From 5967f4ebd3ce38a3f7b9e0c5e78203cd75c65ccd Mon Sep 17 00:00:00 2001
From: rbianchetti <31360514+rbianchetti@users.noreply.github.com>
Date: Fri, 1 Jul 2022 17:32:35 -0700
Subject: [PATCH 1/3] Updating label analysis jupyter notebook with
co-occurrence analysis
---
labels-survey/Label_Analysis.ipynb | 295 +++++++++++++++++++++++------
1 file changed, 242 insertions(+), 53 deletions(-)
diff --git a/labels-survey/Label_Analysis.ipynb b/labels-survey/Label_Analysis.ipynb
index 7c0a4ad..791655b 100644
--- a/labels-survey/Label_Analysis.ipynb
+++ b/labels-survey/Label_Analysis.ipynb
@@ -4,7 +4,8 @@
"metadata": {
"colab": {
"name": "Label Analysis",
- "provenance": []
+ "provenance": [],
+ "collapsed_sections": []
},
"kernelspec": {
"name": "python3",
@@ -17,13 +18,13 @@
"cells": [
{
"cell_type": "code",
- "execution_count": 137,
+ "execution_count": null,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "X36HL-zZXFv_",
- "outputId": "cc495a64-aa37-4e5e-add5-dbf572433b5b"
+ "outputId": "0b41b843-d366-4566-fb01-235df5d4221c"
},
"outputs": [
{
@@ -36,14 +37,18 @@
}
],
"source": [
- "!pip install multidict\n",
"\n",
+ "import itertools\n",
+ "import collections\n",
"import pandas as pd\n",
"import numpy as np\n",
"import plotly.express as px\n",
"import matplotlib.pyplot as plt\n",
"import multidict as multidict\n",
"from wordcloud import WordCloud\n",
+ "from nltk import bigrams\n",
+ "import networkx as nx\n",
+ "\n",
"\n",
"url = 'https://raw.githubusercontent.com/hackforla/data-science/160-survey-repo-labels/labels-survey/output.csv' # GitHub URL to .csv data\n",
"plt.rcParams[\"figure.figsize\"] = (24,5.5)\n",
@@ -62,7 +67,7 @@
{
"cell_type": "markdown",
"source": [
- "Two Research Questions:\n",
+ "Three Research Questions:\n",
"\n",
"**1.- How is the usage of labels in HfLA?**\n",
"\n",
@@ -94,9 +99,9 @@
"height": 542
},
"id": "2noC3Tz7ZdMN",
- "outputId": "a6cf92b5-e036-414e-a62f-05ceaecc203c"
+ "outputId": "d2eb9bac-b4c1-45a0-a23c-212b38a31942"
},
- "execution_count": 22,
+ "execution_count": null,
"outputs": [
{
"output_type": "display_data",
@@ -106,9 +111,9 @@
"\n",
"\n",
" \n",
- "\n",
- "