Merge branch 'dev' of https://github.com/TheBridgeMachineLearningPythonLibrary/MachineLearningToolKit into dev

Author: RamonFCerezo

test/test_convert_to_numeric.py

@@ -0,0 +1,12 @@
+import pandas as pd
+from to_numeric import convert_to_numeric
+
+def test_convert_to_numeric():
+    
+    df = pd.DataFrame({'A': ['1', '2', '3'], 'B': ['4.5', '5.6', '6.7'], 'C': ['a', 'b', 'c']})
+    
+    
+    convert_to_numeric(df, 'A')
+    
+    
+    assert df['A'][0],int

test/test_heatmap_corr.py

@@ -0,0 +1,13 @@
+import numpy as np 
+import matplotlib.pyplot as plt
+import seaborn as sns
+import pandas as pd
+from heatmap_corr import heatmap
+
+def test_heatmap():
+    df = pd.DataFrame({'A': [1, 2, 3], 'B': [4, 5, 6], 'C': [7, 8, 9], 'target': [10, 20, 30]})
+
+    heatmap(df, 2, 'target', None)
+    
+
+    

test/test_log_transform_data.py

@@ -0,0 +1,41 @@
+import pandas as pd
+import numpy as np
+import re
+from datetime import datetime
+from typing import List
+from nltk.corpus import stopwords
+from nltk.stem.snowball import SnowballStemmer
+import cv2 
+import os
+from skimage.io import imread
+import sys
+import pytest
+
+sys.path.append('/home/sean/Documentos/the_bridge_bootcamp/My_Workspaces/MachineLearningToolKit/toolkit')
+from data_processing import log_transform_data
+
+
+def test_log_transform_data_ignore():
+    df = pd.DataFrame({'a':[0, 0, 1, 0],
+                  'b': [16, 7, 6, 16],
+                  'c':[61, 57, 16, 36],
+                  'd':['12','22','13','44'],
+                  'e':['Green','Red','Blue','Yellow'],
+                  'f':[1, 11, 23, 66]})
+
+    df_processed = log_transform_data(df, col_ignore = ['a'])
+
+    pd.testing.assert_frame_equal(df[['a', 'd', 'e']], df_processed[['a', 'd', 'e']])
+
+
+def test_log_transform_data_log():
+    df = pd.DataFrame({'a':[0, 0, 1, 0],
+                  'b': [16, 7, 6, 16],
+                  'c':[61, 57, 16, 36],
+                  'd':['12','22','13','44'],
+                  'e':['Green','Red','Blue','Yellow'],
+                  'f':[1, 11, 23, 66]})
+
+    df_processed = log_transform_data(df, col_ignore = ['a'])
+
+    pd.testing.assert_frame_equal(df_processed[['b']], pd.DataFrame(np.log1p(df['b'])))

test/test_scrap.py

@@ -0,0 +1,24 @@
+from selenium import webdriver
+from selenium.webdriver.common.by import By
+import requests
+from bs4 import BeautifulSoup
+from selenium import webdriver
+import os
+import time
+import io
+from PIL import Image
+from scrap import image_scrap
+import shutil
+
+
+def test_image_scrap():
+    url = 'https://www.google.com/search?q=perros+bonitos&tbm=isch&ved=2ahUKEwiCpOG3z6n9AhVFV6QEHY7KBa0Q2-cCegQIABAA&oq=perros+bonitos&gs_lcp=CgNpbWcQAzIFCAAQgAQyBQgAEIAEMgUIABCABDIFCAAQgAQyBQgAEIAEMgUIABCABDIFCAAQgAQyBAgAEB4yBAgAEB4yBAgAEB5QwAlY6hFg6hJoAHAAeACAAYgBiAHJBpIBAzcuMpgBAKABAaoBC2d3cy13aXotaW1nwAEB&sclient=img&ei=YUz2Y8LvFMWukdUPjpWX6Ao&bih=849&biw=1600&rlz=1C5CHFA_enCA951CA951'
+    n = 5
+    image_scrap(url,n)
+
+    download_dir = './my_images'
+    
+    assert os.path.exists(download_dir)
+    assert len(os.listdir(download_dir)) == n
+
+    shutil.rmtree(download_dir) 

test/test_sunburst.py

@@ -0,0 +1,15 @@
+from sunburst import sunburst
+import plotly.graph_objs as go
+import plotly.express as px
+
+def test_sunburst():
+    df = {
+        'Category': ['Fruit', 'Fruit', 'Vegetable', 'Vegetable', 'Vegetable'],
+        'Subcategory': ['Apple', 'Orange', 'Carrot', 'Tomato', 'Cucumber'],
+        'Value': [20, 30, 40, 15, 25] }
+    
+    fig = sunburst(df, 'Category', 'Subcategory', 'Value', 'My Sunburst Chart')   
+    
+    assert fig.layout.title.text == 'My Sunburst Chart'
+    assert fig.layout.width == 800
+    assert fig.layout.height == 600