR 247.0 \n", + "14 IN India Dhupguri INR 334.0 \n", + "15 PK Pakistan Lahore PKR 247.0 \n", + "16 PK Pakistan Faisalabad PKR 245.0 \n", + "17 PK Pakistan Lahore PKR 247.0 \n", + "18 IN India Maynaguri INR 334.0 \n", + "19 PK Pakistan Lahore PKR 245.0 \n", + "\n", + " posted_time disbursed_time \\\n", + "0 2014-01-01 06:12:39+00:00 2013-12-17 08:00:00+00:00 \n", + "1 2014-01-01 06:51:08+00:00 2013-12-17 08:00:00+00:00 \n", + "2 2014-01-01 09:58:07+00:00 2013-12-17 08:00:00+00:00 \n", + "3 2014-01-01 08:03:11+00:00 2013-12-24 08:00:00+00:00 \n", + "4 2014-01-01 11:53:19+00:00 2013-12-17 08:00:00+00:00 \n", + "5 2014-01-01 10:06:19+00:00 2014-01-30 01:42:48+00:00 \n", + "6 2014-01-01 09:51:02+00:00 2013-12-16 08:00:00+00:00 \n", + "7 2014-01-01 11:46:01+00:00 2013-12-20 08:00:00+00:00 \n", + "8 2014-01-01 11:49:43+00:00 2013-12-20 08:00:00+00:00 \n", + "9 2014-01-01 05:41:03+00:00 2013-12-17 08:00:00+00:00 \n", + "10 2014-01-01 07:32:39+00:00 2013-12-24 08:00:00+00:00 \n", + "11 2014-01-01 12:03:43+00:00 2013-12-16 08:00:00+00:00 \n", + "12 2014-01-01 12:04:57+00:00 2013-12-24 08:00:00+00:00 \n", + "13 2014-01-01 07:57:58+00:00 2013-12-24 08:00:00+00:00 \n", + "14 2014-01-01 11:24:40+00:00 2013-12-20 08:00:00+00:00 \n", + "15 2014-01-01 06:58:07+00:00 2013-12-17 08:00:00+00:00 \n", + "16 2014-01-01 12:09:10+00:00 2013-12-09 08:00:00+00:00 \n", + "17 2014-01-01 06:25:41+00:00 2013-12-17 08:00:00+00:00 \n", + "18 2014-01-01 09:48:35+00:00 2013-12-13 08:00:00+00:00 \n", + "19 2014-01-01 11:48:08+00:00 2013-12-19 08:00:00+00:00 \n", + "\n", + " funded_time term_in_months lender_count \\\n", + "0 2014-01-02 10:06:32+00:00 12.0 12 \n", + "1 2014-01-02 09:17:23+00:00 11.0 14 \n", + "2 2014-01-01 16:01:36+00:00 43.0 6 \n", + "3 2014-01-01 13:00:00+00:00 11.0 8 \n", + "4 2014-01-01 19:18:51+00:00 14.0 16 \n", + "5 2014-01-29 14:14:57+00:00 4.0 6 \n", + "6 2014-01-01 17:18:09+00:00 43.0 8 \n", + "7 2014-01-10 18:18:44+00:00 14.0 8 \n", + "8 2014-01-01 18:47:21+00:00 14.0 19 \n", + "9 2014-01-03 15:45:04+00:00 11.0 24 \n", + "10 2014-01-01 12:18:55+00:00 11.0 3 \n", + "11 2014-01-03 09:19:26+00:00 14.0 16 \n", + "12 2014-01-08 00:35:14+00:00 14.0 16 \n", + "13 2014-01-02 15:47:37+00:00 12.0 10 \n", + "14 2014-01-01 18:58:18+00:00 43.0 7 \n", + "15 2014-01-02 00:04:08+00:00 11.0 9 \n", + "16 2014-01-14 15:57:05+00:00 14.0 11 \n", + "17 2014-01-01 18:07:34+00:00 11.0 25 \n", + "18 2014-01-01 17:18:09+00:00 43.0 4 \n", + "19 2014-01-10 03:22:29+00:00 14.0 18 \n", + "\n", + " tags borrower_genders \\\n", + "0 NaN female \n", + "1 NaN female, female \n", + "2 user_favorite, user_favorite female \n", + "3 NaN female \n", + "4 NaN female \n", + "5 NaN female \n", + "6 user_favorite, user_favorite female \n", + "7 #Elderly, #Woman Owned Biz female \n", + "8 user_favorite female \n", + "9 NaN female \n", + "10 NaN female \n", + "11 NaN female \n", + "12 #Repeat Borrower, #Woman Owned Biz female \n", + "13 NaN female \n", + "14 user_favorite female \n", + "15 NaN female \n", + "16 #Woman Owned Biz, #Parent female \n", + "17 NaN female, female, female \n", + "18 user_favorite, user_favorite female \n", + "19 #Woman Owned Biz female \n", + "\n", + " repayment_interval date \n", + "0 irregular 2014-01-01 \n", + "1 irregular 2014-01-01 \n", + "2 bullet 2014-01-01 \n", + "3 irregular 2014-01-01 \n", + "4 monthly 2014-01-01 \n", + "5 irregular 2014-01-01 \n", + "6 bullet 2014-01-01 \n", + "7 monthly 2014-01-01 \n", + "8 monthly 2014-01-01 \n", + "9 irregular 2014-01-01 \n", + "10 irregular 2014-01-01 \n", + "11 monthly 2014-01-01 \n", + "12 monthly 2014-01-01 \n", + "13 irregular 2014-01-01 \n", + "14 bullet 2014-01-01 \n", + "15 irregular 2014-01-01 \n", + "16 monthly 2014-01-01 \n", + "17 irregular 2014-01-01 \n", + "18 bullet 2014-01-01 \n", + "19 monthly 2014-01-01 " + ] + }, + "execution_count": 28, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "data[data.notnull()].head(20)" + ] + }, + { + "cell_type": "code", + "execution_count": 31, + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
borrower_genders
0female
2female
3female
4female
5female
6female
7female
8female
9female
10female
\n", + "
" + ], + "text/plain": [ + " borrower_genders\n", + "0 female\n", + "2 female\n", + "3 female\n", + "4 female\n", + "5 female\n", + "6 female\n", + "7 female\n", + "8 female\n", + "9 female\n", + "10 female" + ] + }, + "execution_count": 31, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "data.loc[data.borrower_genders == 'female', ['borrower_genders']].head(10)" + ] + }, + { + "cell_type": "code", + "execution_count": 34, + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
idfunded_amountloan_amountactivitysectorusecountry_codecountryregioncurrencypartner_idposted_timedisbursed_timefunded_timeterm_in_monthslender_counttagsborrower_gendersrepayment_intervaldate
0NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
1NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
2NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
3NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
4NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
5NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
6NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
7NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
8NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
9NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
10NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
11NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
12NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
13NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
14NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
15NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
16NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
17NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
18NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
19NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
20NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
21NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
22NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
23NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
24NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
25NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
26NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
27NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
28NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
29NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
...............................................................
671175NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671176NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671177NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671178NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671179NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671180NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671181NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671182NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671183NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671184NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671185NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671186NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671187NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671188NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671189NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671190NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671191NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671192NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671193NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671194NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671195NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671196NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671197NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671198NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671199NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671200NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671201NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671202NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671203NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671204NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
\n", + "

671205 rows × 20 columns

\n", + "
" + ], + "text/plain": [ + " id funded_amount loan_amount activity sector use country_code \\\n", + "0 NaN NaN NaN NaN NaN NaN NaN \n", + "1 NaN NaN NaN NaN NaN NaN NaN \n", + "2 NaN NaN NaN NaN NaN NaN NaN \n", + "3 NaN NaN NaN NaN NaN NaN NaN \n", + "4 NaN NaN NaN NaN NaN NaN NaN \n", + "5 NaN NaN NaN NaN NaN NaN NaN \n", + "6 NaN NaN NaN NaN NaN NaN NaN \n", + "7 NaN NaN NaN NaN NaN NaN NaN \n", + "8 NaN NaN NaN NaN NaN NaN NaN \n", + "9 NaN NaN NaN NaN NaN NaN NaN \n", + "10 NaN NaN NaN NaN NaN NaN NaN \n", + "11 NaN NaN NaN NaN NaN NaN NaN \n", + "12 NaN NaN NaN NaN NaN NaN NaN \n", + "13 NaN NaN NaN NaN NaN NaN NaN \n", + "14 NaN NaN NaN NaN NaN NaN NaN \n", + "15 NaN NaN NaN NaN NaN NaN NaN \n", + "16 NaN NaN NaN NaN NaN NaN NaN \n", + "17 NaN NaN NaN NaN NaN NaN NaN \n", + "18 NaN NaN NaN NaN NaN NaN NaN \n", + "19 NaN NaN NaN NaN NaN NaN NaN \n", + "20 NaN NaN NaN NaN NaN NaN NaN \n", + "21 NaN NaN NaN NaN NaN NaN NaN \n", + "22 NaN NaN NaN NaN NaN NaN NaN \n", + "23 NaN NaN NaN NaN NaN NaN NaN \n", + "24 NaN NaN NaN NaN NaN NaN NaN \n", + "25 NaN NaN NaN NaN NaN NaN NaN \n", + "26 NaN NaN NaN NaN NaN NaN NaN \n", + "27 NaN NaN NaN NaN NaN NaN NaN \n", + "28 NaN NaN NaN NaN NaN NaN NaN \n", + "29 NaN NaN NaN NaN NaN NaN NaN \n", + "... .. ... ... ... ... ... ... \n", + "671175 NaN NaN NaN NaN NaN NaN NaN \n", + "671176 NaN NaN NaN NaN NaN NaN NaN \n", + "671177 NaN NaN NaN NaN NaN NaN NaN \n", + "671178 NaN NaN NaN NaN NaN NaN NaN \n", + "671179 NaN NaN NaN NaN NaN NaN NaN \n", + "671180 NaN NaN NaN NaN NaN NaN NaN \n", + "671181 NaN NaN NaN NaN NaN NaN NaN \n", + "671182 NaN NaN NaN NaN NaN NaN NaN \n", + "671183 NaN NaN NaN NaN NaN NaN NaN \n", + "671184 NaN NaN NaN NaN NaN NaN NaN \n", + "671185 NaN NaN NaN NaN NaN NaN NaN \n", + "671186 NaN NaN NaN NaN NaN NaN NaN \n", + "671187 NaN NaN NaN NaN NaN NaN NaN \n", + "671188 NaN NaN NaN NaN NaN NaN NaN \n", + "671189 NaN NaN NaN NaN NaN NaN NaN \n", + "671190 NaN NaN NaN NaN NaN NaN NaN \n", + "671191 NaN NaN NaN NaN NaN NaN NaN \n", + "671192 NaN NaN NaN NaN NaN NaN NaN \n", + "671193 NaN NaN NaN NaN NaN NaN NaN \n", + "671194 NaN NaN NaN NaN NaN NaN NaN \n", + "671195 NaN NaN NaN NaN NaN NaN NaN \n", + "671196 NaN NaN NaN NaN NaN NaN NaN \n", + "671197 NaN NaN NaN NaN NaN NaN NaN \n", + "671198 NaN NaN NaN NaN NaN NaN NaN \n", + "671199 NaN NaN NaN NaN NaN NaN NaN \n", + "671200 NaN NaN NaN NaN NaN NaN NaN \n", + "671201 NaN NaN NaN NaN NaN NaN NaN \n", + "671202 NaN NaN NaN NaN NaN NaN NaN \n", + "671203 NaN NaN NaN NaN NaN NaN NaN \n", + "671204 NaN NaN NaN NaN NaN NaN NaN \n", + "\n", + " country region currency partner_id posted_time disbursed_time \\\n", + "0 NaN NaN NaN NaN NaN NaN \n", + "1 NaN NaN NaN NaN NaN NaN \n", + "2 NaN NaN NaN NaN NaN NaN \n", + "3 NaN NaN NaN NaN NaN NaN \n", + "4 NaN NaN NaN NaN NaN NaN \n", + "5 NaN NaN NaN NaN NaN NaN \n", + "6 NaN NaN NaN NaN NaN NaN \n", + "7 NaN NaN NaN NaN NaN NaN \n", + "8 NaN NaN NaN NaN NaN NaN \n", + "9 NaN NaN NaN NaN NaN NaN \n", + "10 NaN NaN NaN NaN NaN NaN \n", + "11 NaN NaN NaN NaN NaN NaN \n", + "12 NaN NaN NaN NaN NaN NaN \n", + "13 NaN NaN NaN NaN NaN NaN \n", + "14 NaN NaN NaN NaN NaN NaN \n", + "15 NaN NaN NaN NaN NaN NaN \n", + "16 NaN NaN NaN NaN NaN NaN \n", + "17 NaN NaN NaN NaN NaN NaN \n", + "18 NaN NaN NaN NaN NaN NaN \n", + "19 NaN NaN NaN NaN NaN NaN \n", + "20 NaN NaN NaN NaN NaN NaN \n", + "21 NaN NaN NaN NaN NaN NaN \n", + "22 NaN NaN NaN NaN NaN NaN \n", + "23 NaN NaN NaN NaN NaN NaN \n", + "24 NaN NaN NaN NaN NaN NaN \n", + "25 NaN NaN NaN NaN NaN NaN \n", + "26 NaN NaN NaN NaN NaN NaN \n", + "27 NaN NaN NaN NaN NaN NaN \n", + "28 NaN NaN NaN NaN NaN NaN \n", + "29 NaN NaN NaN NaN NaN NaN \n", + "... ... ... ... ... ... ... \n", + "671175 NaN NaN NaN NaN NaN NaN \n", + "671176 NaN NaN NaN NaN NaN NaN \n", + "671177 NaN NaN NaN NaN NaN NaN \n", + "671178 NaN NaN NaN NaN NaN NaN \n", + "671179 NaN NaN NaN NaN NaN NaN \n", + "671180 NaN NaN NaN NaN NaN NaN \n", + "671181 NaN NaN NaN NaN NaN NaN \n", + "671182 NaN NaN NaN NaN NaN NaN \n", + "671183 NaN NaN NaN NaN NaN NaN \n", + "671184 NaN NaN NaN NaN NaN NaN \n", + "671185 NaN NaN NaN NaN NaN NaN \n", + "671186 NaN NaN NaN NaN NaN NaN \n", + "671187 NaN NaN NaN NaN NaN NaN \n", + "671188 NaN NaN NaN NaN NaN NaN \n", + "671189 NaN NaN NaN NaN NaN NaN \n", + "671190 NaN NaN NaN NaN NaN NaN \n", + "671191 NaN NaN NaN NaN NaN NaN \n", + "671192 NaN NaN NaN NaN NaN NaN \n", + "671193 NaN NaN NaN NaN NaN NaN \n", + "671194 NaN NaN NaN NaN NaN NaN \n", + "671195 NaN NaN NaN NaN NaN NaN \n", + "671196 NaN NaN NaN NaN NaN NaN \n", + "671197 NaN NaN NaN NaN NaN NaN \n", + "671198 NaN NaN NaN NaN NaN NaN \n", + "671199 NaN NaN NaN NaN NaN NaN \n", + "671200 NaN NaN NaN NaN NaN NaN \n", + "671201 NaN NaN NaN NaN NaN NaN \n", + "671202 NaN NaN NaN NaN NaN NaN \n", + "671203 NaN NaN NaN NaN NaN NaN \n", + "671204 NaN NaN NaN NaN NaN NaN \n", + "\n", + " funded_time term_in_months lender_count tags borrower_genders \\\n", + "0 NaN NaN NaN NaN NaN \n", + "1 NaN NaN NaN NaN NaN \n", + "2 NaN NaN NaN NaN NaN \n", + "3 NaN NaN NaN NaN NaN \n", + "4 NaN NaN NaN NaN NaN \n", + "5 NaN NaN NaN NaN NaN \n", + "6 NaN NaN NaN NaN NaN \n", + "7 NaN NaN NaN NaN NaN \n", + "8 NaN NaN NaN NaN NaN \n", + "9 NaN NaN NaN NaN NaN \n", + "10 NaN NaN NaN NaN NaN \n", + "11 NaN NaN NaN NaN NaN \n", + "12 NaN NaN NaN NaN NaN \n", + "13 NaN NaN NaN NaN NaN \n", + "14 NaN NaN NaN NaN NaN \n", + "15 NaN NaN NaN NaN NaN \n", + "16 NaN NaN NaN NaN NaN \n", + "17 NaN NaN NaN NaN NaN \n", + "18 NaN NaN NaN NaN NaN \n", + "19 NaN NaN NaN NaN NaN \n", + "20 NaN NaN NaN NaN NaN \n", + "21 NaN NaN NaN NaN NaN \n", + "22 NaN NaN NaN NaN NaN \n", + "23 NaN NaN NaN NaN NaN \n", + "24 NaN NaN NaN NaN NaN \n", + "25 NaN NaN NaN NaN NaN \n", + "26 NaN NaN NaN NaN NaN \n", + "27 NaN NaN NaN NaN NaN \n", + "28 NaN NaN NaN NaN NaN \n", + "29 NaN NaN NaN NaN NaN \n", + "... ... ... ... ... ... \n", + "671175 NaN NaN NaN NaN NaN \n", + "671176 NaN NaN NaN NaN NaN \n", + "671177 NaN NaN NaN NaN NaN \n", + "671178 NaN NaN NaN NaN NaN \n", + "671179 NaN NaN NaN NaN NaN \n", + "671180 NaN NaN NaN NaN NaN \n", + "671181 NaN NaN NaN NaN NaN \n", + "671182 NaN NaN NaN NaN NaN \n", + "671183 NaN NaN NaN NaN NaN \n", + "671184 NaN NaN NaN NaN NaN \n", + "671185 NaN NaN NaN NaN NaN \n", + "671186 NaN NaN NaN NaN NaN \n", + "671187 NaN NaN NaN NaN NaN \n", + "671188 NaN NaN NaN NaN NaN \n", + "671189 NaN NaN NaN NaN NaN \n", + "671190 NaN NaN NaN NaN NaN \n", + "671191 NaN NaN NaN NaN NaN \n", + "671192 NaN NaN NaN NaN NaN \n", + "671193 NaN NaN NaN NaN NaN \n", + "671194 NaN NaN NaN NaN NaN \n", + "671195 NaN NaN NaN NaN NaN \n", + "671196 NaN NaN NaN NaN NaN \n", + "671197 NaN NaN NaN NaN NaN \n", + "671198 NaN NaN NaN NaN NaN \n", + "671199 NaN NaN NaN NaN NaN \n", + "671200 NaN NaN NaN NaN NaN \n", + "671201 NaN NaN NaN NaN NaN \n", + "671202 NaN NaN NaN NaN NaN \n", + "671203 NaN NaN NaN NaN NaN \n", + "671204 NaN NaN NaN NaN NaN \n", + "\n", + " repayment_interval date \n", + "0 NaN NaN \n", + "1 NaN NaN \n", + "2 NaN NaN \n", + "3 NaN NaN \n", + "4 NaN NaN \n", + "5 NaN NaN \n", + "6 NaN NaN \n", + "7 NaN NaN \n", + "8 NaN NaN \n", + "9 NaN NaN \n", + "10 NaN NaN \n", + "11 NaN NaN \n", + "12 NaN NaN \n", + "13 NaN NaN \n", + "14 NaN NaN \n", + "15 NaN NaN \n", + "16 NaN NaN \n", + "17 NaN NaN \n", + "18 NaN NaN \n", + "19 NaN NaN \n", + "20 NaN NaN \n", + "21 NaN NaN \n", + "22 NaN NaN \n", + "23 NaN NaN \n", + "24 NaN NaN \n", + "25 NaN NaN \n", + "26 NaN NaN \n", + "27 NaN NaN \n", + "28 NaN NaN \n", + "29 NaN NaN \n", + "... ... ... \n", + "671175 NaN NaN \n", + "671176 NaN NaN \n", + "671177 NaN NaN \n", + "671178 NaN NaN \n", + "671179 NaN NaN \n", + "671180 NaN NaN \n", + "671181 NaN NaN \n", + "671182 NaN NaN \n", + "671183 NaN NaN \n", + "671184 NaN NaN \n", + "671185 NaN NaN \n", + "671186 NaN NaN \n", + "671187 NaN NaN \n", + "671188 NaN NaN \n", + "671189 NaN NaN \n", + "671190 NaN NaN \n", + "671191 NaN NaN \n", + "671192 NaN NaN \n", + "671193 NaN NaN \n", + "671194 NaN NaN \n", + "671195 NaN NaN \n", + "671196 NaN NaN \n", + "671197 NaN NaN \n", + "671198 NaN NaN \n", + "671199 NaN NaN \n", + "671200 NaN NaN \n", + "671201 NaN NaN \n", + "671202 NaN NaN \n", + "671203 NaN NaN \n", + "671204 NaN NaN \n", + "\n", + "[671205 rows x 20 columns]" + ] + }, + "execution_count": 34, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "data.fillna(method='ffill')" + ] + }, + { + "cell_type": "code", + "execution_count": 37, + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
LocationNameISOcountryregionworld_regionMPIgeolatlon
0Badakhshan, AfghanistanAFGAfghanistanBadakhshanSouth Asia0.387(36.7347725, 70.81199529999999)36.73477270.811995
1Badghis, AfghanistanAFGAfghanistanBadghisSouth Asia0.466(35.1671339, 63.7695384)35.16713463.769538
2Baghlan, AfghanistanAFGAfghanistanBaghlanSouth Asia0.300(35.8042947, 69.2877535)35.80429569.287754
3Balkh, AfghanistanAFGAfghanistanBalkhSouth Asia0.301(36.7550603, 66.8975372)36.75506066.897537
4Bamyan, AfghanistanAFGAfghanistanBamyanSouth Asia0.325(34.8100067, 67.8212104)34.81000767.821210
5Daykundi, AfghanistanAFGAfghanistanDaykundiSouth Asia0.313(33.669495, 66.0463534)33.66949566.046353
6Farah, AfghanistanAFGAfghanistanFarahSouth Asia0.319(32.4464635, 62.1454133)32.44646462.145413
7Faryab, AfghanistanAFGAfghanistanFaryabSouth Asia0.250(36.0795613, 64.90595499999999)36.07956164.905955
8Ghazni, AfghanistanAFGAfghanistanGhazniSouth Asia0.245(33.5450587, 68.4173972)33.54505968.417397
9Ghor, AfghanistanAFGAfghanistanGhorSouth Asia0.384(34.0995776, 64.90595499999999)34.09957864.905955
\n", + "
" + ], + "text/plain": [ + " LocationName ISO country region world_region MPI \\\n", + "0 Badakhshan, Afghanistan AFG Afghanistan Badakhshan South Asia 0.387 \n", + "1 Badghis, Afghanistan AFG Afghanistan Badghis South Asia 0.466 \n", + "2 Baghlan, Afghanistan AFG Afghanistan Baghlan South Asia 0.300 \n", + "3 Balkh, Afghanistan AFG Afghanistan Balkh South Asia 0.301 \n", + "4 Bamyan, Afghanistan AFG Afghanistan Bamyan South Asia 0.325 \n", + "5 Daykundi, Afghanistan AFG Afghanistan Daykundi South Asia 0.313 \n", + "6 Farah, Afghanistan AFG Afghanistan Farah South Asia 0.319 \n", + "7 Faryab, Afghanistan AFG Afghanistan Faryab South Asia 0.250 \n", + "8 Ghazni, Afghanistan AFG Afghanistan Ghazni South Asia 0.245 \n", + "9 Ghor, Afghanistan AFG Afghanistan Ghor South Asia 0.384 \n", + "\n", + " geo lat lon \n", + "0 (36.7347725, 70.81199529999999) 36.734772 70.811995 \n", + "1 (35.1671339, 63.7695384) 35.167134 63.769538 \n", + "2 (35.8042947, 69.2877535) 35.804295 69.287754 \n", + "3 (36.7550603, 66.8975372) 36.755060 66.897537 \n", + "4 (34.8100067, 67.8212104) 34.810007 67.821210 \n", + "5 (33.669495, 66.0463534) 33.669495 66.046353 \n", + "6 (32.4464635, 62.1454133) 32.446464 62.145413 \n", + "7 (36.0795613, 64.90595499999999) 36.079561 64.905955 \n", + "8 (33.5450587, 68.4173972) 33.545059 68.417397 \n", + "9 (34.0995776, 64.90595499999999) 34.099578 64.905955 " + ] + }, + "execution_count": 37, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "regions = pd.read_csv('C:/Users/user/Desktop/kasee/kiva/kiva_mpi_region_locations.csv')\n", + "regions.head(10)" + ] + }, + { + "cell_type": "code", + "execution_count": 41, + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
sum
MPI
country
Afghanistan10.535
Albania0.000
Algeria0.000
Armenia0.000
Azerbaijan0.000
Bangladesh1.458
Barbados0.000
Belize0.141
Benin3.844
Bhutan2.346
Bolivia, Plurinational State of0.878
Bosnia and Herzegovina0.000
Brazil0.736
Burkina Faso7.120
Burundi2.059
Cambodia3.117
Cameroon2.434
Central African Republic7.256
Chad12.241
China0.055
Colombia0.402
Comoros0.549
Congo, Democratic Republic of the4.352
Congo, Republic of3.187
Cote d'Ivoire3.828
Djibouti0.339
Dominican Republic0.416
Ecuador0.073
Egypt0.342
El Salvador0.441
......
Philippines1.051
Rwanda1.214
Saint Lucia0.000
Sao Tome and Principe0.400
Senegal1.403
Serbia0.000
Sierra Leone6.735
Somalia0.000
South Africa0.000
South Sudan4.948
Sudan5.821
Suriname0.335
Swaziland0.294
Syrian Arab Republic0.205
Tajikistan0.233
Tanzania, United Republic of2.397
Thailand0.000
Timor-Leste4.846
Togo1.634
Trinidad and Tobago0.104
Tunisia0.000
Turkmenistan0.000
Uganda3.753
Ukraine0.000
Uzbekistan0.045
Vanuatu0.000
Viet Nam0.205
Yemen4.745
Zambia3.122
Zimbabwe1.514
\n", + "

102 rows × 1 columns

\n", + "
" + ], + "text/plain": [ + " sum\n", + " MPI\n", + "country \n", + "Afghanistan 10.535\n", + "Albania 0.000\n", + "Algeria 0.000\n", + "Armenia 0.000\n", + "Azerbaijan 0.000\n", + "Bangladesh 1.458\n", + "Barbados 0.000\n", + "Belize 0.141\n", + "Benin 3.844\n", + "Bhutan 2.346\n", + "Bolivia, Plurinational State of 0.878\n", + "Bosnia and Herzegovina 0.000\n", + "Brazil 0.736\n", + "Burkina Faso 7.120\n", + "Burundi 2.059\n", + "Cambodia 3.117\n", + "Cameroon 2.434\n", + "Central African Republic 7.256\n", + "Chad 12.241\n", + "China 0.055\n", + "Colombia 0.402\n", + "Comoros 0.549\n", + "Congo, Democratic Republic of the 4.352\n", + "Congo, Republic of 3.187\n", + "Cote d'Ivoire 3.828\n", + "Djibouti 0.339\n", + "Dominican Republic 0.416\n", + "Ecuador 0.073\n", + "Egypt 0.342\n", + "El Salvador 0.441\n", + "... ...\n", + "Philippines 1.051\n", + "Rwanda 1.214\n", + "Saint Lucia 0.000\n", + "Sao Tome and Principe 0.400\n", + "Senegal 1.403\n", + "Serbia 0.000\n", + "Sierra Leone 6.735\n", + "Somalia 0.000\n", + "South Africa 0.000\n", + "South Sudan 4.948\n", + "Sudan 5.821\n", + "Suriname 0.335\n", + "Swaziland 0.294\n", + "Syrian Arab Republic 0.205\n", + "Tajikistan 0.233\n", + "Tanzania, United Republic of 2.397\n", + "Thailand 0.000\n", + "Timor-Leste 4.846\n", + "Togo 1.634\n", + "Trinidad and Tobago 0.104\n", + "Tunisia 0.000\n", + "Turkmenistan 0.000\n", + "Uganda 3.753\n", + "Ukraine 0.000\n", + "Uzbekistan 0.045\n", + "Vanuatu 0.000\n", + "Viet Nam 0.205\n", + "Yemen 4.745\n", + "Zambia 3.122\n", + "Zimbabwe 1.514\n", + "\n", + "[102 rows x 1 columns]" + ] + }, + "execution_count": 41, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "pt = regions.pivot_table(index=['country'], aggfunc=[np.sum], values=['MPI'])\n", + "pt" + ] + }, + { + "cell_type": "code", + "execution_count": 60, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "country\n", + "Afghanistan 10.535\n", + "Albania 0.000\n", + "Algeria 0.000\n", + "Armenia 0.000\n", + "Azerbaijan 0.000\n", + "Bangladesh 1.458\n", + "Barbados 0.000\n", + "Belize 0.141\n", + "Benin 3.844\n", + "Bhutan 2.346\n", + "Name: MPI, dtype: float64" + ] + }, + "execution_count": 60, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "pt['sum'].MPI.head(10)" + ] + }, + { + "cell_type": "code", + "execution_count": 72, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "0 To buy seasonal, fresh fruits to sell. \n", + "1 to repair and maintain the auto rickshaw used ...\n", + "2 To repair their old cycle-van and buy another ...\n", + "3 to purchase an embroidery machine and a variet...\n", + "4 to purchase one buffalo.\n", + "5 purchase leather for my business using ksh 20000.\n", + "6 To purchase a dairy cow and start a milk produ...\n", + "7 to buy more hair and skin care products. \n", + "8 to purchase leather, plastic soles and heels i...\n", + "9 to buy a stall, gram flour, ketchup, and coal ...\n", + "10 to cover the cost of repairing rickshaw\n", + "11 to purchase biscuits, sweets and juices in bulk.\n", + "12 to buy stock of rice, sugar and flour .\n", + "13 to purchase variety of winter clothes to sell.\n", + "14 to expand her existing poultry farm business.\n", + "15 to buy a three-wheeled rickshaw. \n", + "16 to buy packs of salts, biscuits and beverages.\n", + "17 To buy a sewing machine, lace, zippers and but...\n", + "18 to purchase a sewing machine.\n", + "19 to buy more cosmetics products for her beauty ...\n", + "20 to buy ingredients to make bakery products. \n", + "21 to purchase vegetables, chicken, and oil to co...\n", + "22 To buy winter clothing to sell\n", + "23 to buy reels of threads in different colors an...\n", + "24 to purchase a variety of needed food items to ...\n", + "25 to purchase potato seeds and fertilizers for g...\n", + "26 to purchase stones for starting a business sup...\n", + "27 to cover the cost of repairing rickshaw\n", + "28 to purchase potato seeds and fertilizers for g...\n", + "29 to purchase potato seeds and fertilizer for fa...\n", + " ... \n", + "671175 Pretend the flagged issue was addressed by KC.\n", + "671176 Edited loan use in english.\n", + "671177 [True, u'to start a turducken farm.'] - this l...\n", + "671178 NaN\n", + "671179 [True, u'para compara: cemento, arenya y ladri...\n", + "671180 Translated loan use to english.\n", + "671181 Reviewed loan use in english.\n", + "671182 Pretend the flagged issue was addressed by KC.\n", + "671183 Pretend the issue with spanish loan was addres...\n", + "671184 Translated loan use to english.\n", + "671185 NaN\n", + "671186 [True, u'para compara: cemento, arenya y ladri...\n", + "671187 [True, u'to start a turducken farm.'] - this l...\n", + "671188 Reviewed loan use in english.\n", + "671189 [True, u'to start a turducken farm.'] - this l...\n", + "671190 [True, u'to start a turducken farm.'] - this l...\n", + "671191 Translated loan use to english.\n", + "671192 Translated loan use to english.\n", + "671193 Pretend the flagged issue was addressed by KC.\n", + "671194 Kiva Coordinator fixed issue loan (no longer v...\n", + "671195 Edited loan use in english.\n", + "671196 Reviewed loan use in english.\n", + "671197 Pretend the issue with loan got addressed by K...\n", + "671198 Pretend the issue with spanish loan was addres...\n", + "671199 [True, u'para compara: cemento, arenya y ladri...\n", + "671200 [True, u'para compara: cemento, arenya y ladri...\n", + "671201 [True, u'to start a turducken farm.'] - this l...\n", + "671202 NaN\n", + "671203 [True, u'to start a turducken farm.'] - this l...\n", + "671204 [True, u'to start a turducken farm.'] - this l...\n", + "Name: use, Length: 671205, dtype: object" + ] + }, + "execution_count": 72, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ - "print(np.random.randint(10, size=(3, 4, 5)))\n", - "x1 = np.random.randint(10, size=6)\n", - "x1" + "data['use']" ] } ], @@ -73,7 +5536,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.7.1" + "version": "3.7.2" } }, "nbformat": 4, diff --git a/notebooks/kiva_analytics.ipynb b/notebooks/kiva_analytics.ipynb new file mode 100644 index 0000000..b917ca4 --- /dev/null +++ b/notebooks/kiva_analytics.ipynb @@ -0,0 +1,292 @@ +{ + "cells": [ + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "# KIVA ANALYTICS\n", + "The kiva datasets contain data on money funded to borrowers from different countries.\n", + "A lot of information can be deduced from the datasets." + ] + }, + { + "cell_type": "code", + "execution_count": 1, + "metadata": {}, + "outputs": [], + "source": [ + "# Importing the packages\n", + "import numpy as np\n", + "import pandas as pd" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### Taking a look at the main dataset" + ] + }, + { + "cell_type": "code", + "execution_count": 11, + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
idfunded_amountloan_amountactivitysectorusecountry_codecountryregioncurrencypartner_idposted_timedisbursed_timefunded_timeterm_in_monthslender_counttagsborrower_gendersrepayment_intervaldate
0653051300.0300.0Fruits & VegetablesFoodTo buy seasonal, fresh fruits to sell.PKPakistanLahorePKR247.02014-01-01 06:12:39+00:002013-12-17 08:00:00+00:002014-01-02 10:06:32+00:0012.012NaNfemaleirregular2014-01-01
1653053575.0575.0RickshawTransportationto repair and maintain the auto rickshaw used ...PKPakistanLahorePKR247.02014-01-01 06:51:08+00:002013-12-17 08:00:00+00:002014-01-02 09:17:23+00:0011.014NaNfemale, femaleirregular2014-01-01
2653068150.0150.0TransportationTransportationTo repair their old cycle-van and buy another ...INIndiaMaynaguriINR334.02014-01-01 09:58:07+00:002013-12-17 08:00:00+00:002014-01-01 16:01:36+00:0043.06user_favorite, user_favoritefemalebullet2014-01-01
3653063200.0200.0EmbroideryArtsto purchase an embroidery machine and a variet...PKPakistanLahorePKR247.02014-01-01 08:03:11+00:002013-12-24 08:00:00+00:002014-01-01 13:00:00+00:0011.08NaNfemaleirregular2014-01-01
4653084400.0400.0Milk SalesFoodto purchase one buffalo.PKPakistanAbdul HakeemPKR245.02014-01-01 11:53:19+00:002013-12-17 08:00:00+00:002014-01-01 19:18:51+00:0014.016NaNfemalemonthly2014-01-01
\n", + "
" + ], + "text/plain": [ + " id funded_amount loan_amount activity sector \\\n", + "0 653051 300.0 300.0 Fruits & Vegetables Food \n", + "1 653053 575.0 575.0 Rickshaw Transportation \n", + "2 653068 150.0 150.0 Transportation Transportation \n", + "3 653063 200.0 200.0 Embroidery Arts \n", + "4 653084 400.0 400.0 Milk Sales Food \n", + "\n", + " use country_code country \\\n", + "0 To buy seasonal, fresh fruits to sell. PK Pakistan \n", + "1 to repair and maintain the auto rickshaw used ... PK Pakistan \n", + "2 To repair their old cycle-van and buy another ... IN India \n", + "3 to purchase an embroidery machine and a variet... PK Pakistan \n", + "4 to purchase one buffalo. PK Pakistan \n", + "\n", + " region currency partner_id posted_time \\\n", + "0 Lahore PKR 247.0 2014-01-01 06:12:39+00:00 \n", + "1 Lahore PKR 247.0 2014-01-01 06:51:08+00:00 \n", + "2 Maynaguri INR 334.0 2014-01-01 09:58:07+00:00 \n", + "3 Lahore PKR 247.0 2014-01-01 08:03:11+00:00 \n", + "4 Abdul Hakeem PKR 245.0 2014-01-01 11:53:19+00:00 \n", + "\n", + " disbursed_time funded_time term_in_months \\\n", + "0 2013-12-17 08:00:00+00:00 2014-01-02 10:06:32+00:00 12.0 \n", + "1 2013-12-17 08:00:00+00:00 2014-01-02 09:17:23+00:00 11.0 \n", + "2 2013-12-17 08:00:00+00:00 2014-01-01 16:01:36+00:00 43.0 \n", + "3 2013-12-24 08:00:00+00:00 2014-01-01 13:00:00+00:00 11.0 \n", + "4 2013-12-17 08:00:00+00:00 2014-01-01 19:18:51+00:00 14.0 \n", + "\n", + " lender_count tags borrower_genders \\\n", + "0 12 NaN female \n", + "1 14 NaN female, female \n", + "2 6 user_favorite, user_favorite female \n", + "3 8 NaN female \n", + "4 16 NaN female \n", + "\n", + " repayment_interval date \n", + "0 irregular 2014-01-01 \n", + "1 irregular 2014-01-01 \n", + "2 bullet 2014-01-01 \n", + "3 irregular 2014-01-01 \n", + "4 monthly 2014-01-01 " + ] + }, + "execution_count": 11, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# Read the kiva_loans.csv file\n", + "kiva_main_dataset = pd.read_csv('C:/Users/user/Desktop/kasee/kiva/kiva_loans.csv')\n", + "\n", + "# Display the first 10 entries\n", + "kiva_main_dataset.head()" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## Handling Missing Data\n", + "The very first thing before starting on any analytics is to take care of all missing data in the relevant columns(key interest points) by either dropping them or filling them in." + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] + } + ], + "metadata": { + "kernelspec": { + "display_name": "Python 3", + "language": "python", + "name": "python3" + }, + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 3 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython3", + "version": "3.7.2" + } + }, + "nbformat": 4, + "nbformat_minor": 2 +} diff --git a/notebooks/tests.ipynb b/notebooks/tests.ipynb index 13b4c07..436f48c 100644 --- a/notebooks/tests.ipynb +++ b/notebooks/tests.ipynb @@ -9,116 +9,5514 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 8, "metadata": {}, "outputs": [], "source": [ - "# Numpy version\n", - "import numpy as np\n", - "np.__version__\n", - "\n", - "# numpy namespace and docs\n", - "np.random.RandomState?" + "import pandas as pd\n", + "import numpy as np" ] }, { - "cell_type": "markdown", + "cell_type": "code", + "execution_count": 3, "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
idfunded_amountloan_amountactivitysectorusecountry_codecountryregioncurrencypartner_idposted_timedisbursed_timefunded_timeterm_in_monthslender_counttagsborrower_gendersrepayment_intervaldate
0653051300.0300.0Fruits & VegetablesFoodTo buy seasonal, fresh fruits to sell.PKPakistanLahorePKR247.02014-01-01 06:12:39+00:002013-12-17 08:00:00+00:002014-01-02 10:06:32+00:0012.012NaNfemaleirregular2014-01-01
1653053575.0575.0RickshawTransportationto repair and maintain the auto rickshaw used ...PKPakistanLahorePKR247.02014-01-01 06:51:08+00:002013-12-17 08:00:00+00:002014-01-02 09:17:23+00:0011.014NaNfemale, femaleirregular2014-01-01
2653068150.0150.0TransportationTransportationTo repair their old cycle-van and buy another ...INIndiaMaynaguriINR334.02014-01-01 09:58:07+00:002013-12-17 08:00:00+00:002014-01-01 16:01:36+00:0043.06user_favorite, user_favoritefemalebullet2014-01-01
3653063200.0200.0EmbroideryArtsto purchase an embroidery machine and a variet...PKPakistanLahorePKR247.02014-01-01 08:03:11+00:002013-12-24 08:00:00+00:002014-01-01 13:00:00+00:0011.08NaNfemaleirregular2014-01-01
4653084400.0400.0Milk SalesFoodto purchase one buffalo.PKPakistanAbdul HakeemPKR245.02014-01-01 11:53:19+00:002013-12-17 08:00:00+00:002014-01-01 19:18:51+00:0014.016NaNfemalemonthly2014-01-01
\n", + "
" + ], + "text/plain": [ + " id funded_amount loan_amount activity sector \\\n", + "0 653051 300.0 300.0 Fruits & Vegetables Food \n", + "1 653053 575.0 575.0 Rickshaw Transportation \n", + "2 653068 150.0 150.0 Transportation Transportation \n", + "3 653063 200.0 200.0 Embroidery Arts \n", + "4 653084 400.0 400.0 Milk Sales Food \n", + "\n", + " use country_code country \\\n", + "0 To buy seasonal, fresh fruits to sell. PK Pakistan \n", + "1 to repair and maintain the auto rickshaw used ... PK Pakistan \n", + "2 To repair their old cycle-van and buy another ... IN India \n", + "3 to purchase an embroidery machine and a variet... PK Pakistan \n", + "4 to purchase one buffalo. PK Pakistan \n", + "\n", + " region currency partner_id posted_time \\\n", + "0 Lahore PKR 247.0 2014-01-01 06:12:39+00:00 \n", + "1 Lahore PKR 247.0 2014-01-01 06:51:08+00:00 \n", + "2 Maynaguri INR 334.0 2014-01-01 09:58:07+00:00 \n", + "3 Lahore PKR 247.0 2014-01-01 08:03:11+00:00 \n", + "4 Abdul Hakeem PKR 245.0 2014-01-01 11:53:19+00:00 \n", + "\n", + " disbursed_time funded_time term_in_months \\\n", + "0 2013-12-17 08:00:00+00:00 2014-01-02 10:06:32+00:00 12.0 \n", + "1 2013-12-17 08:00:00+00:00 2014-01-02 09:17:23+00:00 11.0 \n", + "2 2013-12-17 08:00:00+00:00 2014-01-01 16:01:36+00:00 43.0 \n", + "3 2013-12-24 08:00:00+00:00 2014-01-01 13:00:00+00:00 11.0 \n", + "4 2013-12-17 08:00:00+00:00 2014-01-01 19:18:51+00:00 14.0 \n", + "\n", + " lender_count tags borrower_genders \\\n", + "0 12 NaN female \n", + "1 14 NaN female, female \n", + "2 6 user_favorite, user_favorite female \n", + "3 8 NaN female \n", + "4 16 NaN female \n", + "\n", + " repayment_interval date \n", + "0 irregular 2014-01-01 \n", + "1 irregular 2014-01-01 \n", + "2 bullet 2014-01-01 \n", + "3 irregular 2014-01-01 \n", + "4 monthly 2014-01-01 " + ] + }, + "execution_count": 3, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ - "## Python arrays" + "data = pd.read_csv('C:/Users/user/Desktop/kasee/kiva/kiva_loans.csv')\n", + "data.head(5)" ] }, { "cell_type": "code", - "execution_count": null, + "execution_count": 5, "metadata": {}, - "outputs": [], + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
idfunded_amountloan_amountpartner_idterm_in_monthslender_count
count6.712050e+05671205.000000671205.000000657698.000000671205.000000671205.000000
mean9.932486e+05785.995061842.397107178.19961613.73902220.590922
std1.966113e+051130.3989411198.66007394.2475818.59891928.459551
min6.530470e+050.00000025.0000009.0000001.0000000.000000
25%8.230720e+05250.000000275.000000126.0000008.0000007.000000
50%9.927800e+05450.000000500.000000145.00000013.00000013.000000
75%1.163653e+06900.0000001000.000000204.00000014.00000024.000000
max1.340339e+06100000.000000100000.000000536.000000158.0000002986.000000
\n", + "
" + ], + "text/plain": [ + " id funded_amount loan_amount partner_id \\\n", + "count 6.712050e+05 671205.000000 671205.000000 657698.000000 \n", + "mean 9.932486e+05 785.995061 842.397107 178.199616 \n", + "std 1.966113e+05 1130.398941 1198.660073 94.247581 \n", + "min 6.530470e+05 0.000000 25.000000 9.000000 \n", + "25% 8.230720e+05 250.000000 275.000000 126.000000 \n", + "50% 9.927800e+05 450.000000 500.000000 145.000000 \n", + "75% 1.163653e+06 900.000000 1000.000000 204.000000 \n", + "max 1.340339e+06 100000.000000 100000.000000 536.000000 \n", + "\n", + " term_in_months lender_count \n", + "count 671205.000000 671205.000000 \n", + "mean 13.739022 20.590922 \n", + "std 8.598919 28.459551 \n", + "min 1.000000 0.000000 \n", + "25% 8.000000 7.000000 \n", + "50% 13.000000 13.000000 \n", + "75% 14.000000 24.000000 \n", + "max 158.000000 2986.000000 " + ] + }, + "execution_count": 5, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ - "import array\n", - "\n", - "# create a list of 10 items\n", - "my_list = list(range(10))\n", - "\n", - "# Create an array\n", - "# The 'i' is a type code indicating all the contents are integers\n", - "my_array = array.array('i', my_list)\n", - "my_array" + "data.describe()" ] }, { "cell_type": "code", - "execution_count": null, + "execution_count": 21, "metadata": {}, - "outputs": [], + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
sum
funded_amountloan_amount
countrysector
AfghanistanArts14000.014000.0
AlbaniaAgriculture976925.01005350.0
Arts8375.08375.0
Clothing153925.0162050.0
Construction35325.037975.0
Education117075.0118025.0
Entertainment5225.05225.0
Food107375.0123400.0
Health329400.0342550.0
Housing436175.0500900.0
Manufacturing33675.033675.0
Personal Use87550.0108400.0
Retail52250.059875.0
Services83100.090225.0
Transportation50875.057725.0
Wholesale12750.012750.0
ArmeniaAgriculture6607450.07587550.0
Arts63225.063225.0
Clothing288725.0360025.0
Construction146725.0162475.0
\n", + "
" + ], + "text/plain": [ + " sum \n", + " funded_amount loan_amount\n", + "country sector \n", + "Afghanistan Arts 14000.0 14000.0\n", + "Albania Agriculture 976925.0 1005350.0\n", + " Arts 8375.0 8375.0\n", + " Clothing 153925.0 162050.0\n", + " Construction 35325.0 37975.0\n", + " Education 117075.0 118025.0\n", + " Entertainment 5225.0 5225.0\n", + " Food 107375.0 123400.0\n", + " Health 329400.0 342550.0\n", + " Housing 436175.0 500900.0\n", + " Manufacturing 33675.0 33675.0\n", + " Personal Use 87550.0 108400.0\n", + " Retail 52250.0 59875.0\n", + " Services 83100.0 90225.0\n", + " Transportation 50875.0 57725.0\n", + " Wholesale 12750.0 12750.0\n", + "Armenia Agriculture 6607450.0 7587550.0\n", + " Arts 63225.0 63225.0\n", + " Clothing 288725.0 360025.0\n", + " Construction 146725.0 162475.0" + ] + }, + "execution_count": 21, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ - "print(np.random.randint(10, size=(3, 4, 5)))\n", - "x1 = np.random.randint(10, size=6)\n", - "x1" + "data.pivot_table(index=['country', 'sector'], aggfunc=[np.sum], values=['funded_amount', 'loan_amount']).head(20)" ] }, { "cell_type": "code", - "execution_count": null, + "execution_count": 22, "metadata": {}, - "outputs": [], + "outputs": [ + { + "data": { + "text/plain": [ + "0 female\n", + "1 female, female\n", + "2 female\n", + "3 female\n", + "4 female\n", + "5 female\n", + "6 female\n", + "7 female\n", + "8 female\n", + "9 female\n", + "10 female\n", + "11 female\n", + "12 female\n", + "13 female\n", + "14 female\n", + "15 female\n", + "16 female\n", + "17 female, female, female\n", + "18 female\n", + "19 female\n", + "20 female\n", + "21 female\n", + "22 female, female\n", + "23 female\n", + "24 female\n", + "25 female\n", + "26 female\n", + "27 female\n", + "28 female\n", + "29 female\n", + "Name: borrower_genders, dtype: object" + ] + }, + "execution_count": 22, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ - "import pandas as pd" + "data['borrower_genders'].head(30)" ] }, { "cell_type": "code", - "execution_count": null, + "execution_count": 32, "metadata": {}, - "outputs": [], + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
idfunded_amountloan_amountactivitysectorusecountry_codecountryregioncurrencypartner_idposted_timedisbursed_timefunded_timeterm_in_monthslender_counttagsborrower_gendersrepayment_intervaldate
0NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
1NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
2NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
3NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
4NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
5NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
6NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
7NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
8NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
9NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
10NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
11NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
12NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
13NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
14NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
15NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
16NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
17NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
18NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
19NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
20NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
21NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
22NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
23NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
24NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
25NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
26NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
27NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
28NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
29NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
...............................................................
671175NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671176NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671177NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671178NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671179NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671180NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671181NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671182NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671183NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671184NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671185NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671186NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671187NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671188NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671189NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671190NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671191NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671192NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671193NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671194NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671195NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671196NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671197NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671198NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671199NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671200NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671201NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671202NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671203NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671204NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
\n", + "

671205 rows × 20 columns

\n", + "
" + ], + "text/plain": [ + " id funded_amount loan_amount activity sector use country_code \\\n", + "0 NaN NaN NaN NaN NaN NaN NaN \n", + "1 NaN NaN NaN NaN NaN NaN NaN \n", + "2 NaN NaN NaN NaN NaN NaN NaN \n", + "3 NaN NaN NaN NaN NaN NaN NaN \n", + "4 NaN NaN NaN NaN NaN NaN NaN \n", + "5 NaN NaN NaN NaN NaN NaN NaN \n", + "6 NaN NaN NaN NaN NaN NaN NaN \n", + "7 NaN NaN NaN NaN NaN NaN NaN \n", + "8 NaN NaN NaN NaN NaN NaN NaN \n", + "9 NaN NaN NaN NaN NaN NaN NaN \n", + "10 NaN NaN NaN NaN NaN NaN NaN \n", + "11 NaN NaN NaN NaN NaN NaN NaN \n", + "12 NaN NaN NaN NaN NaN NaN NaN \n", + "13 NaN NaN NaN NaN NaN NaN NaN \n", + "14 NaN NaN NaN NaN NaN NaN NaN \n", + "15 NaN NaN NaN NaN NaN NaN NaN \n", + "16 NaN NaN NaN NaN NaN NaN NaN \n", + "17 NaN NaN NaN NaN NaN NaN NaN \n", + "18 NaN NaN NaN NaN NaN NaN NaN \n", + "19 NaN NaN NaN NaN NaN NaN NaN \n", + "20 NaN NaN NaN NaN NaN NaN NaN \n", + "21 NaN NaN NaN NaN NaN NaN NaN \n", + "22 NaN NaN NaN NaN NaN NaN NaN \n", + "23 NaN NaN NaN NaN NaN NaN NaN \n", + "24 NaN NaN NaN NaN NaN NaN NaN \n", + "25 NaN NaN NaN NaN NaN NaN NaN \n", + "26 NaN NaN NaN NaN NaN NaN NaN \n", + "27 NaN NaN NaN NaN NaN NaN NaN \n", + "28 NaN NaN NaN NaN NaN NaN NaN \n", + "29 NaN NaN NaN NaN NaN NaN NaN \n", + "... .. ... ... ... ... ... ... \n", + "671175 NaN NaN NaN NaN NaN NaN NaN \n", + "671176 NaN NaN NaN NaN NaN NaN NaN \n", + "671177 NaN NaN NaN NaN NaN NaN NaN \n", + "671178 NaN NaN NaN NaN NaN NaN NaN \n", + "671179 NaN NaN NaN NaN NaN NaN NaN \n", + "671180 NaN NaN NaN NaN NaN NaN NaN \n", + "671181 NaN NaN NaN NaN NaN NaN NaN \n", + "671182 NaN NaN NaN NaN NaN NaN NaN \n", + "671183 NaN NaN NaN NaN NaN NaN NaN \n", + "671184 NaN NaN NaN NaN NaN NaN NaN \n", + "671185 NaN NaN NaN NaN NaN NaN NaN \n", + "671186 NaN NaN NaN NaN NaN NaN NaN \n", + "671187 NaN NaN NaN NaN NaN NaN NaN \n", + "671188 NaN NaN NaN NaN NaN NaN NaN \n", + "671189 NaN NaN NaN NaN NaN NaN NaN \n", + "671190 NaN NaN NaN NaN NaN NaN NaN \n", + "671191 NaN NaN NaN NaN NaN NaN NaN \n", + "671192 NaN NaN NaN NaN NaN NaN NaN \n", + "671193 NaN NaN NaN NaN NaN NaN NaN \n", + "671194 NaN NaN NaN NaN NaN NaN NaN \n", + "671195 NaN NaN NaN NaN NaN NaN NaN \n", + "671196 NaN NaN NaN NaN NaN NaN NaN \n", + "671197 NaN NaN NaN NaN NaN NaN NaN \n", + "671198 NaN NaN NaN NaN NaN NaN NaN \n", + "671199 NaN NaN NaN NaN NaN NaN NaN \n", + "671200 NaN NaN NaN NaN NaN NaN NaN \n", + "671201 NaN NaN NaN NaN NaN NaN NaN \n", + "671202 NaN NaN NaN NaN NaN NaN NaN \n", + "671203 NaN NaN NaN NaN NaN NaN NaN \n", + "671204 NaN NaN NaN NaN NaN NaN NaN \n", + "\n", + " country region currency partner_id posted_time disbursed_time \\\n", + "0 NaN NaN NaN NaN NaN NaN \n", + "1 NaN NaN NaN NaN NaN NaN \n", + "2 NaN NaN NaN NaN NaN NaN \n", + "3 NaN NaN NaN NaN NaN NaN \n", + "4 NaN NaN NaN NaN NaN NaN \n", + "5 NaN NaN NaN NaN NaN NaN \n", + "6 NaN NaN NaN NaN NaN NaN \n", + "7 NaN NaN NaN NaN NaN NaN \n", + "8 NaN NaN NaN NaN NaN NaN \n", + "9 NaN NaN NaN NaN NaN NaN \n", + "10 NaN NaN NaN NaN NaN NaN \n", + "11 NaN NaN NaN NaN NaN NaN \n", + "12 NaN NaN NaN NaN NaN NaN \n", + "13 NaN NaN NaN NaN NaN NaN \n", + "14 NaN NaN NaN NaN NaN NaN \n", + "15 NaN NaN NaN NaN NaN NaN \n", + "16 NaN NaN NaN NaN NaN NaN \n", + "17 NaN NaN NaN NaN NaN NaN \n", + "18 NaN NaN NaN NaN NaN NaN \n", + "19 NaN NaN NaN NaN NaN NaN \n", + "20 NaN NaN NaN NaN NaN NaN \n", + "21 NaN NaN NaN NaN NaN NaN \n", + "22 NaN NaN NaN NaN NaN NaN \n", + "23 NaN NaN NaN NaN NaN NaN \n", + "24 NaN NaN NaN NaN NaN NaN \n", + "25 NaN NaN NaN NaN NaN NaN \n", + "26 NaN NaN NaN NaN NaN NaN \n", + "27 NaN NaN NaN NaN NaN NaN \n", + "28 NaN NaN NaN NaN NaN NaN \n", + "29 NaN NaN NaN NaN NaN NaN \n", + "... ... ... ... ... ... ... \n", + "671175 NaN NaN NaN NaN NaN NaN \n", + "671176 NaN NaN NaN NaN NaN NaN \n", + "671177 NaN NaN NaN NaN NaN NaN \n", + "671178 NaN NaN NaN NaN NaN NaN \n", + "671179 NaN NaN NaN NaN NaN NaN \n", + "671180 NaN NaN NaN NaN NaN NaN \n", + "671181 NaN NaN NaN NaN NaN NaN \n", + "671182 NaN NaN NaN NaN NaN NaN \n", + "671183 NaN NaN NaN NaN NaN NaN \n", + "671184 NaN NaN NaN NaN NaN NaN \n", + "671185 NaN NaN NaN NaN NaN NaN \n", + "671186 NaN NaN NaN NaN NaN NaN \n", + "671187 NaN NaN NaN NaN NaN NaN \n", + "671188 NaN NaN NaN NaN NaN NaN \n", + "671189 NaN NaN NaN NaN NaN NaN \n", + "671190 NaN NaN NaN NaN NaN NaN \n", + "671191 NaN NaN NaN NaN NaN NaN \n", + "671192 NaN NaN NaN NaN NaN NaN \n", + "671193 NaN NaN NaN NaN NaN NaN \n", + "671194 NaN NaN NaN NaN NaN NaN \n", + "671195 NaN NaN NaN NaN NaN NaN \n", + "671196 NaN NaN NaN NaN NaN NaN \n", + "671197 NaN NaN NaN NaN NaN NaN \n", + "671198 NaN NaN NaN NaN NaN NaN \n", + "671199 NaN NaN NaN NaN NaN NaN \n", + "671200 NaN NaN NaN NaN NaN NaN \n", + "671201 NaN NaN NaN NaN NaN NaN \n", + "671202 NaN NaN NaN NaN NaN NaN \n", + "671203 NaN NaN NaN NaN NaN NaN \n", + "671204 NaN NaN NaN NaN NaN NaN \n", + "\n", + " funded_time term_in_months lender_count tags borrower_genders \\\n", + "0 NaN NaN NaN NaN NaN \n", + "1 NaN NaN NaN NaN NaN \n", + "2 NaN NaN NaN NaN NaN \n", + "3 NaN NaN NaN NaN NaN \n", + "4 NaN NaN NaN NaN NaN \n", + "5 NaN NaN NaN NaN NaN \n", + "6 NaN NaN NaN NaN NaN \n", + "7 NaN NaN NaN NaN NaN \n", + "8 NaN NaN NaN NaN NaN \n", + "9 NaN NaN NaN NaN NaN \n", + "10 NaN NaN NaN NaN NaN \n", + "11 NaN NaN NaN NaN NaN \n", + "12 NaN NaN NaN NaN NaN \n", + "13 NaN NaN NaN NaN NaN \n", + "14 NaN NaN NaN NaN NaN \n", + "15 NaN NaN NaN NaN NaN \n", + "16 NaN NaN NaN NaN NaN \n", + "17 NaN NaN NaN NaN NaN \n", + "18 NaN NaN NaN NaN NaN \n", + "19 NaN NaN NaN NaN NaN \n", + "20 NaN NaN NaN NaN NaN \n", + "21 NaN NaN NaN NaN NaN \n", + "22 NaN NaN NaN NaN NaN \n", + "23 NaN NaN NaN NaN NaN \n", + "24 NaN NaN NaN NaN NaN \n", + "25 NaN NaN NaN NaN NaN \n", + "26 NaN NaN NaN NaN NaN \n", + "27 NaN NaN NaN NaN NaN \n", + "28 NaN NaN NaN NaN NaN \n", + "29 NaN NaN NaN NaN NaN \n", + "... ... ... ... ... ... \n", + "671175 NaN NaN NaN NaN NaN \n", + "671176 NaN NaN NaN NaN NaN \n", + "671177 NaN NaN NaN NaN NaN \n", + "671178 NaN NaN NaN NaN NaN \n", + "671179 NaN NaN NaN NaN NaN \n", + "671180 NaN NaN NaN NaN NaN \n", + "671181 NaN NaN NaN NaN NaN \n", + "671182 NaN NaN NaN NaN NaN \n", + "671183 NaN NaN NaN NaN NaN \n", + "671184 NaN NaN NaN NaN NaN \n", + "671185 NaN NaN NaN NaN NaN \n", + "671186 NaN NaN NaN NaN NaN \n", + "671187 NaN NaN NaN NaN NaN \n", + "671188 NaN NaN NaN NaN NaN \n", + "671189 NaN NaN NaN NaN NaN \n", + "671190 NaN NaN NaN NaN NaN \n", + "671191 NaN NaN NaN NaN NaN \n", + "671192 NaN NaN NaN NaN NaN \n", + "671193 NaN NaN NaN NaN NaN \n", + "671194 NaN NaN NaN NaN NaN \n", + "671195 NaN NaN NaN NaN NaN \n", + "671196 NaN NaN NaN NaN NaN \n", + "671197 NaN NaN NaN NaN NaN \n", + "671198 NaN NaN NaN NaN NaN \n", + "671199 NaN NaN NaN NaN NaN \n", + "671200 NaN NaN NaN NaN NaN \n", + "671201 NaN NaN NaN NaN NaN \n", + "671202 NaN NaN NaN NaN NaN \n", + "671203 NaN NaN NaN NaN NaN \n", + "671204 NaN NaN NaN NaN NaN \n", + "\n", + " repayment_interval date \n", + "0 NaN NaN \n", + "1 NaN NaN \n", + "2 NaN NaN \n", + "3 NaN NaN \n", + "4 NaN NaN \n", + "5 NaN NaN \n", + "6 NaN NaN \n", + "7 NaN NaN \n", + "8 NaN NaN \n", + "9 NaN NaN \n", + "10 NaN NaN \n", + "11 NaN NaN \n", + "12 NaN NaN \n", + "13 NaN NaN \n", + "14 NaN NaN \n", + "15 NaN NaN \n", + "16 NaN NaN \n", + "17 NaN NaN \n", + "18 NaN NaN \n", + "19 NaN NaN \n", + "20 NaN NaN \n", + "21 NaN NaN \n", + "22 NaN NaN \n", + "23 NaN NaN \n", + "24 NaN NaN \n", + "25 NaN NaN \n", + "26 NaN NaN \n", + "27 NaN NaN \n", + "28 NaN NaN \n", + "29 NaN NaN \n", + "... ... ... \n", + "671175 NaN NaN \n", + "671176 NaN NaN \n", + "671177 NaN NaN \n", + "671178 NaN NaN \n", + "671179 NaN NaN \n", + "671180 NaN NaN \n", + "671181 NaN NaN \n", + "671182 NaN NaN \n", + "671183 NaN NaN \n", + "671184 NaN NaN \n", + "671185 NaN NaN \n", + "671186 NaN NaN \n", + "671187 NaN NaN \n", + "671188 NaN NaN \n", + "671189 NaN NaN \n", + "671190 NaN NaN \n", + "671191 NaN NaN \n", + "671192 NaN NaN \n", + "671193 NaN NaN \n", + "671194 NaN NaN \n", + "671195 NaN NaN \n", + "671196 NaN NaN \n", + "671197 NaN NaN \n", + "671198 NaN NaN \n", + "671199 NaN NaN \n", + "671200 NaN NaN \n", + "671201 NaN NaN \n", + "671202 NaN NaN \n", + "671203 NaN NaN \n", + "671204 NaN NaN \n", + "\n", + "[671205 rows x 20 columns]" + ] + }, + "execution_count": 32, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ - "births = pd.read_csv('C:/Users/user/PycharmProjects/Python4ds_cohort-1/data/births.csv')\n", - "births.head(10)" + "data[data.isnull()]" ] }, { "cell_type": "code", - "execution_count": null, + "execution_count": 28, "metadata": {}, - "outputs": [], + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
idfunded_amountloan_amountactivitysectorusecountry_codecountryregioncurrencypartner_idposted_timedisbursed_timefunded_timeterm_in_monthslender_counttagsborrower_gendersrepayment_intervaldate
0653051300.0300.0Fruits & VegetablesFoodTo buy seasonal, fresh fruits to sell.PKPakistanLahorePKR247.02014-01-01 06:12:39+00:002013-12-17 08:00:00+00:002014-01-02 10:06:32+00:0012.012NaNfemaleirregular2014-01-01
1653053575.0575.0RickshawTransportationto repair and maintain the auto rickshaw used ...PKPakistanLahorePKR247.02014-01-01 06:51:08+00:002013-12-17 08:00:00+00:002014-01-02 09:17:23+00:0011.014NaNfemale, femaleirregular2014-01-01
2653068150.0150.0TransportationTransportationTo repair their old cycle-van and buy another ...INIndiaMaynaguriINR334.02014-01-01 09:58:07+00:002013-12-17 08:00:00+00:002014-01-01 16:01:36+00:0043.06user_favorite, user_favoritefemalebullet2014-01-01
3653063200.0200.0EmbroideryArtsto purchase an embroidery machine and a variet...PKPakistanLahorePKR247.02014-01-01 08:03:11+00:002013-12-24 08:00:00+00:002014-01-01 13:00:00+00:0011.08NaNfemaleirregular2014-01-01
4653084400.0400.0Milk SalesFoodto purchase one buffalo.PKPakistanAbdul HakeemPKR245.02014-01-01 11:53:19+00:002013-12-17 08:00:00+00:002014-01-01 19:18:51+00:0014.016NaNfemalemonthly2014-01-01
51080148250.0250.0ServicesServicespurchase leather for my business using ksh 20000.KEKenyaNaNKESNaN2014-01-01 10:06:19+00:002014-01-30 01:42:48+00:002014-01-29 14:14:57+00:004.06NaNfemaleirregular2014-01-01
6653067200.0200.0DairyAgricultureTo purchase a dairy cow and start a milk produ...INIndiaMaynaguriINR334.02014-01-01 09:51:02+00:002013-12-16 08:00:00+00:002014-01-01 17:18:09+00:0043.08user_favorite, user_favoritefemalebullet2014-01-01
7653078400.0400.0Beauty SalonServicesto buy more hair and skin care products.PKPakistanEllahabadPKR245.02014-01-01 11:46:01+00:002013-12-20 08:00:00+00:002014-01-10 18:18:44+00:0014.08#Elderly, #Woman Owned Bizfemalemonthly2014-01-01
8653082475.0475.0ManufacturingManufacturingto purchase leather, plastic soles and heels i...PKPakistanLahorePKR245.02014-01-01 11:49:43+00:002013-12-20 08:00:00+00:002014-01-01 18:47:21+00:0014.019user_favoritefemalemonthly2014-01-01
9653048625.0625.0Food Production/SalesFoodto buy a stall, gram flour, ketchup, and coal ...PKPakistanLahorePKR247.02014-01-01 05:41:03+00:002013-12-17 08:00:00+00:002014-01-03 15:45:04+00:0011.024NaNfemaleirregular2014-01-01
10653060200.0200.0RickshawTransportationto cover the cost of repairing rickshawPKPakistanLahorePKR247.02014-01-01 07:32:39+00:002013-12-24 08:00:00+00:002014-01-01 12:18:55+00:0011.03NaNfemaleirregular2014-01-01
11653088400.0400.0WholesaleWholesaleto purchase biscuits, sweets and juices in bulk.PKPakistanFaisalabadPKR245.02014-01-01 12:03:43+00:002013-12-16 08:00:00+00:002014-01-03 09:19:26+00:0014.016NaNfemalemonthly2014-01-01
12653089400.0400.0General StoreRetailto buy stock of rice, sugar and flour .PKPakistanFaisalabadPKR245.02014-01-01 12:04:57+00:002013-12-24 08:00:00+00:002014-01-08 00:35:14+00:0014.016#Repeat Borrower, #Woman Owned Bizfemalemonthly2014-01-01
13653062400.0400.0Clothing SalesClothingto purchase variety of winter clothes to sell.PKPakistanLahorePKR247.02014-01-01 07:57:58+00:002013-12-24 08:00:00+00:002014-01-02 15:47:37+00:0012.010NaNfemaleirregular2014-01-01
14653075225.0225.0PoultryAgricultureto expand her existing poultry farm business.INIndiaDhupguriINR334.02014-01-01 11:24:40+00:002013-12-20 08:00:00+00:002014-01-01 18:58:18+00:0043.07user_favoritefemalebullet2014-01-01
15653054300.0300.0RickshawTransportationto buy a three-wheeled rickshaw.PKPakistanLahorePKR247.02014-01-01 06:58:07+00:002013-12-17 08:00:00+00:002014-01-02 00:04:08+00:0011.09NaNfemaleirregular2014-01-01
16653091400.0400.0General StoreRetailto buy packs of salts, biscuits and beverages.PKPakistanFaisalabadPKR245.02014-01-01 12:09:10+00:002013-12-09 08:00:00+00:002014-01-14 15:57:05+00:0014.011#Woman Owned Biz, #Parentfemalemonthly2014-01-01
17653052875.0875.0TailoringServicesTo buy a sewing machine, lace, zippers and but...PKPakistanLahorePKR247.02014-01-01 06:25:41+00:002013-12-17 08:00:00+00:002014-01-01 18:07:34+00:0011.025NaNfemale, female, femaleirregular2014-01-01
18653066250.0250.0SewingServicesto purchase a sewing machine.INIndiaMaynaguriINR334.02014-01-01 09:48:35+00:002013-12-13 08:00:00+00:002014-01-01 17:18:09+00:0043.04user_favorite, user_favoritefemalebullet2014-01-01
19653080475.0475.0Beauty SalonServicesto buy more cosmetics products for her beauty ...PKPakistanLahorePKR245.02014-01-01 11:48:08+00:002013-12-19 08:00:00+00:002014-01-10 03:22:29+00:0014.018#Woman Owned Bizfemalemonthly2014-01-01
\n", + "
" + ], + "text/plain": [ + " id funded_amount loan_amount activity \\\n", + "0 653051 300.0 300.0 Fruits & Vegetables \n", + "1 653053 575.0 575.0 Rickshaw \n", + "2 653068 150.0 150.0 Transportation \n", + "3 653063 200.0 200.0 Embroidery \n", + "4 653084 400.0 400.0 Milk Sales \n", + "5 1080148 250.0 250.0 Services \n", + "6 653067 200.0 200.0 Dairy \n", + "7 653078 400.0 400.0 Beauty Salon \n", + "8 653082 475.0 475.0 Manufacturing \n", + "9 653048 625.0 625.0 Food Production/Sales \n", + "10 653060 200.0 200.0 Rickshaw \n", + "11 653088 400.0 400.0 Wholesale \n", + "12 653089 400.0 400.0 General Store \n", + "13 653062 400.0 400.0 Clothing Sales \n", + "14 653075 225.0 225.0 Poultry \n", + "15 653054 300.0 300.0 Rickshaw \n", + "16 653091 400.0 400.0 General Store \n", + "17 653052 875.0 875.0 Tailoring \n", + "18 653066 250.0 250.0 Sewing \n", + "19 653080 475.0 475.0 Beauty Salon \n", + "\n", + " sector use \\\n", + "0 Food To buy seasonal, fresh fruits to sell. \n", + "1 Transportation to repair and maintain the auto rickshaw used ... \n", + "2 Transportation To repair their old cycle-van and buy another ... \n", + "3 Arts to purchase an embroidery machine and a variet... \n", + "4 Food to purchase one buffalo. \n", + "5 Services purchase leather for my business using ksh 20000. \n", + "6 Agriculture To purchase a dairy cow and start a milk produ... \n", + "7 Services to buy more hair and skin care products. \n", + "8 Manufacturing to purchase leather, plastic soles and heels i... \n", + "9 Food to buy a stall, gram flour, ketchup, and coal ... \n", + "10 Transportation to cover the cost of repairing rickshaw \n", + "11 Wholesale to purchase biscuits, sweets and juices in bulk. \n", + "12 Retail to buy stock of rice, sugar and flour . \n", + "13 Clothing to purchase variety of winter clothes to sell. \n", + "14 Agriculture to expand her existing poultry farm business. \n", + "15 Transportation to buy a three-wheeled rickshaw. \n", + "16 Retail to buy packs of salts, biscuits and beverages. \n", + "17 Services To buy a sewing machine, lace, zippers and but... \n", + "18 Services to purchase a sewing machine. \n", + "19 Services to buy more cosmetics products for her beauty ... \n", + "\n", + " country_code country region currency partner_id \\\n", + "0 PK Pakistan Lahore PKR 247.0 \n", + "1 PK Pakistan Lahore PKR 247.0 \n", + "2 IN India Maynaguri INR 334.0 \n", + "3 PK Pakistan Lahore PKR 247.0 \n", + "4 PK Pakistan Abdul Hakeem PKR 245.0 \n", + "5 KE Kenya NaN KES NaN \n", + "6 IN India Maynaguri INR 334.0 \n", + "7 PK Pakistan Ellahabad PKR 245.0 \n", + "8 PK Pakistan Lahore PKR 245.0 \n", + "9 PK Pakistan Lahore PKR 247.0 \n", + "10 PK Pakistan Lahore PKR 247.0 \n", + "11 PK Pakistan Faisalabad PKR 245.0 \n", + "12 PK Pakistan Faisalabad PKR 245.0 \n", + "13 PK Pakistan Lahore PKR 247.0 \n", + "14 IN India Dhupguri INR 334.0 \n", + "15 PK Pakistan Lahore PKR 247.0 \n", + "16 PK Pakistan Faisalabad PKR 245.0 \n", + "17 PK Pakistan Lahore PKR 247.0 \n", + "18 IN India Maynaguri INR 334.0 \n", + "19 PK Pakistan Lahore PKR 245.0 \n", + "\n", + " posted_time disbursed_time \\\n", + "0 2014-01-01 06:12:39+00:00 2013-12-17 08:00:00+00:00 \n", + "1 2014-01-01 06:51:08+00:00 2013-12-17 08:00:00+00:00 \n", + "2 2014-01-01 09:58:07+00:00 2013-12-17 08:00:00+00:00 \n", + "3 2014-01-01 08:03:11+00:00 2013-12-24 08:00:00+00:00 \n", + "4 2014-01-01 11:53:19+00:00 2013-12-17 08:00:00+00:00 \n", + "5 2014-01-01 10:06:19+00:00 2014-01-30 01:42:48+00:00 \n", + "6 2014-01-01 09:51:02+00:00 2013-12-16 08:00:00+00:00 \n", + "7 2014-01-01 11:46:01+00:00 2013-12-20 08:00:00+00:00 \n", + "8 2014-01-01 11:49:43+00:00 2013-12-20 08:00:00+00:00 \n", + "9 2014-01-01 05:41:03+00:00 2013-12-17 08:00:00+00:00 \n", + "10 2014-01-01 07:32:39+00:00 2013-12-24 08:00:00+00:00 \n", + "11 2014-01-01 12:03:43+00:00 2013-12-16 08:00:00+00:00 \n", + "12 2014-01-01 12:04:57+00:00 2013-12-24 08:00:00+00:00 \n", + "13 2014-01-01 07:57:58+00:00 2013-12-24 08:00:00+00:00 \n", + "14 2014-01-01 11:24:40+00:00 2013-12-20 08:00:00+00:00 \n", + "15 2014-01-01 06:58:07+00:00 2013-12-17 08:00:00+00:00 \n", + "16 2014-01-01 12:09:10+00:00 2013-12-09 08:00:00+00:00 \n", + "17 2014-01-01 06:25:41+00:00 2013-12-17 08:00:00+00:00 \n", + "18 2014-01-01 09:48:35+00:00 2013-12-13 08:00:00+00:00 \n", + "19 2014-01-01 11:48:08+00:00 2013-12-19 08:00:00+00:00 \n", + "\n", + " funded_time term_in_months lender_count \\\n", + "0 2014-01-02 10:06:32+00:00 12.0 12 \n", + "1 2014-01-02 09:17:23+00:00 11.0 14 \n", + "2 2014-01-01 16:01:36+00:00 43.0 6 \n", + "3 2014-01-01 13:00:00+00:00 11.0 8 \n", + "4 2014-01-01 19:18:51+00:00 14.0 16 \n", + "5 2014-01-29 14:14:57+00:00 4.0 6 \n", + "6 2014-01-01 17:18:09+00:00 43.0 8 \n", + "7 2014-01-10 18:18:44+00:00 14.0 8 \n", + "8 2014-01-01 18:47:21+00:00 14.0 19 \n", + "9 2014-01-03 15:45:04+00:00 11.0 24 \n", + "10 2014-01-01 12:18:55+00:00 11.0 3 \n", + "11 2014-01-03 09:19:26+00:00 14.0 16 \n", + "12 2014-01-08 00:35:14+00:00 14.0 16 \n", + "13 2014-01-02 15:47:37+00:00 12.0 10 \n", + "14 2014-01-01 18:58:18+00:00 43.0 7 \n", + "15 2014-01-02 00:04:08+00:00 11.0 9 \n", + "16 2014-01-14 15:57:05+00:00 14.0 11 \n", + "17 2014-01-01 18:07:34+00:00 11.0 25 \n", + "18 2014-01-01 17:18:09+00:00 43.0 4 \n", + "19 2014-01-10 03:22:29+00:00 14.0 18 \n", + "\n", + " tags borrower_genders \\\n", + "0 NaN female \n", + "1 NaN female, female \n", + "2 user_favorite, user_favorite female \n", + "3 NaN female \n", + "4 NaN female \n", + "5 NaN female \n", + "6 user_favorite, user_favorite female \n", + "7 #Elderly, #Woman Owned Biz female \n", + "8 user_favorite female \n", + "9 NaN female \n", + "10 NaN female \n", + "11 NaN female \n", + "12 #Repeat Borrower, #Woman Owned Biz female \n", + "13 NaN female \n", + "14 user_favorite female \n", + "15 NaN female \n", + "16 #Woman Owned Biz, #Parent female \n", + "17 NaN female, female, female \n", + "18 user_favorite, user_favorite female \n", + "19 #Woman Owned Biz female \n", + "\n", + " repayment_interval date \n", + "0 irregular 2014-01-01 \n", + "1 irregular 2014-01-01 \n", + "2 bullet 2014-01-01 \n", + "3 irregular 2014-01-01 \n", + "4 monthly 2014-01-01 \n", + "5 irregular 2014-01-01 \n", + "6 bullet 2014-01-01 \n", + "7 monthly 2014-01-01 \n", + "8 monthly 2014-01-01 \n", + "9 irregular 2014-01-01 \n", + "10 irregular 2014-01-01 \n", + "11 monthly 2014-01-01 \n", + "12 monthly 2014-01-01 \n", + "13 irregular 2014-01-01 \n", + "14 bullet 2014-01-01 \n", + "15 irregular 2014-01-01 \n", + "16 monthly 2014-01-01 \n", + "17 irregular 2014-01-01 \n", + "18 bullet 2014-01-01 \n", + "19 monthly 2014-01-01 " + ] + }, + "execution_count": 28, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ - "births.pivot_table(index=['gender', 'month'], aggfunc='sum')" + "data[data.notnull()].head(20)" ] }, { "cell_type": "code", - "execution_count": null, + "execution_count": 31, "metadata": {}, - "outputs": [], + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
borrower_genders
0female
2female
3female
4female
5female
6female
7female
8female
9female
10female
\n", + "
" + ], + "text/plain": [ + " borrower_genders\n", + "0 female\n", + "2 female\n", + "3 female\n", + "4 female\n", + "5 female\n", + "6 female\n", + "7 female\n", + "8 female\n", + "9 female\n", + "10 female" + ] + }, + "execution_count": 31, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ - "births['year'].astype" + "data.loc[data.borrower_genders == 'female', ['borrower_genders']].head(10)" ] }, { "cell_type": "code", - "execution_count": null, + "execution_count": 34, "metadata": {}, - "outputs": [], + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
idfunded_amountloan_amountactivitysectorusecountry_codecountryregioncurrencypartner_idposted_timedisbursed_timefunded_timeterm_in_monthslender_counttagsborrower_gendersrepayment_intervaldate
0NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
1NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
2NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
3NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
4NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
5NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
6NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
7NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
8NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
9NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
10NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
11NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
12NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
13NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
14NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
15NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
16NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
17NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
18NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
19NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
20NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
21NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
22NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
23NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
24NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
25NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
26NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
27NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
28NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
29NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
...............................................................
671175NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671176NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671177NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671178NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671179NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671180NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671181NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671182NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671183NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671184NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671185NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671186NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671187NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671188NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671189NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671190NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671191NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671192NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671193NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671194NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671195NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671196NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671197NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671198NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671199NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671200NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671201NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671202NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671203NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671204NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
\n", + "

671205 rows × 20 columns

\n", + "
" + ], + "text/plain": [ + " id funded_amount loan_amount activity sector use country_code \\\n", + "0 NaN NaN NaN NaN NaN NaN NaN \n", + "1 NaN NaN NaN NaN NaN NaN NaN \n", + "2 NaN NaN NaN NaN NaN NaN NaN \n", + "3 NaN NaN NaN NaN NaN NaN NaN \n", + "4 NaN NaN NaN NaN NaN NaN NaN \n", + "5 NaN NaN NaN NaN NaN NaN NaN \n", + "6 NaN NaN NaN NaN NaN NaN NaN \n", + "7 NaN NaN NaN NaN NaN NaN NaN \n", + "8 NaN NaN NaN NaN NaN NaN NaN \n", + "9 NaN NaN NaN NaN NaN NaN NaN \n", + "10 NaN NaN NaN NaN NaN NaN NaN \n", + "11 NaN NaN NaN NaN NaN NaN NaN \n", + "12 NaN NaN NaN NaN NaN NaN NaN \n", + "13 NaN NaN NaN NaN NaN NaN NaN \n", + "14 NaN NaN NaN NaN NaN NaN NaN \n", + "15 NaN NaN NaN NaN NaN NaN NaN \n", + "16 NaN NaN NaN NaN NaN NaN NaN \n", + "17 NaN NaN NaN NaN NaN NaN NaN \n", + "18 NaN NaN NaN NaN NaN NaN NaN \n", + "19 NaN NaN NaN NaN NaN NaN NaN \n", + "20 NaN NaN NaN NaN NaN NaN NaN \n", + "21 NaN NaN NaN NaN NaN NaN NaN \n", + "22 NaN NaN NaN NaN NaN NaN NaN \n", + "23 NaN NaN NaN NaN NaN NaN NaN \n", + "24 NaN NaN NaN NaN NaN NaN NaN \n", + "25 NaN NaN NaN NaN NaN NaN NaN \n", + "26 NaN NaN NaN NaN NaN NaN NaN \n", + "27 NaN NaN NaN NaN NaN NaN NaN \n", + "28 NaN NaN NaN NaN NaN NaN NaN \n", + "29 NaN NaN NaN NaN NaN NaN NaN \n", + "... .. ... ... ... ... ... ... \n", + "671175 NaN NaN NaN NaN NaN NaN NaN \n", + "671176 NaN NaN NaN NaN NaN NaN NaN \n", + "671177 NaN NaN NaN NaN NaN NaN NaN \n", + "671178 NaN NaN NaN NaN NaN NaN NaN \n", + "671179 NaN NaN NaN NaN NaN NaN NaN \n", + "671180 NaN NaN NaN NaN NaN NaN NaN \n", + "671181 NaN NaN NaN NaN NaN NaN NaN \n", + "671182 NaN NaN NaN NaN NaN NaN NaN \n", + "671183 NaN NaN NaN NaN NaN NaN NaN \n", + "671184 NaN NaN NaN NaN NaN NaN NaN \n", + "671185 NaN NaN NaN NaN NaN NaN NaN \n", + "671186 NaN NaN NaN NaN NaN NaN NaN \n", + "671187 NaN NaN NaN NaN NaN NaN NaN \n", + "671188 NaN NaN NaN NaN NaN NaN NaN \n", + "671189 NaN NaN NaN NaN NaN NaN NaN \n", + "671190 NaN NaN NaN NaN NaN NaN NaN \n", + "671191 NaN NaN NaN NaN NaN NaN NaN \n", + "671192 NaN NaN NaN NaN NaN NaN NaN \n", + "671193 NaN NaN NaN NaN NaN NaN NaN \n", + "671194 NaN NaN NaN NaN NaN NaN NaN \n", + "671195 NaN NaN NaN NaN NaN NaN NaN \n", + "671196 NaN NaN NaN NaN NaN NaN NaN \n", + "671197 NaN NaN NaN NaN NaN NaN NaN \n", + "671198 NaN NaN NaN NaN NaN NaN NaN \n", + "671199 NaN NaN NaN NaN NaN NaN NaN \n", + "671200 NaN NaN NaN NaN NaN NaN NaN \n", + "671201 NaN NaN NaN NaN NaN NaN NaN \n", + "671202 NaN NaN NaN NaN NaN NaN NaN \n", + "671203 NaN NaN NaN NaN NaN NaN NaN \n", + "671204 NaN NaN NaN NaN NaN NaN NaN \n", + "\n", + " country region currency partner_id posted_time disbursed_time \\\n", + "0 NaN NaN NaN NaN NaN NaN \n", + "1 NaN NaN NaN NaN NaN NaN \n", + "2 NaN NaN NaN NaN NaN NaN \n", + "3 NaN NaN NaN NaN NaN NaN \n", + "4 NaN NaN NaN NaN NaN NaN \n", + "5 NaN NaN NaN NaN NaN NaN \n", + "6 NaN NaN NaN NaN NaN NaN \n", + "7 NaN NaN NaN NaN NaN NaN \n", + "8 NaN NaN NaN NaN NaN NaN \n", + "9 NaN NaN NaN NaN NaN NaN \n", + "10 NaN NaN NaN NaN NaN NaN \n", + "11 NaN NaN NaN NaN NaN NaN \n", + "12 NaN NaN NaN NaN NaN NaN \n", + "13 NaN NaN NaN NaN NaN NaN \n", + "14 NaN NaN NaN NaN NaN NaN \n", + "15 NaN NaN NaN NaN NaN NaN \n", + "16 NaN NaN NaN NaN NaN NaN \n", + "17 NaN NaN NaN NaN NaN NaN \n", + "18 NaN NaN NaN NaN NaN NaN \n", + "19 NaN NaN NaN NaN NaN NaN \n", + "20 NaN NaN NaN NaN NaN NaN \n", + "21 NaN NaN NaN NaN NaN NaN \n", + "22 NaN NaN NaN NaN NaN NaN \n", + "23 NaN NaN NaN NaN NaN NaN \n", + "24 NaN NaN NaN NaN NaN NaN \n", + "25 NaN NaN NaN NaN NaN NaN \n", + "26 NaN NaN NaN NaN NaN NaN \n", + "27 NaN NaN NaN NaN NaN NaN \n", + "28 NaN NaN NaN NaN NaN NaN \n", + "29 NaN NaN NaN NaN NaN NaN \n", + "... ... ... ... ... ... ... \n", + "671175 NaN NaN NaN NaN NaN NaN \n", + "671176 NaN NaN NaN NaN NaN NaN \n", + "671177 NaN NaN NaN NaN NaN NaN \n", + "671178 NaN NaN NaN NaN NaN NaN \n", + "671179 NaN NaN NaN NaN NaN NaN \n", + "671180 NaN NaN NaN NaN NaN NaN \n", + "671181 NaN NaN NaN NaN NaN NaN \n", + "671182 NaN NaN NaN NaN NaN NaN \n", + "671183 NaN NaN NaN NaN NaN NaN \n", + "671184 NaN NaN NaN NaN NaN NaN \n", + "671185 NaN NaN NaN NaN NaN NaN \n", + "671186 NaN NaN NaN NaN NaN NaN \n", + "671187 NaN NaN NaN NaN NaN NaN \n", + "671188 NaN NaN NaN NaN NaN NaN \n", + "671189 NaN NaN NaN NaN NaN NaN \n", + "671190 NaN NaN NaN NaN NaN NaN \n", + "671191 NaN NaN NaN NaN NaN NaN \n", + "671192 NaN NaN NaN NaN NaN NaN \n", + "671193 NaN NaN NaN NaN NaN NaN \n", + "671194 NaN NaN NaN NaN NaN NaN \n", + "671195 NaN NaN NaN NaN NaN NaN \n", + "671196 NaN NaN NaN NaN NaN NaN \n", + "671197 NaN NaN NaN NaN NaN NaN \n", + "671198 NaN NaN NaN NaN NaN NaN \n", + "671199 NaN NaN NaN NaN NaN NaN \n", + "671200 NaN NaN NaN NaN NaN NaN \n", + "671201 NaN NaN NaN NaN NaN NaN \n", + "671202 NaN NaN NaN NaN NaN NaN \n", + "671203 NaN NaN NaN NaN NaN NaN \n", + "671204 NaN NaN NaN NaN NaN NaN \n", + "\n", + " funded_time term_in_months lender_count tags borrower_genders \\\n", + "0 NaN NaN NaN NaN NaN \n", + "1 NaN NaN NaN NaN NaN \n", + "2 NaN NaN NaN NaN NaN \n", + "3 NaN NaN NaN NaN NaN \n", + "4 NaN NaN NaN NaN NaN \n", + "5 NaN NaN NaN NaN NaN \n", + "6 NaN NaN NaN NaN NaN \n", + "7 NaN NaN NaN NaN NaN \n", + "8 NaN NaN NaN NaN NaN \n", + "9 NaN NaN NaN NaN NaN \n", + "10 NaN NaN NaN NaN NaN \n", + "11 NaN NaN NaN NaN NaN \n", + "12 NaN NaN NaN NaN NaN \n", + "13 NaN NaN NaN NaN NaN \n", + "14 NaN NaN NaN NaN NaN \n", + "15 NaN NaN NaN NaN NaN \n", + "16 NaN NaN NaN NaN NaN \n", + "17 NaN NaN NaN NaN NaN \n", + "18 NaN NaN NaN NaN NaN \n", + "19 NaN NaN NaN NaN NaN \n", + "20 NaN NaN NaN NaN NaN \n", + "21 NaN NaN NaN NaN NaN \n", + "22 NaN NaN NaN NaN NaN \n", + "23 NaN NaN NaN NaN NaN \n", + "24 NaN NaN NaN NaN NaN \n", + "25 NaN NaN NaN NaN NaN \n", + "26 NaN NaN NaN NaN NaN \n", + "27 NaN NaN NaN NaN NaN \n", + "28 NaN NaN NaN NaN NaN \n", + "29 NaN NaN NaN NaN NaN \n", + "... ... ... ... ... ... \n", + "671175 NaN NaN NaN NaN NaN \n", + "671176 NaN NaN NaN NaN NaN \n", + "671177 NaN NaN NaN NaN NaN \n", + "671178 NaN NaN NaN NaN NaN \n", + "671179 NaN NaN NaN NaN NaN \n", + "671180 NaN NaN NaN NaN NaN \n", + "671181 NaN NaN NaN NaN NaN \n", + "671182 NaN NaN NaN NaN NaN \n", + "671183 NaN NaN NaN NaN NaN \n", + "671184 NaN NaN NaN NaN NaN \n", + "671185 NaN NaN NaN NaN NaN \n", + "671186 NaN NaN NaN NaN NaN \n", + "671187 NaN NaN NaN NaN NaN \n", + "671188 NaN NaN NaN NaN NaN \n", + "671189 NaN NaN NaN NaN NaN \n", + "671190 NaN NaN NaN NaN NaN \n", + "671191 NaN NaN NaN NaN NaN \n", + "671192 NaN NaN NaN NaN NaN \n", + "671193 NaN NaN NaN NaN NaN \n", + "671194 NaN NaN NaN NaN NaN \n", + "671195 NaN NaN NaN NaN NaN \n", + "671196 NaN NaN NaN NaN NaN \n", + "671197 NaN NaN NaN NaN NaN \n", + "671198 NaN NaN NaN NaN NaN \n", + "671199 NaN NaN NaN NaN NaN \n", + "671200 NaN NaN NaN NaN NaN \n", + "671201 NaN NaN NaN NaN NaN \n", + "671202 NaN NaN NaN NaN NaN \n", + "671203 NaN NaN NaN NaN NaN \n", + "671204 NaN NaN NaN NaN NaN \n", + "\n", + " repayment_interval date \n", + "0 NaN NaN \n", + "1 NaN NaN \n", + "2 NaN NaN \n", + "3 NaN NaN \n", + "4 NaN NaN \n", + "5 NaN NaN \n", + "6 NaN NaN \n", + "7 NaN NaN \n", + "8 NaN NaN \n", + "9 NaN NaN \n", + "10 NaN NaN \n", + "11 NaN NaN \n", + "12 NaN NaN \n", + "13 NaN NaN \n", + "14 NaN NaN \n", + "15 NaN NaN \n", + "16 NaN NaN \n", + "17 NaN NaN \n", + "18 NaN NaN \n", + "19 NaN NaN \n", + "20 NaN NaN \n", + "21 NaN NaN \n", + "22 NaN NaN \n", + "23 NaN NaN \n", + "24 NaN NaN \n", + "25 NaN NaN \n", + "26 NaN NaN \n", + "27 NaN NaN \n", + "28 NaN NaN \n", + "29 NaN NaN \n", + "... ... ... \n", + "671175 NaN NaN \n", + "671176 NaN NaN \n", + "671177 NaN NaN \n", + "671178 NaN NaN \n", + "671179 NaN NaN \n", + "671180 NaN NaN \n", + "671181 NaN NaN \n", + "671182 NaN NaN \n", + "671183 NaN NaN \n", + "671184 NaN NaN \n", + "671185 NaN NaN \n", + "671186 NaN NaN \n", + "671187 NaN NaN \n", + "671188 NaN NaN \n", + "671189 NaN NaN \n", + "671190 NaN NaN \n", + "671191 NaN NaN \n", + "671192 NaN NaN \n", + "671193 NaN NaN \n", + "671194 NaN NaN \n", + "671195 NaN NaN \n", + "671196 NaN NaN \n", + "671197 NaN NaN \n", + "671198 NaN NaN \n", + "671199 NaN NaN \n", + "671200 NaN NaN \n", + "671201 NaN NaN \n", + "671202 NaN NaN \n", + "671203 NaN NaN \n", + "671204 NaN NaN \n", + "\n", + "[671205 rows x 20 columns]" + ] + }, + "execution_count": 34, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ - "births['year'].cat" + "data.fillna(method='ffill')" ] }, { "cell_type": "code", - "execution_count": null, + "execution_count": 37, "metadata": {}, - "outputs": [], + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
LocationNameISOcountryregionworld_regionMPIgeolatlon
0Badakhshan, AfghanistanAFGAfghanistanBadakhshanSouth Asia0.387(36.7347725, 70.81199529999999)36.73477270.811995
1Badghis, AfghanistanAFGAfghanistanBadghisSouth Asia0.466(35.1671339, 63.7695384)35.16713463.769538
2Baghlan, AfghanistanAFGAfghanistanBaghlanSouth Asia0.300(35.8042947, 69.2877535)35.80429569.287754
3Balkh, AfghanistanAFGAfghanistanBalkhSouth Asia0.301(36.7550603, 66.8975372)36.75506066.897537
4Bamyan, AfghanistanAFGAfghanistanBamyanSouth Asia0.325(34.8100067, 67.8212104)34.81000767.821210
5Daykundi, AfghanistanAFGAfghanistanDaykundiSouth Asia0.313(33.669495, 66.0463534)33.66949566.046353
6Farah, AfghanistanAFGAfghanistanFarahSouth Asia0.319(32.4464635, 62.1454133)32.44646462.145413
7Faryab, AfghanistanAFGAfghanistanFaryabSouth Asia0.250(36.0795613, 64.90595499999999)36.07956164.905955
8Ghazni, AfghanistanAFGAfghanistanGhazniSouth Asia0.245(33.5450587, 68.4173972)33.54505968.417397
9Ghor, AfghanistanAFGAfghanistanGhorSouth Asia0.384(34.0995776, 64.90595499999999)34.09957864.905955
\n", + "
" + ], + "text/plain": [ + " LocationName ISO country region world_region MPI \\\n", + "0 Badakhshan, Afghanistan AFG Afghanistan Badakhshan South Asia 0.387 \n", + "1 Badghis, Afghanistan AFG Afghanistan Badghis South Asia 0.466 \n", + "2 Baghlan, Afghanistan AFG Afghanistan Baghlan South Asia 0.300 \n", + "3 Balkh, Afghanistan AFG Afghanistan Balkh South Asia 0.301 \n", + "4 Bamyan, Afghanistan AFG Afghanistan Bamyan South Asia 0.325 \n", + "5 Daykundi, Afghanistan AFG Afghanistan Daykundi South Asia 0.313 \n", + "6 Farah, Afghanistan AFG Afghanistan Farah South Asia 0.319 \n", + "7 Faryab, Afghanistan AFG Afghanistan Faryab South Asia 0.250 \n", + "8 Ghazni, Afghanistan AFG Afghanistan Ghazni South Asia 0.245 \n", + "9 Ghor, Afghanistan AFG Afghanistan Ghor South Asia 0.384 \n", + "\n", + " geo lat lon \n", + "0 (36.7347725, 70.81199529999999) 36.734772 70.811995 \n", + "1 (35.1671339, 63.7695384) 35.167134 63.769538 \n", + "2 (35.8042947, 69.2877535) 35.804295 69.287754 \n", + "3 (36.7550603, 66.8975372) 36.755060 66.897537 \n", + "4 (34.8100067, 67.8212104) 34.810007 67.821210 \n", + "5 (33.669495, 66.0463534) 33.669495 66.046353 \n", + "6 (32.4464635, 62.1454133) 32.446464 62.145413 \n", + "7 (36.0795613, 64.90595499999999) 36.079561 64.905955 \n", + "8 (33.5450587, 68.4173972) 33.545059 68.417397 \n", + "9 (34.0995776, 64.90595499999999) 34.099578 64.905955 " + ] + }, + "execution_count": 37, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ - "pt = births.pivot_table(values='births', columns='month', index=['gender'], aggfunc='sum')\n", - "pt.head(10)" + "regions = pd.read_csv('C:/Users/user/Desktop/kasee/kiva/kiva_mpi_region_locations.csv')\n", + "regions.head(10)" ] }, { "cell_type": "code", - "execution_count": null, + "execution_count": 41, "metadata": {}, - "outputs": [], + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
sum
MPI
country
Afghanistan10.535
Albania0.000
Algeria0.000
Armenia0.000
Azerbaijan0.000
Bangladesh1.458
Barbados0.000
Belize0.141
Benin3.844
Bhutan2.346
Bolivia, Plurinational State of0.878
Bosnia and Herzegovina0.000
Brazil0.736
Burkina Faso7.120
Burundi2.059
Cambodia3.117
Cameroon2.434
Central African Republic7.256
Chad12.241
China0.055
Colombia0.402
Comoros0.549
Congo, Democratic Republic of the4.352
Congo, Republic of3.187
Cote d'Ivoire3.828
Djibouti0.339
Dominican Republic0.416
Ecuador0.073
Egypt0.342
El Salvador0.441
......
Philippines1.051
Rwanda1.214
Saint Lucia0.000
Sao Tome and Principe0.400
Senegal1.403
Serbia0.000
Sierra Leone6.735
Somalia0.000
South Africa0.000
South Sudan4.948
Sudan5.821
Suriname0.335
Swaziland0.294
Syrian Arab Republic0.205
Tajikistan0.233
Tanzania, United Republic of2.397
Thailand0.000
Timor-Leste4.846
Togo1.634
Trinidad and Tobago0.104
Tunisia0.000
Turkmenistan0.000
Uganda3.753
Ukraine0.000
Uzbekistan0.045
Vanuatu0.000
Viet Nam0.205
Yemen4.745
Zambia3.122
Zimbabwe1.514
\n", + "

102 rows × 1 columns

\n", + "
" + ], + "text/plain": [ + " sum\n", + " MPI\n", + "country \n", + "Afghanistan 10.535\n", + "Albania 0.000\n", + "Algeria 0.000\n", + "Armenia 0.000\n", + "Azerbaijan 0.000\n", + "Bangladesh 1.458\n", + "Barbados 0.000\n", + "Belize 0.141\n", + "Benin 3.844\n", + "Bhutan 2.346\n", + "Bolivia, Plurinational State of 0.878\n", + "Bosnia and Herzegovina 0.000\n", + "Brazil 0.736\n", + "Burkina Faso 7.120\n", + "Burundi 2.059\n", + "Cambodia 3.117\n", + "Cameroon 2.434\n", + "Central African Republic 7.256\n", + "Chad 12.241\n", + "China 0.055\n", + "Colombia 0.402\n", + "Comoros 0.549\n", + "Congo, Democratic Republic of the 4.352\n", + "Congo, Republic of 3.187\n", + "Cote d'Ivoire 3.828\n", + "Djibouti 0.339\n", + "Dominican Republic 0.416\n", + "Ecuador 0.073\n", + "Egypt 0.342\n", + "El Salvador 0.441\n", + "... ...\n", + "Philippines 1.051\n", + "Rwanda 1.214\n", + "Saint Lucia 0.000\n", + "Sao Tome and Principe 0.400\n", + "Senegal 1.403\n", + "Serbia 0.000\n", + "Sierra Leone 6.735\n", + "Somalia 0.000\n", + "South Africa 0.000\n", + "South Sudan 4.948\n", + "Sudan 5.821\n", + "Suriname 0.335\n", + "Swaziland 0.294\n", + "Syrian Arab Republic 0.205\n", + "Tajikistan 0.233\n", + "Tanzania, United Republic of 2.397\n", + "Thailand 0.000\n", + "Timor-Leste 4.846\n", + "Togo 1.634\n", + "Trinidad and Tobago 0.104\n", + "Tunisia 0.000\n", + "Turkmenistan 0.000\n", + "Uganda 3.753\n", + "Ukraine 0.000\n", + "Uzbekistan 0.045\n", + "Vanuatu 0.000\n", + "Viet Nam 0.205\n", + "Yemen 4.745\n", + "Zambia 3.122\n", + "Zimbabwe 1.514\n", + "\n", + "[102 rows x 1 columns]" + ] + }, + "execution_count": 41, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "pt = regions.pivot_table(index=['country'], aggfunc=[np.sum], values=['MPI'])\n", + "pt" + ] + }, + { + "cell_type": "code", + "execution_count": 60, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "country\n", + "Afghanistan 10.535\n", + "Albania 0.000\n", + "Algeria 0.000\n", + "Armenia 0.000\n", + "Azerbaijan 0.000\n", + "Bangladesh 1.458\n", + "Barbados 0.000\n", + "Belize 0.141\n", + "Benin 3.844\n", + "Bhutan 2.346\n", + "Name: MPI, dtype: float64" + ] + }, + "execution_count": 60, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "pt['sum'].MPI.head(10)" + ] + }, + { + "cell_type": "code", + "execution_count": 72, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "0 To buy seasonal, fresh fruits to sell. \n", + "1 to repair and maintain the auto rickshaw used ...\n", + "2 To repair their old cycle-van and buy another ...\n", + "3 to purchase an embroidery machine and a variet...\n", + "4 to purchase one buffalo.\n", + "5 purchase leather for my business using ksh 20000.\n", + "6 To purchase a dairy cow and start a milk produ...\n", + "7 to buy more hair and skin care products. \n", + "8 to purchase leather, plastic soles and heels i...\n", + "9 to buy a stall, gram flour, ketchup, and coal ...\n", + "10 to cover the cost of repairing rickshaw\n", + "11 to purchase biscuits, sweets and juices in bulk.\n", + "12 to buy stock of rice, sugar and flour .\n", + "13 to purchase variety of winter clothes to sell.\n", + "14 to expand her existing poultry farm business.\n", + "15 to buy a three-wheeled rickshaw. \n", + "16 to buy packs of salts, biscuits and beverages.\n", + "17 To buy a sewing machine, lace, zippers and but...\n", + "18 to purchase a sewing machine.\n", + "19 to buy more cosmetics products for her beauty ...\n", + "20 to buy ingredients to make bakery products. \n", + "21 to purchase vegetables, chicken, and oil to co...\n", + "22 To buy winter clothing to sell\n", + "23 to buy reels of threads in different colors an...\n", + "24 to purchase a variety of needed food items to ...\n", + "25 to purchase potato seeds and fertilizers for g...\n", + "26 to purchase stones for starting a business sup...\n", + "27 to cover the cost of repairing rickshaw\n", + "28 to purchase potato seeds and fertilizers for g...\n", + "29 to purchase potato seeds and fertilizer for fa...\n", + " ... \n", + "671175 Pretend the flagged issue was addressed by KC.\n", + "671176 Edited loan use in english.\n", + "671177 [True, u'to start a turducken farm.'] - this l...\n", + "671178 NaN\n", + "671179 [True, u'para compara: cemento, arenya y ladri...\n", + "671180 Translated loan use to english.\n", + "671181 Reviewed loan use in english.\n", + "671182 Pretend the flagged issue was addressed by KC.\n", + "671183 Pretend the issue with spanish loan was addres...\n", + "671184 Translated loan use to english.\n", + "671185 NaN\n", + "671186 [True, u'para compara: cemento, arenya y ladri...\n", + "671187 [True, u'to start a turducken farm.'] - this l...\n", + "671188 Reviewed loan use in english.\n", + "671189 [True, u'to start a turducken farm.'] - this l...\n", + "671190 [True, u'to start a turducken farm.'] - this l...\n", + "671191 Translated loan use to english.\n", + "671192 Translated loan use to english.\n", + "671193 Pretend the flagged issue was addressed by KC.\n", + "671194 Kiva Coordinator fixed issue loan (no longer v...\n", + "671195 Edited loan use in english.\n", + "671196 Reviewed loan use in english.\n", + "671197 Pretend the issue with loan got addressed by K...\n", + "671198 Pretend the issue with spanish loan was addres...\n", + "671199 [True, u'para compara: cemento, arenya y ladri...\n", + "671200 [True, u'para compara: cemento, arenya y ladri...\n", + "671201 [True, u'to start a turducken farm.'] - this l...\n", + "671202 NaN\n", + "671203 [True, u'to start a turducken farm.'] - this l...\n", + "671204 [True, u'to start a turducken farm.'] - this l...\n", + "Name: use, Length: 671205, dtype: object" + ] + }, + "execution_count": 72, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ - "pt.ix[:, :3]" + "data['use']" ] } ], From d86ac3716d8ea11cb2abbd5493092f9ba75ebbaa Mon Sep 17 00:00:00 2001 From: kasre96 Date: Sat, 16 Feb 2019 12:52:20 +0300 Subject: [PATCH 21/43] analyse kiva sector loans --- .gitignore | 3 +- .idea/Python4ds_cohort-1.iml | 2 +- .idea/isaka.iml | 13 + .idea/misc.xml | 2 +- .idea/workspace.xml | 76 +- .../kiva_analytics-checkpoint.ipynb | 1278 +++++- .../.ipynb_checkpoints/tests-checkpoint.ipynb | 3822 ++++++++--------- notebooks/kiva_analytics.ipynb | 1048 ++++- notebooks/tests.ipynb | 3811 ++++++++-------- requirements.txt | 2 + 10 files changed, 5843 insertions(+), 4214 deletions(-) create mode 100644 .idea/isaka.iml diff --git a/.gitignore b/.gitignore index c5d561e..d174d47 100644 --- a/.gitignore +++ b/.gitignore @@ -1,3 +1,4 @@ env/ venv/ -myvenv/ \ No newline at end of file +myvenv/ +kiva_loans.csv \ No newline at end of file diff --git a/.idea/Python4ds_cohort-1.iml b/.idea/Python4ds_cohort-1.iml index c597cfb..d9f7706 100644 --- a/.idea/Python4ds_cohort-1.iml +++ b/.idea/Python4ds_cohort-1.iml @@ -4,7 +4,7 @@ - + diff --git a/.idea/isaka.iml b/.idea/isaka.iml new file mode 100644 index 0000000..5821e6f --- /dev/null +++ b/.idea/isaka.iml @@ -0,0 +1,13 @@ + + + + + + + + + + + + \ No newline at end of file diff --git a/.idea/misc.xml b/.idea/misc.xml index 22be2d5..f9ea3e3 100644 --- a/.idea/misc.xml +++ b/.idea/misc.xml @@ -1,4 +1,4 @@ - + \ No newline at end of file diff --git a/.idea/workspace.xml b/.idea/workspace.xml index 8029d79..f8a436b 100644 --- a/.idea/workspace.xml +++ b/.idea/workspace.xml @@ -2,9 +2,15 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + @@ -23,8 +62,8 @@ @@ -37,22 +76,22 @@ + - - + + + diff --git a/notebooks/.ipynb_checkpoints/kiva_analytics-checkpoint.ipynb b/notebooks/.ipynb_checkpoints/kiva_analytics-checkpoint.ipynb index 04b76b3..affaa3f 100644 --- a/notebooks/.ipynb_checkpoints/kiva_analytics-checkpoint.ipynb +++ b/notebooks/.ipynb_checkpoints/kiva_analytics-checkpoint.ipynb @@ -29,7 +29,7 @@ }, { "cell_type": "code", - "execution_count": 3, + "execution_count": 16, "metadata": {}, "outputs": [ { @@ -239,7 +239,7 @@ "4 monthly 2014-01-01 " ] }, - "execution_count": 3, + "execution_count": 16, "metadata": {}, "output_type": "execute_result" } @@ -264,7 +264,7 @@ }, { "cell_type": "code", - "execution_count": 13, + "execution_count": 3, "metadata": {}, "outputs": [ { @@ -474,7 +474,7 @@ "4 monthly 2014-01-01 " ] }, - "execution_count": 13, + "execution_count": 3, "metadata": {}, "output_type": "execute_result" } @@ -496,7 +496,7 @@ }, { "cell_type": "code", - "execution_count": 5, + "execution_count": 4, "metadata": {}, "outputs": [ { @@ -627,7 +627,7 @@ "max 158.000000 2986.000000 " ] }, - "execution_count": 5, + "execution_count": 4, "metadata": {}, "output_type": "execute_result" } @@ -662,7 +662,7 @@ }, { "cell_type": "code", - "execution_count": 6, + "execution_count": 5, "metadata": {}, "outputs": [ { @@ -774,7 +774,7 @@ "Burkina Faso 2909975.0 2972700.0" ] }, - "execution_count": 6, + "execution_count": 5, "metadata": {}, "output_type": "execute_result" } @@ -788,7 +788,7 @@ }, { "cell_type": "code", - "execution_count": 10, + "execution_count": 6, "metadata": {}, "outputs": [ { @@ -861,7 +861,7 @@ "Belize 114025.0 114025.0" ] }, - "execution_count": 10, + "execution_count": 6, "metadata": {}, "output_type": "execute_result" } @@ -883,7 +883,7 @@ }, { "cell_type": "code", - "execution_count": 27, + "execution_count": 7, "metadata": {}, "outputs": [], "source": [ @@ -901,7 +901,7 @@ }, { "cell_type": "code", - "execution_count": 30, + "execution_count": 8, "metadata": {}, "outputs": [ { @@ -962,7 +962,7 @@ }, { "cell_type": "code", - "execution_count": 35, + "execution_count": 9, "metadata": {}, "outputs": [ { @@ -1078,7 +1078,7 @@ "Wholesale 995200.0" ] }, - "execution_count": 35, + "execution_count": 9, "metadata": {}, "output_type": "execute_result" } @@ -1099,7 +1099,7 @@ }, { "cell_type": "code", - "execution_count": 36, + "execution_count": 10, "metadata": {}, "outputs": [ { @@ -1175,7 +1175,7 @@ "max 1.430679e+08" ] }, - "execution_count": 36, + "execution_count": 10, "metadata": {}, "output_type": "execute_result" } @@ -1205,7 +1205,7 @@ }, { "cell_type": "code", - "execution_count": 37, + "execution_count": 11, "metadata": {}, "outputs": [ { @@ -1230,7 +1230,7 @@ "Name: loan_amount, dtype: float64" ] }, - "execution_count": 37, + "execution_count": 11, "metadata": {}, "output_type": "execute_result" } @@ -1243,7 +1243,7 @@ }, { "cell_type": "code", - "execution_count": 38, + "execution_count": 12, "metadata": {}, "outputs": [ { @@ -1254,7 +1254,7 @@ "Name: loan_amount, dtype: float64" ] }, - "execution_count": 38, + "execution_count": 12, "metadata": {}, "output_type": "execute_result" } @@ -1266,7 +1266,7 @@ }, { "cell_type": "code", - "execution_count": 39, + "execution_count": 13, "metadata": {}, "outputs": [ { @@ -1277,7 +1277,7 @@ "Name: loan_amount, dtype: float64" ] }, - "execution_count": 39, + "execution_count": 13, "metadata": {}, "output_type": "execute_result" } @@ -1296,12 +1296,426 @@ "2. The sector with the smallest amount used on it was **Wholesale**, with a total of **995,200 USD** used on it." ] }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "# Date/Time based Analytics\n", + "Since the dates provided in the dataset are all objects, we first convert them to date/time values for easier manipulation." + ] + }, { "cell_type": "code", - "execution_count": null, + "execution_count": 26, "metadata": {}, "outputs": [], - "source": [] + "source": [ + "# Extract all time columns and convert them first to YYYY-mm-dd formatted objects then to datetime values\n", + "kiva_available_data['posted_time'] = pd.to_datetime(kiva_available_data['posted_time'].dt.strftime(\"%Y-%m-%d\"))\n", + "kiva_available_data['funded_time'] = pd.to_datetime(kiva_available_data['funded_time'].dt.strftime(\"%Y-%m-%d\"))\n", + "kiva_available_data['disbursed_time'] = pd.to_datetime(kiva_available_data['disbursed_time'].dt.strftime(\"%Y-%m-%d\"))" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "#### Next we create a column containing the time difference between when the loan was funded and when it was posted" + ] + }, + { + "cell_type": "code", + "execution_count": 31, + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
idfunded_amountloan_amountactivitysectorusecountry_codecountryregioncurrency...disbursed_timefunded_timeterm_in_monthslender_counttagsborrower_gendersrepayment_intervaldatefunding_perioddisbursement_period
0653051300.0300.0Fruits & VegetablesFoodTo buy seasonal, fresh fruits to sell.PKPakistanLahorePKR...2013-12-172014-01-0212.012NaNfemaleirregular2014-01-011 days-16 days
1653053575.0575.0RickshawTransportationto repair and maintain the auto rickshaw used ...PKPakistanLahorePKR...2013-12-172014-01-0211.014NaNfemale, femaleirregular2014-01-011 days-16 days
2653068150.0150.0TransportationTransportationTo repair their old cycle-van and buy another ...INIndiaMaynaguriINR...2013-12-172014-01-0143.06user_favorite, user_favoritefemalebullet2014-01-010 days-15 days
3653063200.0200.0EmbroideryArtsto purchase an embroidery machine and a variet...PKPakistanLahorePKR...2013-12-242014-01-0111.08NaNfemaleirregular2014-01-010 days-8 days
4653084400.0400.0Milk SalesFoodto purchase one buffalo.PKPakistanAbdul HakeemPKR...2013-12-172014-01-0114.016NaNfemalemonthly2014-01-010 days-15 days
\n", + "

5 rows × 22 columns

\n", + "
" + ], + "text/plain": [ + " id funded_amount loan_amount activity sector \\\n", + "0 653051 300.0 300.0 Fruits & Vegetables Food \n", + "1 653053 575.0 575.0 Rickshaw Transportation \n", + "2 653068 150.0 150.0 Transportation Transportation \n", + "3 653063 200.0 200.0 Embroidery Arts \n", + "4 653084 400.0 400.0 Milk Sales Food \n", + "\n", + " use country_code country \\\n", + "0 To buy seasonal, fresh fruits to sell. PK Pakistan \n", + "1 to repair and maintain the auto rickshaw used ... PK Pakistan \n", + "2 To repair their old cycle-van and buy another ... IN India \n", + "3 to purchase an embroidery machine and a variet... PK Pakistan \n", + "4 to purchase one buffalo. PK Pakistan \n", + "\n", + " region currency ... disbursed_time funded_time term_in_months \\\n", + "0 Lahore PKR ... 2013-12-17 2014-01-02 12.0 \n", + "1 Lahore PKR ... 2013-12-17 2014-01-02 11.0 \n", + "2 Maynaguri INR ... 2013-12-17 2014-01-01 43.0 \n", + "3 Lahore PKR ... 2013-12-24 2014-01-01 11.0 \n", + "4 Abdul Hakeem PKR ... 2013-12-17 2014-01-01 14.0 \n", + "\n", + " lender_count tags borrower_genders \\\n", + "0 12 NaN female \n", + "1 14 NaN female, female \n", + "2 6 user_favorite, user_favorite female \n", + "3 8 NaN female \n", + "4 16 NaN female \n", + "\n", + " repayment_interval date funding_period disbursement_period \n", + "0 irregular 2014-01-01 1 days -16 days \n", + "1 irregular 2014-01-01 1 days -16 days \n", + "2 bullet 2014-01-01 0 days -15 days \n", + "3 irregular 2014-01-01 0 days -8 days \n", + "4 monthly 2014-01-01 0 days -15 days \n", + "\n", + "[5 rows x 22 columns]" + ] + }, + "execution_count": 31, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# Create a funding period column: Difference between time posted and time funded for a loan\n", + "kiva_available_data['funding_period'] = (kiva_available_data['funded_time'] - kiva_available_data['posted_time'])\n", + "\n", + "kiva_available_data.head()" + ] + }, + { + "cell_type": "code", + "execution_count": 38, + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
idfunded_amountloan_amountactivitysectorusecountry_codecountryregioncurrency...disbursed_timefunded_timeterm_in_monthslender_counttagsborrower_gendersrepayment_intervaldatefunding_perioddisbursement_period
423441080950125.0125.0ServicesServicesadd more stock to my shopKEKenyaNaNKES...2015-06-092015-06-036.05NaNfemaleirregular2014-04-08421 days6 days
\n", + "

1 rows × 22 columns

\n", + "
" + ], + "text/plain": [ + " id funded_amount loan_amount activity sector \\\n", + "42344 1080950 125.0 125.0 Services Services \n", + "\n", + " use country_code country region currency ... \\\n", + "42344 add more stock to my shop KE Kenya NaN KES ... \n", + "\n", + " disbursed_time funded_time term_in_months lender_count tags \\\n", + "42344 2015-06-09 2015-06-03 6.0 5 NaN \n", + "\n", + " borrower_genders repayment_interval date funding_period \\\n", + "42344 female irregular 2014-04-08 421 days \n", + "\n", + " disbursement_period \n", + "42344 6 days \n", + "\n", + "[1 rows x 22 columns]" + ] + }, + "execution_count": 38, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# Extract the funding period column where there are no null values\n", + "funding_period = kiva_available_data[kiva_available_data['funding_period'].notnull()]['funding_period']\n", + "\n", + "# return the maximum funding period\n", + "min_funding_period = funding_period.max()\n", + "\n", + "#Fetch the data at that period\n", + "kiva_available_data.query('funding_period == @min_funding_period')" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### From the data above, we can see that:\n", + " 1. The maximum amount it took for a loan from the time it was posted on kiva to the time it was funded was **421 days**.\n", + " 2. This loan also took 6 days to be disbursed to the borrower from the time it was funded.\n", + " 3. The loan, a total of **125 USD**, was loaned to a female in kenya, which she used to add more stock to her shop." + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### More date/time analytics" + ] + }, + { + "cell_type": "code", + "execution_count": 42, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "count 622874\n", + "mean 14 days 12:29:57.844186\n", + "std 14 days 10:18:20.006715\n", + "min -18 days +00:00:00\n", + "25% 5 days 00:00:00\n", + "50% 9 days 00:00:00\n", + "75% 22 days 00:00:00\n", + "max 421 days 00:00:00\n", + "Name: funding_period, dtype: object" + ] + }, + "execution_count": 42, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "funding_period.describe()" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## From the above table, we see that:\n", + "1. It took an average of **14 days** for a loan to be funded from the time of posting.\n", + "2. Some loans were funded the same day they were posted." + ] } ], "metadata": { diff --git a/notebooks/.ipynb_checkpoints/tests-checkpoint.ipynb b/notebooks/.ipynb_checkpoints/tests-checkpoint.ipynb index 4ba3307..d3f78cd 100644 --- a/notebooks/.ipynb_checkpoints/tests-checkpoint.ipynb +++ b/notebooks/.ipynb_checkpoints/tests-checkpoint.ipynb @@ -9,7 +9,7 @@ }, { "cell_type": "code", - "execution_count": 3, + "execution_count": 1, "metadata": {}, "outputs": [], "source": [ @@ -19,7 +19,7 @@ }, { "cell_type": "code", - "execution_count": 4, + "execution_count": 2, "metadata": {}, "outputs": [ { @@ -229,7 +229,7 @@ "4 monthly 2014-01-01 " ] }, - "execution_count": 4, + "execution_count": 2, "metadata": {}, "output_type": "execute_result" } @@ -241,7 +241,7 @@ }, { "cell_type": "code", - "execution_count": 5, + "execution_count": 3, "metadata": {}, "outputs": [ { @@ -372,7 +372,7 @@ "max 158.000000 2986.000000 " ] }, - "execution_count": 5, + "execution_count": 3, "metadata": {}, "output_type": "execute_result" } @@ -383,7 +383,7 @@ }, { "cell_type": "code", - "execution_count": 6, + "execution_count": 4, "metadata": {}, "outputs": [ { @@ -561,7 +561,7 @@ " Construction 146725.0 162475.0" ] }, - "execution_count": 6, + "execution_count": 4, "metadata": {}, "output_type": "execute_result" } @@ -572,7 +572,7 @@ }, { "cell_type": "code", - "execution_count": 7, + "execution_count": 5, "metadata": {}, "outputs": [ { @@ -611,7 +611,7 @@ "Name: borrower_genders, dtype: object" ] }, - "execution_count": 7, + "execution_count": 5, "metadata": {}, "output_type": "execute_result" } @@ -622,7 +622,7 @@ }, { "cell_type": "code", - "execution_count": 8, + "execution_count": 6, "metadata": {}, "outputs": [ { @@ -2333,7 +2333,7 @@ "[671205 rows x 20 columns]" ] }, - "execution_count": 8, + "execution_count": 6, "metadata": {}, "output_type": "execute_result" } @@ -2344,7 +2344,7 @@ }, { "cell_type": "code", - "execution_count": 9, + "execution_count": 7, "metadata": {}, "outputs": [ { @@ -3011,7 +3011,7 @@ "19 monthly 2014-01-01 " ] }, - "execution_count": 9, + "execution_count": 7, "metadata": {}, "output_type": "execute_result" } @@ -3022,7 +3022,7 @@ }, { "cell_type": "code", - "execution_count": 10, + "execution_count": 8, "metadata": {}, "outputs": [ { @@ -3108,7 +3108,7 @@ "10 female" ] }, - "execution_count": 10, + "execution_count": 8, "metadata": {}, "output_type": "execute_result" } @@ -3119,7 +3119,7 @@ }, { "cell_type": "code", - "execution_count": 11, + "execution_count": 9, "metadata": {}, "outputs": [ { @@ -5019,7 +5019,7 @@ "[671205 rows x 20 columns]" ] }, - "execution_count": 11, + "execution_count": 9, "metadata": {}, "output_type": "execute_result" } @@ -5030,7 +5030,7 @@ }, { "cell_type": "code", - "execution_count": 13, + "execution_count": 10, "metadata": {}, "outputs": [ { @@ -5097,58 +5097,100 @@ " 114025.0\n", " 114025.0\n", " \n", - " \n", - " Benin\n", - " 516825.0\n", - " 518950.0\n", - " \n", - " \n", - " Bhutan\n", - " 15625.0\n", - " 20000.0\n", - " \n", - " \n", - " Bolivia\n", - " 18276200.0\n", - " 19843250.0\n", - " \n", - " \n", - " Brazil\n", - " 661025.0\n", - " 662200.0\n", - " \n", - " \n", - " Burkina Faso\n", - " 2909975.0\n", - " 2972700.0\n", - " \n", " \n", "\n", "" ], "text/plain": [ - " sum \n", - " funded_amount loan_amount\n", - "country \n", - "Afghanistan 14000.0 14000.0\n", - "Albania 2490000.0 2666500.0\n", - "Armenia 11186675.0 12915400.0\n", - "Azerbaijan 2699575.0 2888700.0\n", - "Belize 114025.0 114025.0\n", - "Benin 516825.0 518950.0\n", - "Bhutan 15625.0 20000.0\n", - "Bolivia 18276200.0 19843250.0\n", - "Brazil 661025.0 662200.0\n", - "Burkina Faso 2909975.0 2972700.0" + " sum \n", + " funded_amount loan_amount\n", + "country \n", + "Afghanistan 14000.0 14000.0\n", + "Albania 2490000.0 2666500.0\n", + "Armenia 11186675.0 12915400.0\n", + "Azerbaijan 2699575.0 2888700.0\n", + "Belize 114025.0 114025.0" + ] + }, + "execution_count": 10, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "country_pt = data.pivot_table(index=['country'], aggfunc=[np.sum], values=['funded_amount', 'loan_amount'])\n", + "\n", + "country_pt.head()" + ] + }, + { + "cell_type": "code", + "execution_count": 11, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "country\n", + "Philippines 54476375.0\n", + "Name: funded_amount, dtype: float64" ] }, - "execution_count": 13, + "execution_count": 11, "metadata": {}, "output_type": "execute_result" } ], "source": [ - "country_pt = data.pivot_table(index=['country'], aggfunc=[np.sum], values=['funded_amount', 'loan_amount']).head(10)" + "funded = country_pt['sum']['funded_amount']\n", + "funded[funded == funded.max()]" + ] + }, + { + "cell_type": "code", + "execution_count": 22, + "metadata": {}, + "outputs": [ + { + "ename": "AttributeError", + "evalue": "'Series' object has no attribute 'strftime'", + "output_type": "error", + "traceback": [ + "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m", + "\u001b[1;31mAttributeError\u001b[0m Traceback (most recent call last)", + "\u001b[1;32m\u001b[0m in \u001b[0;36m\u001b[1;34m\u001b[0m\n\u001b[1;32m----> 1\u001b[1;33m \u001b[0mdata\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;34m'posted_time'\u001b[0m\u001b[1;33m]\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mpd\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mto_datetime\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mdata\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;34m'posted_time'\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mformat\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;34m'%d-%m-%Y'\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mstrftime\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34m\"%Y\"\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 2\u001b[0m \u001b[0mdata\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;34m'funded_time'\u001b[0m\u001b[1;33m]\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mpd\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mto_datetime\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mdata\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;34m'funded_time'\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 3\u001b[0m \u001b[0mdata\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mhead\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", + "\u001b[1;32mf:\\isaka\\python4ds\\env\\lib\\site-packages\\pandas\\core\\generic.py\u001b[0m in \u001b[0;36m__getattr__\u001b[1;34m(self, name)\u001b[0m\n\u001b[0;32m 5065\u001b[0m \u001b[1;32mif\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_info_axis\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_can_hold_identifiers_and_holds_name\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mname\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 5066\u001b[0m \u001b[1;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m[\u001b[0m\u001b[0mname\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m-> 5067\u001b[1;33m \u001b[1;32mreturn\u001b[0m \u001b[0mobject\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m__getattribute__\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mname\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 5068\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 5069\u001b[0m \u001b[1;32mdef\u001b[0m \u001b[0m__setattr__\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mname\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mvalue\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", + "\u001b[1;31mAttributeError\u001b[0m: 'Series' object has no attribute 'strftime'" + ] + } + ], + "source": [ + "data['posted_time'] = pd.to_datetime(data['posted_time'], format='%d-%m-%Y')\n", + "data['funded_time'] = pd.to_datetime(data['funded_time'])\n", + "data.head()" + ] + }, + { + "cell_type": "code", + "execution_count": 20, + "metadata": {}, + "outputs": [ + { + "ename": "AttributeError", + "evalue": "'Series' object has no attribute 'day'", + "output_type": "error", + "traceback": [ + "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m", + "\u001b[1;31mAttributeError\u001b[0m Traceback (most recent call last)", + "\u001b[1;32m\u001b[0m in \u001b[0;36m\u001b[1;34m\u001b[0m\n\u001b[0;32m 1\u001b[0m \u001b[0mdata\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;34m'time_diff'\u001b[0m\u001b[1;33m]\u001b[0m \u001b[1;33m=\u001b[0m \u001b[1;33m(\u001b[0m\u001b[0mdata\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;34m'funded_time'\u001b[0m\u001b[1;33m]\u001b[0m \u001b[1;33m-\u001b[0m \u001b[0mdata\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;34m'posted_time'\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m----> 2\u001b[1;33m \u001b[0mdata\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;34m'time_diff'\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mday\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m", + "\u001b[1;32mf:\\isaka\\python4ds\\env\\lib\\site-packages\\pandas\\core\\generic.py\u001b[0m in \u001b[0;36m__getattr__\u001b[1;34m(self, name)\u001b[0m\n\u001b[0;32m 5065\u001b[0m \u001b[1;32mif\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_info_axis\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_can_hold_identifiers_and_holds_name\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mname\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 5066\u001b[0m \u001b[1;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m[\u001b[0m\u001b[0mname\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m-> 5067\u001b[1;33m \u001b[1;32mreturn\u001b[0m \u001b[0mobject\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m__getattribute__\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mname\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 5068\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 5069\u001b[0m \u001b[1;32mdef\u001b[0m \u001b[0m__setattr__\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mname\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mvalue\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", + "\u001b[1;31mAttributeError\u001b[0m: 'Series' object has no attribute 'day'" + ] + } + ], + "source": [ + "data['time_diff'] = (data['funded_time'] - data['posted_time'])\n", + "data['time_diff'].day()" ] } ], diff --git a/notebooks/kiva_analytics.ipynb b/notebooks/kiva_analytics.ipynb index 04b76b3..affaa3f 100644 --- a/notebooks/kiva_analytics.ipynb +++ b/notebooks/kiva_analytics.ipynb @@ -29,7 +29,7 @@ }, { "cell_type": "code", - "execution_count": 3, + "execution_count": 16, "metadata": {}, "outputs": [ { @@ -239,7 +239,7 @@ "4 monthly 2014-01-01 " ] }, - "execution_count": 3, + "execution_count": 16, "metadata": {}, "output_type": "execute_result" } @@ -264,7 +264,7 @@ }, { "cell_type": "code", - "execution_count": 13, + "execution_count": 3, "metadata": {}, "outputs": [ { @@ -474,7 +474,7 @@ "4 monthly 2014-01-01 " ] }, - "execution_count": 13, + "execution_count": 3, "metadata": {}, "output_type": "execute_result" } @@ -496,7 +496,7 @@ }, { "cell_type": "code", - "execution_count": 5, + "execution_count": 4, "metadata": {}, "outputs": [ { @@ -627,7 +627,7 @@ "max 158.000000 2986.000000 " ] }, - "execution_count": 5, + "execution_count": 4, "metadata": {}, "output_type": "execute_result" } @@ -662,7 +662,7 @@ }, { "cell_type": "code", - "execution_count": 6, + "execution_count": 5, "metadata": {}, "outputs": [ { @@ -774,7 +774,7 @@ "Burkina Faso 2909975.0 2972700.0" ] }, - "execution_count": 6, + "execution_count": 5, "metadata": {}, "output_type": "execute_result" } @@ -788,7 +788,7 @@ }, { "cell_type": "code", - "execution_count": 10, + "execution_count": 6, "metadata": {}, "outputs": [ { @@ -861,7 +861,7 @@ "Belize 114025.0 114025.0" ] }, - "execution_count": 10, + "execution_count": 6, "metadata": {}, "output_type": "execute_result" } @@ -883,7 +883,7 @@ }, { "cell_type": "code", - "execution_count": 27, + "execution_count": 7, "metadata": {}, "outputs": [], "source": [ @@ -901,7 +901,7 @@ }, { "cell_type": "code", - "execution_count": 30, + "execution_count": 8, "metadata": {}, "outputs": [ { @@ -962,7 +962,7 @@ }, { "cell_type": "code", - "execution_count": 35, + "execution_count": 9, "metadata": {}, "outputs": [ { @@ -1078,7 +1078,7 @@ "Wholesale 995200.0" ] }, - "execution_count": 35, + "execution_count": 9, "metadata": {}, "output_type": "execute_result" } @@ -1099,7 +1099,7 @@ }, { "cell_type": "code", - "execution_count": 36, + "execution_count": 10, "metadata": {}, "outputs": [ { @@ -1175,7 +1175,7 @@ "max 1.430679e+08" ] }, - "execution_count": 36, + "execution_count": 10, "metadata": {}, "output_type": "execute_result" } @@ -1205,7 +1205,7 @@ }, { "cell_type": "code", - "execution_count": 37, + "execution_count": 11, "metadata": {}, "outputs": [ { @@ -1230,7 +1230,7 @@ "Name: loan_amount, dtype: float64" ] }, - "execution_count": 37, + "execution_count": 11, "metadata": {}, "output_type": "execute_result" } @@ -1243,7 +1243,7 @@ }, { "cell_type": "code", - "execution_count": 38, + "execution_count": 12, "metadata": {}, "outputs": [ { @@ -1254,7 +1254,7 @@ "Name: loan_amount, dtype: float64" ] }, - "execution_count": 38, + "execution_count": 12, "metadata": {}, "output_type": "execute_result" } @@ -1266,7 +1266,7 @@ }, { "cell_type": "code", - "execution_count": 39, + "execution_count": 13, "metadata": {}, "outputs": [ { @@ -1277,7 +1277,7 @@ "Name: loan_amount, dtype: float64" ] }, - "execution_count": 39, + "execution_count": 13, "metadata": {}, "output_type": "execute_result" } @@ -1296,12 +1296,426 @@ "2. The sector with the smallest amount used on it was **Wholesale**, with a total of **995,200 USD** used on it." ] }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "# Date/Time based Analytics\n", + "Since the dates provided in the dataset are all objects, we first convert them to date/time values for easier manipulation." + ] + }, { "cell_type": "code", - "execution_count": null, + "execution_count": 26, "metadata": {}, "outputs": [], - "source": [] + "source": [ + "# Extract all time columns and convert them first to YYYY-mm-dd formatted objects then to datetime values\n", + "kiva_available_data['posted_time'] = pd.to_datetime(kiva_available_data['posted_time'].dt.strftime(\"%Y-%m-%d\"))\n", + "kiva_available_data['funded_time'] = pd.to_datetime(kiva_available_data['funded_time'].dt.strftime(\"%Y-%m-%d\"))\n", + "kiva_available_data['disbursed_time'] = pd.to_datetime(kiva_available_data['disbursed_time'].dt.strftime(\"%Y-%m-%d\"))" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "#### Next we create a column containing the time difference between when the loan was funded and when it was posted" + ] + }, + { + "cell_type": "code", + "execution_count": 31, + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
idfunded_amountloan_amountactivitysectorusecountry_codecountryregioncurrency...disbursed_timefunded_timeterm_in_monthslender_counttagsborrower_gendersrepayment_intervaldatefunding_perioddisbursement_period
0653051300.0300.0Fruits & VegetablesFoodTo buy seasonal, fresh fruits to sell.PKPakistanLahorePKR...2013-12-172014-01-0212.012NaNfemaleirregular2014-01-011 days-16 days
1653053575.0575.0RickshawTransportationto repair and maintain the auto rickshaw used ...PKPakistanLahorePKR...2013-12-172014-01-0211.014NaNfemale, femaleirregular2014-01-011 days-16 days
2653068150.0150.0TransportationTransportationTo repair their old cycle-van and buy another ...INIndiaMaynaguriINR...2013-12-172014-01-0143.06user_favorite, user_favoritefemalebullet2014-01-010 days-15 days
3653063200.0200.0EmbroideryArtsto purchase an embroidery machine and a variet...PKPakistanLahorePKR...2013-12-242014-01-0111.08NaNfemaleirregular2014-01-010 days-8 days
4653084400.0400.0Milk SalesFoodto purchase one buffalo.PKPakistanAbdul HakeemPKR...2013-12-172014-01-0114.016NaNfemalemonthly2014-01-010 days-15 days
\n", + "

5 rows × 22 columns

\n", + "
" + ], + "text/plain": [ + " id funded_amount loan_amount activity sector \\\n", + "0 653051 300.0 300.0 Fruits & Vegetables Food \n", + "1 653053 575.0 575.0 Rickshaw Transportation \n", + "2 653068 150.0 150.0 Transportation Transportation \n", + "3 653063 200.0 200.0 Embroidery Arts \n", + "4 653084 400.0 400.0 Milk Sales Food \n", + "\n", + " use country_code country \\\n", + "0 To buy seasonal, fresh fruits to sell. PK Pakistan \n", + "1 to repair and maintain the auto rickshaw used ... PK Pakistan \n", + "2 To repair their old cycle-van and buy another ... IN India \n", + "3 to purchase an embroidery machine and a variet... PK Pakistan \n", + "4 to purchase one buffalo. PK Pakistan \n", + "\n", + " region currency ... disbursed_time funded_time term_in_months \\\n", + "0 Lahore PKR ... 2013-12-17 2014-01-02 12.0 \n", + "1 Lahore PKR ... 2013-12-17 2014-01-02 11.0 \n", + "2 Maynaguri INR ... 2013-12-17 2014-01-01 43.0 \n", + "3 Lahore PKR ... 2013-12-24 2014-01-01 11.0 \n", + "4 Abdul Hakeem PKR ... 2013-12-17 2014-01-01 14.0 \n", + "\n", + " lender_count tags borrower_genders \\\n", + "0 12 NaN female \n", + "1 14 NaN female, female \n", + "2 6 user_favorite, user_favorite female \n", + "3 8 NaN female \n", + "4 16 NaN female \n", + "\n", + " repayment_interval date funding_period disbursement_period \n", + "0 irregular 2014-01-01 1 days -16 days \n", + "1 irregular 2014-01-01 1 days -16 days \n", + "2 bullet 2014-01-01 0 days -15 days \n", + "3 irregular 2014-01-01 0 days -8 days \n", + "4 monthly 2014-01-01 0 days -15 days \n", + "\n", + "[5 rows x 22 columns]" + ] + }, + "execution_count": 31, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# Create a funding period column: Difference between time posted and time funded for a loan\n", + "kiva_available_data['funding_period'] = (kiva_available_data['funded_time'] - kiva_available_data['posted_time'])\n", + "\n", + "kiva_available_data.head()" + ] + }, + { + "cell_type": "code", + "execution_count": 38, + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
idfunded_amountloan_amountactivitysectorusecountry_codecountryregioncurrency...disbursed_timefunded_timeterm_in_monthslender_counttagsborrower_gendersrepayment_intervaldatefunding_perioddisbursement_period
423441080950125.0125.0ServicesServicesadd more stock to my shopKEKenyaNaNKES...2015-06-092015-06-036.05NaNfemaleirregular2014-04-08421 days6 days
\n", + "

1 rows × 22 columns

\n", + "
" + ], + "text/plain": [ + " id funded_amount loan_amount activity sector \\\n", + "42344 1080950 125.0 125.0 Services Services \n", + "\n", + " use country_code country region currency ... \\\n", + "42344 add more stock to my shop KE Kenya NaN KES ... \n", + "\n", + " disbursed_time funded_time term_in_months lender_count tags \\\n", + "42344 2015-06-09 2015-06-03 6.0 5 NaN \n", + "\n", + " borrower_genders repayment_interval date funding_period \\\n", + "42344 female irregular 2014-04-08 421 days \n", + "\n", + " disbursement_period \n", + "42344 6 days \n", + "\n", + "[1 rows x 22 columns]" + ] + }, + "execution_count": 38, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# Extract the funding period column where there are no null values\n", + "funding_period = kiva_available_data[kiva_available_data['funding_period'].notnull()]['funding_period']\n", + "\n", + "# return the maximum funding period\n", + "min_funding_period = funding_period.max()\n", + "\n", + "#Fetch the data at that period\n", + "kiva_available_data.query('funding_period == @min_funding_period')" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### From the data above, we can see that:\n", + " 1. The maximum amount it took for a loan from the time it was posted on kiva to the time it was funded was **421 days**.\n", + " 2. This loan also took 6 days to be disbursed to the borrower from the time it was funded.\n", + " 3. The loan, a total of **125 USD**, was loaned to a female in kenya, which she used to add more stock to her shop." + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### More date/time analytics" + ] + }, + { + "cell_type": "code", + "execution_count": 42, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "count 622874\n", + "mean 14 days 12:29:57.844186\n", + "std 14 days 10:18:20.006715\n", + "min -18 days +00:00:00\n", + "25% 5 days 00:00:00\n", + "50% 9 days 00:00:00\n", + "75% 22 days 00:00:00\n", + "max 421 days 00:00:00\n", + "Name: funding_period, dtype: object" + ] + }, + "execution_count": 42, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "funding_period.describe()" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## From the above table, we see that:\n", + "1. It took an average of **14 days** for a loan to be funded from the time of posting.\n", + "2. Some loans were funded the same day they were posted." + ] } ], "metadata": { diff --git a/notebooks/tests.ipynb b/notebooks/tests.ipynb index 25e1774..abcfe36 100644 --- a/notebooks/tests.ipynb +++ b/notebooks/tests.ipynb @@ -9,7 +9,7 @@ }, { "cell_type": "code", - "execution_count": 3, + "execution_count": 1, "metadata": {}, "outputs": [], "source": [ @@ -19,7 +19,7 @@ }, { "cell_type": "code", - "execution_count": 4, + "execution_count": 2, "metadata": {}, "outputs": [ { @@ -229,7 +229,7 @@ "4 monthly 2014-01-01 " ] }, - "execution_count": 4, + "execution_count": 2, "metadata": {}, "output_type": "execute_result" } @@ -241,7 +241,7 @@ }, { "cell_type": "code", - "execution_count": 5, + "execution_count": 3, "metadata": {}, "outputs": [ { @@ -372,7 +372,7 @@ "max 158.000000 2986.000000 " ] }, - "execution_count": 5, + "execution_count": 3, "metadata": {}, "output_type": "execute_result" } @@ -383,7 +383,7 @@ }, { "cell_type": "code", - "execution_count": 6, + "execution_count": 4, "metadata": {}, "outputs": [ { @@ -561,7 +561,7 @@ " Construction 146725.0 162475.0" ] }, - "execution_count": 6, + "execution_count": 4, "metadata": {}, "output_type": "execute_result" } @@ -572,7 +572,7 @@ }, { "cell_type": "code", - "execution_count": 7, + "execution_count": 5, "metadata": {}, "outputs": [ { @@ -611,7 +611,7 @@ "Name: borrower_genders, dtype: object" ] }, - "execution_count": 7, + "execution_count": 5, "metadata": {}, "output_type": "execute_result" } @@ -622,7 +622,7 @@ }, { "cell_type": "code", - "execution_count": 8, + "execution_count": 6, "metadata": {}, "outputs": [ { @@ -2333,7 +2333,7 @@ "[671205 rows x 20 columns]" ] }, - "execution_count": 8, + "execution_count": 6, "metadata": {}, "output_type": "execute_result" } @@ -2344,7 +2344,7 @@ }, { "cell_type": "code", - "execution_count": 9, + "execution_count": 7, "metadata": {}, "outputs": [ { @@ -3011,7 +3011,7 @@ "19 monthly 2014-01-01 " ] }, - "execution_count": 9, + "execution_count": 7, "metadata": {}, "output_type": "execute_result" } @@ -3022,7 +3022,7 @@ }, { "cell_type": "code", - "execution_count": 10, + "execution_count": 8, "metadata": {}, "outputs": [ { @@ -3108,7 +3108,7 @@ "10 female" ] }, - "execution_count": 10, + "execution_count": 8, "metadata": {}, "output_type": "execute_result" } @@ -3119,7 +3119,7 @@ }, { "cell_type": "code", - "execution_count": 11, + "execution_count": 9, "metadata": {}, "outputs": [ { @@ -5019,7 +5019,7 @@ "[671205 rows x 20 columns]" ] }, - "execution_count": 11, + "execution_count": 9, "metadata": {}, "output_type": "execute_result" } @@ -5030,7 +5030,7 @@ }, { "cell_type": "code", - "execution_count": 14, + "execution_count": 10, "metadata": {}, "outputs": [ { @@ -5112,7 +5112,7 @@ "Belize 114025.0 114025.0" ] }, - "execution_count": 14, + "execution_count": 10, "metadata": {}, "output_type": "execute_result" } @@ -5125,7 +5125,7 @@ }, { "cell_type": "code", - "execution_count": 27, + "execution_count": 11, "metadata": {}, "outputs": [ { @@ -5136,7 +5136,7 @@ "Name: funded_amount, dtype: float64" ] }, - "execution_count": 27, + "execution_count": 11, "metadata": {}, "output_type": "execute_result" } @@ -5145,6 +5145,252 @@ "funded = country_pt['sum']['funded_amount']\n", "funded[funded == funded.max()]" ] + }, + { + "cell_type": "code", + "execution_count": 31, + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
idfunded_amountloan_amountactivitysectorusecountry_codecountryregioncurrency...posted_timedisbursed_timefunded_timeterm_in_monthslender_counttagsborrower_gendersrepayment_intervaldatetime_diff
0653051300.0300.0Fruits & VegetablesFoodTo buy seasonal, fresh fruits to sell.PKPakistanLahorePKR...2014-01-012013-12-17 08:00:00+00:002014-01-0212.012NaNfemaleirregular2014-01-011 days 03:53:53
1653053575.0575.0RickshawTransportationto repair and maintain the auto rickshaw used ...PKPakistanLahorePKR...2014-01-012013-12-17 08:00:00+00:002014-01-0211.014NaNfemale, femaleirregular2014-01-011 days 02:26:15
2653068150.0150.0TransportationTransportationTo repair their old cycle-van and buy another ...INIndiaMaynaguriINR...2014-01-012013-12-17 08:00:00+00:002014-01-0143.06user_favorite, user_favoritefemalebullet2014-01-010 days 06:03:29
3653063200.0200.0EmbroideryArtsto purchase an embroidery machine and a variet...PKPakistanLahorePKR...2014-01-012013-12-24 08:00:00+00:002014-01-0111.08NaNfemaleirregular2014-01-010 days 04:56:49
4653084400.0400.0Milk SalesFoodto purchase one buffalo.PKPakistanAbdul HakeemPKR...2014-01-012013-12-17 08:00:00+00:002014-01-0114.016NaNfemalemonthly2014-01-010 days 07:25:32
\n", + "

5 rows × 21 columns

\n", + "
" + ], + "text/plain": [ + " id funded_amount loan_amount activity sector \\\n", + "0 653051 300.0 300.0 Fruits & Vegetables Food \n", + "1 653053 575.0 575.0 Rickshaw Transportation \n", + "2 653068 150.0 150.0 Transportation Transportation \n", + "3 653063 200.0 200.0 Embroidery Arts \n", + "4 653084 400.0 400.0 Milk Sales Food \n", + "\n", + " use country_code country \\\n", + "0 To buy seasonal, fresh fruits to sell. PK Pakistan \n", + "1 to repair and maintain the auto rickshaw used ... PK Pakistan \n", + "2 To repair their old cycle-van and buy another ... IN India \n", + "3 to purchase an embroidery machine and a variet... PK Pakistan \n", + "4 to purchase one buffalo. PK Pakistan \n", + "\n", + " region currency ... posted_time disbursed_time \\\n", + "0 Lahore PKR ... 2014-01-01 2013-12-17 08:00:00+00:00 \n", + "1 Lahore PKR ... 2014-01-01 2013-12-17 08:00:00+00:00 \n", + "2 Maynaguri INR ... 2014-01-01 2013-12-17 08:00:00+00:00 \n", + "3 Lahore PKR ... 2014-01-01 2013-12-24 08:00:00+00:00 \n", + "4 Abdul Hakeem PKR ... 2014-01-01 2013-12-17 08:00:00+00:00 \n", + "\n", + " funded_time term_in_months lender_count tags \\\n", + "0 2014-01-02 12.0 12 NaN \n", + "1 2014-01-02 11.0 14 NaN \n", + "2 2014-01-01 43.0 6 user_favorite, user_favorite \n", + "3 2014-01-01 11.0 8 NaN \n", + "4 2014-01-01 14.0 16 NaN \n", + "\n", + " borrower_genders repayment_interval date time_diff \n", + "0 female irregular 2014-01-01 1 days 03:53:53 \n", + "1 female, female irregular 2014-01-01 1 days 02:26:15 \n", + "2 female bullet 2014-01-01 0 days 06:03:29 \n", + "3 female irregular 2014-01-01 0 days 04:56:49 \n", + "4 female monthly 2014-01-01 0 days 07:25:32 \n", + "\n", + "[5 rows x 21 columns]" + ] + }, + "execution_count": 31, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "data['posted_time'] = pd.to_datetime(data['posted_time'].dt.strftime(\"%Y-%m-%d\"))\n", + "data['funded_time'] = pd.to_datetime(data['funded_time'].dt.strftime(\"%Y-%m-%d\"))\n", + "data.head()" + ] + }, + { + "cell_type": "code", + "execution_count": 35, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "Timedelta('14 days 12:29:57.844186')" + ] + }, + "execution_count": 35, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "data['time_diff'] = (data['funded_time'] - data['posted_time'])\n", + "data['time_diff'].mean()" + ] } ], "metadata": { From 3b811abc8bbd24128227b90841dc214956dfc03f Mon Sep 17 00:00:00 2001 From: kasre96 Date: Mon, 18 Feb 2019 09:30:02 +0300 Subject: [PATCH 23/43] Kiva challenge initial completion --- .idea/workspace.xml | 10 +- .../kiva_analytics-checkpoint.ipynb | 796 ++++++++++++++++-- notebooks/kiva_analytics.ipynb | 796 ++++++++++++++++-- notebooks/tests.ipynb | 234 +---- 4 files changed, 1457 insertions(+), 379 deletions(-) diff --git a/.idea/workspace.xml b/.idea/workspace.xml index 3de5c4c..960ea65 100644 --- a/.idea/workspace.xml +++ b/.idea/workspace.xml @@ -3,6 +3,9 @@ + + + @@ -162,7 +165,6 @@ - @@ -196,9 +198,7 @@ - - - + @@ -214,7 +214,7 @@ - + diff --git a/notebooks/.ipynb_checkpoints/full_kiva_loans_analysis-checkpoint.ipynb b/notebooks/.ipynb_checkpoints/full_kiva_loans_analysis-checkpoint.ipynb index f4244c8..9c651a5 100644 --- a/notebooks/.ipynb_checkpoints/full_kiva_loans_analysis-checkpoint.ipynb +++ b/notebooks/.ipynb_checkpoints/full_kiva_loans_analysis-checkpoint.ipynb @@ -15,7 +15,10 @@ "4. [Data cleaning and preparation](#data-prep)
\n", " 4.1. [Handling Missing Data](#missing-data)\n", "5. [Data Exploration and Visualization](#data-exploration)
\n", - " 5.1. [Loan counts per sector](#per-sector)" + " 5.1. [Loan counts per sector](#per-sector)
\n", + " 5.2. [Loan counts per world region](#per-region)
\n", + " 5.3. [World Region MPIs](#region-mpis)
\n", + " 5.4. [Repayment Intervals](#repayment)
" ] }, { @@ -41,7 +44,7 @@ }, { "cell_type": "code", - "execution_count": 31, + "execution_count": 1, "metadata": {}, "outputs": [], "source": [ @@ -53,6 +56,7 @@ "import pandas as pd\n", "import matplotlib.pyplot as plt\n", "import seaborn as sns\n", + "import folium\n", "\n", "# Set default seaborn settings\n", "sns.set()" @@ -1120,7 +1124,7 @@ }, { "cell_type": "code", - "execution_count": 24, + "execution_count": 9, "metadata": {}, "outputs": [], "source": [ @@ -1158,7 +1162,7 @@ }, { "cell_type": "code", - "execution_count": 25, + "execution_count": 10, "metadata": {}, "outputs": [ { @@ -1315,7 +1319,7 @@ "id 0 0.000000" ] }, - "execution_count": 25, + "execution_count": 10, "metadata": {}, "output_type": "execute_result" } @@ -1333,7 +1337,7 @@ }, { "cell_type": "code", - "execution_count": 26, + "execution_count": 11, "metadata": {}, "outputs": [ { @@ -1424,7 +1428,7 @@ "geo 0 0.000000" ] }, - "execution_count": 26, + "execution_count": 11, "metadata": {}, "output_type": "execute_result" } @@ -1442,7 +1446,7 @@ }, { "cell_type": "code", - "execution_count": 27, + "execution_count": 12, "metadata": {}, "outputs": [ { @@ -1503,7 +1507,7 @@ "id 0 0.000000" ] }, - "execution_count": 27, + "execution_count": 12, "metadata": {}, "output_type": "execute_result" } @@ -1521,7 +1525,7 @@ }, { "cell_type": "code", - "execution_count": 28, + "execution_count": 13, "metadata": {}, "outputs": [ { @@ -1684,7 +1688,7 @@ "Partner ID 0 0.000000" ] }, - "execution_count": 28, + "execution_count": 13, "metadata": {}, "output_type": "execute_result" } @@ -1716,17 +1720,19 @@ }, { "cell_type": "code", - "execution_count": 64, + "execution_count": 14, "metadata": {}, "outputs": [ { "data": { - "image/png": "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\n", + "image/png": "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\n", "text/plain": [ "
" ] }, - "metadata": {}, + "metadata": { + "needs_background": "light" + }, "output_type": "display_data" } ], @@ -1760,6 +1766,235 @@ "**Wholesale** had the least loan counts." ] }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### 5.2. Loan counts per world region\n", + "" + ] + }, + { + "cell_type": "code", + "execution_count": 54, + "metadata": {}, + "outputs": [ + { + "data": { + "image/png": "iVBORw0KGgoAAAANSUhEUgAABEQAAAJCCAYAAADJDBIEAAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAALEgAACxIB0t1+/AAAADl0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uIDMuMC4yLCBodHRwOi8vbWF0cGxvdGxpYi5vcmcvOIA7rQAAIABJREFUeJzs3XmYHVWZ+PFvdydkDwlJWELYAy8CQfZFRUA2RWDcEBWQRVRccPnp6OjMKKKM4y7jqKgo6oCAK5uogLKKbJF9edm3sIUkBEL2pH9/nOr0Ted2p7vTSSe538/z9NN1q06de6rurU7qrXPe09Ta2ookSZIkSVIjae7vBkiSJEmSJK1qBkQkSZIkSVLDMSAiSZIkSZIajgERSZIkSZLUcAyISJIkSZKkhmNARJIkSZIkNZwB/d0ASZJ6IiKuBvatXm6RmY/1X2vWPBExFngP8EZgEjAOWAxMBW4HLgLOz8zZ/dbIVSwiNgemZebLq/h9r6b9u9yZ+cDLwOPANcDZmXnXSm5aw4uIU4EvVi/3zswbe1HH1ZTP9/HM3LyH++4HXNWNoouBucDzwL3ApcBZmbmgJ++3KvXFuZWkvmIPEUmSGkBEDI6I/wKeAM4A3gRMAAYBQ4BNgSOAnwIPRMRh/dXWVSUiBkXEf1JuJMf0d3s6sQ6lbbsAnwRuj4jT+7dJWo00A0OBzYFDgR8Ad0TEhP5slCStKewhIknSWi4i1gf+COxWrZoK/B9wPfA00AJsC7wLOAjYGLgoIj6YmWet+havMp8BTuvvRlTeTPksOhoAjAL2Bz5Bufn9fERMzczvrsL2qf9cAnyhk23NwFhgb+BDwAbAq4A/RMRemblo1TRRktZMBkQkSVqLRcRgSjf6tmDI+cAHM/OlDkVvAH4WEe8CfkHpmfDDiLgnM/+xyhq8arX0dwNq3Luc4V9XRsQVwBWU/799OSJ+uqqH+ahfTM/M25dT5vKIOJMS5JxIud7fAvxuZTeupzLzVODUfm6GJAEOmZEkaW33BWD3avl84Jg6wZAlMvN84NPVywGU4TVaDWTm1cCvq5fDgX/pv9ZodZOZzwH/WrPqXf3VFklaUxgQkSRpLRUR4yh5JwBeBE7uZhf6HwAPVMu7R8SeK6N96pU/1SxP6rdWaHX115rlif3WCklaQzhkRpLUsCJie+AjlPwMmwBNlDwO1wA/zMzJy9l/MHAsJZnhzpSx/AOBGcDdlKEqP8nMV+rsezVlBoqLMvMtEbEr8DFgP0oegJeAWygzRvyhl4f4XmBwtfy9zJzZnZ0yc1FEfBl4NXAdcF+9clVukg9Rjn8bSn6LqcDNwLnA7zOztc5+xwNnVy/fXfVKqVf/p4FvVC/3r3pItG37OXAccEdm7hQRW1NybBxCyYEyG7gT+CXwi8xc3Mn7t3k0IqDDjCARMQA4BjiKkth0Pdpnffkb5XvyUL32ryTP1yyPqlcgItYDTqHkJZlI+VyeB26kzFLzp072O5728zKa0gPlc8AWwHTgVuDIzJzbWeMi4v8o56sVGJeZ0+qUOQ34z+rlpzPzW3XKTAQerF5+KDPP7LC9V9duzQwnM6tj/BTwUWAjyjm6KjPf29nxdahrFPBB4Ehgq6oNdwA/yMwLulPHSlD7sHNgZ4UiYijl2n0LJX/QSGAa5TP+FfDr2mumkzoOpxz/HsC6wHOUIV1fy8wHImIuJWnzl6phMm37ncpyZpmJiEGUv1/vAHaifFYvAvcAFwI/zsw5nbSr7W/OJzPzuxHxNuAkyvU7umrnVcB3M/O2ro5R0trPgIgkqeFERBPwVUr38o69JSdWPydGxPcp/6leWKeOXShT1NabzWGD6ucA4MMRsX9mTumiPacA32bpf5fHUQINh1Y3mcfVCy4sx6E1y5f0ZMfMPAc4p7PtEfFO4MeUG6FaGwNvrX6ujYh3ZObUnrx3T0XE2ymBj6E1qwdTgkv7Ae+JiMMyc14P612Xkoz2tR02ja5+dgI+HhEfz8zv9671PbZ+zfILHTdGxKGUYFTHYMkm1c+REXExZehUV/lHTqZcI202BIZ3FQypXEoJiDRRvv+/rlPmwJrl/YFlAiKUYE6bJd/dvrh2a3wV+GzN6wlAt5KQRsROlN46G3bY9Hrg9dUsTf3RE7t2GuesVyAidgf+QLlWa20EHF79nFJdu8/U2b8ZOBN4f4dNmwAnUq63Y3vXfIiIHSnfm+iwaRzt1/SnIuJtmXlrF1W1RMS5lGnGO7bzvcAxEXFyZv6kt22VtOZzyIwkqRF9h3Ij1Ey5qfx3yo3E6yhPjJ+m3NB9FFhmlpWIGEN5Etp2A3UW5Unr3pQbuX+n/WZ1a+CbXbRlL0qejpcoT81fX7Xlv4D5VZljgXf24jh3rn7PBvrsSWj1xPU8SjBkAWWIzRspx3I8pYcIlGO5KiKG99V717EpJQAA8HXKTfjrgH+jnFMoN+CfqNnnYsq5+VHNujdX62qDSN+mPRjyU+AwSj6WQyg3069QErP+T3WDvCrUBgqWSnYbEQdQjm0U5Wn/aZTzsRdwNHBlVfQIyiwkXSWVPR14ktIL53WUvDL1Ahcd/RloC0Ic1HFjRIykPacNwD6dtKPtc5jcIZi4QtdujRFVPfdQeni8npLo84dd7NN2DBtTeqJsSOkJ83PK9/81wMeBZyhBoY6BtJWqus7+q2bVMr1Uqp41V9Hei+pblO/zHpTeGL+tir4GuKKTa/cM2oMhDwMfoHzHjqAkcR1M6WWyTi+OYWvK97QtGHIp5fPZkxJkbQuwbQJcHRE7dFHdpynBkPtq2vgm2s9LM/C9iNisp+2UtPawh4gkqaFExGspNy1QnqDu3+Ep6N+r4RiXA7sCx0XExZn5+5oyn6QMnYDS5b/j9KeXRcQvKDdb6wJviYgBnTyt3oByA7VXZj5Rs/7aiLiD9v+8H0+dG5wujnMkpRcDwJTlPCnvtqreH1NuJmYDh2Tm9TVFbqp6tPwYeB+wPeUm7WN98f51jKYEJl7XYSaOv0fENZTZc5oo5+9rAJk5HZgeEc/WlF9qlpeIWIcSRIAybKnj0/DLI+J6Sg+SZsqxntJXB1VPRPwL7YGxJ4G/1GwbQunR00LJ/7J/ZtZO43sT8KuIOB34PCVQ8n7Kk/56Wimfbdtwqb93p42ZObM6L/tRJyBSrR9ACaQNpAzV2JkyVKPtWIbS3tPh4pr1fXHttmmmDJvZv6YH03XdOUZK4G1ktfyBDlNT/yMiLqjq2rqb9fVaFbDYgBLQ+VzNe/6V9uBGrXOAYZThQfvVfL5Qhuj9LiLeT7l+twf+gxJcbHu/nYEPVy9vBg7s0NPokoj4FF0HgbvyA0pPEIBPZea3O2y/MCIuowShhgHnRsROnfSe25ByHg7r0LPpzxExg9ILahAl+ezXetleSWs4e4hIkhpN7SwMx9brEl7dMB9Fe/f5z3YosjEliPEsUHeoRPVU++rq5WBgTBdt+kqHYEib31DykUDJ59ETI2qWlxlasQJOpP1YvtghGAJAlXvgw7QnZn1/lddiZflBvWlJq9wEd1Yvt63yEnTXaMrNErTnsuhY/2XA/wBfYulkp72xXUTsVOfntRFxbHWT/Xva/+92SmYuqNn/GNqHb3yoQzCk1hdoH0rx8U7KAFzd4Wa5Jy6tfm9WPfGv1TZc5mJKTggoQZJaB9B+7i+uWd8X126t3/Z0OFeVN6QtKHVlh2BIWxueo+TW6CvHRURrvR9KPpuHgJ/RHgy5BHhbxxwgEXEQZZgXwOc6+3yrISRtvYk+FBG1uUhOoXwHWynD+JYZdlXlhPlrx/XLU/Wyavt+/LFOMKSt/l9QAiIAO1J653TmY50M86rtHdbTv62S1iIGRCRJDaNKkPmG6uU/M/OWzspm5sO0P4HfvRom07bthMwcD2zc4aa0o9oeCF3djF/eSRtagUerlyPqlelCbS6EngQClueQmvo7HZKQmfNrtrfl81hZ6p6/ysM1yz0ZuvM8JZEowOcj4riqF8ZSMvPjmXlqFRxZEX+kDGvq+HM9JT/KOyn/b5sLnJiZF3XYv20ozQLaA3HLqGYZavtebxsR4zspukyiyx6ozVfTsZdI2w3vXym9VqDkEan1pur3E22Brr66djvozTEeTHsP61910YaraL92V4VHKEGCN2TmEZ1MrV073OqK5dTX9n1eMsSpyh3SVsc/MvP+Lvb/URfbOnNIzfLy9v9BzfKbOikzJTPv7WRb7d+Fnv5tlbQWcciMJKmRbEb7f367czN0IyWXQROl+/i1tRvbnsBWT1A3A7akzLYyiZJPpHZa1K4eQjzWxbZZ1e+e/ps9g/IUt4mue6f0VNuY/czMF7ssufQ53oHSw2Fl6OrGc1bNcrfPYWa2RsTXKF3p16XcbJ4ZEddRnp5fTpnhpqeJbntqFuWzvIfy/ftZ1QOho7Z8MQOBRdWMOd2xJSXvRkdP9rCdS1QzjDxI6bFwENXNaxV8eVVV7G+UWZkOAV4XES01U0K33eDWBlb69Nqt9OYYt61ZXqZXUge3UGboWVGXUHr2tBkAbE6ZJWZJkAj4bGY+T+d2rll+ooffkRsoSVfbkvp2lcwU2oNdPVGbD2R5n/FtlBxL63TYr1af/12QtPbxD4AkqZHUBga6unFoU3vjuVRQocpz8GFK0r5J1P83dTHL7405bzn5PdpuuJuWU89SMnNeRDxFST64QRc5THqq7Tys0PnrY8tMa1yjNmDR03P49Srh538CQyg9XQ6qfr4GPB0RvwW+U5t/pJe2WME6xvZyv9GdrK/Xw6An/khJZLt/TbCjrXfIM5mZEXFV9XokZUrUWyJiO8rNPiw9XKbPrt0avTnGDWqWl5lSuIs2rIjpdYaE3RoRv6Mkmf04JSHqbhHxmnpDiSor+h2pPfblDcPrzmfUUdvntHh59WfmwoiYRgnSdPb5dvp3oQp4tr3s0d8FSWsXAyKSpEZSG5zozpP92tkvlozHj4gtKD0EJtZsn0/JmXEfMJkyC8WxtCcg7A83UQIigymzNHQrMSZARGxEmXXjKko+ibbhP203D70+fz3Q70N7M/OrEXEmZYaLIyhP5Nt6KoynJIv9QES8MzN7NLVxH2v7P92dlJlhuquzp+gr2vPlUkpAZF3KkIsbaQ+ItAVCbqLctA6jDKm6hfbZZV5m6aE/fXLtdtCbY+zJPl0Np1th1U39Jyk9cQ6lBJL+FBF7dZI3o+078gL1E952pm2Wn9pZY5Z3bfbm3Pb0em/7jHvzt0WSAAMikqTGUvtEd4NOS9UvM71m+TzagyHnAd8Dbu2YTyQiTu5NI/vQHylPjqHkPuh2QIQyxewHqp9zKMEdKOdhPCt2/rrba2PdbrzHSpeZMyhJK39W5bLYnXJD+U7KcIzBwC8jYrNOcjesCtMpSVXH1ksw2w+upfTAGEk5VzfSPrzjKoDMXBARf6d8N/cDvkH7cJk/V3lo2vTVtbuiantfrA/US4bcZmUmEgaWBEWOB+6iHPOrKVNCf7JO8bbzMBq4v5OgSVdqe22M67RU0ZveKG2fcXO1f6cJb6thim09V/ry85XUYPr9yYskSavQI7SPHd+zG+X3qllOgIjYrWbfqzLzPZn5j06Sq27a65b2jd9TnrQDnFQvKWg9EdEEfKRm1fk1y3e2F4tRy6mq9vzVJmCsHboztIv9+/X8RcSEiDigCoIApat+9XmfRhkq9btq0yjgtf3Rzsrd1e/xEbFNVwUj4h0R8fGI+JeIGLYyGlNdD23Jbg+KiK0oszNByR9Ch+V9ImI0sE/1una4DPTBtdtH7qlZ3n05ZXdazvY+Uc2UU9sT7eMR8Zo6Rdu+Iy2UaXo7FREHRsSnIuLtEdEW3HiE9mFGuyynWbsuZ3s9d9YsL+8z3pWSLweW/tsiST1iQESS1DCqPAZtN2C7RkSn/2mPiIm0d/G/oyZZYe0wmcld7L85S98gr/JemVVvhTOql+Mp+Qa64//RPhXl7bTPOAHtN7ktwPs6qyAi1qFM0QslAHJ1zebaZKybd7L/IMr0qytTp13tI+I/KEk3r6STm8cqoeqfa1YN7tPW9cxfapY/0VmhKgDyI+C7wLms+NCYrrRNv7sX7bOTPJGZj9SUabseRwCfo0oKy9Lfub66dvvCX2gPzJxQBQ/rtWESqyggApCZvwd+W71soiQA7vg3p7vfkSZKr7dvVnUOq95jMe2fy15VkKszPRm21aZ2tqjlTVv8oZrl5c2YI0mdMiAiSWo0365Z/r+IWKb7ffWk+nzax6h/s2ZzbbfxA6uu2x333xD4DUuPue/LqW974r8oeU0APhgRP+qsV0BENEXEJ4CvV6sWAB/sMJPKz2gPaHwpIvauU08z8H1KbgOAX1RPsdvUPgk+NiLqDY35b0rCxJVpXs1yxyl5L61Z/mpELBPsqI7zqOrlYspMH/3lLNqf3p8cEUd1LFDd6P6E9qEcZ2Xm7JXYpsso52Ug8K/Vuqs6lJlM+/fplOr39ZlZbxjEil67Kywz59A+JezuwBfrtGEk5TpZ1T5Be4+wSZTAZq0/UHp5ALwpIj7TST1fpX02nYsy8/GabWfQPnvV2VVy6aVExLHA23ra+My8jfbA6WER8bF65SLivcB7q5f3s/S1Kkk9Yg4RSdKa7PMR0Z2cDXdn5s8BMvOaiPge5ebrVcCdEfFd4HrKzdselBuJCdW+52XmOTV1XU/JI7AR5QnwXyPif4HHKTea+1J6TnQcQ98v+TAyc05EvJmS02ECJSfIWyPiF5TEr89SggE7UZ7qtj3VXgicmJk3d6hvZkScRPuT46sj4seUqUFnUqYd/gjtXd4foMPT6Mx8MiKupuSN2Ay4tpri9hFKj5H3U/JNPAx09RR6RdXmg/jPiPgW0JyZN2bm7dUsHm+nfCfuiIj/oQSX5lOmIj2ZMr0ywM873DiuUpn5YkR8gBIMaALOi4gjqtdTKefxI7S391FK0tyV2aapEXEzpYdI2/X0tw5lFkfEtZSEtW1Bp47DZdrKrui121e+CLyFck6/GBG7UAJSz1ECEZ+l9CRrSxi7SmTmlIj4Iu2Boy9GxK/bZi/KzEVVMOEqSpDqaxGxL3A2pTfUJsAJtCe2ncGy1+6NEfEjynd/H2ByRHyTMhxnNCVA2LF3SE96IZ1EmdJ3FHBGRBwA/LJq34bAu2kPQs4F3tVHs2dJalAGRCRJa7L3d7PcRcDPa15/gtI74FOUxIj/VWefVsqwgs/WrszMudUT0EsoU7HuQ3veg1oPAD+lTM8KJfnmDd1sb5/KzEer3Cc/AQ6nJET8dPVTz6PA+zKz49P8tvp+FxHvptwEDgM+Wv10dAVwbGbOqrPtA5Qbs42BHSnDN2r9A/gMcF0Xh7airqA8UR9BSZD6TmBBRAyvEnq+j/L92IcS6PnfTur5A/07mxAAmXlBNUzix5TcLO+pfjq6Bzg8M1+ss62vXcrS+Tzqfaf+RgmItKkbEKn0+trtK5n5SkS8npK0eCfKNXV4h2KXURKururEyv9DCUi8mvId+F9KgmQAMvPvEXEoJVA2hhL8OLROPU8Bb+lkKuhTKMHfd1J6kpzVYfssSi+z06rX8+imzHy4CtJcCGxB+V4cUafoI8BRmXlHd+uWpHocMiNJajiZuTgz/xXYmdL9/QFgNuXm+B7KTcROmfn/6iVLzcy/VvueRQkezK9+nqbcZH+AcqP0w6peKDcP/SYzn8vMIyjd/L9FCTi8QBkWM4fSw+V3wNHAtp0FQ2rqO5/yhPwrtA97mAs8RBkudChwSGY+18n+D1KCRKdShtDMpvQwuZHSk2Efls410ucy8xnKDCh/rd57HuUz3LTaPpPSi+UYSgDsKcrnPIfyuZ9DOca3ZWa3b/pWpsw8l9J75cuUaWxnUHr7TKMEHk4GdsnMzqbb7Wu1UxE/nJlP1ilT22vkvsx8qLPKVvTa7SuZ+TQl0HMSZfamaZQeIbdRpmI+nJILZZWqcq2cTHuvjDdHxDs6lLmS8h35LCXg+ALlO/Ii5Vg+A2yXmXVzJFWJhY+iDIv5I/A85bp4khKM256lA5n1AqJdHcOdlB5AH6Fcm1Mpf6eeql6/D5iUmbf2pF5JqqeptXVl5tKSJEmS1Egi4m20z8D09irpqyStdhwyI0mSJGm5IuLrlPxJt2Xmt7so+oaaZYe1SFptOWRGkiRJUncMpgwh+1aVl2gZEbEn7VNu35GZD6+qxklSTzlkRpIkSdJyRcTOlNw0LZScI9+n5B2ZTklyewAlr8owSl6S12XmTf3TWklaPgMikiRJkrolIk6kJIxep4tiM4DjMvOSLspIUr8zIKJGMYgys8Iz9EPWd0mSpLXFf//3f29yySWXHPPSSy+9dsGCBZu1trYObmlpmT5gwICnxo4de/l73/ve3x1//PEv9Hc7JTWcFkqeo1vo5pTfBkTUKF7H0lPASZIkSZLWPvsA13enoLPMqFE8AzBjxissXmwQUAIYM2Y406bN6u9mSKsFrwdpaV4T0tK8JlZ/zc1NjB49DKp7v+4wIKJGsQhg8eJWAyJSDa8HqZ3Xg7Q0rwlpaV4Ta4xup0hw2l1JkiRJktRwDIhIkiRJkqSGY0BEkiRJkiQ1HAMikiRJkiSp4RgQkSRJkiRJDaeptdVMuWoImwOP9ncjJEmSJGlNMnfeAl5+aW5/N2O5mpubGDNmOMAWwGPd2cdpd9VQPvbVC3lhxiv93QxJkiRJWiP86utH8zKrf0CkNxwyI0mSJEmSGo4BEUmSJEmS1HAMiEiSJEmSpIZjQESSJEmSJDUcAyKSJEmSJKnhGBCRJEmSJEkNx4CIJEmSJElqOAZEJEmSJElSwzEgIkmSJEmSGo4BEUmSJEmS1HAMiEiSJEmSpIZjQESSJEmSJDUcAyKSJEmSJKnhGBCRJEmSJEkNx4CIJEmSJElqOAZEJEmSJElSwzEgIkmSJEmSGs6A/m6AtDZZtGAet172XZqam9nj8H9dsr61dTHPPHQzTz9wA3NensbAQcMYt+kkNtvxIAYMHLxUHXNnzeCxOy9nxjMPsGD+bNYZPIKxm2zP5jsezIB1hqzqQ5IkSZKktZIBEakPPTT5EubOmsaQkeOWWv/o7X/myXuvZszGr2L81nsz+6WpTHngBl58/hF2PvgjNLeUS3HBvNncdvkPWDh/NuO32ZshI8by8rQnmfLADcx8/lF2OvgjtAwY2B+HJkmSJElrFQMiUh+Z9tS9PPvwLTQ1tyy1fu6s6SUYMmF7dtj3uCXrBw8fzcOTL+H5x+9gwy13BeDxu65g/pyZ7HjABxi94cRScOu9GD56PA/dehHPPHQTE7Z93So7JkmSJElaW5lDROoD8+fOIm/6LRttvSfrDBm51La5r8xgxJhNGb/N3kutH73h1gDMmvH0knUznnmQwcPHtAdDKhtssQsAM59/dGU0X5IkSZIajj1EpD7wwE2/o2XAILba5TCmP51LbRu1wVbs8saPLrPPrOlTABg8bPSSdTsecBILF8xbpuz8ubMAaGpq6stmS5IkSVLDMiAiraBnH76FaVPuZacDT6ZlwDpdlm1dvIi5s2cy45kHeOS2yxgyYuyS4TIAg4aOYlCd/Z6671qgBFckSZIkSSvOgIi0AubOmsFDky9hwravZ931t1hu+ZlTH+eOK88EoLllIBN3f8tyZ455/vE7eOahmxk8fD022HK3Pmm3JEmSJDU6c4hIvdTaupj7/3E+g4auyxavPqRb+wwaOpLt9jmWbfY6kiEjxnLX337KMw/d1Gn5qU/cyf03nE/zgIFs97pjnGFGkiRJkvqIARGpl5667zpmTn2MrXY9nEUL5rFg7issmPsKtLZC62IWzH2FRR3ygQwZMZZxm05io612Z+eDP8zgYaN4+J9/ZNHCBcvUPyVv4N7rz6W5uYVJ+53AiDETVtWhSZIkSdJazyEzUi9Nm3IftLZy19/Oqrv9ht99iQ223JVt9z6q7vaWgYMYM2E7puTfmTtrGsNGbbhk2yO3/Ykn772KgYOGscP+JzJyzCYr5RgkSZIkqVEZEOkjEfEO4HOUc9oM/DIzv7Gcfa4GTs3Mq5dTbhTwfWDHatUU4JTMfLCLffar6t6ve0fQ9yJiAPAk8NvMPKVm/abAFcAcYJ/MfLlm21nAmZl566pub09ttcthLJw/Z5n1991wHs3NA4i9jmSdoSN54p6reOr+69jxDScxfPT4pcq2zSjT3NI+FOahyRcz5f7rGTx8DDu+4X0MGTF25R6IJEmSJDUgAyJ9ICI2Br4F7JKZ0yJiOHBNRGRmXtwHb/FV4O7MPLp6v3cDFwC79EHdK9OhwM3AOyPis5k5u1q/HzA5M9/TcYfMPGkVtm+FdDaEpbllIM0tAxi90dYAzHlpKgvmzuKp+69bqrfInJen8cITdzJs3Q0ZMmIMAM8+citT7r+eISPGstNBH2KdISNW/oFIkiRJUgMyINI3xgIDgaHAtMycFRHHAXMBIuIxYL/MfKxOz40PRMR3quVPdtJbZEPg+YhozszFlGDIrKrukcBPgQnAeOBKoC2oMC4iLgO2AhI4MjPnRcTpwAHAesDTwFGZ+VxETAVuBTYCdgd+AOwAbADcCby7Wv4DcDewM/BcVe/0Ou0+oSrbDLwL+FlE7AR8BRgeEWcCzwJ7AZsC3wOOAk4FrgH+G3grsBD4UWaeERH7AqdX53pUdc4uqvPeq40xE7ZnvfHb8twjk1k4fy7rbbQN82bP5OkH/wE0sc3eRwKweNECHrntsiX7zHh22Q5A6wwZyegNJ67K5kuSJEnSWsmkqn0gM+8ALgIeiYibI+JrQEtmPtSN3Wdl5s7AccA5ETGoTpmvACcCz0XEBdXyFdW2NwO3Z+bewNbAvrT3HNkU+AjwKkpQ5cCImAhsC7wmM7cBngCOqcqPBb6WmTsBewPzq3onUoIPh1blXg18OzN3AF4Eju7Y4IgYBxxUnZcLgA9W5+p24AvAxZl5clV8cGZul5k/rKniHcBrgUnAHsAJEbEhcApwUmbuQgn8fKX+aV19NDU1sf2+x7H5jocwe+azPHTrRTzz0E2M3mgbdnnTx5bkB3nlxWdZMHcWAE/ddw3333D+Mj9P3nt1Px6JJEmSJK097CHSRzLzQxHxFeAzJJguAAAgAElEQVRg4BDgxog4OjN/v5xdf1rtf2dEPE8JVtzRoe7JEbEFJUBwIPAp4IMRsXdmnhcRe0TEJyiBjzHA8GrXOzLzUYCIuA8Ym5l/jIhPASdFRFACHw/XvN1N1XteGxHTIuIjVZu2rqn3+cy8rVq+m9LTpKNjgL9m5oyIuAj4SUTsXLNfrXrzzu4L/Doz5wHzgJ2q4zgGOCwijqT0LBleZ99+tddbPrfMuubmFjabdACbTTqg0/1GjNmEfY/++spsmiRJkiSpYkCkD0TEm4HhmXkBcDZwdkS8H3gf8HugFWiqig/ssPvCmuVmYEE1zKUt++abgf+gDA25hpKb5DTgQWDniNiL0pvix5ThMjvUvFdt3a1AU0TsCpwHfBv4LbCopjyZOac6piOA04AzqmMaW1Nubsd665yW44Hx1XAhgMWUXiIn1ym7bGZSWFDVTdWezYGpwNXAVdXvvwK/qrOvJEmSJEldcshM35gNfLW6aScimig9Gtp6Q7wAbF8t/0uHfdsSpe4GjAAezMxDM3On6mcKsB3w6Yho+7y2oASzHqYMS/lRZp4LDK7et6WLtu4LXJ2ZZwIPAId1Uv5ASg+NsynDYvZfTr1LVEGXTYBNM3PzzNycEtg5OiK6myX0WuDtETEwIoYCf6acw20oQ27+RDmX3WqTJEmSJEm1DIj0gcy8CvgScGlEJHA/pefFl6siXwTOiIhbKMGFWsMj4jbgTOA9mbmgzlu8i9Lz49GIuBf4RVV2OvBd4IsRcVe1fAMlYNKZC4BXV+WvpiRRrVf+J8C7q3K/Af6+nHprnQCc3dbbBKBKFvsAdfKN1JOZf6je85/ALcAZmXkzZYjRPcB9lADS0IgY1s12SZIkSZIEQFNra+vyS0lrvs2BRz/21Qt5YcYr/d0WSZIkSVoj/OrrRzN16sv93Yzlam5uYsyY4VAe5D/WrX1WZoMkSZIkSZJWRwZEJEmSJElSwzEgIkmSJEmSGo4BEUmSJEmS1HAMiEiSJEmSpIZjQESSJEmSJDUcAyKSJEmSJKnhGBCRJEmSJEkNx4CIJEmSJElqOAZEJEmSJElSwzEgIkmSJEmSGo4BEUmSJEmS1HAMiEiSJEmSpIZjQESSJEmSJDUcAyKSJEmSJKnhGBCRJEmSJEkNx4CIJEmSJElqOAZEJEmSJElSwzEgIkmSJEmSGo4BEUmSJEmS1HAMiEiSJEmSpIZjQESSJEmSJDUcAyKSJEmSJKnhGBCRJEmSJEkNx4CIJEmSJElqOAZEJEmSJElSwzEgIkmSJEmSGk5Ta2trf7dBWhU2Bx7t70ZIkiRJ0ppk7rwFvPzS3P5uxnI1NzcxZsxwgC2Ax7qzz4CV2SBpdTNt2iwWLzYIKAGMGzeCqVNf7u9mSKsFrwdpaV4T0tK8JtZODpmRJEmSJEkNx4CIJEmSJElqOAZEJEmSJElSwzEgIkmSJEmSGo4BEUmSJEmS1HAMiEiSJEmSpIZjQESSJEmSJDUcAyKSJEmSJKnhGBCRJEmSJEkNx4CIJEmSJElqOAZEJEmSJElSwzEgIkmSJEmSGo4BEUmSJEmS1HAMiEiSJEmSpIZjQESSJEmSJDWcAf3dAGlVGjNmeH83QVqtjBs3or+bIK021oTrYeH8ecyYOb+/myFJ0lrBgIgayl1nfpb5L03r72ZIktQru37mLMCAiCRJfcEhM5IkSZIkqeEYEJEkSZIkSQ3HgIgkSZIkSWo4BkQkSZIkSVLDMSAiSZIkSZIajgERSZIkSZLUcAyISJIkSZKkhmNARJIkSZIkNRwDIpIkSZIkqeEYEJEkSZIkSQ3HgIgkSZIkSWo4BkQkSZIkSVLDMSAiSZIkSZIajgERSZIkSZLUcAyISJIkSZKkhmNARJIkSZIkNRwDIpIkSZIkqeEM6O8GSGu6x154mfNufJC7p0xnzvyFjB0xhP1iPEfusRUDW9pjjlfc8yR/uvMJnpg2i+bmJrYcN5Ijd9+KXTcf12ndz86czSnnXM8pB+7A62P8qjgcSZIkSWoI9hCRVsAzL77CZ3/zD+6eMp1Dd9yU9++7HVutP5Lzb36I0y+ZTGtrKwC/u/Vhvnfl3QxsaeG9rw3etedEZs6ez2kX3co19z9dt+6X5szn9EsmM2/holV5SJIkSZLUEOwhIq2An157PwsWLeZb73oNE0YPB+BNO27Kz667nwv/+Sg3P/o822wwinP/8SCTJqzHl9+2B81NTQC8cdKmfOzc6znr2vt43TYb0tLcHp98+PmZfO2y23l25ux+OS5JkiRJWtvZQ0TqpUWLW7lryjS2H7/ekmBIm/22LcNb7pkyg3umTGfh4lYO3H7CkmAIwNB1BrDnluszc858npr+ypL1v775YT51/g3MXbCQg3fYZNUcjCRJkiQ1GHuISL3U3ARnvOd1S4bF1Jo5e96SMrtvsT7fO/p1jBkxuE65+aVcc3ug5LEXXuLgHTbhmL234ZZHn+fyu59cSUcgSZIkSY3LgIjUS01NTWy47tC62y687TEAJk0Yw6CBLWw2dsQyZZ57aTb/ePg51hs2iI1HD1uy/pMH78jAAS0rpc2SJEmSpMIhM1If+/3kR7jt8RfYdqNR7LLZ2Lpl5i5YyDcuu50FixZz1B4TlxpKYzBEkiRJklY+e4hIfeji2x7j59cno4cO4tNv3ImmmkBHm9nzF/KViyfzwHMzef02G/GmHTfth5ZKkiRJUmMzICL1gdbWVv7vhgf47a2PMHroIL78tt1Zf+SQZcpNf2Uup100mUemvsTeW23AJw7esR9aK0mSJEkyICKtoIWLFvM/V97F1fc/zYbrDuVLb9mNjUYNW6bcU9NnceqFt/L8y3M4ePsJfOgNO9DSvGwPEkmSJEnSyrfa5BCJiP0i4uoe7nNVzfLtvXjPwyOiNSJ27em+PXiPyyJi/Mqqv5tteCwiNq+zfqOIOCci7omIOyLi0ojYsod1nxwRJ1fLy063UtZfHRH79abtq7tFi1v55p/v4Or7n2bi+uvyjXfuVTcY8vSMV/j8727i+Zfn8K49JvLRAycZDJEkSZKkfrTaBER6ab+2hczcqRf7nwD8BvhgXzWoo8w8NDOfXln191ZEDAOuAa4FdsjMVwPnAVdExMDu1pOZZ2bmmSupmau9X9/8EDc89CzbbjSK09++B+sOHbRMmXkLF3H6pZN5cfZ8TthnW96z99b90FJJkiRJUq3VfshMRAwAfgjsAGwA3Am8G/hatf2mzNwzIlozsykiTgU2BrYGNgPOyszT69Q7FngDsBNwe0R8OjNfqrY9C1wI7Ak8C/wM+BgwATg+M6+JiIlVu8YAs4FTMvO2iPh5tW4i8Bnge5TAzbPA94HXAQuAL2fmBRFxJPApYAgwCDgxM2/o0NZ9gdOBocAo4JOZeVH1XjOBXatjPi0zz46I9YBzgE2Ae4HBdU7tu4DnM/PHbSsy89yImAcMioghwE+rYx4PXAmcBOwLfB1oAe4GHq32PbVq64+BPYAXqmN5oqr+AxHxnWr5k5l5dUQMr87JDlV9X8vM8yJiZBfv/fnqfL8KuAt4T2bOr3N8K92MV+bx21sfoQnYc8sNuPGR55Yps/GoYdz39AyenP4KG647lFFD1+Gq+6csU27XzcYxcsg6q6DVkiRJkiRYM3qIvAaYn5l7U4IMo4BDM/NjAJm5Z519dgQOpgQ0/i0iRtUpcwxweWY+BtwKHF2zbQPgT5m5MyWY8NbM3Ac4FfhEVeYXwGcycxfgA8D5NftPy8xXZeYlNetOAYZTbuQPBL4QEesAJwOHVT00vg58rk5bTwFOqt7rJOArNds2AfYBjgC+Wa07DfhnZk6iBBw2qFPnzsA/O67MzN9m5izgzcDt1XnfmhKM2KUqtg3whsw8rk6911S9df4AnFGzflZ1Po8DzomIQcB/AJMzc1fg9cC/V0N2unrv1wAfpZzHTYFD6rRhlbj36eksWLSYVuAXf0++85c7l/m58p6nuOPJaQA8O3N23TLf+cudPP3iK/11GJIkSZLUkFb7HiKZeW1ETIuIjwDbUm6Qhy9nt6uqXgPPR8R0YF3gxQ5ljge+VC1fQLnJ/mHN9j9Vvx8Hrq9ZHl31bNgdODsi2soPj4gx1fJNddq0L/DjzFxM6S2yPUBEvBU4PEpF+wGL6ux7DHBY1ZtkL5Y+/sszszUi7gbWq9btR+lF03b+HqlT52Jgbp31VPudFxF7RMQnKMGHMTXvm5k5s85uczLz3Gr5/1g6cPPTasc7I+J5ymd5IDA0Ik6sygwDtl/Oe9+dmU8BRMR9Nce8yr126424+OMbrdT3OGC7CRyw3YSV+h6SJEmS1IhW+4BIRBxB6fFwBnA2MBZYXjbK2hv91o7lI2IXYBJwRjWMowUYHxF7ZeaNAB2GYSzsUH8LMLc2b0lETACmVy/n1GnTgqotbeUnAs8DN1OGt1xLGQ700Tr7XgdcBVwN/BX4VcdjrYIinR1zx/ZD6RVzfMeVEXEW8B3KcKJ3AD+mDFnZoabOescHSwdzmijHXK8NzdW2FuCYzPxn9d4bANMj4pQu3rvLz1aSJEmSpO5YE4bMHAj8OjPPpvTy2J9yIw2wqMox0lMnUHprbJqZm2fmJpQeDSd3Z+eqd8SDEXEMQEQcRAlodOVa4KiIaIqI9SkJTXem3NT/FyXg8Tbaj42q7vUoQ1S+QOm18i8dy9RxJXBstf/ulKFGHf0G2Dwi3lfzXidQepc8BBwE/Kjq8TGYkmtlee87vApgAZxYtaPN0dV77AaMAB4E/gZ8qFq/ESUgtGkv31uSJEmSpG5b3QIi+0TErJqfM4GfAO+OiLsoN/F/B7aoyl8E3BER9ZKG1lXl7Xg38IMOm74NvDMiRnezqqOBkyLiTuCrwFGZWXfa2coPgFeAOyiBglMoQ3FuB+4H7gGmUhLBLpGZ0ynDTe4B7qMEE4ZWs8R05ovAVhFxD/BvwDJDZjJzDiXYdEQ17e7dwFuBgzNzHvBd4IvVef8ucAPt570zLwJviYg7KEGNT9ZsGx4RtwFnUhKhLqAMWRpSvfffKDlZHu7le0uSJEmS1G1Nra1d3cNLa43NgUfvOvOzzH9pWn+3RZKkXtn1M2cxderL/d0MNYBx40b4XZNqeE2s/pqbmxgzZjiUh+mPdWufldkgSZIkSZKk1ZEBEUmSJEmS1HAMiEiSJEmSpIZjQESSJEmSJDUcAyKSJEmSJKnhGBCRJEmSJEkNx4CIJEmSJElqOAZEJEmSJElSwzEgIkmSJEmSGo4BEUmSJEmS1HAMiEiSJEmSpIZjQESSJEmSJDUcAyKSJEmSJKnhGBCRJEmSJEkNx4CIJEmSJElqOAZEJEmSJElSwzEgIkmSJEmSGo4BEUmSJEmS1HAMiEiSJEmSpIZjQESSJEmSJDUcAyKSJEmSJKnhGBCRJEmSJEkNx4CIJEmSJElqOAZEJEmSJElSwzEgIkmSJEmSGo4BEUmSJEmS1HAMiEiSJEmSpIYzoL8bIK1Kk07+Wn83QZKkXls4f15/N0GSpLWGARE1lGnTZrF4cWt/N0NaLYwbN4KpU1/u72ZIqwWvB0mSGo9DZiRJkiRJUsMxICJJkiRJkhqOARFJkiRJktRwDIhIkiRJkqSGY0BEkiRJkiQ1HAMikiRJkiSp4RgQkSRJkiRJDceAiCRJkiRJajgGRCRJkiRJUsMxICJJkiRJkhqOARFJkiRJktRwDIhIkiRJkqSGY0BEkiRJkiQ1HAMikiRJkiSp4Qzo7wZIq9KYMcP7uwnSamXcuBH93YRVYt78+bw0c15/N0OSJEmrkR4HRCJiY+BTwGuBUVUdTZ0Ub83MrXrfPKlvffo3X+KFWdP7uxmSVrGfn3AGYEBEkiRJ7XoUEImIzYCbgHF0HgSp1dqbRkmSJEmSJK1MPe0h8h/A+sDLwM+B+4A5fdwmSZIkSZKklaqnAZE3Unp9HJyZN62E9kiSJEmSJK10PZ1lZhxwr8EQSZIkSZK0JutpQGQqMHBlNESSJEmSJGlV6WlA5Apgq4hw5hhJkiRJkrTG6mlA5EvAK8AvImLcSmiPJEmSJEnSStfTpKqHABcA7weeiIhbgSnA/E7Kt2bmcSvQPkmSJEmSpD7X04DImZRZZgAGAa/tpFwr0FT9NiAiSZIkSZJWKz0NiPyS9oCIJEmSJEnSGqlHAZHMPH4ltUOSJEmSJGmV6WlSVUmSJEmSpDVeT4fMABARzcC7gLcAAYwAXgYeBP4E/DIzF/RVIyVJkiRJkvpSjwMiETEeuAjYhZI4tdYk4K3AhyPibZn5+Io3UZIkSZIkqW/1KCASEYMpPUAmAXOAPwCTgZeA0cBuwBHAzsCFEbFnZnY2Ja8kSZIkSVK/6GkPkZMpwZAE3pSZj3UsEBFbApcBOwInUqbqlSRJkiRJWm30NKnqUZRpd4+qFwwByMxHqnJNwHtWqHWSJEmSJEkrQU97iLwKeCAz7+yqUGbeEREJbNvrlklroGfvepK7LriJ13/2MAaNGLzUtufuforHrktemfoyLeu0MDY2YuJBOzBo+NLlFi9azOPXJVNue5x5M2czZPQwJuy5FZvsuRVNTR3T9kiSJEmSeqOnPUQGU2aT6Y5ZwPAe1i+tsWZOmc59F06uu+3Jmx7mzvNvpHlAM1sfvAMb77oFz931JDef+TcWzF46zc69F07moSvvYfSmY4g378TQsSPIS2/n4SvvWRWHIUmSJEkNoac9RJ4EtouI4Zk5q7NCETEc2A54ekUaJ60pnrnjCe67aDKL5i9aZtui+Qt58C93MmL8aHZ73340NZdeHiM3Hs0dv/oHT9z4EFu9YTsAXnxyGs/c9jibvz7Y+uBJAEzYfUvuvOBGHrs+2Xi3LRgyetiqOzBJkiRJWkv1tIfIlcAQ4BvLKfctSm+SK3vTKGlN8s9fXMfdv7mZYeuPZMzWGyyzfc6MVxix0Wg22XPLJcEQgPW2KmVnPfviknXP3FZmqt5074lL1bHZa7ehdVErz9755Mo4BEmSJElqOD3tIfJt4HjgAxGxGXAGZdrdmcC6wK7AJ4CDgflVeWmtNnvaLLZ+445suvdE7q0zZGb4Buuy+/v3W2b9y8/MAGDwqPYeHzOfnM7gdYcwaMSQpcqO2GgUTc1NvDRlet82XpIkSZIaVI8CIpn5YEScBJwNHFL9dNQELATen5kPrHgTpdXbaz52MM0DWrpVtrW1lbkz5/Di4y/w4F/uYuCwQWz6mq2XbJ/70hyGrrfskJjmlmYGDhvEnBmz+6zdkiRJktTIejpkhsw8F9gHuAJYQAmAtP0sBC4HXp+Z5/RhO6XVVneDIQBzZ87h+m9ext2/uZn5s+ayzRt3ZMiooUu2L5y7gJZ16scpWwa2sGj+whVuryRJkiSp50NmAMjMm4A3RsRQYEtgJGX2mYcz00fYUidaBjQz6ag9WbxwMU9PfpR7fncLs6fNYuKB21clWjvfuRVodtpdSZIkSeoLvQqItKmCH3f3UVuktd46wwez4aRNANjo1Ztyy4+v4rFr72fCblsweNRQWtYZwKIFy85UA7BowSIGD1tnVTZXkiRJktZanQZEImLLavHxzFzUYV23ZeYjvWybtFZram5ig0kTmPnUdF5+9kUGjxrKkNHDmPfSnGXKLl60mAWz5zFqszH90FJJkiRJWvt01UPkIWAxsB3Qlhz1wR7W37qc91jpImJzSvvv7bDpJ5n5/R7WtQfw9sz8bCfbDwcuBnbLzGWnG1m67GnArZl5cU/a0BvVObg6MzfvsP4wYJvM/HZEnAqQmaf2sv62c9wKrAM8DZyQmU/1sK7dgJMz86SI2AW4EHgMuJpVdL762jO3P86Df7mLbY/YhfVfNX6pbQvnlZwgLQPLZTJy/Gim3Poo82fNZZ3hg5eUe/mZF2ld3Mq6E9ZbdQ2XJEmSpLXY8oIVHZOu9jSBweqS8ODpzNypD+rZDtigi+0nAL8BPgh8oKuKMvMLfdCeFbVbH9a11DmOiG8B3wDe3ZNKMvNW4KTq5WHAOZn5+T5rZT8Ytv5I5r08lydueJBx225EU1O5LBbMns+UWx9l4LBBrLtp6fmx4Y6bMOXWR3n87w+y9SGTltTx+N8foKmlaclwG0mSJEnSiukqILJF9XtKnXVrjYj4KHAsMAyYD7w7MzMivgkcROklcyFwBnAaMDwi/j0zT+9Qz1jgDcBOwO0R8enMfCkiBgI/A3aoiv4gM38SET+n9Nr4eUScDhwArEfpWXFUZj7XzXY+BvwfZQrkYcB7M3NyROwM/LTa/Y46x70dcHK1/Hi1eo+IuAHYGDg7M0+NiBZKYGM/oAX4eWZ+pxun9irgq1X9RwKfAoYAg4ATM/OGiNgJ+BEwFJgOHA1MBE4Fvg58uNp/LiV5b9v5+mTV9kXAJZ312FldjBw/mgl7bsVTNz3M5J9dywY7TGDB7Pk8dcsjzH9lLq9+9960DCwz1ay35fqsv/3GPHZdMv+Veay76RimPfAMz9/7NFu+YTsG18xII0mSJEnqvU4DIpn5eHfWrSHGR8TtHdYdCzwOvAXYLzPnVMNYPloFQ96UmdtXM+mcDcwFvlCVPZ1lHQNcnpmPRcStlJv7HwKvAdbLzJ0jYjzw38BP2naKiInAtsBrMnNxRPyyqutbNWVG1msncEpVZFpm7hERpwCfB94O/BL4f5l5RUT8J7B/bWMz896IOLNaPrsaMrNB1d4RwONVL4+jqzK7RMQg4C8RcWtmXtfZya6CQO8A/hERzZTgxWGZ+UJEnAh8DjgcOBf4bGZeGhEfAj4O/LF6v8tq2ndaFUAiInanBEp2A14B/hwRuy5viFJ/2/awnRi+/kieuvlh8rLbaRk4gFGbjWXL/V+1zDCYSUfuwSNj7+OZ2x/n2TufYMh6w9n28J3ZZM+t+qn1kiRJkrT26df8HqtQp0NmIuI9wLsiYhvgjcDtlF4xcyLi78CllJv2uRHR1XscD3ypWr6AErD4IWUWnoiIvwCXAf9au1NmPhQRnwJOivIGewMPdyjzUiftbPPn6vfdwNuq3irjM/OKav3Pgfd11fjKnzJzHjAvIl6g9Fg5ENgpIt5QlRkOTAI6BkRqg06DgJuBf6uCPG8FDq+Obz9gUdXGjTLz0uoYf0g5Ufstp437UnqFzKxeH9iN41pldnj77uzw9t2XWd/U1MQme27VraBG84AWJh60AxMP2mG5ZSVJkiRJvdOjgEhE/KwHxRcCs4FngX8Cf22brWZ1ERGbUJJ1/i/wJ0pbd87MhRGxJ+Xm+1BKT4d9u6hnF0qQ4IyI+A5laMn4iNgrM2+MiO0pw28OBf5ZvW7bd1fgPODbwG8pw0CaOtRft501ReZWv1urfdt+t1nYzVNSW66tjhbgM5n5+6otY4FZdfatG3SKiOGU4Mg5wLXAnZRg0YLqPdrKDQbGd9y/jo77jQdmZ+aL3dhXkiRJkiRg2aSpy3M8cFzNz/F1ftq2vQ/4GHA65Sb+jipvxepkd+ChKifGLcBbgZYq/8Y1wLWZ+WnK7ClBCRjUCyKdAPw4Mzf9/+zdd5xddZ3/8dekEkgvQEhCEko+AQIJVap0lCK6LoiABVAW+66iu/tzxe6yKro2FMEV+4quDRQQQXpvgTQ+oSS0UFIgBdIzvz/OGTIZMpNMcmdukvN6Ph73ce8953vO+dzhngeZ93xLZo7KzBEU83p8ICJOLl//heLnsQhoPjPm4RRzY1xCsVLLSRQhxDrrbO1DZeZciiEvJ5abzmilaWufp7m/A+dGRPcy3LgNOHAdxzQ3hiLA+E+KeUXeDnQte3g8ExHHle3eTTFHy7rcCpwQEb0johtFmFTLyWElSZIkSRXQ3kDkbOAqip4DSyh+GT0fOBf4BPBTYGG5/2HgUuB3wFyKFVqujogBNam8fXaIiIktHt8BrgO6RMRUil4sjwCjM/NB4E5gckQ8QBGIXEPR0+HAiPivphNHRA+KlVS+3+Ka3wTeUZ5nMTClPP4XmTmpWbsrgPERMYlyaVleP3ntWutcx2d+F/C5iHgQaG2cxi3AmeXcI625hGK55QfL2i7PzJvWce3mHqIY3vMIxc9gNjCyWY2fLYfanEaL4URrk5kPUPSUubM89y2ZeX076pEkSZIkiYbGxsZ1typFxH7AHRS/3J6UmU+tpc0Q4EpgL+DAzJwUEb0owpO3AJ9tZVJSqSONAmZ88rdfYM6iefWuRVIn+8nZ32b27IX1LkObsCFD+vgdkZrxnpDW5D2x6evSpYFBg3pD0Xlg5nod085rXFAec8rawhCAzJxN8df+HsDnym2LgX+iGKLx9nZeU5IkSZIkqabaG4gcCkzJzOltNSrDksk0W+o1M1+kWD1lVDuvKUmSJEmSVFPtDUS6t+OYbsBWLba9QtFzRJIkSZIkqW7aG4g8DuwWEePaahQRu1FMojqj2bauFGN5nmlvkZIkSZIkSbXU3kDk5+Uxv29tCd2IGEOxsgzAb5vt+hdgIMWysZIkSZIkSXXTrZ3tf0AxYer+wMMRcRvF0qeLgL4UK8scDHSlmEPkawAR8WvgVKAR+FZNKpckSZIkSdpA7QpEMnNxRBwPfA94J/BG4LBmTRrK5z8C55ary0ARoCwH/j0zH9i4kiVJkiRJkjZOe3uIkJnzgDMi4ovAPwDjgMEUE6ZOAn6fmQ+1OOw84MHMnLuR9UqSJEmSJG20dgciTTLzEeDC9Wx7/YZeR5IkSZIkqdY2OBCJiC7APsBYoH9mfi8iugPDM3NG20dLkiRJkiTVT3tXmQEgIs4GZgJ3Az8Fvl3uGglMj4hfRESvmlQoSZIkSZJUY+0ORCLiQuBHwHCKVWNWNNs9nGKFmdOBayNig3ugSJIkSZIkdZR2BSIRcSTwb8CrwAeBAcA9Tfsz8ybg3RQTrB4K/FOtCpUkSZIkSaqV9vYQ+RhFr5BzMvOHmbmwZYPM/CVFKNIAnLnxJUqSJEmSJNVWewmijBQAACAASURBVAORg4DnM/O3bTXKzD8Bs4A9NrQwSZIkSZKkjtLeQGQA8Ox6tn0WcGJVSZIkSZK0yWlvIDIX2GldjSKiARgNzNmQoiRJkiRJkjpSewORO4ABEfHOdbR7LzAYuHODqpIkSZIkSepA7Q1EvkMxWerFEXFyy50R0SUi3gdcTDH56iUbX6IkSZIkSVJttSsQycxbgK9RzCXyh4h4GdgXICLuAeYBl1LMHXJZZl5f23IlSZIkSZI2Xnt7iJCZ/w58EJgN9AW2oug1sl/5fgHw75n5gRrWKUmSJEmSVDPdNuSgzPxhRPwYOBgYB/QDXgESuCUzX61diZIkSZIkSbW1QYEIQGYuB24uH2sVEUMyc/aGXkOSJEmSJKkjtHvIzPqKiLOAaR11fkmSJEmSpA21zh4iEXEI8AGKoTENFEvvfjMzH2ul/Sjgh8AxtStTkiRJkiSpdtrsIRIRXwBuAc4AxgN7AecBD0bEUWtp/3FgEkUY0kAx8aokSZIkSdImpdVAJCKOBS6gCDZeBq4G/gy8CmwD/Coiepdtt42I64GLyn0NwE+B3Tu0ekmSJEmSpA3Q1pCZD5bPNwCnZeY8KCZKBa4C9gfeFRFXATcBO1EEIY8B52XmjR1VtCRJkiRJ0sZoKxCZAKwE3tsUhgBk5uyIeB/F0JjjgNOBnYFVwDeBz2Tm0o4rWdpwF536uXqXIKkOli5bVu8SJEmStIlpKxDZHng0M2e13JGZUyLiWeBEoDvwLHBGZt7aMWVKtTF37iJWrWqsdxnSJmHIkD7Mnr2w3mVIkiRJddFWINITmNvG/ueBYcAM4LC1BSeSJEmSJEmborZWmWkA2vpT+pJy/ycNQyRJkiRJ0uakzWV319PVNTiHJEmSJElSp9noQMQJVCVJkiRJ0uamFj1EJEmSJEmSNisGIpIkSZIkqXLaWmUGYL+IeKKVfdsDtLEfoDEzd96gyiRJkiRJkjrIugKRrYBR62jT1v62VqmRJEmSJEmqi7YCkS90WhWSJEmSJEmdqNVAJDMNRCRJkiRJ0hbJSVUlSZIkSVLlGIhIkiRJkqTKMRCRJEmSJEmVYyAiSZIkSZIqZ13L7kpblEGDete7BGmTMmRIn3qXsIblS5by8sJl9S5DkiRJFWAgokq58ROfZPGcufUuQ1IrTvjZ5WAgIkmSpE7gkBlJkiRJklQ5BiKSJEmSJKlyDEQkSZIkSVLltDqHSET8rAbnb8zM99bgPJIkSZIkSTXT1qSq7wIagYa17Gts9rrl/sZm2xsBAxFJkiRJkrRJaSsQ+RlrBh9NxgH7AsuBvwETgZeAXsAewEnA1sBfgLtqWawkSZIkSVIttBqIZOZZLbdFxC7A/cBk4G2Z+cRa2mwP/Ak4GvhszSqVJEmSJEmqkfZOqvolit4fb19bGAKQmc8Dp1KELV/auPIkSZIkSZJqr72ByDHAlMx8rK1GmfkUMAk4eEMLkyRJkiRJ6ijtDUR6Al3Xs21v1j4hqyRJkiRJUl21NxB5DNg9IvZqq1FEHAXsCkzZ0MIkSZIkSZI6SnsDkZ9S9Pq4MiIOXVuDiHgLcAXFCjWXblx5kiRJkiRJtdfWsrtrcwnwDuAg4OaImEmx4swioC8wHhhGEZr8LjN/VrNKJUmSJEmSaqRdPUQycylwAvA/FD1ARgNvAU4HTgSGAyuAC4Eza1qpJEmSJElSjbS3hwiZOR84NyIuAI4HAhgAzAUSuDIzX6pplZIkSZIkSTXU7kCkSWY+D1xew1okSZIkSZI6RXsnVZUkSZIkSdrstdpDJCJuqcH5GzPz8BqcR9os3PvC81w6+WEuOvRw+vXs2Wq7/37wfro2NPCxCfu8bt/CZcv44+OPMXHOiyxZsYKh2/TmqBEjOHjosI4sXZIkSZIqpa0hM2tdVredGmtwDmmzMHPBfH4+beo62/3fo9OZOm8uew4a/Lp9ryxfzoX33c3sxYt5w/ZD2blfP6a/9BKXT53C0wsXctqYsR1RuiRJkiRVTluByBc6rQppM3f388/x80emsnTlylbbLF6xgl88MpV7Xni+1TZXPfE4sxcv5u0778rxo0YDcOTwHek/Pbn+6SfZe8i2jBkwsOb1S5IkSVLVtBqIZObrApGI6J+ZL3dsSdLm5dsT72fy3LmM7tuXrbt1Z8q8ua9r89TCBXzrwQdYtHwZJ4wazdUzZ6z1XA/OfpE+3btz7I4j19h+4ujRXP/0k9w661kDEUmSJEmqgfZOqvq3iLg1IvyNTCq98OqrnLrLGP5t3wPo28q8IbNffZVtt+7Fv+13ACeP3rnVc720dAlDt+lNty5r3pq9u/dg627dmLlgQU1rlyRJkqSqau+yu2OB2Zk5ryOKkTZHXzjwELp3aTtb3GvItuy73fYArFy1qtV2Pbp2ZfGKFa/bvmLVKpasXEnjsqUbV6wkSZIkCWh/D5HlwCsdUYi0uVpXGLK+bQB26defWa8s4tlFi9bY/uDsF1nV2MjyNuYokSRJkiStv/YGIj8Hdo+IUzqiGKnqThq9E43A9x56kIdmv8icxYu567lZ/CqnsXW3bnRdz2BFkiRJktS29g6Z+RGwD3BFRNwK3AY8Byxu7YDM/PGGlydVyy79B3DeuL34xSNT+d7DEwHYuls3/nGXMdw+61leXuqQGUmSJEmqhfYGIhPL5wbgsPKxLgYiUjvss+127DV4CE8vXAjA8N696d61K3964jGGbrNNnauTJEmSpC1DewORp4HGjihEHS8ixgGTgFMy83ftPLYxMxvW0aY/cDGwV7npWeCjmfloRIwGPpOZ71vHOW7MzCPbU9uWJF+ax+zFizl0h2GM7tfvte2zFi1iwbJlHDFsRB2rkyRJkqQtR7sCkcwc1UF1qHOcA/wWOA9oVyCyni4EJmfmmQARcTpwBcUwq5FA6+vNrnZEB9S12Zg8dw7XPjmTEb37MLJvX6BYYeZ3j0+nR5cuHD5seJ0rlCRJkqQtQ3t7iGgzFRHdgTMphjndERE7Z+bjETETuBuYUO77Z+BoYCAwCzgtM18oz3EpcAAwBzgnM59qcZntgRcjoktmrqIIQ5qWS/kOsFNEXFxe4wfAOGA74GHgdOCr5XXuzsw3RMSbgS8C3YEZwLmZOTciLgKOBVYBf8zML9TuJ1VfRw7fkdtmPct3H3qQo0fsSK9u3bj7+ed4fP7LvHu33enbs2e9S5QkSZKkLcIGL1kRETtGxIci4tsR8ePy+SMRsUstC1TNnAg8mZnTgT8C/9Rs3zWZGUBfYCxwcGaOAZ4C3tWs3c2ZOQH4A/DttVzjyxS9UF6IiCvK138r930MuC8zPwwcDCzLzIOAXYD+wAmZ+TGAMgwZAvwX8KbM3Bv4K/DViBgJHJ+Z44FDKFY92mqjfjKbkIFbbcWn9tmfUX37ct1TM/n944/SpaGBj03Yh8N2sHeIJEmSJNVKu3uIRERX4CLgw0DXcnMDq+cWaYyIHwIfz8xlNalStXA28L/l6yuAX0bEBeX7uwEy87GIOB94f0QEcBDweNlmcWb+snz9c4rwYw2ZeX85V8ghwDHA+cB5EXFQi3a3RMTciPgwRQCzK9C7xeneAOwI3FiUQldgHsW8JIsj4nbgz8C/ZeaSdv80Osg5u4/jnN3Htdmma5cuXHb0ca3u36F3bz4yfu9alyZJkiRJamZDeoj8kuKv/d0ohlT8udx2DfB8ec4PAD+rUY3aSBGxLXA8cH45ROZHwADg7WWTxWW7fYHrKP4b/h9FT5CmiVRXNjtlA7C8xTUaIuIHQLfMvDkzL6CYXHUIsHeLtidTfGdeBS4Hbml2nSZdgdsyc0LZK2V/4B8zcwVFWHIBMAi4MyLGtPNHIkmSJEmquHYFIhHxD8A7KOaFOD0zR2TmWzPz3Zl5EjCcYojFK8CpEXFSzSvWhng3cENmDs/MUZk5EvgKRXDV3OHATZl5CTAdOInVvYB6l0EGFENhrm9+YGY2ArsDn4yIpu/VaIrg7HFgBat7JB0D/CYzLwdeBo5sdp2VEdGNotfKQc3CjguAiyJib+Bm4JbM/CQwFYgN+aFIkiRJkqqrvT1EzqUYGnNOZl7RcmdmNmbmryiGZzQAbS6xqk5zFvD9Ftsuppggtfn8G1cA4yNiEnATcB9FqAFFcPG2iHiIYkLTj6/lOu+kmCh1RkRMBX4KnJGZ84BpQP+I+DlwGXB6eZ3fArc3u86fgIfK650D/KZstw9wfmY+CNwJTI6IBygCkWva+wORJEmSJFVbQ2Nj47pblSLiRWBpZo5Yj7bPAI3r01bqBKOAGTd+4pMsnjO33rVIasUJP7uc2bMX1rsMVdCQIX387knNeE9Ia/Ke2PR16dLAoEG9ofhj+8z1Oqad1+hHManl+niGYv4ISZIkSZKkTUp7A5G5wE7rahQRDWW7eRtSlCRJkiRJUkdqbyByJzAoIs5bR7sPAIPL9pIkSZIkSZuUbutusobvA/8AfCci+gHfz8xFTTsjojfwYeBLFJOv/qBWhUqSJEmSJNVKuwKRzLwhIi6mCD0uBL4UEY8C8ynmF9m1PGcDRVhyfasnkyRJkiRJqpP2DpkhMz8KfIoiBOkO7A4cVD53p1gu9V8z8yM1rFOSJEmSJKlm2jtkBoDM/EZEfA84DBgL9AUWAo8At2Xm4tqVKEmSJEmSVFutBiIRsXtmTm1tf2YuBa4vH5IkSZIkSZuNtnqITIqIWRSBx3XA3zJzTueUJUmSJEmS1HHaCkQagGHAe8pHY0Q8TBGOXAfcmpnLO75ESZIkSZKk2morENkbeGP5OAzYFpgAjKeYVHVxRNwC/A24LjOndHCtkiRJkiRJNdFqIJKZDwEPAd8FiIixrBmQjADeDLyp3P8cRTjyN4rhNbM7tHJJkiRJkqQNtN6rzGTmIxSryFwKEBGjWR2QHA7sBLyXNYfX/DUz/1+ti5YkSZIkSdoYG7TsLkBmzgBmAD8FiIjtgUMpeo2cxurhNQYikiRJkiRpk7LBgUiTiBgPHEkxjGYCMIpiQlaAZRt7fkmSJEmSpFprdyASETtQ9AJ5M3AUMKDc1RSCTGP1SjQ3bXyJkiRJkiRJtbXOQCQiulP0/mgKQfYodzUFIHOBGygCkL9m5rMdUKckSZIkSVLNtBqIRMQHgeOBI4BtWB2ALAfuYnUvkPsys7Fjy5QkSZIkSaqdtnqIXAw0UgQhjwPXUiyp+/fMXNQJtUmSJEmSJHWI9ZlDZArwc+D6zHygg+uRJEmSJEnqcG0FItdRzB2yB3AhcGFEzKHoJfJX4LrMfKHjS5QkSZIkSaqtVgORzHxzRPSkmEPkzcCbgLHAGcDpABHxMGU4Atyamcs7umBJkiRJkqSN1eaQmcxcShF4/BUgIkZQTLTatOTu+PLxKeDViLi5qX1mTu/AuiVJkiRJkjbY+swh8prMfBq4FLg0IroCB7N6Od4JwAnlozEinqIIRj5Q25IlSZIkSZI2TrsCkeYycyVwa/n4j4gYSDHnyLHAu4GRwLmAgYgkSZIkSdqkbHAg0iQidgEOAd4AHADsCXQvdzdu7PklSZIkSZJqrV2BSER0B/alCECaHoPL3Q3l8xPA9cAN5UOSJEmSJGmT0mYgUg6DOZjV4cd+QM9yd1MA8iLwd4rw4/rMfLJjSpU23pHfvKjeJUhqw/IlS+tdgiRJkiqi1UAkIqYC0WxTUwCyiGLekOuBGzLz4Y4rT6qtuXMXsWqVI7kkgCFD+jB79sJ6lyFJkiTVRVs9RMaWz8uBe1g9DOauzFzR0YVJkiRJkiR1lLYCkW9RhCA3Z+YrnVSPJEmSJElSh2s1EMnMT3RmIZIkSZIkSZ2lS70LkCRJkiRJ6mwGIpIkSZIkqXIMRCRJkiRJUuUYiEiSJEmSpMoxEJEkSZIkSZVjICJJkiRJkirHQESSJEmSJFWOgYgkSZIkSaocAxFJkiRJklQ5BiKSJEmSJKlyDEQkSZIkSVLldKt3AVJnGjSod71LkFi2dAXzFyyudxmSJElSpRmIqFIu/vrVzH/51XqXoYr79FdOqXcJkiRJUuU5ZEaSJEmSJFWOgYgkSZIkSaocAxFJkiRJklQ5BiKSJEmSJKlyDEQkSZIkSVLlGIhIkiRJkqTKMRCRJEmSJEmVYyAiSZIkSZIqx0BEkiRJkiRVjoGIJEmSJEmqHAMRSZIkSZJUOQYikiRJkiSpcgxEJEmSJElS5RiISJIkSZKkyjEQkSRJkiRJlWMgIkmSJEmSKsdARJIkSZIkVU63ehcgbe5emv8Cd95/FbOef4wVK5YzcMBQ9t3rWHYeOf61No2Nq5gy/U4mP3Ir8xfMYauttmHnURM4YMLx9Oi+VR2rlyRJkqRqsoeItBEWLprH76/+Nk/PSsaNPZSD938rq1at4tobf0w+fu9r7e68/8/cfOdv6NN7EIfs/zZ22nE8k6bdyh+v/R4rV66o4yeQJEmSpGqyh4i0ER6adjNLlr7Cm484m51HTQBg7C4H8Ks//Cd33HclY3baj4WL5vHg5BsYPWJPTjj6/a8d27f3QG679w88OuMBxu5yQL0+giRJkiRVkj1EpI0wf8EcAHYctttr23p034odtt+FVxcv4NXFC1m4aB7bDR7JuLGHrnHs8B3GADBn3rOdV7AkSZIkCTAQkTbKgH7bAfDS/BfX2L5gwRy6du3OVj23ZtjQXTnlpE+w47Cxa7RpCkL69B7YOcVKkiRJkl5jICJthAl7HMmAftvx99t/yawXHmf+gjnccd+VvDDnSfYedxRdu645Km3VqpUsWDiXKXkHt9z1O/r1HeJwGUmSJEmqA+cQkTbC1r36cMDeJ/D3237FH675zmvbd9/1IN6w9wmva//8izP4w7XfBaBbtx4cfuAp9OzRq9PqlSRJkiQVDESkjXD/w3/jrgf+zMD+2zN+9yPo2aMXTz47jamP3sWy5Us49o3voUuX1R2xtt66H28+8hyWLlvMw1Nv5srrLuHIg09j9zEH1fFTSJIkSVL1GIhIG2jZsiXc99Bf6dN7IP944ifo0b0nADuPmkDf3gO5+8Gr2XHYWHbb9cDXjunfdwj9+w4BYJdRe/PrP/0Xt9/7J8bstC/duvWoy+eQJEmSpCpyDhFpA7284EVWrFzOziMnvBaGNGnq8fH0rGz1+B7dezJqxDiWLV/M/IVzOrRWSZIkSdKa7CFSQRFxCvD/KP77dwF+lplf38BznQSMycxvRsTnATLz8+tx3FuAK4H9MvP+dbT9InBfZl65ITV2lKYJUxsbV71uX2Nj42vPD0y6nolTbuTk4z7E4IHD1mi3fPkSAHuHSJIkSVIns4dIxUTEMOAbwHGZOR44CHhnRJy8gafcD+i7AcedDfwWOG9dDTPzs5taGAIwsP/29N5mAI/OeIDFSxatsW/SI7cBMGKHoH/fISxesoiHpty0Rpv5C+bw+MyHGNh/KP36DO6ssiVJkiRJ2EOkigYD3YGtgbmZuSgi3gssAYiIA4FvA1sBc4DzMvOxiLgJ+Hxm3hQRo4CbgBOAD5THPVme/4CIuAMYBly+tt4iETEYOAqYAEyMiE9m5oKI6A78GBhXNv1+Zl4WET8BbsrMn0TEV4CjgYHALOC0zHyhZj+ddmho6MKRB5/GX264jN9c9XX2GHMIW/XcmqefS5548mF22G4XYpcD6NLQhZHDd+eRx+9h6fLF7LjDWBa9Op/Jj9wGDXDUoafXo3xJkiRJqjR7iFRMZj4E/Al4IiLuiYivAl3L0KMH8GvgI2XvkUuA/23jXFPLNpdk5uXl5u2AI4F9gU9FRJ+1HPou4LrMnAncB5xZbj8YGJiZewMnAoc1PygidgHGAgdn5hjgqfJcdbPjsN14+/H/zKABOzBxyt+59Z7fM++l5zlgwvGcfNwH6dqlKw0NDRx/1Pt5w94nMO+l57j17t8xJW9nx2FjecdJn2S7wSPr+REkSZIkqZLsIVJBmfnBiPgycBzwJuCuiDgTmA68lJn3lu1+GxGXRkS/dpz+msxcCiyNiDkUPTkWtmhzFvCF8vUVwEeAHwCTgYiIvwJXA59qUfdjEXE+8P6ICIrhPo+3o7YOsd2QkZx0TNsjf7p26cp+49/EfuPf1ElVSZIkSZLaYg+RiomIEyPitMx8NjMvz8x3Ah8D3sfavw8NQFegsXwNxZCb1qxo9rr5MU3X3wfYE/h2RMwEPguMi4gDM3MusAfwXSCAByKif7Nj9wWuK+v8P+APLc8vSZIkSdL6MBCpnleBC8t5QIiIBoq5PB4EEhgUEfuX+94BPJmZ8yjmE9mjPMfbmp1vBe3raXQ2cGlm7piZozJzBPBz4APlxK4/B/5CEdIsAkY0O/ZwirlELqHozXISRVgjSZIkSVK7GIhUTGbeSDFc5c8RkcAjwErgS+VQl9OA70XEZIqhLKeVh34N+FBEPAD0anbKW4AzI+Kj67p2OUfJ6cD3W+z6JvAO4E5gMTAFuAf4RWZOatbuCmB8REyimNT1PmD0en50SZIkSZJe09DY2FjvGqTOMAqYcfHXr2b+y6/WuxZV3Ke/cgqzZ7ecWqfzDRnSZ5OoQ9oUeD9Ia/KekNbkPbHp69KlgUGDekPxR/OZ63VMRxYkSZIkSZK0KTIQkSRJkiRJlWMgIkmSJEmSKsdARJIkSZIkVY6BiCRJkiRJqhwDEUmSJEmSVDkGIpIkSZIkqXIMRCRJkiRJUuUYiEiSJEmSpMoxEJEkSZIkSZVjICJJkiRJkirHQESSJEmSJFWOgYgkSZIkSaocAxFJkiRJklQ5BiKSJEmSJKlyDEQkSZIkSVLlGIhIkiRJkqTKMRCRJEmSJEmVYyAiSZIkSZIqx0BEkiRJkiRVjoGIJEmSJEmqHAMRSZIkSZJUOQYikiRJkiSpcgxEJEmSJElS5RiISJIkSZKkyjEQkSRJkiRJlWMgIkmSJEmSKsdARJIkSZIkVU63ehcgdaYPf+qEepcgsWzpinqXIEmSJFWegYgqZe7cRaxa1VjvMiRJkiRJdeaQGUmSJEmSVDkGIpIkSZIkqXIMRCRJkiRJUuUYiEiSJEmSpMoxEJEkSZIkSZVjICJJkiRJkirHQESSJEmSJFWOgYgkSZIkSaocAxFJkiRJklQ5BiKSJEmSJKlyDEQkSZIkSVLlGIhIkiRJkqTKMRCRJEmSJEmVYyAiSZIkSZIqp1u9C5A606BBvetdQrssW7qU+QuW1bsMSZIkSdriGIioUn701U+z4OW59S5jvX3iwh8CBiKSJEmSVGsOmZEkSZIkSZVjICJJkiRJkirHQESSJEmSJFWOgYgkSZIkSaocAxFJkiRJklQ5BiKSJEmSJKlyDEQkSZIkSVLlGIhIkiRJkqTKMRCRJEmSJEmVYyAiSZIkSZIqx0BEkiRJkiRVjoGIJEmSJEmqHAMRSZIkSZJUOQYikiRJkiSpcgxEJEmSJElS5RiISJIkSZKkyjEQkSRJkiRJldOt3gVIm7vZLy3gzoem8/QLc1m2fAV9t+nF2NHDOHDPXenadXXmOP3JWdw7+XHmzl9E927d2Gn4thy691i26dWzjtVLkiRJUjUZiEgb4eWFr/Dra++gS0MDE8aOonevrXjq+Tnc9fCjPD/nZd5+9AE0NDQwMWdyw92TGbbtQA7bZzdeWbyEB6bN4Knn5vCukw6jV88e9f4okiRJklQpBiLSRrjx3qmsXLmKM9/yRgb26w3A+BjJTfdN5f6pT/D4My8wcugQbrl/GtsN6sc7jjuILl0aANhuUH+uvOk+Jj4yk4PGj6nnx5AkSZKkynEOEWkDrVrVyDMvzGXYtgNfC0Oa7L7TMACeeWEe8xe9yrYD+zF+zMjXwhCAkUMHA/DiSws6r2hJkiRJEmAPEWmDNTTAe056I400vm7fq0uWAdCloYHB/fvwzjcf/Lo2L86bD0C/bXp1bKGSJEmSpNcxEJE2UENDA/36bL3WffdPfQKAEdsPWmN7Y2MjC19ZwrOz53HL/dPotVUP9tltpw6vVZIkSZK0JgMRqcbunfw4M2fNZuiQAYzaYcga+xa+soTLfn8DUAQqbzp4PH1720NEkiRJkjqbgYhUQw9Me4JbHpjGNr16ctJhe9PQ0LDG/m5du3DSG/dh5cpVTHrsKa69fSIvL3yFQyZEnSqWJEmSpGpyUlWpBhobG7n1gUe48d6pbNOrJ6cceyB9e79+OM3WvXoSo3Zg952Hc+qxBzF0cH/unvQYC15ZXIeqJUmSJKm6DESkjbRy1SquuX0i90x+jP59tuadbz6Ywf37rPO4Ll0aGDNqBxobG5ntSjOSJEmS1KkqMWQmIkYB04GpLXZdlpkXd35FtRMRM4EjMnNmi+1Dga8DewMrgKeBj2XmExt4nRsz88h2tB8F3JSZo1rZ/w3gPcDwzFy6jnNdDbw/M2etf8WdY9WqRq6+9UGmP/kc2w3qx9uPPoCtt+q5RpupTzzDrfdP4+gD92SXEduvsW/Z8hUAdO/atdNqliRJkiRVJBApzcrMCfUuojNExDbAzcBFwLszszEizgT+FhFjM3P5Bpz2iBrW1w14B3AH8I/Ar9pqn5kn1OratXbXpEeZ/uRzDB0ygFOOeQM9ur/+lhrUrw+LFi/lgWkz2Hn4dq/NK7J46TImPfoUvbbqwdAhAzq7dEmSJEmqtCoFIq2KiMbMbChfn0XR4+KssvfF3cAE4DDgROB8oBG4H/hIZi6KiBeB3wMHAwuBMzNzZkTsD/w3sDUwBzgvM2e0uPbhwFfKNv2Bj2fmnyLiJ8B8YF9gGPDFzLw8IgYCvwBGUPR42WotH+mdwIuZeWnThsz8ZUQsBXpGxCqK3iNHAF2Bn2Tmf0fEEcCngVeB3YBJwBkUwQoRcXdmviEiZgP3AUOB/YHvA+OA7YCHgdPX8SM/EXgc+Bnwz5SBSEQMB34JbAOsoujRcldTLxhgHvA/wHBgB+B6ip4jjeu4Xod4ZfES7pn0GAC7jNiOx55+/nVtxf/dsgAADuVJREFUBvTdhqGDBzA+RvJQPslvr7uLMSOHsmTZch6a/iSvLlnKyYfvR/du9hCRJEmSpM5UpTlEdoiIiS0ee67HcddkZlD8sv8fwOGZuSfwCvC5ss0Q4M7M3Av4NfCdiOgB/Ag4IzP3Ab4BXLaW83+U4pf6fYD3A19utm8ERRBzMmUoAXwReKCs4eKyrpb2Bh5ouTEz/y8zFwHnlu/3AQ4A3hoRh5XNDgY+QhGI7Ai8KTM/VrZ/Q9lmMPDVssfNQcCyzDwI2IUi1FlXj46zgd8AVwMTImL3cvv7gD9n5n7AZ4FDWxx3IjCxvNauwOHAPuu4Vod59sV5rFy1CoBbH3iEa26b+LrH5MeeBuDoA8Zx9AHjWLx0GTfeN4X7pj7BtgP7cvqbD2HnEWv7TyhJkiRJ6khV6iGyoUNm7i6fDweuysy55ftLgcvL10soejsA/BS4EBgD7AxcGfHakqp913L+dwEnRcSpwIFA72b7riuHu0wGBpbbjqDsgZGZt0TE2uYEWVXW1JpjKIKIo8r3vYE9KXqcTM7MZwAiYlqz67Z0d7Ma5kbEh4GxFEFF71aOISK2BY4Dzs3MxRFxFXAeRU+R64HfR8TewF+A7zU/NjP/NyIOiIh/oQhsBrV1rY42ZuQOnP+eHdarbUNDAxPGjmLC2FEdW5QkSZIkab1UqYdImyKioXzZvcWupvVQW/6sGlgdKK1qNmyjC8Ukpl2BJzJzQhnE7MvrezwA3ErRS+N+iqEzDc32LQFoMSSksUWbFWs5533Afi03RsSPImKPsrZ/bVbbgcCPm1+zlWu9JjMXl+c8mWKYy6sUAdEtrR1Tele5/95yKMwxwHsioldm3g7sDvwVOA24qkX9H6UY6jMb+C5FgNPWtSRJkiRJWisDkcIcYI8yFDm5lTY3ASeXc3hAMezkxvL11hHxlvL12cA1wCPAwGZDUc6hxeSh5bnGUAwPuQZ4K0VY0ZbrgXeXx+9PMUylpd8CoyLifc2udTZF75LHgL8D50ZE94joDdxGEYq0ZWU5GWpLxwC/yczLgZeBI9fxGc4CzsrMUeUKNEMp5gY5LSK+BrwrM39KMWyn5XCYY4EfZuYvKeZOmbCOa0mSJEmStFZVCkTWNofId8p9/w78GbgTyLUdnJkPUwyFuTkiHqGYK+MzzZqcGhEPA28C/qVcSvZU4Bvl9vdSzJHR/JxNk4ROAaYBfSjClW3a+ByfA3aOiCll3a8bMlP23jiGIsCZUg65+QfguLKuS4BHgQcpepNcnpk3tXFNgD8BD0VEy0lcLwNOj4hJFEHM7cDotZ0gIvajmG/l981qXQV8C/gARa+PUyJiIvAHimV5m/sW8LnyWt+iWKVmrdeSJEmSJKktDY2NdVmgY4vSfJUabbJGATN+9NVPs+Dluetqu8n4xIU/ZPbshfUuQ1uoIUP6+P2SSt4P0pq8J6Q1eU9s+rp0aWDQoN5Q/NF85nod05EFSZIkSZIkbYoMRGrA3iGSJEmSJG1eDEQkSZIkSVLlGIhIkiRJkqTKMRCRJEmSJEmVYyAiSZIkSZIqx0BEkiRJkiRVjoGIJEmSJEmqHAMRSZIkSZJUOQYikiRJkiSpcgxEJEmSJElS5RiISJIkSZKkyjEQkSRJkiRJlWMgIkmSJEmSKsdARJIkSZIkVY6BiCRJkiRJqhwDEUmSJEmSVDkGIpIkSZIkqXIMRCRJkiRJUuUYiEiSJEmSpMoxEJEkSZIkSZVjICJJkiRJkirHQESSJEmSJFWOgYgkSZIkSaocAxFJkiRJklQ5BiKSJEmSJKlyDEQkSZIkSVLldKt3AVJnev+//We9S2iXZUuX1rsESZIkSdoiGYioUubOXcSqVY31LkOSJEmSVGcOmZEkSZIkSZVjICJJkiRJkirHQESSJEmSJFWOgYgkSZIkSaocAxFJkiRJklQ5rjKjqugK0KVLQ73rkDYp3hPSat4P0pq8J6Q1eU9s2pr99+m6vsc0NDa6BKkq4VDg1noXIUmSJEnqUIcBt61PQwMRVUVPYH/gOWBlnWuRJEmSJNVWV2AocC+wdH0OMBCRJEmSJEmV46SqkiRJkiSpcgxEJEmSJElS5RiISJIkSZKkyjEQkSRJkiRJlWMgIkmSJEmSKsdARJIkSZIkVY6BiCRJkiRJqpxu9S5A6mgRcQbwGaA78K3MvLjOJUmdJiL6AncAJ2XmzIg4Bvgm0Au4IjM/U7abAPwI6AvcAnwgM1fUqWypQ0TE54B3lG//kpn/6j2hKouILwKnAI3A/2TmN70nVHURcREwODPPau17HxE7Ar8AtgUSODMzF9WtaG0we4hoixYRw4CvAIcCE4B/iojd61uV1Dki4g3AbcCY8n0v4MfAW4HdgP0j4viy+S+Aj2TmGKABOLfzK5Y6TvlL3nHA3hT/P9g3Ik7He0IVFRGHA0cBewH7AR+NiPF4T6jCIuJo4L3NNrX2vf8+8P3MHAvcB1zQqYWqZgxEtKU7Bvh7Zs7LzFeA/6P4S4hUBecCHwZmle8PAB7NzBnlX/V+AZwaESOBXpl5V9nuJ8CpnV2s1MGeA87PzGWZuRyYRhEWek+okjLzZuDI8ru/LUXP8f54T6iiImIgxR9S/7N8v9bvfUR0B95I8XvFa9s7tVjVjIGItnQ7UPwjuMlzwPA61SJ1qsx8f2be2mxTa/eD94m2eJk5pekftRGxK8XQmVV4T6jCMnN5RHwBmArcgP+fULX9EPgP4KXyfWvf+8HAgmZDxrwfNmMGItrSdaEYF9ukgeIfwFIVtXY/eJ+oMiJiD+BvwKeAJ/CeUMVl5ueAIcAIil5T3hOqnIh4P/B0Zt7QbPP6/rsJvB82WwYi2tI9Awxt9n57Vg8fkKqmtfvB+0SVEBGHUPwV/N8z86d4T6jCImJsOWEkmfkq8HvgCLwnVE2nAcdFxETgi8DJwPtZ+/f+RaBfRHQttw/F+2GzZSCiLd31wNERMSQitgb+Ebi2zjVJ9XI3EBGxS/k/8TOAazLzSWBJ+csiwLuBa+pVpNQRImIE8EfgjMz8dbnZe0JVthNwWUT0jIgeFBOp/hDvCVVQZh6bmeMycwLwWeDKzDybtXzvy3mobqUIUQDeg/fDZstARFu0zHyWYizgjcBE4FeZeU99q5LqIzOXAGcBv6MYL/4IqycEOxP474h4BOgNfKceNUod6JPAVsA3I2Ji+VfAs/CeUEVl5tXAX4AHgfuBO8qw8Cy8J6QmrX3vP0SxeuVU4DDgM3WqTxupobGx5fAnSZIkSZKkLZs9RCRJkiRJUuUYiEiSJEmSpMoxEJEkSZIkSZVjICJJkiRJkirHQESSJEmSJFVOt3oXIEmSVAUR0Rd4D3AysBcwCFgCPAHcAFySmdPrV+HGi4jhwILMXFDvWiRJWhd7iEiSJHWwiDgJeBz4LnAs0B2YBMwF9gA+DkyOiP+oW5EbISJ6RMQXgenAtvWuR5Kk9WEgIkmS1IEi4nzgKmAw8BtgXGYOysx9MnMUMAL4PkVI8uWI+FLdit1wOwAXAL3qXYgkSevLQESSJKmDRMQhwFfLt1/KzNMyc0rzNpn5XGZ+GGgKQj4dEft2Zp2SJFWRgYgkSVIHiIgG4DKgK3B3Zn52HYd8GXia4t9nn+jg8iRJqjwnVZUkSeoYhwK7la//a12NM3NZRJxTvr2z+b6IGAB8DHgbsCtFaPIk8BfgG5n5XIv2ZwGXA89m5vCW14qIUcCM8u3ozJxZbv888DmKXi0XUQyDOZliSMzLwI3AVzJzUrNz3QQc3uz0j0YEwJGZedO6PrckSfViICJJktQxjimfVwJ/X58DMvP6ltsiYk/gWopQYhUwDVgOjAPOB86JiLfXOHwYCUwsr/lkec09gdOAt0TEYZn5QNl2ErANsF/5/n6K1XPm17AeSZJqziEzkiRJHWNs+TxzQ5ehjYg+rA5D7gR2zcxxmbk3MJxistYBwB8jYnQNam7yTmARcEBmjs7MCcDuwDPA1sBrw38y86PAqc2PzcxDM/PBGtYjSVLNGYhIkiR1jIHl8+yNOMeHKcKQF4ATM/OJph2Z+QJwCkUPjX5ArZfsPSMz72t2vQT+u3x7SI2vJUlSpzMQkSRJ6hivlM/dN+Icbymff5qZL7XcmZnLgO+Wb08uJ3KthVnNhsQ0N6187l+j60iSVDcGIpIkSR2jaaLTwRtxjqZhN/e30aZp3xBW90rZWM+2sn1x+ew8dJKkzZ6BiCRJUsfI8nl4RPRbnwMiYnC5AkyTvuVzWxOUNp+fpM/6l9emZTU6jyRJmywDEUmSpI7xp/K5K3DUeh5zLjAjIqZHRA9gYbm9rUBlQLPXC1vsa20IzTbrWY8kSVssAxFJkqQOkJkzgLvLt59a1/weZQBybvl2Wjk/yCPl+33bOLRpuduXMnNu+XpF+dyzlWN2aKsWSZKqwEBEkiSp4/wL0AgcxLpXgfkvYDSwCvhSue2q8vm9ETGg5QFliPKh8u01zXbNKZ8HRsS2a7nWP6y79HZZ1ex1rSZ2lSSpQxmISJIkdZDMvAu4sHz7pYj4VUTs0bxNRIyKiF8AHy83faHZcrc/oJjgdDvgLxExutlx2wK/BcZRDJX5fLPT3g0spwgnvhURvcpjukfEPwP/VLtPCcCiZq9H1vjckiR1iIbGxsZ61yBJkrRFi4hPAF+jmE8E4HngaYr5P3Ypty0DLsjMr7U4dm/gL8BQip4YUynCjnEUS/rOA87IzL+2OO7LrO6V8hLwBDAKGEQRtJwMDANGZ+bM8pjPA58Dbs/MQ9fyOY4AbgTIzIYW+2ZShCGLKIb6XJCZ167jRyNJUt3YQ0SSJKmDZeY3gd2ArwP3AlsB+1D0/JgIXATs3jIMKY99kCL8+BIwGdgJ2JViFZuvAHu2DEPK4z4DnAncRhGcBDAdeFdmfqhl+xo4BbiTIvQZw+qgR5KkTZI9RCRJkiRJUuXYQ0SSJEmSJFWOgYgkSZIkSaocAxFJkiRJklQ5BiKSJEmSJKlyDEQkSZIkSVLlGIhIkiRJkqTKMRCRJEmSJEmVYyAiSZIkSZIqx0BEkiRJ0v9vxw4EAAAAAAT5Ww9yYQSwI0QAAACAHSECAAAA7ARmFda5YmZ/SwAAAABJRU5ErkJggg==\n", + "text/plain": [ + "
" + ] + }, + "metadata": { + "needs_background": "light" + }, + "output_type": "display_data" + } + ], + "source": [ + "world_regions = mpi_region_locations['world_region'].value_counts()\n", + "# print(world_regions)\n", + "fig = plt.figure(figsize=(16, 9))\n", + "\n", + "sns.barplot(x=world_regions.values, y=world_regions.index)\n", + "\n", + "plt.title(\"Loan Counts Per world Region\", fontsize=30)\n", + "\n", + "for i, v in enumerate(world_regions.values):\n", + " plt.text(10,i,v,color='k',fontsize=19)\n", + "\n", + "plt.xlabel(\"Count\", fontsize=25)\n", + "plt.ylabel(\"World Region\", fontsize=25)\n", + "plt.show()" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "**Sub-Saharan Africa** has the highest number of loans followed by **Latin America and Carribean** region, while **Europe and Central Asia** has the least number of loans.\n", + "
\n", + "
\n", + "To account for this trend, we take a look at each region's mean poverty index.\n", + "" + ] + }, + { + "cell_type": "code", + "execution_count": 56, + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
MPI
world_region
Sub-Saharan Africa0.337128
South Asia0.219630
East Asia and the Pacific0.136266
Arab States0.115287
Latin America and Caribbean0.063665
Europe and Central Asia0.025273
\n", + "
" + ], + "text/plain": [ + " MPI\n", + "world_region \n", + "Sub-Saharan Africa 0.337128\n", + "South Asia 0.219630\n", + "East Asia and the Pacific 0.136266\n", + "Arab States 0.115287\n", + "Latin America and Caribbean 0.063665\n", + "Europe and Central Asia 0.025273" + ] + }, + "execution_count": 56, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "poverty_index_table = pd.pivot_table(mpi_region_locations, aggfunc=[np.mean], index=['world_region'], values=['MPI'])['mean'].sort_values(by=['MPI'], ascending=False)\n", + "poverty_index_table" + ] + }, + { + "cell_type": "code", + "execution_count": 60, + "metadata": {}, + "outputs": [ + { + "data": { + "image/png": "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\n", + "text/plain": [ + "
" + ] + }, + "metadata": { + "needs_background": "light" + }, + "output_type": "display_data" + } + ], + "source": [ + "poverty_index = poverty_index_table['MPI'].round(2)\n", + "# print(poverty_index['MPI'])\n", + "fig = plt.figure(figsize=(15, 8))\n", + "\n", + "sns.barplot(x=poverty_index.values, y=poverty_index.index)\n", + "\n", + "for i, v in enumerate(poverty_index.values):\n", + " plt.text(0.01, i, v, color='k', fontsize=19)\n", + "\n", + "plt.title(\"Region Poverty Indexes\", fontsize=30)\n", + "plt.ylabel(\"World Region\", fontsize=25)\n", + "plt.xlabel(\"MPI\", fontsize=25)\n", + "\n", + "plt.show()" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "From the above charts, its clear that **Sub-Saharan Africa** has the highest Multidimensional Poverty Index while **Europe and Central ASia** has the lowest. This explains why the two regions have the highest and lowest loan counts respectively.\n", + "
\n", + "
\n", + "A [study](https://blogs.worldbank.org/opendata/number-extremely-poor-people-continues-rise-sub-saharan-africa) conducted by The World Bank shows that the number of extremely poor people continues to rise in Sub-Saharan africa while it falls in other regions ([World bank Data Blog](https://blogs.worldbank.org/opendata/number-extremely-poor-people-continues-rise-sub-saharan-africa)).\n", + "
\n", + "
\n", + "From this study, it is expected that the number of loan counts from **Sub-Saharan Africa** will always be high." + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### 5.4. Repayment Intervals\n", + "" + ] + }, + { + "cell_type": "code", + "execution_count": 73, + "metadata": {}, + "outputs": [ + { + "data": { + "image/png": "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\n", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "intervals = kiva_loans['repayment_interval'].value_counts()\n", + "# print(intervals)\n", + "plt.figure(figsize=(15,8))\n", + "\n", + "plt.pie(intervals.values, labels=intervals.index, shadow=True, autopct='%1.1f%%', startangle=90)\n", + "\n", + "plt.axis('equal')\n", + "plt.title('Repayment Intervals', fontsize=30)\n", + "\n", + "plt.show()" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "With a percentage of **51.1%**, majority of the loans are repaid **monthly**." + ] + }, { "cell_type": "code", "execution_count": null, diff --git a/notebooks/.ipynb_checkpoints/tests-checkpoint.ipynb b/notebooks/.ipynb_checkpoints/tests-checkpoint.ipynb index d3f78cd..a995a9b 100644 --- a/notebooks/.ipynb_checkpoints/tests-checkpoint.ipynb +++ b/notebooks/.ipynb_checkpoints/tests-checkpoint.ipynb @@ -14,371 +14,8 @@ "outputs": [], "source": [ "import pandas as pd\n", - "import numpy as np" - ] - }, - { - "cell_type": "code", - "execution_count": 2, - "metadata": {}, - "outputs": [ - { - "data": { - "text/html": [ - "
\n", - "\n", - "\n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - "
idfunded_amountloan_amountactivitysectorusecountry_codecountryregioncurrencypartner_idposted_timedisbursed_timefunded_timeterm_in_monthslender_counttagsborrower_gendersrepayment_intervaldate
0653051300.0300.0Fruits & VegetablesFoodTo buy seasonal, fresh fruits to sell.PKPakistanLahorePKR247.02014-01-01 06:12:39+00:002013-12-17 08:00:00+00:002014-01-02 10:06:32+00:0012.012NaNfemaleirregular2014-01-01
1653053575.0575.0RickshawTransportationto repair and maintain the auto rickshaw used ...PKPakistanLahorePKR247.02014-01-01 06:51:08+00:002013-12-17 08:00:00+00:002014-01-02 09:17:23+00:0011.014NaNfemale, femaleirregular2014-01-01
2653068150.0150.0TransportationTransportationTo repair their old cycle-van and buy another ...INIndiaMaynaguriINR334.02014-01-01 09:58:07+00:002013-12-17 08:00:00+00:002014-01-01 16:01:36+00:0043.06user_favorite, user_favoritefemalebullet2014-01-01
3653063200.0200.0EmbroideryArtsto purchase an embroidery machine and a variet...PKPakistanLahorePKR247.02014-01-01 08:03:11+00:002013-12-24 08:00:00+00:002014-01-01 13:00:00+00:0011.08NaNfemaleirregular2014-01-01
4653084400.0400.0Milk SalesFoodto purchase one buffalo.PKPakistanAbdul HakeemPKR245.02014-01-01 11:53:19+00:002013-12-17 08:00:00+00:002014-01-01 19:18:51+00:0014.016NaNfemalemonthly2014-01-01
\n", - "
" - ], - "text/plain": [ - " id funded_amount loan_amount activity sector \\\n", - "0 653051 300.0 300.0 Fruits & Vegetables Food \n", - "1 653053 575.0 575.0 Rickshaw Transportation \n", - "2 653068 150.0 150.0 Transportation Transportation \n", - "3 653063 200.0 200.0 Embroidery Arts \n", - "4 653084 400.0 400.0 Milk Sales Food \n", - "\n", - " use country_code country \\\n", - "0 To buy seasonal, fresh fruits to sell. PK Pakistan \n", - "1 to repair and maintain the auto rickshaw used ... PK Pakistan \n", - "2 To repair their old cycle-van and buy another ... IN India \n", - "3 to purchase an embroidery machine and a variet... PK Pakistan \n", - "4 to purchase one buffalo. PK Pakistan \n", - "\n", - " region currency partner_id posted_time \\\n", - "0 Lahore PKR 247.0 2014-01-01 06:12:39+00:00 \n", - "1 Lahore PKR 247.0 2014-01-01 06:51:08+00:00 \n", - "2 Maynaguri INR 334.0 2014-01-01 09:58:07+00:00 \n", - "3 Lahore PKR 247.0 2014-01-01 08:03:11+00:00 \n", - "4 Abdul Hakeem PKR 245.0 2014-01-01 11:53:19+00:00 \n", - "\n", - " disbursed_time funded_time term_in_months \\\n", - "0 2013-12-17 08:00:00+00:00 2014-01-02 10:06:32+00:00 12.0 \n", - "1 2013-12-17 08:00:00+00:00 2014-01-02 09:17:23+00:00 11.0 \n", - "2 2013-12-17 08:00:00+00:00 2014-01-01 16:01:36+00:00 43.0 \n", - "3 2013-12-24 08:00:00+00:00 2014-01-01 13:00:00+00:00 11.0 \n", - "4 2013-12-17 08:00:00+00:00 2014-01-01 19:18:51+00:00 14.0 \n", - "\n", - " lender_count tags borrower_genders \\\n", - "0 12 NaN female \n", - "1 14 NaN female, female \n", - "2 6 user_favorite, user_favorite female \n", - "3 8 NaN female \n", - "4 16 NaN female \n", - "\n", - " repayment_interval date \n", - "0 irregular 2014-01-01 \n", - "1 irregular 2014-01-01 \n", - "2 bullet 2014-01-01 \n", - "3 irregular 2014-01-01 \n", - "4 monthly 2014-01-01 " - ] - }, - "execution_count": 2, - "metadata": {}, - "output_type": "execute_result" - } - ], - "source": [ - "data = pd.read_csv('F:/isaka/python4DS/kiva_loans.csv')\n", - "data.head(5)" - ] - }, - { - "cell_type": "code", - "execution_count": 3, - "metadata": {}, - "outputs": [ - { - "data": { - "text/html": [ - "
\n", - "\n", - "\n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - "
idfunded_amountloan_amountpartner_idterm_in_monthslender_count
count6.712050e+05671205.000000671205.000000657698.000000671205.000000671205.000000
mean9.932486e+05785.995061842.397107178.19961613.73902220.590922
std1.966113e+051130.3989411198.66007394.2475818.59891928.459551
min6.530470e+050.00000025.0000009.0000001.0000000.000000
25%8.230720e+05250.000000275.000000126.0000008.0000007.000000
50%9.927800e+05450.000000500.000000145.00000013.00000013.000000
75%1.163653e+06900.0000001000.000000204.00000014.00000024.000000
max1.340339e+06100000.000000100000.000000536.000000158.0000002986.000000
\n", - "
" - ], - "text/plain": [ - " id funded_amount loan_amount partner_id \\\n", - "count 6.712050e+05 671205.000000 671205.000000 657698.000000 \n", - "mean 9.932486e+05 785.995061 842.397107 178.199616 \n", - "std 1.966113e+05 1130.398941 1198.660073 94.247581 \n", - "min 6.530470e+05 0.000000 25.000000 9.000000 \n", - "25% 8.230720e+05 250.000000 275.000000 126.000000 \n", - "50% 9.927800e+05 450.000000 500.000000 145.000000 \n", - "75% 1.163653e+06 900.000000 1000.000000 204.000000 \n", - "max 1.340339e+06 100000.000000 100000.000000 536.000000 \n", - "\n", - " term_in_months lender_count \n", - "count 671205.000000 671205.000000 \n", - "mean 13.739022 20.590922 \n", - "std 8.598919 28.459551 \n", - "min 1.000000 0.000000 \n", - "25% 8.000000 7.000000 \n", - "50% 13.000000 13.000000 \n", - "75% 14.000000 24.000000 \n", - "max 158.000000 2986.000000 " - ] - }, - "execution_count": 3, - "metadata": {}, - "output_type": "execute_result" - } - ], - "source": [ - "data.describe()" + "import numpy as np\n", + "import matplotlib.pyplot as plt" ] }, { @@ -388,177 +25,8 @@ "outputs": [ { "data": { - "text/html": [ - "
\n", - "\n", - "\n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - "
sum
funded_amountloan_amount
countrysector
AfghanistanArts14000.014000.0
AlbaniaAgriculture976925.01005350.0
Arts8375.08375.0
Clothing153925.0162050.0
Construction35325.037975.0
Education117075.0118025.0
Entertainment5225.05225.0
Food107375.0123400.0
Health329400.0342550.0
Housing436175.0500900.0
Manufacturing33675.033675.0
Personal Use87550.0108400.0
Retail52250.059875.0
Services83100.090225.0
Transportation50875.057725.0
Wholesale12750.012750.0
ArmeniaAgriculture6607450.07587550.0
Arts63225.063225.0
Clothing288725.0360025.0
Construction146725.0162475.0
\n", - "
" - ], "text/plain": [ - " sum \n", - " funded_amount loan_amount\n", - "country sector \n", - "Afghanistan Arts 14000.0 14000.0\n", - "Albania Agriculture 976925.0 1005350.0\n", - " Arts 8375.0 8375.0\n", - " Clothing 153925.0 162050.0\n", - " Construction 35325.0 37975.0\n", - " Education 117075.0 118025.0\n", - " Entertainment 5225.0 5225.0\n", - " Food 107375.0 123400.0\n", - " Health 329400.0 342550.0\n", - " Housing 436175.0 500900.0\n", - " Manufacturing 33675.0 33675.0\n", - " Personal Use 87550.0 108400.0\n", - " Retail 52250.0 59875.0\n", - " Services 83100.0 90225.0\n", - " Transportation 50875.0 57725.0\n", - " Wholesale 12750.0 12750.0\n", - "Armenia Agriculture 6607450.0 7587550.0\n", - " Arts 63225.0 63225.0\n", - " Clothing 288725.0 360025.0\n", - " Construction 146725.0 162475.0" + "array([342717, 257158, 70728, 602], dtype=int64)" ] }, "execution_count": 4, @@ -567,4631 +35,16 @@ } ], "source": [ - "data.pivot_table(index=['country', 'sector'], aggfunc=[np.sum], values=['funded_amount', 'loan_amount']).head(20)" - ] - }, - { - "cell_type": "code", - "execution_count": 5, - "metadata": {}, - "outputs": [ - { - "data": { - "text/plain": [ - "0 female\n", - "1 female, female\n", - "2 female\n", - "3 female\n", - "4 female\n", - "5 female\n", - "6 female\n", - "7 female\n", - "8 female\n", - "9 female\n", - "10 female\n", - "11 female\n", - "12 female\n", - "13 female\n", - "14 female\n", - "15 female\n", - "16 female\n", - "17 female, female, female\n", - "18 female\n", - "19 female\n", - "20 female\n", - "21 female\n", - "22 female, female\n", - "23 female\n", - "24 female\n", - "25 female\n", - "26 female\n", - "27 female\n", - "28 female\n", - "29 female\n", - "Name: borrower_genders, dtype: object" - ] - }, - "execution_count": 5, - "metadata": {}, - "output_type": "execute_result" - } - ], - "source": [ - "data['borrower_genders'].head(30)" - ] - }, - { - "cell_type": "code", - "execution_count": 6, - "metadata": {}, - "outputs": [ - { - "data": { - "text/html": [ - "
\n", - "\n", - "\n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - "
idfunded_amountloan_amountactivitysectorusecountry_codecountryregioncurrencypartner_idposted_timedisbursed_timefunded_timeterm_in_monthslender_counttagsborrower_gendersrepayment_intervaldate
0NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
1NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
2NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
3NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
4NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
5NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
6NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
7NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
8NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
9NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
10NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
11NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
12NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
13NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
14NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
15NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
16NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
17NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
18NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
19NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
20NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
21NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
22NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
23NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
24NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
25NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
26NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
27NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
28NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
29NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
...............................................................
671175NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671176NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671177NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671178NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671179NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671180NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671181NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671182NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671183NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671184NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671185NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671186NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671187NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671188NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671189NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671190NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671191NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671192NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671193NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671194NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671195NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671196NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671197NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671198NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671199NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671200NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671201NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671202NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671203NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
671204NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
\n", - "

671205 rows × 20 columns

\n", - "
" - ], - "text/plain": [ - " id funded_amount loan_amount activity sector use country_code \\\n", - "0 NaN NaN NaN NaN NaN NaN NaN \n", - "1 NaN NaN NaN NaN NaN NaN NaN \n", - "2 NaN NaN NaN NaN NaN NaN NaN \n", - "3 NaN NaN NaN NaN NaN NaN NaN \n", - "4 NaN NaN NaN NaN NaN NaN NaN \n", - "5 NaN NaN NaN NaN NaN NaN NaN \n", - "6 NaN NaN NaN NaN NaN NaN NaN \n", - "7 NaN NaN NaN NaN NaN NaN NaN \n", - "8 NaN NaN NaN NaN NaN NaN NaN \n", - "9 NaN NaN NaN NaN NaN NaN NaN \n", - "10 NaN NaN NaN NaN NaN NaN NaN \n", - "11 NaN NaN NaN NaN NaN NaN NaN \n", - "12 NaN NaN NaN NaN NaN NaN NaN \n", - "13 NaN NaN NaN NaN NaN NaN NaN \n", - "14 NaN NaN NaN NaN NaN NaN NaN \n", - "15 NaN NaN NaN NaN NaN NaN NaN \n", - "16 NaN NaN NaN NaN NaN NaN NaN \n", - "17 NaN NaN NaN NaN NaN NaN NaN \n", - "18 NaN NaN NaN NaN NaN NaN NaN \n", - "19 NaN NaN NaN NaN NaN NaN NaN \n", - "20 NaN NaN NaN NaN NaN NaN NaN \n", - "21 NaN NaN NaN NaN NaN NaN NaN \n", - "22 NaN NaN NaN NaN NaN NaN NaN \n", - "23 NaN NaN NaN NaN NaN NaN NaN \n", - "24 NaN NaN NaN NaN NaN NaN NaN \n", - "25 NaN NaN NaN NaN NaN NaN NaN \n", - "26 NaN NaN NaN NaN NaN NaN NaN \n", - "27 NaN NaN NaN NaN NaN NaN NaN \n", - "28 NaN NaN NaN NaN NaN NaN NaN \n", - "29 NaN NaN NaN NaN NaN NaN NaN \n", - "... .. ... ... ... ... ... ... \n", - "671175 NaN NaN NaN NaN NaN NaN NaN \n", - "671176 NaN NaN NaN NaN NaN NaN NaN \n", - "671177 NaN NaN NaN NaN NaN NaN NaN \n", - "671178 NaN NaN NaN NaN NaN NaN NaN \n", - "671179 NaN NaN NaN NaN NaN NaN NaN \n", - "671180 NaN NaN NaN NaN NaN NaN NaN \n", - "671181 NaN NaN NaN NaN NaN NaN NaN \n", - "671182 NaN NaN NaN NaN NaN NaN NaN \n", - "671183 NaN NaN NaN NaN NaN NaN NaN \n", - "671184 NaN NaN NaN NaN NaN NaN NaN \n", - "671185 NaN NaN NaN NaN NaN NaN NaN \n", - "671186 NaN NaN NaN NaN NaN NaN NaN \n", - "671187 NaN NaN NaN NaN NaN NaN NaN \n", - "671188 NaN NaN NaN NaN NaN NaN NaN \n", - "671189 NaN NaN NaN NaN NaN NaN NaN \n", - "671190 NaN NaN NaN NaN NaN NaN NaN \n", - "671191 NaN NaN NaN NaN NaN NaN NaN \n", - "671192 NaN NaN NaN NaN NaN NaN NaN \n", - "671193 NaN NaN NaN NaN NaN NaN NaN \n", - "671194 NaN NaN NaN NaN NaN NaN NaN \n", - "671195 NaN NaN NaN NaN NaN NaN NaN \n", - "671196 NaN NaN NaN NaN NaN NaN NaN \n", - "671197 NaN NaN NaN NaN NaN NaN NaN \n", - "671198 NaN NaN NaN NaN NaN NaN NaN \n", - "671199 NaN NaN NaN NaN NaN NaN NaN \n", - "671200 NaN NaN NaN NaN NaN NaN NaN \n", - "671201 NaN NaN NaN NaN NaN NaN NaN \n", - "671202 NaN NaN NaN NaN NaN NaN NaN \n", - "671203 NaN NaN NaN NaN NaN NaN NaN \n", - "671204 NaN NaN NaN NaN NaN NaN NaN \n", - "\n", - " country region currency partner_id posted_time disbursed_time \\\n", - "0 NaN NaN NaN NaN NaN NaN \n", - "1 NaN NaN NaN NaN NaN NaN \n", - "2 NaN NaN NaN NaN NaN NaN \n", - "3 NaN NaN NaN NaN NaN NaN \n", - "4 NaN NaN NaN NaN NaN NaN \n", - "5 NaN NaN NaN NaN NaN NaN \n", - "6 NaN NaN NaN NaN NaN NaN \n", - "7 NaN NaN NaN NaN NaN NaN \n", - "8 NaN NaN NaN NaN NaN NaN \n", - "9 NaN NaN NaN NaN NaN NaN \n", - "10 NaN NaN NaN NaN NaN NaN \n", - "11 NaN NaN NaN NaN NaN NaN \n", - "12 NaN NaN NaN NaN NaN NaN \n", - "13 NaN NaN NaN NaN NaN NaN \n", - "14 NaN NaN NaN NaN NaN NaN \n", - "15 NaN NaN NaN NaN NaN NaN \n", - "16 NaN NaN NaN NaN NaN NaN \n", - "17 NaN NaN NaN NaN NaN NaN \n", - "18 NaN NaN NaN NaN NaN NaN \n", - "19 NaN NaN NaN NaN NaN NaN \n", - "20 NaN NaN NaN NaN NaN NaN \n", - "21 NaN NaN NaN NaN NaN NaN \n", - "22 NaN NaN NaN NaN NaN NaN \n", - "23 NaN NaN NaN NaN NaN NaN \n", - "24 NaN NaN NaN NaN NaN NaN \n", - "25 NaN NaN NaN NaN NaN NaN \n", - "26 NaN NaN NaN NaN NaN NaN \n", - "27 NaN NaN NaN NaN NaN NaN \n", - "28 NaN NaN NaN NaN NaN NaN \n", - "29 NaN NaN NaN NaN NaN NaN \n", - "... ... ... ... ... ... ... \n", - "671175 NaN NaN NaN NaN NaN NaN \n", - "671176 NaN NaN NaN NaN NaN NaN \n", - "671177 NaN NaN NaN NaN NaN NaN \n", - "671178 NaN NaN NaN NaN NaN NaN \n", - "671179 NaN NaN NaN NaN NaN NaN \n", - "671180 NaN NaN NaN NaN NaN NaN \n", - "671181 NaN NaN NaN NaN NaN NaN \n", - "671182 NaN NaN NaN NaN NaN NaN \n", - "671183 NaN NaN NaN NaN NaN NaN \n", - "671184 NaN NaN NaN NaN NaN NaN \n", - "671185 NaN NaN NaN NaN NaN NaN \n", - "671186 NaN NaN NaN NaN NaN NaN \n", - "671187 NaN NaN NaN NaN NaN NaN \n", - "671188 NaN NaN NaN NaN NaN NaN \n", - "671189 NaN NaN NaN NaN NaN NaN \n", - "671190 NaN NaN NaN NaN NaN NaN \n", - "671191 NaN NaN NaN NaN NaN NaN \n", - "671192 NaN NaN NaN NaN NaN NaN \n", - "671193 NaN NaN NaN NaN NaN NaN \n", - "671194 NaN NaN NaN NaN NaN NaN \n", - "671195 NaN NaN NaN NaN NaN NaN \n", - "671196 NaN NaN NaN NaN NaN NaN \n", - "671197 NaN NaN NaN NaN NaN NaN \n", - "671198 NaN NaN NaN NaN NaN NaN \n", - "671199 NaN NaN NaN NaN NaN NaN \n", - "671200 NaN NaN NaN NaN NaN NaN \n", - "671201 NaN NaN NaN NaN NaN NaN \n", - "671202 NaN NaN NaN NaN NaN NaN \n", - "671203 NaN NaN NaN NaN NaN NaN \n", - "671204 NaN NaN NaN NaN NaN NaN \n", - "\n", - " funded_time term_in_months lender_count tags borrower_genders \\\n", - "0 NaN NaN NaN NaN NaN \n", - "1 NaN NaN NaN NaN NaN \n", - "2 NaN NaN NaN NaN NaN \n", - "3 NaN NaN NaN NaN NaN \n", - "4 NaN NaN NaN NaN NaN \n", - "5 NaN NaN NaN NaN NaN \n", - "6 NaN NaN NaN NaN NaN \n", - "7 NaN NaN NaN NaN NaN \n", - "8 NaN NaN NaN NaN NaN \n", - "9 NaN NaN NaN NaN NaN \n", - "10 NaN NaN NaN NaN NaN \n", - "11 NaN NaN NaN NaN NaN \n", - "12 NaN NaN NaN NaN NaN \n", - "13 NaN NaN NaN NaN NaN \n", - "14 NaN NaN NaN NaN NaN \n", - "15 NaN NaN NaN NaN NaN \n", - "16 NaN NaN NaN NaN NaN \n", - "17 NaN NaN NaN NaN NaN \n", - "18 NaN NaN NaN NaN NaN \n", - "19 NaN NaN NaN NaN NaN \n", - "20 NaN NaN NaN NaN NaN \n", - "21 NaN NaN NaN NaN NaN \n", - "22 NaN NaN NaN NaN NaN \n", - "23 NaN NaN NaN NaN NaN \n", - "24 NaN NaN NaN NaN NaN \n", - "25 NaN NaN NaN NaN NaN \n", - "26 NaN NaN NaN NaN NaN \n", - "27 NaN NaN NaN NaN NaN \n", - "28 NaN NaN NaN NaN NaN \n", - "29 NaN NaN NaN NaN NaN \n", - "... ... ... ... ... ... \n", - "671175 NaN NaN NaN NaN NaN \n", - "671176 NaN NaN NaN NaN NaN \n", - "671177 NaN NaN NaN NaN NaN \n", - "671178 NaN NaN NaN NaN NaN \n", - "671179 NaN NaN NaN NaN NaN \n", - "671180 NaN NaN NaN NaN NaN \n", - "671181 NaN NaN NaN NaN NaN \n", - "671182 NaN NaN NaN NaN NaN \n", - "671183 NaN NaN NaN NaN NaN \n", - "671184 NaN NaN NaN NaN NaN \n", - "671185 NaN NaN NaN NaN NaN \n", - "671186 NaN NaN NaN NaN NaN \n", - "671187 NaN NaN NaN NaN NaN \n", - "671188 NaN NaN NaN NaN NaN \n", - "671189 NaN NaN NaN NaN NaN \n", - "671190 NaN NaN NaN NaN NaN \n", - "671191 NaN NaN NaN NaN NaN \n", - "671192 NaN NaN NaN NaN NaN \n", - "671193 NaN NaN NaN NaN NaN \n", - "671194 NaN NaN NaN NaN NaN \n", - "671195 NaN NaN NaN NaN NaN \n", - "671196 NaN NaN NaN NaN NaN \n", - "671197 NaN NaN NaN NaN NaN \n", - "671198 NaN NaN NaN NaN NaN \n", - "671199 NaN NaN NaN NaN NaN \n", - "671200 NaN NaN NaN NaN NaN \n", - "671201 NaN NaN NaN NaN NaN \n", - "671202 NaN NaN NaN NaN NaN \n", - "671203 NaN NaN NaN NaN NaN \n", - "671204 NaN NaN NaN NaN NaN \n", - "\n", - " repayment_interval date \n", - "0 NaN NaN \n", - "1 NaN NaN \n", - "2 NaN NaN \n", - "3 NaN NaN \n", - "4 NaN NaN \n", - "5 NaN NaN \n", - "6 NaN NaN \n", - "7 NaN NaN \n", - "8 NaN NaN \n", - "9 NaN NaN \n", - "10 NaN NaN \n", - "11 NaN NaN \n", - "12 NaN NaN \n", - "13 NaN NaN \n", - "14 NaN NaN \n", - "15 NaN NaN \n", - "16 NaN NaN \n", - "17 NaN NaN \n", - "18 NaN NaN \n", - "19 NaN NaN \n", - "20 NaN NaN \n", - "21 NaN NaN \n", - "22 NaN NaN \n", - "23 NaN NaN \n", - "24 NaN NaN \n", - "25 NaN NaN \n", - "26 NaN NaN \n", - "27 NaN NaN \n", - "28 NaN NaN \n", - "29 NaN NaN \n", - "... ... ... \n", - "671175 NaN NaN \n", - "671176 NaN NaN \n", - "671177 NaN NaN \n", - "671178 NaN NaN \n", - "671179 NaN NaN \n", - "671180 NaN NaN \n", - "671181 NaN NaN \n", - "671182 NaN NaN \n", - "671183 NaN NaN \n", - "671184 NaN NaN \n", - "671185 NaN NaN \n", - "671186 NaN NaN \n", - "671187 NaN NaN \n", - "671188 NaN NaN \n", - "671189 NaN NaN \n", - "671190 NaN NaN \n", - "671191 NaN NaN \n", - "671192 NaN NaN \n", - "671193 NaN NaN \n", - "671194 NaN NaN \n", - "671195 NaN NaN \n", - "671196 NaN NaN \n", - "671197 NaN NaN \n", - "671198 NaN NaN \n", - "671199 NaN NaN \n", - "671200 NaN NaN \n", - "671201 NaN NaN \n", - "671202 NaN NaN \n", - "671203 NaN NaN \n", - "671204 NaN NaN \n", - "\n", - "[671205 rows x 20 columns]" - ] - }, - "execution_count": 6, - "metadata": {}, - "output_type": "execute_result" - } - ], - "source": [ - "data[data.isnull()]" - ] - }, - { - "cell_type": "code", - "execution_count": 7, - "metadata": {}, - "outputs": [ - { - "data": { - "text/html": [ - "
\n", - "\n", - "\n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - "
idfunded_amountloan_amountactivitysectorusecountry_codecountryregioncurrencypartner_idposted_timedisbursed_timefunded_timeterm_in_monthslender_counttagsborrower_gendersrepayment_intervaldate
0653051300.0300.0Fruits & VegetablesFoodTo buy seasonal, fresh fruits to sell.PKPakistanLahorePKR247.02014-01-01 06:12:39+00:002013-12-17 08:00:00+00:002014-01-02 10:06:32+00:0012.012NaNfemaleirregular2014-01-01
1653053575.0575.0RickshawTransportationto repair and maintain the auto rickshaw used ...PKPakistanLahorePKR247.02014-01-01 06:51:08+00:002013-12-17 08:00:00+00:002014-01-02 09:17:23+00:0011.014NaNfemale, femaleirregular2014-01-01
2653068150.0150.0TransportationTransportationTo repair their old cycle-van and buy another ...INIndiaMaynaguriINR334.02014-01-01 09:58:07+00:002013-12-17 08:00:00+00:002014-01-01 16:01:36+00:0043.06user_favorite, user_favoritefemalebullet2014-01-01
3653063200.0200.0EmbroideryArtsto purchase an embroidery machine and a variet...PKPakistanLahorePKR247.02014-01-01 08:03:11+00:002013-12-24 08:00:00+00:002014-01-01 13:00:00+00:0011.08NaNfemaleirregular2014-01-01
4653084400.0400.0Milk SalesFoodto purchase one buffalo.PKPakistanAbdul HakeemPKR245.02014-01-01 11:53:19+00:002013-12-17 08:00:00+00:002014-01-01 19:18:51+00:0014.016NaNfemalemonthly2014-01-01
51080148250.0250.0ServicesServicespurchase leather for my business using ksh 20000.KEKenyaNaNKESNaN2014-01-01 10:06:19+00:002014-01-30 01:42:48+00:002014-01-29 14:14:57+00:004.06NaNfemaleirregular2014-01-01
6653067200.0200.0DairyAgricultureTo purchase a dairy cow and start a milk produ...INIndiaMaynaguriINR334.02014-01-01 09:51:02+00:002013-12-16 08:00:00+00:002014-01-01 17:18:09+00:0043.08user_favorite, user_favoritefemalebullet2014-01-01
7653078400.0400.0Beauty SalonServicesto buy more hair and skin care products.PKPakistanEllahabadPKR245.02014-01-01 11:46:01+00:002013-12-20 08:00:00+00:002014-01-10 18:18:44+00:0014.08#Elderly, #Woman Owned Bizfemalemonthly2014-01-01
8653082475.0475.0ManufacturingManufacturingto purchase leather, plastic soles and heels i...PKPakistanLahorePKR245.02014-01-01 11:49:43+00:002013-12-20 08:00:00+00:002014-01-01 18:47:21+00:0014.019user_favoritefemalemonthly2014-01-01
9653048625.0625.0Food Production/SalesFoodto buy a stall, gram flour, ketchup, and coal ...PKPakistanLahorePKR247.02014-01-01 05:41:03+00:002013-12-17 08:00:00+00:002014-01-03 15:45:04+00:0011.024NaNfemaleirregular2014-01-01
10653060200.0200.0RickshawTransportationto cover the cost of repairing rickshawPKPakistanLahorePKR247.02014-01-01 07:32:39+00:002013-12-24 08:00:00+00:002014-01-01 12:18:55+00:0011.03NaNfemaleirregular2014-01-01
11653088400.0400.0WholesaleWholesaleto purchase biscuits, sweets and juices in bulk.PKPakistanFaisalabadPKR245.02014-01-01 12:03:43+00:002013-12-16 08:00:00+00:002014-01-03 09:19:26+00:0014.016NaNfemalemonthly2014-01-01
12653089400.0400.0General StoreRetailto buy stock of rice, sugar and flour .PKPakistanFaisalabadPKR245.02014-01-01 12:04:57+00:002013-12-24 08:00:00+00:002014-01-08 00:35:14+00:0014.016#Repeat Borrower, #Woman Owned Bizfemalemonthly2014-01-01
13653062400.0400.0Clothing SalesClothingto purchase variety of winter clothes to sell.PKPakistanLahorePKR247.02014-01-01 07:57:58+00:002013-12-24 08:00:00+00:002014-01-02 15:47:37+00:0012.010NaNfemaleirregular2014-01-01
14653075225.0225.0PoultryAgricultureto expand her existing poultry farm business.INIndiaDhupguriINR334.02014-01-01 11:24:40+00:002013-12-20 08:00:00+00:002014-01-01 18:58:18+00:0043.07user_favoritefemalebullet2014-01-01
15653054300.0300.0RickshawTransportationto buy a three-wheeled rickshaw.PKPakistanLahorePKR247.02014-01-01 06:58:07+00:002013-12-17 08:00:00+00:002014-01-02 00:04:08+00:0011.09NaNfemaleirregular2014-01-01
16653091400.0400.0General StoreRetailto buy packs of salts, biscuits and beverages.PKPakistanFaisalabadPKR245.02014-01-01 12:09:10+00:002013-12-09 08:00:00+00:002014-01-14 15:57:05+00:0014.011#Woman Owned Biz, #Parentfemalemonthly2014-01-01
17653052875.0875.0TailoringServicesTo buy a sewing machine, lace, zippers and but...PKPakistanLahorePKR247.02014-01-01 06:25:41+00:002013-12-17 08:00:00+00:002014-01-01 18:07:34+00:0011.025NaNfemale, female, femaleirregular2014-01-01
18653066250.0250.0SewingServicesto purchase a sewing machine.INIndiaMaynaguriINR334.02014-01-01 09:48:35+00:002013-12-13 08:00:00+00:002014-01-01 17:18:09+00:0043.04user_favorite, user_favoritefemalebullet2014-01-01
19653080475.0475.0Beauty SalonServicesto buy more cosmetics products for her beauty ...PKPakistanLahorePKR245.02014-01-01 11:48:08+00:002013-12-19 08:00:00+00:002014-01-10 03:22:29+00:0014.018#Woman Owned Bizfemalemonthly2014-01-01
\n", - "
" - ], - "text/plain": [ - " id funded_amount loan_amount activity \\\n", - "0 653051 300.0 300.0 Fruits & Vegetables \n", - "1 653053 575.0 575.0 Rickshaw \n", - "2 653068 150.0 150.0 Transportation \n", - "3 653063 200.0 200.0 Embroidery \n", - "4 653084 400.0 400.0 Milk Sales \n", - "5 1080148 250.0 250.0 Services \n", - "6 653067 200.0 200.0 Dairy \n", - "7 653078 400.0 400.0 Beauty Salon \n", - "8 653082 475.0 475.0 Manufacturing \n", - "9 653048 625.0 625.0 Food Production/Sales \n", - "10 653060 200.0 200.0 Rickshaw \n", - "11 653088 400.0 400.0 Wholesale \n", - "12 653089 400.0 400.0 General Store \n", - "13 653062 400.0 400.0 Clothing Sales \n", - "14 653075 225.0 225.0 Poultry \n", - "15 653054 300.0 300.0 Rickshaw \n", - "16 653091 400.0 400.0 General Store \n", - "17 653052 875.0 875.0 Tailoring \n", - "18 653066 250.0 250.0 Sewing \n", - "19 653080 475.0 475.0 Beauty Salon \n", - "\n", - " sector use \\\n", - "0 Food To buy seasonal, fresh fruits to sell. \n", - "1 Transportation to repair and maintain the auto rickshaw used ... \n", - "2 Transportation To repair their old cycle-van and buy another ... \n", - "3 Arts to purchase an embroidery machine and a variet... \n", - "4 Food to purchase one buffalo. \n", - "5 Services purchase leather for my business using ksh 20000. \n", - "6 Agriculture To purchase a dairy cow and start a milk produ... \n", - "7 Services to buy more hair and skin care products. \n", - "8 Manufacturing to purchase leather, plastic soles and heels i... \n", - "9 Food to buy a stall, gram flour, ketchup, and coal ... \n", - "10 Transportation to cover the cost of repairing rickshaw \n", - "11 Wholesale to purchase biscuits, sweets and juices in bulk. \n", - "12 Retail to buy stock of rice, sugar and flour . \n", - "13 Clothing to purchase variety of winter clothes to sell. \n", - "14 Agriculture to expand her existing poultry farm business. \n", - "15 Transportation to buy a three-wheeled rickshaw. \n", - "16 Retail to buy packs of salts, biscuits and beverages. \n", - "17 Services To buy a sewing machine, lace, zippers and but... \n", - "18 Services to purchase a sewing machine. \n", - "19 Services to buy more cosmetics products for her beauty ... \n", - "\n", - " country_code country region currency partner_id \\\n", - "0 PK Pakistan Lahore PKR 247.0 \n", - "1 PK Pakistan Lahore PKR 247.0 \n", - "2 IN India Maynaguri INR 334.0 \n", - "3 PK Pakistan Lahore PKR 247.0 \n", - "4 PK Pakistan Abdul Hakeem PKR 245.0 \n", - "5 KE Kenya NaN KES NaN \n", - "6 IN India Maynaguri INR 334.0 \n", - "7 PK Pakistan Ellahabad PKR 245.0 \n", - "8 PK Pakistan Lahore PKR 245.0 \n", - "9 PK Pakistan Lahore PKR 247.0 \n", - "10 PK Pakistan Lahore PKR 247.0 \n", - "11 PK Pakistan Faisalabad PKR 245.0 \n", - "12 PK Pakistan Faisalabad PKR 245.0 \n", - "13 PK Pakistan Lahore PKR 247.0 \n", - "14 IN India Dhupguri INR 334.0 \n", - "15 PK Pakistan Lahore PKR 247.0 \n", - "16 PK Pakistan Faisalabad PKR 245.0 \n", - "17 PK Pakistan Lahore PKR 247.0 \n", - "18 IN India Maynaguri INR 334.0 \n", - "19 PK Pakistan Lahore PKR 245.0 \n", - "\n", - " posted_time disbursed_time \\\n", - "0 2014-01-01 06:12:39+00:00 2013-12-17 08:00:00+00:00 \n", - "1 2014-01-01 06:51:08+00:00 2013-12-17 08:00:00+00:00 \n", - "2 2014-01-01 09:58:07+00:00 2013-12-17 08:00:00+00:00 \n", - "3 2014-01-01 08:03:11+00:00 2013-12-24 08:00:00+00:00 \n", - "4 2014-01-01 11:53:19+00:00 2013-12-17 08:00:00+00:00 \n", - "5 2014-01-01 10:06:19+00:00 2014-01-30 01:42:48+00:00 \n", - "6 2014-01-01 09:51:02+00:00 2013-12-16 08:00:00+00:00 \n", - "7 2014-01-01 11:46:01+00:00 2013-12-20 08:00:00+00:00 \n", - "8 2014-01-01 11:49:43+00:00 2013-12-20 08:00:00+00:00 \n", - "9 2014-01-01 05:41:03+00:00 2013-12-17 08:00:00+00:00 \n", - "10 2014-01-01 07:32:39+00:00 2013-12-24 08:00:00+00:00 \n", - "11 2014-01-01 12:03:43+00:00 2013-12-16 08:00:00+00:00 \n", - "12 2014-01-01 12:04:57+00:00 2013-12-24 08:00:00+00:00 \n", - "13 2014-01-01 07:57:58+00:00 2013-12-24 08:00:00+00:00 \n", - "14 2014-01-01 11:24:40+00:00 2013-12-20 08:00:00+00:00 \n", - "15 2014-01-01 06:58:07+00:00 2013-12-17 08:00:00+00:00 \n", - "16 2014-01-01 12:09:10+00:00 2013-12-09 08:00:00+00:00 \n", - "17 2014-01-01 06:25:41+00:00 2013-12-17 08:00:00+00:00 \n", - "18 2014-01-01 09:48:35+00:00 2013-12-13 08:00:00+00:00 \n", - "19 2014-01-01 11:48:08+00:00 2013-12-19 08:00:00+00:00 \n", - "\n", - " funded_time term_in_months lender_count \\\n", - "0 2014-01-02 10:06:32+00:00 12.0 12 \n", - "1 2014-01-02 09:17:23+00:00 11.0 14 \n", - "2 2014-01-01 16:01:36+00:00 43.0 6 \n", - "3 2014-01-01 13:00:00+00:00 11.0 8 \n", - "4 2014-01-01 19:18:51+00:00 14.0 16 \n", - "5 2014-01-29 14:14:57+00:00 4.0 6 \n", - "6 2014-01-01 17:18:09+00:00 43.0 8 \n", - "7 2014-01-10 18:18:44+00:00 14.0 8 \n", - "8 2014-01-01 18:47:21+00:00 14.0 19 \n", - "9 2014-01-03 15:45:04+00:00 11.0 24 \n", - "10 2014-01-01 12:18:55+00:00 11.0 3 \n", - "11 2014-01-03 09:19:26+00:00 14.0 16 \n", - "12 2014-01-08 00:35:14+00:00 14.0 16 \n", - "13 2014-01-02 15:47:37+00:00 12.0 10 \n", - "14 2014-01-01 18:58:18+00:00 43.0 7 \n", - "15 2014-01-02 00:04:08+00:00 11.0 9 \n", - "16 2014-01-14 15:57:05+00:00 14.0 11 \n", - "17 2014-01-01 18:07:34+00:00 11.0 25 \n", - "18 2014-01-01 17:18:09+00:00 43.0 4 \n", - "19 2014-01-10 03:22:29+00:00 14.0 18 \n", - "\n", - " tags borrower_genders \\\n", - "0 NaN female \n", - "1 NaN female, female \n", - "2 user_favorite, user_favorite female \n", - "3 NaN female \n", - "4 NaN female \n", - "5 NaN female \n", - "6 user_favorite, user_favorite female \n", - "7 #Elderly, #Woman Owned Biz female \n", - "8 user_favorite female \n", - "9 NaN female \n", - "10 NaN female \n", - "11 NaN female \n", - "12 #Repeat Borrower, #Woman Owned Biz female \n", - "13 NaN female \n", - "14 user_favorite female \n", - "15 NaN female \n", - "16 #Woman Owned Biz, #Parent female \n", - "17 NaN female, female, female \n", - "18 user_favorite, user_favorite female \n", - "19 #Woman Owned Biz female \n", - "\n", - " repayment_interval date \n", - "0 irregular 2014-01-01 \n", - "1 irregular 2014-01-01 \n", - "2 bullet 2014-01-01 \n", - "3 irregular 2014-01-01 \n", - "4 monthly 2014-01-01 \n", - "5 irregular 2014-01-01 \n", - "6 bullet 2014-01-01 \n", - "7 monthly 2014-01-01 \n", - "8 monthly 2014-01-01 \n", - "9 irregular 2014-01-01 \n", - "10 irregular 2014-01-01 \n", - "11 monthly 2014-01-01 \n", - "12 monthly 2014-01-01 \n", - "13 irregular 2014-01-01 \n", - "14 bullet 2014-01-01 \n", - "15 irregular 2014-01-01 \n", - "16 monthly 2014-01-01 \n", - "17 irregular 2014-01-01 \n", - "18 bullet 2014-01-01 \n", - "19 monthly 2014-01-01 " - ] - }, - "execution_count": 7, - "metadata": {}, - "output_type": "execute_result" - } - ], - "source": [ - "data[data.notnull()].head(20)" - ] - }, - { - "cell_type": "code", - "execution_count": 8, - "metadata": {}, - "outputs": [ - { - "data": { - "text/html": [ - "
\n", - "\n", - "\n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - "
borrower_genders
0female
2female
3female
4female
5female
6female
7female
8female
9female
10female
\n", - "
" - ], - "text/plain": [ - " borrower_genders\n", - "0 female\n", - "2 female\n", - "3 female\n", - "4 female\n", - "5 female\n", - "6 female\n", - "7 female\n", - "8 female\n", - "9 female\n", - "10 female" - ] - }, - "execution_count": 8, - "metadata": {}, - "output_type": "execute_result" - } - ], - "source": [ - "data.loc[data.borrower_genders == 'female', ['borrower_genders']].head(10)" - ] - }, - { - "cell_type": "code", - "execution_count": 9, - "metadata": {}, - "outputs": [ - { - "data": { - "text/html": [ - "
\n", - "\n", - "\n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - "
idfunded_amountloan_amountactivitysectorusecountry_codecountryregioncurrencypartner_idposted_timedisbursed_timefunded_timeterm_in_monthslender_counttagsborrower_gendersrepayment_intervaldate
0653051300.0300.0Fruits & VegetablesFoodTo buy seasonal, fresh fruits to sell.PKPakistanLahorePKR247.02014-01-01 06:12:39+00:002013-12-17 08:00:00+00:002014-01-02 10:06:32+00:0012.012NaNfemaleirregular2014-01-01
1653053575.0575.0RickshawTransportationto repair and maintain the auto rickshaw used ...PKPakistanLahorePKR247.02014-01-01 06:51:08+00:002013-12-17 08:00:00+00:002014-01-02 09:17:23+00:0011.014NaNfemale, femaleirregular2014-01-01
2653068150.0150.0TransportationTransportationTo repair their old cycle-van and buy another ...INIndiaMaynaguriINR334.02014-01-01 09:58:07+00:002013-12-17 08:00:00+00:002014-01-01 16:01:36+00:0043.06user_favorite, user_favoritefemalebullet2014-01-01
3653063200.0200.0EmbroideryArtsto purchase an embroidery machine and a variet...PKPakistanLahorePKR247.02014-01-01 08:03:11+00:002013-12-24 08:00:00+00:002014-01-01 13:00:00+00:0011.08user_favorite, user_favoritefemaleirregular2014-01-01
4653084400.0400.0Milk SalesFoodto purchase one buffalo.PKPakistanAbdul HakeemPKR245.02014-01-01 11:53:19+00:002013-12-17 08:00:00+00:002014-01-01 19:18:51+00:0014.016user_favorite, user_favoritefemalemonthly2014-01-01
51080148250.0250.0ServicesServicespurchase leather for my business using ksh 20000.KEKenyaAbdul HakeemKES245.02014-01-01 10:06:19+00:002014-01-30 01:42:48+00:002014-01-29 14:14:57+00:004.06user_favorite, user_favoritefemaleirregular2014-01-01
6653067200.0200.0DairyAgricultureTo purchase a dairy cow and start a milk produ...INIndiaMaynaguriINR334.02014-01-01 09:51:02+00:002013-12-16 08:00:00+00:002014-01-01 17:18:09+00:0043.08user_favorite, user_favoritefemalebullet2014-01-01
7653078400.0400.0Beauty SalonServicesto buy more hair and skin care products.PKPakistanEllahabadPKR245.02014-01-01 11:46:01+00:002013-12-20 08:00:00+00:002014-01-10 18:18:44+00:0014.08#Elderly, #Woman Owned Bizfemalemonthly2014-01-01
8653082475.0475.0ManufacturingManufacturingto purchase leather, plastic soles and heels i...PKPakistanLahorePKR245.02014-01-01 11:49:43+00:002013-12-20 08:00:00+00:002014-01-01 18:47:21+00:0014.019user_favoritefemalemonthly2014-01-01
9653048625.0625.0Food Production/SalesFoodto buy a stall, gram flour, ketchup, and coal ...PKPakistanLahorePKR247.02014-01-01 05:41:03+00:002013-12-17 08:00:00+00:002014-01-03 15:45:04+00:0011.024user_favoritefemaleirregular2014-01-01
10653060200.0200.0RickshawTransportationto cover the cost of repairing rickshawPKPakistanLahorePKR247.02014-01-01 07:32:39+00:002013-12-24 08:00:00+00:002014-01-01 12:18:55+00:0011.03user_favoritefemaleirregular2014-01-01
11653088400.0400.0WholesaleWholesaleto purchase biscuits, sweets and juices in bulk.PKPakistanFaisalabadPKR245.02014-01-01 12:03:43+00:002013-12-16 08:00:00+00:002014-01-03 09:19:26+00:0014.016user_favoritefemalemonthly2014-01-01
12653089400.0400.0General StoreRetailto buy stock of rice, sugar and flour .PKPakistanFaisalabadPKR245.02014-01-01 12:04:57+00:002013-12-24 08:00:00+00:002014-01-08 00:35:14+00:0014.016#Repeat Borrower, #Woman Owned Bizfemalemonthly2014-01-01
13653062400.0400.0Clothing SalesClothingto purchase variety of winter clothes to sell.PKPakistanLahorePKR247.02014-01-01 07:57:58+00:002013-12-24 08:00:00+00:002014-01-02 15:47:37+00:0012.010#Repeat Borrower, #Woman Owned Bizfemaleirregular2014-01-01
14653075225.0225.0PoultryAgricultureto expand her existing poultry farm business.INIndiaDhupguriINR334.02014-01-01 11:24:40+00:002013-12-20 08:00:00+00:002014-01-01 18:58:18+00:0043.07user_favoritefemalebullet2014-01-01
15653054300.0300.0RickshawTransportationto buy a three-wheeled rickshaw.PKPakistanLahorePKR247.02014-01-01 06:58:07+00:002013-12-17 08:00:00+00:002014-01-02 00:04:08+00:0011.09user_favoritefemaleirregular2014-01-01
16653091400.0400.0General StoreRetailto buy packs of salts, biscuits and beverages.PKPakistanFaisalabadPKR245.02014-01-01 12:09:10+00:002013-12-09 08:00:00+00:002014-01-14 15:57:05+00:0014.011#Woman Owned Biz, #Parentfemalemonthly2014-01-01
17653052875.0875.0TailoringServicesTo buy a sewing machine, lace, zippers and but...PKPakistanLahorePKR247.02014-01-01 06:25:41+00:002013-12-17 08:00:00+00:002014-01-01 18:07:34+00:0011.025#Woman Owned Biz, #Parentfemale, female, femaleirregular2014-01-01
18653066250.0250.0SewingServicesto purchase a sewing machine.INIndiaMaynaguriINR334.02014-01-01 09:48:35+00:002013-12-13 08:00:00+00:002014-01-01 17:18:09+00:0043.04user_favorite, user_favoritefemalebullet2014-01-01
19653080475.0475.0Beauty SalonServicesto buy more cosmetics products for her beauty ...PKPakistanLahorePKR245.02014-01-01 11:48:08+00:002013-12-19 08:00:00+00:002014-01-10 03:22:29+00:0014.018#Woman Owned Bizfemalemonthly2014-01-01
20653065250.0250.0BakeryFoodto buy ingredients to make bakery products.PKPakistanLahorePKR247.02014-01-01 08:26:34+00:002013-12-18 08:00:00+00:002014-01-01 15:35:59+00:0011.010#Woman Owned Bizfemaleirregular2014-01-01
21653055350.0350.0RestaurantFoodto purchase vegetables, chicken, and oil to co...PKPakistanLahorePKR247.02014-01-01 07:14:40+00:002013-12-24 08:00:00+00:002014-01-01 21:54:18+00:0012.013#Woman Owned Bizfemaleirregular2014-01-01
22653050575.0575.0Clothing SalesClothingTo buy winter clothing to sellPKPakistanLahorePKR247.02014-01-01 06:05:17+00:002013-12-17 08:00:00+00:002014-01-02 23:56:08+00:0012.020#Woman Owned Bizfemale, femaleirregular2014-01-01
23653079350.0350.0EmbroideryArtsto buy reels of threads in different colors an...PKPakistanLahorePKR245.02014-01-01 11:47:03+00:002013-12-13 08:00:00+00:002014-01-01 15:45:51+00:0014.06#Woman Owned Bizfemalemonthly2014-01-01
24653061250.0250.0Food StallFoodto purchase a variety of needed food items to ...PKPakistanLahorePKR247.02014-01-01 07:46:28+00:002013-12-24 08:00:00+00:002014-01-02 01:33:55+00:0011.07#Woman Owned Bizfemaleirregular2014-01-01
25653074250.0250.0FarmingAgricultureto purchase potato seeds and fertilizers for g...INIndiaDhupguriINR334.02014-01-01 11:13:09+00:002013-12-13 08:00:00+00:002014-01-01 19:01:19+00:0043.09#Woman Owned Bizfemalebullet2014-01-01
26653069250.0250.0Construction SuppliesConstructionto purchase stones for starting a business sup...INIndiaMaynaguriINR334.02014-01-01 10:04:17+00:002013-12-10 08:00:00+00:002014-01-01 22:12:43+00:0043.010user_favorite, user_favoritefemalebullet2014-01-01
27653056475.0475.0RickshawTransportationto cover the cost of repairing rickshawPKPakistanLahorePKR247.02014-01-01 07:20:09+00:002013-12-24 08:00:00+00:002014-01-01 20:26:48+00:0012.017user_favorite, user_favoritefemaleirregular2014-01-01
28653071125.0125.0FarmingAgricultureto purchase potato seeds and fertilizers for g...INIndiaMaynaguriINR334.02014-01-01 10:35:20+00:002013-12-17 08:00:00+00:002014-01-01 16:06:47+00:0043.05user_favorite, user_favoritefemalebullet2014-01-01
29653073250.0250.0FarmingAgricultureto purchase potato seeds and fertilizer for fa...INIndiaDhupguriINR334.02014-01-01 11:09:26+00:002013-12-19 08:00:00+00:002014-01-01 21:47:05+00:0043.010user_favorite, user_favoritefemalebullet2014-01-01
...............................................................
671175134027475.0125.0LivestockAgriculturePretend the flagged issue was addressed by KC.MXMexicoIztacalcoMXN294.02017-07-21 23:31:40+00:002017-07-21 07:00:00+00:002017-07-22 13:07:29+00:0013.03#Parent, #Repair Renew Replacefemale, femalemonthly2017-07-21
67117613402590.050.0LivestockAgricultureEdited loan use in english.GHGhanaDansomanGHS231.02017-07-21 15:54:42+00:002017-07-21 07:00:00+00:002017-07-22 13:07:29+00:0013.00#Parent, #Repair Renew Replacefemale, femalemonthly2017-07-21
671177134027925.025.0LivestockAgriculture[True, u'to start a turducken farm.'] - this l...KEKenyaDansomanKES138.02017-07-22 06:04:07+00:002017-07-21 07:00:00+00:002017-07-24 12:44:16+00:0013.01#Parent, #Repair Renew Replacefemalemonthly2017-07-22
67117813402800.025.0LivestockAgriculture[True, u'to start a turducken farm.'] - this l...KEKenyaDansomanKES138.02017-07-22 06:16:55+00:002017-07-21 07:00:00+00:002017-07-24 12:44:16+00:0013.00#Parent, #Repair Renew Replacefemalemonthly2017-07-22
67117913402820.025.0LivestockAgriculture[True, u'para compara: cemento, arenya y ladri...PYParaguayConcepciónUSD58.02017-07-22 06:49:47+00:002017-07-21 07:00:00+00:002017-07-24 12:44:16+00:0013.00#Parent, #Repair Renew Replacefemalemonthly2017-07-22
67118013402860.0725.0LivestockAgricultureTranslated loan use to english.BOBoliviaLa PazBOB59.02017-07-23 22:11:47+00:002017-07-23 07:00:00+00:002017-07-24 12:44:16+00:0013.00#Parent, #Repair Renew Replacefemalemonthly2017-07-23
67118113402850.025.0LivestockAgricultureReviewed loan use in english.PKPakistanAttockPKR245.02017-07-23 21:57:42+00:002017-07-23 07:00:00+00:002017-07-24 12:44:16+00:0013.00#Parent, #Repair Renew Replacefemalemonthly2017-07-23
67118213402920.0125.0LivestockAgriculturePretend the flagged issue was addressed by KC.MXMexicoIztacalcoMXN294.02017-07-23 23:19:01+00:002017-07-23 07:00:00+00:002017-07-24 12:44:16+00:0013.00#Parent, #Repair Renew Replacefemale, femalemonthly2017-07-23
67118313402900.075.0LivestockAgriculturePretend the issue with spanish loan was addres...MXMexicoIztacalcoMXN294.02017-07-23 22:56:35+00:002017-07-23 07:00:00+00:002017-07-24 12:44:16+00:0013.00#Parent, #Repair Renew Replacefemalemonthly2017-07-23
67118413402870.0875.0LivestockAgricultureTranslated loan use to english.BOBoliviaLa PazBOB59.02017-07-23 22:25:39+00:002017-07-23 07:00:00+00:002017-07-24 12:44:16+00:0013.00#Parent, #Repair Renew Replacefemale, femalemonthly2017-07-23
67118513402980.025.0LivestockAgricultureTranslated loan use to english.KEKenyaLa PazKES138.02017-07-24 07:34:50+00:002017-07-17 07:00:00+00:002017-07-24 12:44:16+00:0013.00#Parent, #Repair Renew Replacefemale, femalemonthly2017-07-24
671186134030025.025.0LivestockAgriculture[True, u'para compara: cemento, arenya y ladri...PYParaguayConcepciónUSD58.02017-07-24 08:09:10+00:002017-07-24 07:00:00+00:002017-07-25 00:19:01+00:0013.01#Parent, #Repair Renew Replacefemalemonthly2017-07-24
67118713402970.025.0LivestockAgriculture[True, u'to start a turducken farm.'] - this l...KEKenyaConcepciónKES138.02017-07-24 07:14:47+00:002017-07-24 07:00:00+00:002017-07-25 00:19:01+00:0013.00#Parent, #Repair Renew Replacefemalemonthly2017-07-24
67118813403020.0250.0LivestockAgricultureReviewed loan use in english.GHGhanaDansomanGHS231.02017-07-24 21:36:17+00:002017-07-24 07:00:00+00:002017-07-25 00:19:01+00:0013.00#Parent, #Repair Renew Replacefemalemonthly2017-07-24
67118913403150.025.0LivestockAgriculture[True, u'to start a turducken farm.'] - this l...KEKenyaDansomanKES138.02017-07-25 05:59:38+00:002017-07-24 07:00:00+00:002017-07-25 00:19:01+00:0013.00#Parent, #Repair Renew Replacefemalemonthly2017-07-25
67119013403210.025.0LivestockAgriculture[True, u'to start a turducken farm.'] - this l...KEKenyaDansomanKES138.02017-07-25 16:24:08+00:002017-07-25 07:00:00+00:002017-07-25 00:19:01+00:0013.00#Parent, #Repair Renew Replacefemalemonthly2017-07-25
67119113403270.0725.0LivestockAgricultureTranslated loan use to english.BOBoliviaLa PazBOB59.02017-07-25 22:10:23+00:002017-07-25 07:00:00+00:002017-07-25 00:19:01+00:0013.00#Parent, #Repair Renew Replacefemalemonthly2017-07-25
67119213403280.0875.0LivestockAgricultureTranslated loan use to english.BOBoliviaLa PazBOB59.02017-07-25 22:27:44+00:002017-07-25 07:00:00+00:002017-07-25 00:19:01+00:0013.00#Parent, #Repair Renew Replacefemale, femalemonthly2017-07-25
67119313403330.0125.0LivestockAgriculturePretend the flagged issue was addressed by KC.MXMexicoIztacalcoMXN294.02017-07-25 23:45:38+00:002017-07-25 07:00:00+00:002017-07-25 00:19:01+00:0013.00#Parent, #Repair Renew Replacefemale, femalemonthly2017-07-25
67119413403320.025.0LivestockAgricultureKiva Coordinator fixed issue loan (no longer v...KEKenyaIztacalcoKES138.02017-07-25 23:29:57+00:002017-07-25 07:00:00+00:002017-07-25 00:19:01+00:0013.00#Parent, #Repair Renew Replacefemale, femalemonthly2017-07-25
67119513403290.050.0LivestockAgricultureEdited loan use in english.GHGhanaDansomanGHS231.02017-07-25 22:40:59+00:002017-07-25 07:00:00+00:002017-07-25 00:19:01+00:0013.00#Parent, #Repair Renew Replacefemale, femalemonthly2017-07-25
67119613403250.0250.0LivestockAgricultureReviewed loan use in english.GHGhanaDansomanGHS231.02017-07-25 21:36:20+00:002017-07-25 07:00:00+00:002017-07-25 00:19:01+00:0013.00#Parent, #Repair Renew Replacefemalemonthly2017-07-25
67119713403300.025.0LivestockAgriculturePretend the issue with loan got addressed by K...KEKenyaDansomanKES138.02017-07-25 22:55:42+00:002017-07-25 07:00:00+00:002017-07-25 00:19:01+00:0013.00#Parent, #Repair Renew Replacefemalemonthly2017-07-25
67119813403310.075.0LivestockAgriculturePretend the issue with spanish loan was addres...MXMexicoIztacalcoMXN294.02017-07-25 23:13:50+00:002017-07-25 07:00:00+00:002017-07-25 00:19:01+00:0013.00#Parent, #Repair Renew Replacefemalemonthly2017-07-25
67119913403180.025.0LivestockAgriculture[True, u'para compara: cemento, arenya y ladri...PYParaguayConcepciónUSD58.02017-07-25 06:45:02+00:002017-07-24 07:00:00+00:002017-07-25 00:19:01+00:0013.00#Parent, #Repair Renew Replacefemalemonthly2017-07-25
67120013403230.025.0LivestockAgriculture[True, u'para compara: cemento, arenya y ladri...PYParaguayConcepciónUSD58.02017-07-25 16:55:34+00:002017-07-25 07:00:00+00:002017-07-25 00:19:01+00:0013.00#Parent, #Repair Renew Replacefemalemonthly2017-07-25
671201134031625.025.0LivestockAgriculture[True, u'to start a turducken farm.'] - this l...KEKenyaConcepciónKES138.02017-07-25 06:14:08+00:002017-07-24 07:00:00+00:002017-07-26 02:09:43+00:0013.01#Parent, #Repair Renew Replacefemalemonthly2017-07-25
67120213403340.025.0GamesEntertainment[True, u'to start a turducken farm.'] - this l...KEKenyaConcepciónKES138.02017-07-26 00:02:07+00:002017-07-25 07:00:00+00:002017-07-26 02:09:43+00:0013.00#Parent, #Repair Renew Replacefemalemonthly2017-07-26
67120313403380.025.0LivestockAgriculture[True, u'to start a turducken farm.'] - this l...KEKenyaConcepciónKES138.02017-07-26 06:12:55+00:002017-07-25 07:00:00+00:002017-07-26 02:09:43+00:0013.00#Parent, #Repair Renew Replacefemalemonthly2017-07-26
67120413403390.025.0LivestockAgriculture[True, u'to start a turducken farm.'] - this l...KEKenyaConcepciónKES138.02017-07-26 06:31:46+00:002017-07-25 07:00:00+00:002017-07-26 02:09:43+00:0013.00#Parent, #Repair Renew Replacefemalemonthly2017-07-26
\n", - "

671205 rows × 20 columns

\n", - "
" - ], - "text/plain": [ - " id funded_amount loan_amount activity \\\n", - "0 653051 300.0 300.0 Fruits & Vegetables \n", - "1 653053 575.0 575.0 Rickshaw \n", - "2 653068 150.0 150.0 Transportation \n", - "3 653063 200.0 200.0 Embroidery \n", - "4 653084 400.0 400.0 Milk Sales \n", - "5 1080148 250.0 250.0 Services \n", - "6 653067 200.0 200.0 Dairy \n", - "7 653078 400.0 400.0 Beauty Salon \n", - "8 653082 475.0 475.0 Manufacturing \n", - "9 653048 625.0 625.0 Food Production/Sales \n", - "10 653060 200.0 200.0 Rickshaw \n", - "11 653088 400.0 400.0 Wholesale \n", - "12 653089 400.0 400.0 General Store \n", - "13 653062 400.0 400.0 Clothing Sales \n", - "14 653075 225.0 225.0 Poultry \n", - "15 653054 300.0 300.0 Rickshaw \n", - "16 653091 400.0 400.0 General Store \n", - "17 653052 875.0 875.0 Tailoring \n", - "18 653066 250.0 250.0 Sewing \n", - "19 653080 475.0 475.0 Beauty Salon \n", - "20 653065 250.0 250.0 Bakery \n", - "21 653055 350.0 350.0 Restaurant \n", - "22 653050 575.0 575.0 Clothing Sales \n", - "23 653079 350.0 350.0 Embroidery \n", - "24 653061 250.0 250.0 Food Stall \n", - "25 653074 250.0 250.0 Farming \n", - "26 653069 250.0 250.0 Construction Supplies \n", - "27 653056 475.0 475.0 Rickshaw \n", - "28 653071 125.0 125.0 Farming \n", - "29 653073 250.0 250.0 Farming \n", - "... ... ... ... ... \n", - "671175 1340274 75.0 125.0 Livestock \n", - "671176 1340259 0.0 50.0 Livestock \n", - "671177 1340279 25.0 25.0 Livestock \n", - "671178 1340280 0.0 25.0 Livestock \n", - "671179 1340282 0.0 25.0 Livestock \n", - "671180 1340286 0.0 725.0 Livestock \n", - "671181 1340285 0.0 25.0 Livestock \n", - "671182 1340292 0.0 125.0 Livestock \n", - "671183 1340290 0.0 75.0 Livestock \n", - "671184 1340287 0.0 875.0 Livestock \n", - "671185 1340298 0.0 25.0 Livestock \n", - "671186 1340300 25.0 25.0 Livestock \n", - "671187 1340297 0.0 25.0 Livestock \n", - "671188 1340302 0.0 250.0 Livestock \n", - "671189 1340315 0.0 25.0 Livestock \n", - "671190 1340321 0.0 25.0 Livestock \n", - "671191 1340327 0.0 725.0 Livestock \n", - "671192 1340328 0.0 875.0 Livestock \n", - "671193 1340333 0.0 125.0 Livestock \n", - "671194 1340332 0.0 25.0 Livestock \n", - "671195 1340329 0.0 50.0 Livestock \n", - "671196 1340325 0.0 250.0 Livestock \n", - "671197 1340330 0.0 25.0 Livestock \n", - "671198 1340331 0.0 75.0 Livestock \n", - "671199 1340318 0.0 25.0 Livestock \n", - "671200 1340323 0.0 25.0 Livestock \n", - "671201 1340316 25.0 25.0 Livestock \n", - "671202 1340334 0.0 25.0 Games \n", - "671203 1340338 0.0 25.0 Livestock \n", - "671204 1340339 0.0 25.0 Livestock \n", - "\n", - " sector use \\\n", - "0 Food To buy seasonal, fresh fruits to sell. \n", - "1 Transportation to repair and maintain the auto rickshaw used ... \n", - "2 Transportation To repair their old cycle-van and buy another ... \n", - "3 Arts to purchase an embroidery machine and a variet... \n", - "4 Food to purchase one buffalo. \n", - "5 Services purchase leather for my business using ksh 20000. \n", - "6 Agriculture To purchase a dairy cow and start a milk produ... \n", - "7 Services to buy more hair and skin care products. \n", - "8 Manufacturing to purchase leather, plastic soles and heels i... \n", - "9 Food to buy a stall, gram flour, ketchup, and coal ... \n", - "10 Transportation to cover the cost of repairing rickshaw \n", - "11 Wholesale to purchase biscuits, sweets and juices in bulk. \n", - "12 Retail to buy stock of rice, sugar and flour . \n", - "13 Clothing to purchase variety of winter clothes to sell. \n", - "14 Agriculture to expand her existing poultry farm business. \n", - "15 Transportation to buy a three-wheeled rickshaw. \n", - "16 Retail to buy packs of salts, biscuits and beverages. \n", - "17 Services To buy a sewing machine, lace, zippers and but... \n", - "18 Services to purchase a sewing machine. \n", - "19 Services to buy more cosmetics products for her beauty ... \n", - "20 Food to buy ingredients to make bakery products. \n", - "21 Food to purchase vegetables, chicken, and oil to co... \n", - "22 Clothing To buy winter clothing to sell \n", - "23 Arts to buy reels of threads in different colors an... \n", - "24 Food to purchase a variety of needed food items to ... \n", - "25 Agriculture to purchase potato seeds and fertilizers for g... \n", - "26 Construction to purchase stones for starting a business sup... \n", - "27 Transportation to cover the cost of repairing rickshaw \n", - "28 Agriculture to purchase potato seeds and fertilizers for g... \n", - "29 Agriculture to purchase potato seeds and fertilizer for fa... \n", - "... ... ... \n", - "671175 Agriculture Pretend the flagged issue was addressed by KC. \n", - "671176 Agriculture Edited loan use in english. \n", - "671177 Agriculture [True, u'to start a turducken farm.'] - this l... \n", - "671178 Agriculture [True, u'to start a turducken farm.'] - this l... \n", - "671179 Agriculture [True, u'para compara: cemento, arenya y ladri... \n", - "671180 Agriculture Translated loan use to english. \n", - "671181 Agriculture Reviewed loan use in english. \n", - "671182 Agriculture Pretend the flagged issue was addressed by KC. \n", - "671183 Agriculture Pretend the issue with spanish loan was addres... \n", - "671184 Agriculture Translated loan use to english. \n", - "671185 Agriculture Translated loan use to english. \n", - "671186 Agriculture [True, u'para compara: cemento, arenya y ladri... \n", - "671187 Agriculture [True, u'to start a turducken farm.'] - this l... \n", - "671188 Agriculture Reviewed loan use in english. \n", - "671189 Agriculture [True, u'to start a turducken farm.'] - this l... \n", - "671190 Agriculture [True, u'to start a turducken farm.'] - this l... \n", - "671191 Agriculture Translated loan use to english. \n", - "671192 Agriculture Translated loan use to english. \n", - "671193 Agriculture Pretend the flagged issue was addressed by KC. \n", - "671194 Agriculture Kiva Coordinator fixed issue loan (no longer v... \n", - "671195 Agriculture Edited loan use in english. \n", - "671196 Agriculture Reviewed loan use in english. \n", - "671197 Agriculture Pretend the issue with loan got addressed by K... \n", - "671198 Agriculture Pretend the issue with spanish loan was addres... \n", - "671199 Agriculture [True, u'para compara: cemento, arenya y ladri... \n", - "671200 Agriculture [True, u'para compara: cemento, arenya y ladri... \n", - "671201 Agriculture [True, u'to start a turducken farm.'] - this l... \n", - "671202 Entertainment [True, u'to start a turducken farm.'] - this l... \n", - "671203 Agriculture [True, u'to start a turducken farm.'] - this l... \n", - "671204 Agriculture [True, u'to start a turducken farm.'] - this l... \n", - "\n", - " country_code country region currency partner_id \\\n", - "0 PK Pakistan Lahore PKR 247.0 \n", - "1 PK Pakistan Lahore PKR 247.0 \n", - "2 IN India Maynaguri INR 334.0 \n", - "3 PK Pakistan Lahore PKR 247.0 \n", - "4 PK Pakistan Abdul Hakeem PKR 245.0 \n", - "5 KE Kenya Abdul Hakeem KES 245.0 \n", - "6 IN India Maynaguri INR 334.0 \n", - "7 PK Pakistan Ellahabad PKR 245.0 \n", - "8 PK Pakistan Lahore PKR 245.0 \n", - "9 PK Pakistan Lahore PKR 247.0 \n", - "10 PK Pakistan Lahore PKR 247.0 \n", - "11 PK Pakistan Faisalabad PKR 245.0 \n", - "12 PK Pakistan Faisalabad PKR 245.0 \n", - "13 PK Pakistan Lahore PKR 247.0 \n", - "14 IN India Dhupguri INR 334.0 \n", - "15 PK Pakistan Lahore PKR 247.0 \n", - "16 PK Pakistan Faisalabad PKR 245.0 \n", - "17 PK Pakistan Lahore PKR 247.0 \n", - "18 IN India Maynaguri INR 334.0 \n", - "19 PK Pakistan Lahore PKR 245.0 \n", - "20 PK Pakistan Lahore PKR 247.0 \n", - "21 PK Pakistan Lahore PKR 247.0 \n", - "22 PK Pakistan Lahore PKR 247.0 \n", - "23 PK Pakistan Lahore PKR 245.0 \n", - "24 PK Pakistan Lahore PKR 247.0 \n", - "25 IN India Dhupguri INR 334.0 \n", - "26 IN India Maynaguri INR 334.0 \n", - "27 PK Pakistan Lahore PKR 247.0 \n", - "28 IN India Maynaguri INR 334.0 \n", - "29 IN India Dhupguri INR 334.0 \n", - "... ... ... ... ... ... \n", - "671175 MX Mexico Iztacalco MXN 294.0 \n", - "671176 GH Ghana Dansoman GHS 231.0 \n", - "671177 KE Kenya Dansoman KES 138.0 \n", - "671178 KE Kenya Dansoman KES 138.0 \n", - "671179 PY Paraguay Concepción USD 58.0 \n", - "671180 BO Bolivia La Paz BOB 59.0 \n", - "671181 PK Pakistan Attock PKR 245.0 \n", - "671182 MX Mexico Iztacalco MXN 294.0 \n", - "671183 MX Mexico Iztacalco MXN 294.0 \n", - "671184 BO Bolivia La Paz BOB 59.0 \n", - "671185 KE Kenya La Paz KES 138.0 \n", - "671186 PY Paraguay Concepción USD 58.0 \n", - "671187 KE Kenya Concepción KES 138.0 \n", - "671188 GH Ghana Dansoman GHS 231.0 \n", - "671189 KE Kenya Dansoman KES 138.0 \n", - "671190 KE Kenya Dansoman KES 138.0 \n", - "671191 BO Bolivia La Paz BOB 59.0 \n", - "671192 BO Bolivia La Paz BOB 59.0 \n", - "671193 MX Mexico Iztacalco MXN 294.0 \n", - "671194 KE Kenya Iztacalco KES 138.0 \n", - "671195 GH Ghana Dansoman GHS 231.0 \n", - "671196 GH Ghana Dansoman GHS 231.0 \n", - "671197 KE Kenya Dansoman KES 138.0 \n", - "671198 MX Mexico Iztacalco MXN 294.0 \n", - "671199 PY Paraguay Concepción USD 58.0 \n", - "671200 PY Paraguay Concepción USD 58.0 \n", - "671201 KE Kenya Concepción KES 138.0 \n", - "671202 KE Kenya Concepción KES 138.0 \n", - "671203 KE Kenya Concepción KES 138.0 \n", - "671204 KE Kenya Concepción KES 138.0 \n", - "\n", - " posted_time disbursed_time \\\n", - "0 2014-01-01 06:12:39+00:00 2013-12-17 08:00:00+00:00 \n", - "1 2014-01-01 06:51:08+00:00 2013-12-17 08:00:00+00:00 \n", - "2 2014-01-01 09:58:07+00:00 2013-12-17 08:00:00+00:00 \n", - "3 2014-01-01 08:03:11+00:00 2013-12-24 08:00:00+00:00 \n", - "4 2014-01-01 11:53:19+00:00 2013-12-17 08:00:00+00:00 \n", - "5 2014-01-01 10:06:19+00:00 2014-01-30 01:42:48+00:00 \n", - "6 2014-01-01 09:51:02+00:00 2013-12-16 08:00:00+00:00 \n", - "7 2014-01-01 11:46:01+00:00 2013-12-20 08:00:00+00:00 \n", - "8 2014-01-01 11:49:43+00:00 2013-12-20 08:00:00+00:00 \n", - "9 2014-01-01 05:41:03+00:00 2013-12-17 08:00:00+00:00 \n", - "10 2014-01-01 07:32:39+00:00 2013-12-24 08:00:00+00:00 \n", - "11 2014-01-01 12:03:43+00:00 2013-12-16 08:00:00+00:00 \n", - "12 2014-01-01 12:04:57+00:00 2013-12-24 08:00:00+00:00 \n", - "13 2014-01-01 07:57:58+00:00 2013-12-24 08:00:00+00:00 \n", - "14 2014-01-01 11:24:40+00:00 2013-12-20 08:00:00+00:00 \n", - "15 2014-01-01 06:58:07+00:00 2013-12-17 08:00:00+00:00 \n", - "16 2014-01-01 12:09:10+00:00 2013-12-09 08:00:00+00:00 \n", - "17 2014-01-01 06:25:41+00:00 2013-12-17 08:00:00+00:00 \n", - "18 2014-01-01 09:48:35+00:00 2013-12-13 08:00:00+00:00 \n", - "19 2014-01-01 11:48:08+00:00 2013-12-19 08:00:00+00:00 \n", - "20 2014-01-01 08:26:34+00:00 2013-12-18 08:00:00+00:00 \n", - "21 2014-01-01 07:14:40+00:00 2013-12-24 08:00:00+00:00 \n", - "22 2014-01-01 06:05:17+00:00 2013-12-17 08:00:00+00:00 \n", - "23 2014-01-01 11:47:03+00:00 2013-12-13 08:00:00+00:00 \n", - "24 2014-01-01 07:46:28+00:00 2013-12-24 08:00:00+00:00 \n", - "25 2014-01-01 11:13:09+00:00 2013-12-13 08:00:00+00:00 \n", - "26 2014-01-01 10:04:17+00:00 2013-12-10 08:00:00+00:00 \n", - "27 2014-01-01 07:20:09+00:00 2013-12-24 08:00:00+00:00 \n", - "28 2014-01-01 10:35:20+00:00 2013-12-17 08:00:00+00:00 \n", - "29 2014-01-01 11:09:26+00:00 2013-12-19 08:00:00+00:00 \n", - "... ... ... \n", - "671175 2017-07-21 23:31:40+00:00 2017-07-21 07:00:00+00:00 \n", - "671176 2017-07-21 15:54:42+00:00 2017-07-21 07:00:00+00:00 \n", - "671177 2017-07-22 06:04:07+00:00 2017-07-21 07:00:00+00:00 \n", - "671178 2017-07-22 06:16:55+00:00 2017-07-21 07:00:00+00:00 \n", - "671179 2017-07-22 06:49:47+00:00 2017-07-21 07:00:00+00:00 \n", - "671180 2017-07-23 22:11:47+00:00 2017-07-23 07:00:00+00:00 \n", - "671181 2017-07-23 21:57:42+00:00 2017-07-23 07:00:00+00:00 \n", - "671182 2017-07-23 23:19:01+00:00 2017-07-23 07:00:00+00:00 \n", - "671183 2017-07-23 22:56:35+00:00 2017-07-23 07:00:00+00:00 \n", - "671184 2017-07-23 22:25:39+00:00 2017-07-23 07:00:00+00:00 \n", - "671185 2017-07-24 07:34:50+00:00 2017-07-17 07:00:00+00:00 \n", - "671186 2017-07-24 08:09:10+00:00 2017-07-24 07:00:00+00:00 \n", - "671187 2017-07-24 07:14:47+00:00 2017-07-24 07:00:00+00:00 \n", - "671188 2017-07-24 21:36:17+00:00 2017-07-24 07:00:00+00:00 \n", - "671189 2017-07-25 05:59:38+00:00 2017-07-24 07:00:00+00:00 \n", - "671190 2017-07-25 16:24:08+00:00 2017-07-25 07:00:00+00:00 \n", - "671191 2017-07-25 22:10:23+00:00 2017-07-25 07:00:00+00:00 \n", - "671192 2017-07-25 22:27:44+00:00 2017-07-25 07:00:00+00:00 \n", - "671193 2017-07-25 23:45:38+00:00 2017-07-25 07:00:00+00:00 \n", - "671194 2017-07-25 23:29:57+00:00 2017-07-25 07:00:00+00:00 \n", - "671195 2017-07-25 22:40:59+00:00 2017-07-25 07:00:00+00:00 \n", - "671196 2017-07-25 21:36:20+00:00 2017-07-25 07:00:00+00:00 \n", - "671197 2017-07-25 22:55:42+00:00 2017-07-25 07:00:00+00:00 \n", - "671198 2017-07-25 23:13:50+00:00 2017-07-25 07:00:00+00:00 \n", - "671199 2017-07-25 06:45:02+00:00 2017-07-24 07:00:00+00:00 \n", - "671200 2017-07-25 16:55:34+00:00 2017-07-25 07:00:00+00:00 \n", - "671201 2017-07-25 06:14:08+00:00 2017-07-24 07:00:00+00:00 \n", - "671202 2017-07-26 00:02:07+00:00 2017-07-25 07:00:00+00:00 \n", - "671203 2017-07-26 06:12:55+00:00 2017-07-25 07:00:00+00:00 \n", - "671204 2017-07-26 06:31:46+00:00 2017-07-25 07:00:00+00:00 \n", - "\n", - " funded_time term_in_months lender_count \\\n", - "0 2014-01-02 10:06:32+00:00 12.0 12 \n", - "1 2014-01-02 09:17:23+00:00 11.0 14 \n", - "2 2014-01-01 16:01:36+00:00 43.0 6 \n", - "3 2014-01-01 13:00:00+00:00 11.0 8 \n", - "4 2014-01-01 19:18:51+00:00 14.0 16 \n", - "5 2014-01-29 14:14:57+00:00 4.0 6 \n", - "6 2014-01-01 17:18:09+00:00 43.0 8 \n", - "7 2014-01-10 18:18:44+00:00 14.0 8 \n", - "8 2014-01-01 18:47:21+00:00 14.0 19 \n", - "9 2014-01-03 15:45:04+00:00 11.0 24 \n", - "10 2014-01-01 12:18:55+00:00 11.0 3 \n", - "11 2014-01-03 09:19:26+00:00 14.0 16 \n", - "12 2014-01-08 00:35:14+00:00 14.0 16 \n", - "13 2014-01-02 15:47:37+00:00 12.0 10 \n", - "14 2014-01-01 18:58:18+00:00 43.0 7 \n", - "15 2014-01-02 00:04:08+00:00 11.0 9 \n", - "16 2014-01-14 15:57:05+00:00 14.0 11 \n", - "17 2014-01-01 18:07:34+00:00 11.0 25 \n", - "18 2014-01-01 17:18:09+00:00 43.0 4 \n", - "19 2014-01-10 03:22:29+00:00 14.0 18 \n", - "20 2014-01-01 15:35:59+00:00 11.0 10 \n", - "21 2014-01-01 21:54:18+00:00 12.0 13 \n", - "22 2014-01-02 23:56:08+00:00 12.0 20 \n", - "23 2014-01-01 15:45:51+00:00 14.0 6 \n", - "24 2014-01-02 01:33:55+00:00 11.0 7 \n", - "25 2014-01-01 19:01:19+00:00 43.0 9 \n", - "26 2014-01-01 22:12:43+00:00 43.0 10 \n", - "27 2014-01-01 20:26:48+00:00 12.0 17 \n", - "28 2014-01-01 16:06:47+00:00 43.0 5 \n", - "29 2014-01-01 21:47:05+00:00 43.0 10 \n", - "... ... ... ... \n", - "671175 2017-07-22 13:07:29+00:00 13.0 3 \n", - "671176 2017-07-22 13:07:29+00:00 13.0 0 \n", - "671177 2017-07-24 12:44:16+00:00 13.0 1 \n", - "671178 2017-07-24 12:44:16+00:00 13.0 0 \n", - "671179 2017-07-24 12:44:16+00:00 13.0 0 \n", - "671180 2017-07-24 12:44:16+00:00 13.0 0 \n", - "671181 2017-07-24 12:44:16+00:00 13.0 0 \n", - "671182 2017-07-24 12:44:16+00:00 13.0 0 \n", - "671183 2017-07-24 12:44:16+00:00 13.0 0 \n", - "671184 2017-07-24 12:44:16+00:00 13.0 0 \n", - "671185 2017-07-24 12:44:16+00:00 13.0 0 \n", - "671186 2017-07-25 00:19:01+00:00 13.0 1 \n", - "671187 2017-07-25 00:19:01+00:00 13.0 0 \n", - "671188 2017-07-25 00:19:01+00:00 13.0 0 \n", - "671189 2017-07-25 00:19:01+00:00 13.0 0 \n", - "671190 2017-07-25 00:19:01+00:00 13.0 0 \n", - "671191 2017-07-25 00:19:01+00:00 13.0 0 \n", - "671192 2017-07-25 00:19:01+00:00 13.0 0 \n", - "671193 2017-07-25 00:19:01+00:00 13.0 0 \n", - "671194 2017-07-25 00:19:01+00:00 13.0 0 \n", - "671195 2017-07-25 00:19:01+00:00 13.0 0 \n", - "671196 2017-07-25 00:19:01+00:00 13.0 0 \n", - "671197 2017-07-25 00:19:01+00:00 13.0 0 \n", - "671198 2017-07-25 00:19:01+00:00 13.0 0 \n", - "671199 2017-07-25 00:19:01+00:00 13.0 0 \n", - "671200 2017-07-25 00:19:01+00:00 13.0 0 \n", - "671201 2017-07-26 02:09:43+00:00 13.0 1 \n", - "671202 2017-07-26 02:09:43+00:00 13.0 0 \n", - "671203 2017-07-26 02:09:43+00:00 13.0 0 \n", - "671204 2017-07-26 02:09:43+00:00 13.0 0 \n", - "\n", - " tags borrower_genders \\\n", - "0 NaN female \n", - "1 NaN female, female \n", - "2 user_favorite, user_favorite female \n", - "3 user_favorite, user_favorite female \n", - "4 user_favorite, user_favorite female \n", - "5 user_favorite, user_favorite female \n", - "6 user_favorite, user_favorite female \n", - "7 #Elderly, #Woman Owned Biz female \n", - "8 user_favorite female \n", - "9 user_favorite female \n", - "10 user_favorite female \n", - "11 user_favorite female \n", - "12 #Repeat Borrower, #Woman Owned Biz female \n", - "13 #Repeat Borrower, #Woman Owned Biz female \n", - "14 user_favorite female \n", - "15 user_favorite female \n", - "16 #Woman Owned Biz, #Parent female \n", - "17 #Woman Owned Biz, #Parent female, female, female \n", - "18 user_favorite, user_favorite female \n", - "19 #Woman Owned Biz female \n", - "20 #Woman Owned Biz female \n", - "21 #Woman Owned Biz female \n", - "22 #Woman Owned Biz female, female \n", - "23 #Woman Owned Biz female \n", - "24 #Woman Owned Biz female \n", - "25 #Woman Owned Biz female \n", - "26 user_favorite, user_favorite female \n", - "27 user_favorite, user_favorite female \n", - "28 user_favorite, user_favorite female \n", - "29 user_favorite, user_favorite female \n", - "... ... ... \n", - "671175 #Parent, #Repair Renew Replace female, female \n", - "671176 #Parent, #Repair Renew Replace female, female \n", - "671177 #Parent, #Repair Renew Replace female \n", - "671178 #Parent, #Repair Renew Replace female \n", - "671179 #Parent, #Repair Renew Replace female \n", - "671180 #Parent, #Repair Renew Replace female \n", - "671181 #Parent, #Repair Renew Replace female \n", - "671182 #Parent, #Repair Renew Replace female, female \n", - "671183 #Parent, #Repair Renew Replace female \n", - "671184 #Parent, #Repair Renew Replace female, female \n", - "671185 #Parent, #Repair Renew Replace female, female \n", - "671186 #Parent, #Repair Renew Replace female \n", - "671187 #Parent, #Repair Renew Replace female \n", - "671188 #Parent, #Repair Renew Replace female \n", - "671189 #Parent, #Repair Renew Replace female \n", - "671190 #Parent, #Repair Renew Replace female \n", - "671191 #Parent, #Repair Renew Replace female \n", - "671192 #Parent, #Repair Renew Replace female, female \n", - "671193 #Parent, #Repair Renew Replace female, female \n", - "671194 #Parent, #Repair Renew Replace female, female \n", - "671195 #Parent, #Repair Renew Replace female, female \n", - "671196 #Parent, #Repair Renew Replace female \n", - "671197 #Parent, #Repair Renew Replace female \n", - "671198 #Parent, #Repair Renew Replace female \n", - "671199 #Parent, #Repair Renew Replace female \n", - "671200 #Parent, #Repair Renew Replace female \n", - "671201 #Parent, #Repair Renew Replace female \n", - "671202 #Parent, #Repair Renew Replace female \n", - "671203 #Parent, #Repair Renew Replace female \n", - "671204 #Parent, #Repair Renew Replace female \n", - "\n", - " repayment_interval date \n", - "0 irregular 2014-01-01 \n", - "1 irregular 2014-01-01 \n", - "2 bullet 2014-01-01 \n", - "3 irregular 2014-01-01 \n", - "4 monthly 2014-01-01 \n", - "5 irregular 2014-01-01 \n", - "6 bullet 2014-01-01 \n", - "7 monthly 2014-01-01 \n", - "8 monthly 2014-01-01 \n", - "9 irregular 2014-01-01 \n", - "10 irregular 2014-01-01 \n", - "11 monthly 2014-01-01 \n", - "12 monthly 2014-01-01 \n", - "13 irregular 2014-01-01 \n", - "14 bullet 2014-01-01 \n", - "15 irregular 2014-01-01 \n", - "16 monthly 2014-01-01 \n", - "17 irregular 2014-01-01 \n", - "18 bullet 2014-01-01 \n", - "19 monthly 2014-01-01 \n", - "20 irregular 2014-01-01 \n", - "21 irregular 2014-01-01 \n", - "22 irregular 2014-01-01 \n", - "23 monthly 2014-01-01 \n", - "24 irregular 2014-01-01 \n", - "25 bullet 2014-01-01 \n", - "26 bullet 2014-01-01 \n", - "27 irregular 2014-01-01 \n", - "28 bullet 2014-01-01 \n", - "29 bullet 2014-01-01 \n", - "... ... ... \n", - "671175 monthly 2017-07-21 \n", - "671176 monthly 2017-07-21 \n", - "671177 monthly 2017-07-22 \n", - "671178 monthly 2017-07-22 \n", - "671179 monthly 2017-07-22 \n", - "671180 monthly 2017-07-23 \n", - "671181 monthly 2017-07-23 \n", - "671182 monthly 2017-07-23 \n", - "671183 monthly 2017-07-23 \n", - "671184 monthly 2017-07-23 \n", - "671185 monthly 2017-07-24 \n", - "671186 monthly 2017-07-24 \n", - "671187 monthly 2017-07-24 \n", - "671188 monthly 2017-07-24 \n", - "671189 monthly 2017-07-25 \n", - "671190 monthly 2017-07-25 \n", - "671191 monthly 2017-07-25 \n", - "671192 monthly 2017-07-25 \n", - "671193 monthly 2017-07-25 \n", - "671194 monthly 2017-07-25 \n", - "671195 monthly 2017-07-25 \n", - "671196 monthly 2017-07-25 \n", - "671197 monthly 2017-07-25 \n", - "671198 monthly 2017-07-25 \n", - "671199 monthly 2017-07-25 \n", - "671200 monthly 2017-07-25 \n", - "671201 monthly 2017-07-25 \n", - "671202 monthly 2017-07-26 \n", - "671203 monthly 2017-07-26 \n", - "671204 monthly 2017-07-26 \n", - "\n", - "[671205 rows x 20 columns]" - ] - }, - "execution_count": 9, - "metadata": {}, - "output_type": "execute_result" - } - ], - "source": [ - "data.fillna(method='ffill')" - ] - }, - { - "cell_type": "code", - "execution_count": 10, - "metadata": {}, - "outputs": [ - { - "data": { - "text/html": [ - "
\n", - "\n", - "\n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - "
sum
funded_amountloan_amount
country
Afghanistan14000.014000.0
Albania2490000.02666500.0
Armenia11186675.012915400.0
Azerbaijan2699575.02888700.0
Belize114025.0114025.0
\n", - "
" - ], - "text/plain": [ - " sum \n", - " funded_amount loan_amount\n", - "country \n", - "Afghanistan 14000.0 14000.0\n", - "Albania 2490000.0 2666500.0\n", - "Armenia 11186675.0 12915400.0\n", - "Azerbaijan 2699575.0 2888700.0\n", - "Belize 114025.0 114025.0" - ] - }, - "execution_count": 10, - "metadata": {}, - "output_type": "execute_result" - } - ], - "source": [ - "country_pt = data.pivot_table(index=['country'], aggfunc=[np.sum], values=['funded_amount', 'loan_amount'])\n", - "\n", - "country_pt.head()" - ] - }, - { - "cell_type": "code", - "execution_count": 11, - "metadata": {}, - "outputs": [ - { - "data": { - "text/plain": [ - "country\n", - "Philippines 54476375.0\n", - "Name: funded_amount, dtype: float64" - ] - }, - "execution_count": 11, - "metadata": {}, - "output_type": "execute_result" - } - ], - "source": [ - "funded = country_pt['sum']['funded_amount']\n", - "funded[funded == funded.max()]" - ] - }, - { - "cell_type": "code", - "execution_count": 22, - "metadata": {}, - "outputs": [ - { - "ename": "AttributeError", - "evalue": "'Series' object has no attribute 'strftime'", - "output_type": "error", - "traceback": [ - "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m", - "\u001b[1;31mAttributeError\u001b[0m Traceback (most recent call last)", - "\u001b[1;32m\u001b[0m in \u001b[0;36m\u001b[1;34m\u001b[0m\n\u001b[1;32m----> 1\u001b[1;33m \u001b[0mdata\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;34m'posted_time'\u001b[0m\u001b[1;33m]\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mpd\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mto_datetime\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mdata\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;34m'posted_time'\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mformat\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;34m'%d-%m-%Y'\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mstrftime\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34m\"%Y\"\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 2\u001b[0m \u001b[0mdata\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;34m'funded_time'\u001b[0m\u001b[1;33m]\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mpd\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mto_datetime\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mdata\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;34m'funded_time'\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 3\u001b[0m \u001b[0mdata\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mhead\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", - "\u001b[1;32mf:\\isaka\\python4ds\\env\\lib\\site-packages\\pandas\\core\\generic.py\u001b[0m in \u001b[0;36m__getattr__\u001b[1;34m(self, name)\u001b[0m\n\u001b[0;32m 5065\u001b[0m \u001b[1;32mif\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_info_axis\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_can_hold_identifiers_and_holds_name\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mname\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 5066\u001b[0m \u001b[1;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m[\u001b[0m\u001b[0mname\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m-> 5067\u001b[1;33m \u001b[1;32mreturn\u001b[0m \u001b[0mobject\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m__getattribute__\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mname\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 5068\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 5069\u001b[0m \u001b[1;32mdef\u001b[0m \u001b[0m__setattr__\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mname\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mvalue\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", - "\u001b[1;31mAttributeError\u001b[0m: 'Series' object has no attribute 'strftime'" - ] - } - ], - "source": [ - "data['posted_time'] = pd.to_datetime(data['posted_time'], format='%d-%m-%Y')\n", - "data['funded_time'] = pd.to_datetime(data['funded_time'])\n", + "data = pd.read_csv('F:/isaka/python4DS/kiva_loans.csv')\n", "data.head()" ] }, { "cell_type": "code", - "execution_count": 20, + "execution_count": null, "metadata": {}, - "outputs": [ - { - "ename": "AttributeError", - "evalue": "'Series' object has no attribute 'day'", - "output_type": "error", - "traceback": [ - "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m", - "\u001b[1;31mAttributeError\u001b[0m Traceback (most recent call last)", - "\u001b[1;32m\u001b[0m in \u001b[0;36m\u001b[1;34m\u001b[0m\n\u001b[0;32m 1\u001b[0m \u001b[0mdata\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;34m'time_diff'\u001b[0m\u001b[1;33m]\u001b[0m \u001b[1;33m=\u001b[0m \u001b[1;33m(\u001b[0m\u001b[0mdata\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;34m'funded_time'\u001b[0m\u001b[1;33m]\u001b[0m \u001b[1;33m-\u001b[0m \u001b[0mdata\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;34m'posted_time'\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m----> 2\u001b[1;33m \u001b[0mdata\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;34m'time_diff'\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mday\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m", - "\u001b[1;32mf:\\isaka\\python4ds\\env\\lib\\site-packages\\pandas\\core\\generic.py\u001b[0m in \u001b[0;36m__getattr__\u001b[1;34m(self, name)\u001b[0m\n\u001b[0;32m 5065\u001b[0m \u001b[1;32mif\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_info_axis\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_can_hold_identifiers_and_holds_name\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mname\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 5066\u001b[0m \u001b[1;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m[\u001b[0m\u001b[0mname\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m-> 5067\u001b[1;33m \u001b[1;32mreturn\u001b[0m \u001b[0mobject\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m__getattribute__\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mname\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 5068\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 5069\u001b[0m \u001b[1;32mdef\u001b[0m \u001b[0m__setattr__\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mname\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mvalue\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", - "\u001b[1;31mAttributeError\u001b[0m: 'Series' object has no attribute 'day'" - ] - } - ], - "source": [ - "data['time_diff'] = (data['funded_time'] - data['posted_time'])\n", - "data['time_diff'].day()" - ] + "outputs": [], + "source": [] } ], "metadata": { diff --git a/notebooks/Pandas in General.ipynb b/notebooks/Pandas in General.ipynb index 9f9f580..17d22e6 100644 --- a/notebooks/Pandas in General.ipynb +++ b/notebooks/Pandas in General.ipynb @@ -1296,7 +1296,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.7.2" + "version": "3.7.1" } }, "nbformat": 4, diff --git a/notebooks/full_kiva_loans_analysis.ipynb b/notebooks/full_kiva_loans_analysis.ipynb index f4244c8..9c651a5 100644 --- a/notebooks/full_kiva_loans_analysis.ipynb +++ b/notebooks/full_kiva_loans_analysis.ipynb @@ -15,7 +15,10 @@ "4. [Data cleaning and preparation](#data-prep)
\n", " 4.1. [Handling Missing Data](#missing-data)\n", "5. [Data Exploration and Visualization](#data-exploration)
\n", - " 5.1. [Loan counts per sector](#per-sector)" + " 5.1. [Loan counts per sector](#per-sector)
\n", + " 5.2. [Loan counts per world region](#per-region)
\n", + " 5.3. [World Region MPIs](#region-mpis)
\n", + " 5.4. [Repayment Intervals](#repayment)
" ] }, { @@ -41,7 +44,7 @@ }, { "cell_type": "code", - "execution_count": 31, + "execution_count": 1, "metadata": {}, "outputs": [], "source": [ @@ -53,6 +56,7 @@ "import pandas as pd\n", "import matplotlib.pyplot as plt\n", "import seaborn as sns\n", + "import folium\n", "\n", "# Set default seaborn settings\n", "sns.set()" @@ -1120,7 +1124,7 @@ }, { "cell_type": "code", - "execution_count": 24, + "execution_count": 9, "metadata": {}, "outputs": [], "source": [ @@ -1158,7 +1162,7 @@ }, { "cell_type": "code", - "execution_count": 25, + "execution_count": 10, "metadata": {}, "outputs": [ { @@ -1315,7 +1319,7 @@ "id 0 0.000000" ] }, - "execution_count": 25, + "execution_count": 10, "metadata": {}, "output_type": "execute_result" } @@ -1333,7 +1337,7 @@ }, { "cell_type": "code", - "execution_count": 26, + "execution_count": 11, "metadata": {}, "outputs": [ { @@ -1424,7 +1428,7 @@ "geo 0 0.000000" ] }, - "execution_count": 26, + "execution_count": 11, "metadata": {}, "output_type": "execute_result" } @@ -1442,7 +1446,7 @@ }, { "cell_type": "code", - "execution_count": 27, + "execution_count": 12, "metadata": {}, "outputs": [ { @@ -1503,7 +1507,7 @@ "id 0 0.000000" ] }, - "execution_count": 27, + "execution_count": 12, "metadata": {}, "output_type": "execute_result" } @@ -1521,7 +1525,7 @@ }, { "cell_type": "code", - "execution_count": 28, + "execution_count": 13, "metadata": {}, "outputs": [ { @@ -1684,7 +1688,7 @@ "Partner ID 0 0.000000" ] }, - "execution_count": 28, + "execution_count": 13, "metadata": {}, "output_type": "execute_result" } @@ -1716,17 +1720,19 @@ }, { "cell_type": "code", - "execution_count": 64, + "execution_count": 14, "metadata": {}, "outputs": [ { "data": { - "image/png": "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\n", + "image/png": "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\n", "text/plain": [ "
" ] }, - "metadata": {}, + "metadata": { + "needs_background": "light" + }, "output_type": "display_data" } ], @@ -1760,6 +1766,235 @@ "**Wholesale** had the least loan counts." ] }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### 5.2. Loan counts per world region\n", + "" + ] + }, + { + "cell_type": "code", + "execution_count": 54, + "metadata": {}, + "outputs": [ + { + "data": { + "image/png": "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\n", + "text/plain": [ + "
" + ] + }, + "metadata": { + "needs_background": "light" + }, + "output_type": "display_data" + } + ], + "source": [ + "world_regions = mpi_region_locations['world_region'].value_counts()\n", + "# print(world_regions)\n", + "fig = plt.figure(figsize=(16, 9))\n", + "\n", + "sns.barplot(x=world_regions.values, y=world_regions.index)\n", + "\n", + "plt.title(\"Loan Counts Per world Region\", fontsize=30)\n", + "\n", + "for i, v in enumerate(world_regions.values):\n", + " plt.text(10,i,v,color='k',fontsize=19)\n", + "\n", + "plt.xlabel(\"Count\", fontsize=25)\n", + "plt.ylabel(\"World Region\", fontsize=25)\n", + "plt.show()" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "**Sub-Saharan Africa** has the highest number of loans followed by **Latin America and Carribean** region, while **Europe and Central Asia** has the least number of loans.\n", + "
\n", + "
\n", + "To account for this trend, we take a look at each region's mean poverty index.\n", + "" + ] + }, + { + "cell_type": "code", + "execution_count": 56, + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
MPI
world_region
Sub-Saharan Africa0.337128
South Asia0.219630
East Asia and the Pacific0.136266
Arab States0.115287
Latin America and Caribbean0.063665
Europe and Central Asia0.025273
\n", + "
" + ], + "text/plain": [ + " MPI\n", + "world_region \n", + "Sub-Saharan Africa 0.337128\n", + "South Asia 0.219630\n", + "East Asia and the Pacific 0.136266\n", + "Arab States 0.115287\n", + "Latin America and Caribbean 0.063665\n", + "Europe and Central Asia 0.025273" + ] + }, + "execution_count": 56, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "poverty_index_table = pd.pivot_table(mpi_region_locations, aggfunc=[np.mean], index=['world_region'], values=['MPI'])['mean'].sort_values(by=['MPI'], ascending=False)\n", + "poverty_index_table" + ] + }, + { + "cell_type": "code", + "execution_count": 60, + "metadata": {}, + "outputs": [ + { + "data": { + "image/png": "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\n", + "text/plain": [ + "
" + ] + }, + "metadata": { + "needs_background": "light" + }, + "output_type": "display_data" + } + ], + "source": [ + "poverty_index = poverty_index_table['MPI'].round(2)\n", + "# print(poverty_index['MPI'])\n", + "fig = plt.figure(figsize=(15, 8))\n", + "\n", + "sns.barplot(x=poverty_index.values, y=poverty_index.index)\n", + "\n", + "for i, v in enumerate(poverty_index.values):\n", + " plt.text(0.01, i, v, color='k', fontsize=19)\n", + "\n", + "plt.title(\"Region Poverty Indexes\", fontsize=30)\n", + "plt.ylabel(\"World Region\", fontsize=25)\n", + "plt.xlabel(\"MPI\", fontsize=25)\n", + "\n", + "plt.show()" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "From the above charts, its clear that **Sub-Saharan Africa** has the highest Multidimensional Poverty Index while **Europe and Central ASia** has the lowest. This explains why the two regions have the highest and lowest loan counts respectively.\n", + "
\n", + "
\n", + "A [study](https://blogs.worldbank.org/opendata/number-extremely-poor-people-continues-rise-sub-saharan-africa) conducted by The World Bank shows that the number of extremely poor people continues to rise in Sub-Saharan africa while it falls in other regions ([World bank Data Blog](https://blogs.worldbank.org/opendata/number-extremely-poor-people-continues-rise-sub-saharan-africa)).\n", + "
\n", + "
\n", + "From this study, it is expected that the number of loan counts from **Sub-Saharan Africa** will always be high." + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### 5.4. Repayment Intervals\n", + "" + ] + }, + { + "cell_type": "code", + "execution_count": 73, + "metadata": {}, + "outputs": [ + { + "data": { + "image/png": "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\n", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "intervals = kiva_loans['repayment_interval'].value_counts()\n", + "# print(intervals)\n", + "plt.figure(figsize=(15,8))\n", + "\n", + "plt.pie(intervals.values, labels=intervals.index, shadow=True, autopct='%1.1f%%', startangle=90)\n", + "\n", + "plt.axis('equal')\n", + "plt.title('Repayment Intervals', fontsize=30)\n", + "\n", + "plt.show()" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "With a percentage of **51.1%**, majority of the loans are repaid **monthly**." + ] + }, { "cell_type": "code", "execution_count": null, diff --git a/notebooks/tests.ipynb b/notebooks/tests.ipynb index 314ab06..ee5b8fd 100644 --- a/notebooks/tests.ipynb +++ b/notebooks/tests.ipynb @@ -25,8 +25,115 @@ "outputs": [ { "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
LocationNameISOcountryregionworld_regionMPIgeolatlon
0Badakhshan, AfghanistanAFGAfghanistanBadakhshanSouth Asia0.387(36.7347725, 70.81199529999999)36.73477270.811995
1Badghis, AfghanistanAFGAfghanistanBadghisSouth Asia0.466(35.1671339, 63.7695384)35.16713463.769538
2Baghlan, AfghanistanAFGAfghanistanBaghlanSouth Asia0.300(35.8042947, 69.2877535)35.80429569.287754
3Balkh, AfghanistanAFGAfghanistanBalkhSouth Asia0.301(36.7550603, 66.8975372)36.75506066.897537
4Bamyan, AfghanistanAFGAfghanistanBamyanSouth Asia0.325(34.8100067, 67.8212104)34.81000767.821210
\n", + "
" + ], "text/plain": [ - "array([342717, 257158, 70728, 602], dtype=int64)" + " LocationName ISO country region world_region MPI \\\n", + "0 Badakhshan, Afghanistan AFG Afghanistan Badakhshan South Asia 0.387 \n", + "1 Badghis, Afghanistan AFG Afghanistan Badghis South Asia 0.466 \n", + "2 Baghlan, Afghanistan AFG Afghanistan Baghlan South Asia 0.300 \n", + "3 Balkh, Afghanistan AFG Afghanistan Balkh South Asia 0.301 \n", + "4 Bamyan, Afghanistan AFG Afghanistan Bamyan South Asia 0.325 \n", + "\n", + " geo lat lon \n", + "0 (36.7347725, 70.81199529999999) 36.734772 70.811995 \n", + "1 (35.1671339, 63.7695384) 35.167134 63.769538 \n", + "2 (35.8042947, 69.2877535) 35.804295 69.287754 \n", + "3 (36.7550603, 66.8975372) 36.755060 66.897537 \n", + "4 (34.8100067, 67.8212104) 34.810007 67.821210 " ] }, "execution_count": 4, @@ -35,16 +142,173 @@ } ], "source": [ - "data = pd.read_csv('F:/isaka/python4DS/kiva_loans.csv')\n", - "data['repayment_interval'].value_counts().values" + "data = pd.read_csv('../data/kiva/kiva_loans.csv')\n", + "regions = pd.read_csv('../data/kiva/kiva_mpi_region_locations.csv')\n", + "regions.head()" ] }, { "cell_type": "code", - "execution_count": null, + "execution_count": 20, "metadata": {}, - "outputs": [], - "source": [] + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
idfunded_amountloan_amountactivitysectorusecountry_codecountryregioncurrency...borrower_gendersrepayment_intervaldateLocationNameISOworld_regionMPIgeolatlon
0653359600.0600.0Machinery RentalServicesto invest in working capital and to maintain g...NINicaraguaLeonNIO...femalemonthly2014-01-02Leon, NicaraguaNICLatin America and Caribbean0.031(28.3998551, 83.6895693)28.39985583.689569
16533731000.01000.0Grocery StoreFoodto invest in working capital and to provide hi...NINicaraguaLeonNIO...malemonthly2014-01-02Leon, NicaraguaNICLatin America and Caribbean0.031(28.3998551, 83.6895693)28.39985583.689569
\n", + "

2 rows × 27 columns

\n", + "
" + ], + "text/plain": [ + " id funded_amount loan_amount activity sector \\\n", + "0 653359 600.0 600.0 Machinery Rental Services \n", + "1 653373 1000.0 1000.0 Grocery Store Food \n", + "\n", + " use country_code country \\\n", + "0 to invest in working capital and to maintain g... NI Nicaragua \n", + "1 to invest in working capital and to provide hi... NI Nicaragua \n", + "\n", + " region currency ... borrower_genders repayment_interval date \\\n", + "0 Leon NIO ... female monthly 2014-01-02 \n", + "1 Leon NIO ... male monthly 2014-01-02 \n", + "\n", + " LocationName ISO world_region MPI \\\n", + "0 Leon, Nicaragua NIC Latin America and Caribbean 0.031 \n", + "1 Leon, Nicaragua NIC Latin America and Caribbean 0.031 \n", + "\n", + " geo lat lon \n", + "0 (28.3998551, 83.6895693) 28.399855 83.689569 \n", + "1 (28.3998551, 83.6895693) 28.399855 83.689569 \n", + "\n", + "[2 rows x 27 columns]" + ] + }, + "execution_count": 20, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df = pd.merge(data, regions).dropna().head(2)\n", + "df" + ] + }, + { + "cell_type": "code", + "execution_count": 21, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "Index(['id', 'funded_amount', 'loan_amount', 'activity', 'sector', 'use',\n", + " 'country_code', 'country', 'region', 'currency', 'partner_id',\n", + " 'posted_time', 'disbursed_time', 'funded_time', 'term_in_months',\n", + " 'lender_count', 'tags', 'borrower_genders', 'repayment_interval',\n", + " 'date', 'LocationName', 'ISO', 'world_region', 'MPI', 'geo', 'lat',\n", + " 'lon'],\n", + " dtype='object')" + ] + }, + "execution_count": 21, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df.columns" + ] } ], "metadata": { From 82a7a420b10b29a8852639326b4b8abd17fa0a32 Mon Sep 17 00:00:00 2001 From: kasre96 Date: Tue, 26 Feb 2019 15:53:11 +0300 Subject: [PATCH 27/43] Finish visualization self challenge --- .idea/workspace.xml | 21 +- .../GeoJSON_and_choropleth-checkpoint.ipynb | 951 ++++++++++++++++++ .../full_kiva_loans_analysis-checkpoint.ipynb | 361 ++++++- notebooks/full_kiva_loans_analysis.ipynb | 361 ++++++- 4 files changed, 1667 insertions(+), 27 deletions(-) create mode 100644 notebooks/.ipynb_checkpoints/GeoJSON_and_choropleth-checkpoint.ipynb diff --git a/.idea/workspace.xml b/.idea/workspace.xml index 3afa423..87ce5cf 100644 --- a/.idea/workspace.xml +++ b/.idea/workspace.xml @@ -4,10 +4,7 @@ - - -