Skip to content

Instantly share code, notes, and snippets.

@michmzr

michmzr/pearson.ipynb

Last active October 28, 2018 17:56
Show Gist options
  • Save michmzr/51a8cf4b8b52a3bd73a7ff94c64c3fce to your computer and use it in GitHub Desktop.
Save michmzr/51a8cf4b8b52a3bd73a7ff94c64c3fce to your computer and use it in GitHub Desktop.
Download ZIP
Data Correlactions
Display the source blob
Display the rendered blob
Raw
pearson.ipynb
{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Pearson data correlaction\n",
"\n",
"Data from Pima Indians Diabetes dataset"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [],
"source": [
"import pandas as pd\n",
"import numpy as np\n",
"from sklearn.datasets import load_boston\n",
"import seaborn as sns\n",
"import matplotlib.pyplot as plt\n",
"%matplotlib inline"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
" 0 1 2 3 4 5 \\\n",
"count 768.000000 768.000000 768.000000 768.000000 768.000000 768.000000 \n",
"mean 3.845052 120.894531 69.105469 20.536458 79.799479 31.992578 \n",
"std 3.369578 31.972618 19.355807 15.952218 115.244002 7.884160 \n",
"min 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 \n",
"25% 1.000000 99.000000 62.000000 0.000000 0.000000 27.300000 \n",
"50% 3.000000 117.000000 72.000000 23.000000 30.500000 32.000000 \n",
"75% 6.000000 140.250000 80.000000 32.000000 127.250000 36.600000 \n",
"max 17.000000 199.000000 122.000000 99.000000 846.000000 67.100000 \n",
"\n",
" 6 7 8 \n",
"count 768.000000 768.000000 768.000000 \n",
"mean 0.471876 33.240885 0.348958 \n",
"std 0.331329 11.760232 0.476951 \n",
"min 0.078000 21.000000 0.000000 \n",
"25% 0.243750 24.000000 0.000000 \n",
"50% 0.372500 29.000000 0.000000 \n",
"75% 0.626250 41.000000 1.000000 \n",
"max 2.420000 81.000000 1.000000 \n",
"0 0\n",
"1 5\n",
"2 35\n",
"3 227\n",
"4 374\n",
"5 11\n",
"6 0\n",
"7 0\n",
"8 0\n",
"dtype: int64\n",
"0 0\n",
"1 0\n",
"2 0\n",
"3 0\n",
"4 0\n",
"5 0\n",
"6 0\n",
"7 0\n",
"8 0\n",
"dtype: int64\n"
]
},
{
"data": {
"text/html": [
"<style type=\"text/css\" >\n",
" #T_227be366_dadb_11e8_b9d7_f48e38ee2210row0_col0 {\n",
" background-color: #b40426;\n",
" } #T_227be366_dadb_11e8_b9d7_f48e38ee2210row0_col1 {\n",
" background-color: #6b8df0;\n",
" } #T_227be366_dadb_11e8_b9d7_f48e38ee2210row0_col2 {\n",
" background-color: #86a9fc;\n",
" } #T_227be366_dadb_11e8_b9d7_f48e38ee2210row0_col3 {\n",
" background-color: #5d7ce6;\n",
" } #T_227be366_dadb_11e8_b9d7_f48e38ee2210row0_col4 {\n",
" background-color: #5572df;\n",
" } #T_227be366_dadb_11e8_b9d7_f48e38ee2210row0_col5 {\n",
" background-color: #4a63d3;\n",
" } #T_227be366_dadb_11e8_b9d7_f48e38ee2210row0_col6 {\n",
" background-color: #3b4cc0;\n",
" } #T_227be366_dadb_11e8_b9d7_f48e38ee2210row0_col7 {\n",
" background-color: #ebd3c6;\n",
" } #T_227be366_dadb_11e8_b9d7_f48e38ee2210row0_col8 {\n",
" background-color: #8caffe;\n",
" } #T_227be366_dadb_11e8_b9d7_f48e38ee2210row1_col0 {\n",
" background-color: #3b4cc0;\n",
" } #T_227be366_dadb_11e8_b9d7_f48e38ee2210row1_col1 {\n",
" background-color: #b40426;\n",
" } #T_227be366_dadb_11e8_b9d7_f48e38ee2210row1_col2 {\n",
" background-color: #5a78e4;\n",
" } #T_227be366_dadb_11e8_b9d7_f48e38ee2210row1_col3 {\n",
" background-color: #516ddb;\n",
" } #T_227be366_dadb_11e8_b9d7_f48e38ee2210row1_col4 {\n",
" background-color: #aac7fd;\n",
" } #T_227be366_dadb_11e8_b9d7_f48e38ee2210row1_col5 {\n",
" background-color: #5f7fe8;\n",
" } #T_227be366_dadb_11e8_b9d7_f48e38ee2210row1_col6 {\n",
" background-color: #3d50c3;\n",
" } #T_227be366_dadb_11e8_b9d7_f48e38ee2210row1_col7 {\n",
" background-color: #6c8ff1;\n",
" } #T_227be366_dadb_11e8_b9d7_f48e38ee2210row1_col8 {\n",
" background-color: #c6d6f1;\n",
" } #T_227be366_dadb_11e8_b9d7_f48e38ee2210row2_col0 {\n",
" background-color: #7ea1fa;\n",
" } #T_227be366_dadb_11e8_b9d7_f48e38ee2210row2_col1 {\n",
" background-color: #82a6fb;\n",
" } #T_227be366_dadb_11e8_b9d7_f48e38ee2210row2_col2 {\n",
" background-color: #b40426;\n",
" } #T_227be366_dadb_11e8_b9d7_f48e38ee2210row2_col3 {\n",
" background-color: #799cf8;\n",
" } #T_227be366_dadb_11e8_b9d7_f48e38ee2210row2_col4 {\n",
" background-color: #516ddb;\n",
" } #T_227be366_dadb_11e8_b9d7_f48e38ee2210row2_col5 {\n",
" background-color: #98b9ff;\n",
" } #T_227be366_dadb_11e8_b9d7_f48e38ee2210row2_col6 {\n",
" background-color: #3b4cc0;\n",
" } #T_227be366_dadb_11e8_b9d7_f48e38ee2210row2_col7 {\n",
" background-color: #a7c5fe;\n",
" } #T_227be366_dadb_11e8_b9d7_f48e38ee2210row2_col8 {\n",
" background-color: #7093f3;\n",
" } #T_227be366_dadb_11e8_b9d7_f48e38ee2210row3_col0 {\n",
" background-color: #3b4cc0;\n",
" } #T_227be366_dadb_11e8_b9d7_f48e38ee2210row3_col1 {\n",
" background-color: #5f7fe8;\n",
" } #T_227be366_dadb_11e8_b9d7_f48e38ee2210row3_col2 {\n",
" background-color: #5f7fe8;\n",
" } #T_227be366_dadb_11e8_b9d7_f48e38ee2210row3_col3 {\n",
" background-color: #b40426;\n",
" } #T_227be366_dadb_11e8_b9d7_f48e38ee2210row3_col4 {\n",
" background-color: #536edd;\n",
" } #T_227be366_dadb_11e8_b9d7_f48e38ee2210row3_col5 {\n",
" background-color: #dddcdc;\n",
" } #T_227be366_dadb_11e8_b9d7_f48e38ee2210row3_col6 {\n",
" background-color: #4055c8;\n",
" } #T_227be366_dadb_11e8_b9d7_f48e38ee2210row3_col7 {\n",
" background-color: #4961d2;\n",
" } #T_227be366_dadb_11e8_b9d7_f48e38ee2210row3_col8 {\n",
" background-color: #6788ee;\n",
" } #T_227be366_dadb_11e8_b9d7_f48e38ee2210row4_col0 {\n",
" background-color: #3b4cc0;\n",
" } #T_227be366_dadb_11e8_b9d7_f48e38ee2210row4_col1 {\n",
" background-color: #bbd1f8;\n",
" } #T_227be366_dadb_11e8_b9d7_f48e38ee2210row4_col2 {\n",
" background-color: #3f53c6;\n",
" } #T_227be366_dadb_11e8_b9d7_f48e38ee2210row4_col3 {\n",
" background-color: #5b7ae5;\n",
" } #T_227be366_dadb_11e8_b9d7_f48e38ee2210row4_col4 {\n",
" background-color: #b40426;\n",
" } #T_227be366_dadb_11e8_b9d7_f48e38ee2210row4_col5 {\n",
" background-color: #5e7de7;\n",
" } #T_227be366_dadb_11e8_b9d7_f48e38ee2210row4_col6 {\n",
" background-color: #485fd1;\n",
" } #T_227be366_dadb_11e8_b9d7_f48e38ee2210row4_col7 {\n",
" background-color: #5470de;\n",
" } #T_227be366_dadb_11e8_b9d7_f48e38ee2210row4_col8 {\n",
" background-color: #6f92f3;\n",
" } #T_227be366_dadb_11e8_b9d7_f48e38ee2210row5_col0 {\n",
" background-color: #3b4cc0;\n",
" } #T_227be366_dadb_11e8_b9d7_f48e38ee2210row5_col1 {\n",
" background-color: #80a3fa;\n",
" } #T_227be366_dadb_11e8_b9d7_f48e38ee2210row5_col2 {\n",
" background-color: #92b4fe;\n",
" } #T_227be366_dadb_11e8_b9d7_f48e38ee2210row5_col3 {\n",
" background-color: #e5d8d1;\n",
" } #T_227be366_dadb_11e8_b9d7_f48e38ee2210row5_col4 {\n",
" background-color: #688aef;\n",
" } #T_227be366_dadb_11e8_b9d7_f48e38ee2210row5_col5 {\n",
" background-color: #b40426;\n",
" } #T_227be366_dadb_11e8_b9d7_f48e38ee2210row5_col6 {\n",
" background-color: #6485ec;\n",
" } #T_227be366_dadb_11e8_b9d7_f48e38ee2210row5_col7 {\n",
" background-color: #3c4ec2;\n",
" } #T_227be366_dadb_11e8_b9d7_f48e38ee2210row5_col8 {\n",
" background-color: #9dbdff;\n",
" } #T_227be366_dadb_11e8_b9d7_f48e38ee2210row6_col0 {\n",
" background-color: #3b4cc0;\n",
" } #T_227be366_dadb_11e8_b9d7_f48e38ee2210row6_col1 {\n",
" background-color: #6f92f3;\n",
" } #T_227be366_dadb_11e8_b9d7_f48e38ee2210row6_col2 {\n",
" background-color: #4358cb;\n",
" } #T_227be366_dadb_11e8_b9d7_f48e38ee2210row6_col3 {\n",
" background-color: #6384eb;\n",
" } #T_227be366_dadb_11e8_b9d7_f48e38ee2210row6_col4 {\n",
" background-color: #6282ea;\n",
" } #T_227be366_dadb_11e8_b9d7_f48e38ee2210row6_col5 {\n",
" background-color: #7597f6;\n",
" } #T_227be366_dadb_11e8_b9d7_f48e38ee2210row6_col6 {\n",
" background-color: #b40426;\n",
" } #T_227be366_dadb_11e8_b9d7_f48e38ee2210row6_col7 {\n",
" background-color: #4e68d8;\n",
" } #T_227be366_dadb_11e8_b9d7_f48e38ee2210row6_col8 {\n",
" background-color: #7b9ff9;\n",
" } #T_227be366_dadb_11e8_b9d7_f48e38ee2210row7_col0 {\n",
" background-color: #e5d8d1;\n",
" } #T_227be366_dadb_11e8_b9d7_f48e38ee2210row7_col1 {\n",
" background-color: #8caffe;\n",
" } #T_227be366_dadb_11e8_b9d7_f48e38ee2210row7_col2 {\n",
" background-color: #a1c0ff;\n",
" } #T_227be366_dadb_11e8_b9d7_f48e38ee2210row7_col3 {\n",
" background-color: #5a78e4;\n",
" } #T_227be366_dadb_11e8_b9d7_f48e38ee2210row7_col4 {\n",
" background-color: #5e7de7;\n",
" } #T_227be366_dadb_11e8_b9d7_f48e38ee2210row7_col5 {\n",
" background-color: #3b4cc0;\n",
" } #T_227be366_dadb_11e8_b9d7_f48e38ee2210row7_col6 {\n",
" background-color: #3d50c3;\n",
" } #T_227be366_dadb_11e8_b9d7_f48e38ee2210row7_col7 {\n",
" background-color: #b40426;\n",
" } #T_227be366_dadb_11e8_b9d7_f48e38ee2210row7_col8 {\n",
" background-color: #81a4fb;\n",
" } #T_227be366_dadb_11e8_b9d7_f48e38ee2210row8_col0 {\n",
" background-color: #4f69d9;\n",
" } #T_227be366_dadb_11e8_b9d7_f48e38ee2210row8_col1 {\n",
" background-color: #bed2f6;\n",
" } #T_227be366_dadb_11e8_b9d7_f48e38ee2210row8_col2 {\n",
" background-color: #3b4cc0;\n",
" } #T_227be366_dadb_11e8_b9d7_f48e38ee2210row8_col3 {\n",
" background-color: #4c66d6;\n",
" } #T_227be366_dadb_11e8_b9d7_f48e38ee2210row8_col4 {\n",
" background-color: #4b64d5;\n",
" } #T_227be366_dadb_11e8_b9d7_f48e38ee2210row8_col5 {\n",
" background-color: #7295f4;\n",
" } #T_227be366_dadb_11e8_b9d7_f48e38ee2210row8_col6 {\n",
" background-color: #3d50c3;\n",
" } #T_227be366_dadb_11e8_b9d7_f48e38ee2210row8_col7 {\n",
" background-color: #5572df;\n",
" } #T_227be366_dadb_11e8_b9d7_f48e38ee2210row8_col8 {\n",
" background-color: #b40426;\n",
" }</style> \n",
"<table id=\"T_227be366_dadb_11e8_b9d7_f48e38ee2210\" > \n",
"<thead> <tr> \n",
" <th class=\"blank level0\" ></th> \n",
" <th class=\"col_heading level0 col0\" >0</th> \n",
" <th class=\"col_heading level0 col1\" >1</th> \n",
" <th class=\"col_heading level0 col2\" >2</th> \n",
" <th class=\"col_heading level0 col3\" >3</th> \n",
" <th class=\"col_heading level0 col4\" >4</th> \n",
" <th class=\"col_heading level0 col5\" >5</th> \n",
" <th class=\"col_heading level0 col6\" >6</th> \n",
" <th class=\"col_heading level0 col7\" >7</th> \n",
" <th class=\"col_heading level0 col8\" >8</th> \n",
" </tr></thead> \n",
"<tbody> <tr> \n",
" <th id=\"T_227be366_dadb_11e8_b9d7_f48e38ee2210level0_row0\" class=\"row_heading level0 row0\" >0</th> \n",
" <td id=\"T_227be366_dadb_11e8_b9d7_f48e38ee2210row0_col0\" class=\"data row0 col0\" >1.0</td> \n",
" <td id=\"T_227be366_dadb_11e8_b9d7_f48e38ee2210row0_col1\" class=\"data row0 col1\" >0.13</td> \n",
" <td id=\"T_227be366_dadb_11e8_b9d7_f48e38ee2210row0_col2\" class=\"data row0 col2\" >0.21</td> \n",
" <td id=\"T_227be366_dadb_11e8_b9d7_f48e38ee2210row0_col3\" class=\"data row0 col3\" >0.083</td> \n",
" <td id=\"T_227be366_dadb_11e8_b9d7_f48e38ee2210row0_col4\" class=\"data row0 col4\" >0.056</td> \n",
" <td id=\"T_227be366_dadb_11e8_b9d7_f48e38ee2210row0_col5\" class=\"data row0 col5\" >0.022</td> \n",
" <td id=\"T_227be366_dadb_11e8_b9d7_f48e38ee2210row0_col6\" class=\"data row0 col6\" >-0.034</td> \n",
" <td id=\"T_227be366_dadb_11e8_b9d7_f48e38ee2210row0_col7\" class=\"data row0 col7\" >0.54</td> \n",
" <td id=\"T_227be366_dadb_11e8_b9d7_f48e38ee2210row0_col8\" class=\"data row0 col8\" >0.22</td> \n",
" </tr> <tr> \n",
" <th id=\"T_227be366_dadb_11e8_b9d7_f48e38ee2210level0_row1\" class=\"row_heading level0 row1\" >1</th> \n",
" <td id=\"T_227be366_dadb_11e8_b9d7_f48e38ee2210row1_col0\" class=\"data row1 col0\" >0.13</td> \n",
" <td id=\"T_227be366_dadb_11e8_b9d7_f48e38ee2210row1_col1\" class=\"data row1 col1\" >1.0</td> \n",
" <td id=\"T_227be366_dadb_11e8_b9d7_f48e38ee2210row1_col2\" class=\"data row1 col2\" >0.22</td> \n",
" <td id=\"T_227be366_dadb_11e8_b9d7_f48e38ee2210row1_col3\" class=\"data row1 col3\" >0.19</td> \n",
" <td id=\"T_227be366_dadb_11e8_b9d7_f48e38ee2210row1_col4\" class=\"data row1 col4\" >0.42</td> \n",
" <td id=\"T_227be366_dadb_11e8_b9d7_f48e38ee2210row1_col5\" class=\"data row1 col5\" >0.23</td> \n",
" <td id=\"T_227be366_dadb_11e8_b9d7_f48e38ee2210row1_col6\" class=\"data row1 col6\" >0.14</td> \n",
" <td id=\"T_227be366_dadb_11e8_b9d7_f48e38ee2210row1_col7\" class=\"data row1 col7\" >0.27</td> \n",
" <td id=\"T_227be366_dadb_11e8_b9d7_f48e38ee2210row1_col8\" class=\"data row1 col8\" >0.49</td> \n",
" </tr> <tr> \n",
" <th id=\"T_227be366_dadb_11e8_b9d7_f48e38ee2210level0_row2\" class=\"row_heading level0 row2\" >2</th> \n",
" <td id=\"T_227be366_dadb_11e8_b9d7_f48e38ee2210row2_col0\" class=\"data row2 col0\" >0.21</td> \n",
" <td id=\"T_227be366_dadb_11e8_b9d7_f48e38ee2210row2_col1\" class=\"data row2 col1\" >0.22</td> \n",
" <td id=\"T_227be366_dadb_11e8_b9d7_f48e38ee2210row2_col2\" class=\"data row2 col2\" >1.0</td> \n",
" <td id=\"T_227be366_dadb_11e8_b9d7_f48e38ee2210row2_col3\" class=\"data row2 col3\" >0.19</td> \n",
" <td id=\"T_227be366_dadb_11e8_b9d7_f48e38ee2210row2_col4\" class=\"data row2 col4\" >0.073</td> \n",
" <td id=\"T_227be366_dadb_11e8_b9d7_f48e38ee2210row2_col5\" class=\"data row2 col5\" >0.28</td> \n",
" <td id=\"T_227be366_dadb_11e8_b9d7_f48e38ee2210row2_col6\" class=\"data row2 col6\" >-0.0028</td> \n",
" <td id=\"T_227be366_dadb_11e8_b9d7_f48e38ee2210row2_col7\" class=\"data row2 col7\" >0.32</td> \n",
" <td id=\"T_227be366_dadb_11e8_b9d7_f48e38ee2210row2_col8\" class=\"data row2 col8\" >0.17</td> \n",
" </tr> <tr> \n",
" <th id=\"T_227be366_dadb_11e8_b9d7_f48e38ee2210level0_row3\" class=\"row_heading level0 row3\" >3</th> \n",
" <td id=\"T_227be366_dadb_11e8_b9d7_f48e38ee2210row3_col0\" class=\"data row3 col0\" >0.083</td> \n",
" <td id=\"T_227be366_dadb_11e8_b9d7_f48e38ee2210row3_col1\" class=\"data row3 col1\" >0.19</td> \n",
" <td id=\"T_227be366_dadb_11e8_b9d7_f48e38ee2210row3_col2\" class=\"data row3 col2\" >0.19</td> \n",
" <td id=\"T_227be366_dadb_11e8_b9d7_f48e38ee2210row3_col3\" class=\"data row3 col3\" >1.0</td> \n",
" <td id=\"T_227be366_dadb_11e8_b9d7_f48e38ee2210row3_col4\" class=\"data row3 col4\" >0.16</td> \n",
" <td id=\"T_227be366_dadb_11e8_b9d7_f48e38ee2210row3_col5\" class=\"data row3 col5\" >0.54</td> \n",
" <td id=\"T_227be366_dadb_11e8_b9d7_f48e38ee2210row3_col6\" class=\"data row3 col6\" >0.1</td> \n",
" <td id=\"T_227be366_dadb_11e8_b9d7_f48e38ee2210row3_col7\" class=\"data row3 col7\" >0.13</td> \n",
" <td id=\"T_227be366_dadb_11e8_b9d7_f48e38ee2210row3_col8\" class=\"data row3 col8\" >0.22</td> \n",
" </tr> <tr> \n",
" <th id=\"T_227be366_dadb_11e8_b9d7_f48e38ee2210level0_row4\" class=\"row_heading level0 row4\" >4</th> \n",
" <td id=\"T_227be366_dadb_11e8_b9d7_f48e38ee2210row4_col0\" class=\"data row4 col0\" >0.056</td> \n",
" <td id=\"T_227be366_dadb_11e8_b9d7_f48e38ee2210row4_col1\" class=\"data row4 col1\" >0.42</td> \n",
" <td id=\"T_227be366_dadb_11e8_b9d7_f48e38ee2210row4_col2\" class=\"data row4 col2\" >0.073</td> \n",
" <td id=\"T_227be366_dadb_11e8_b9d7_f48e38ee2210row4_col3\" class=\"data row4 col3\" >0.16</td> \n",
" <td id=\"T_227be366_dadb_11e8_b9d7_f48e38ee2210row4_col4\" class=\"data row4 col4\" >1.0</td> \n",
" <td id=\"T_227be366_dadb_11e8_b9d7_f48e38ee2210row4_col5\" class=\"data row4 col5\" >0.17</td> \n",
" <td id=\"T_227be366_dadb_11e8_b9d7_f48e38ee2210row4_col6\" class=\"data row4 col6\" >0.099</td> \n",
" <td id=\"T_227be366_dadb_11e8_b9d7_f48e38ee2210row4_col7\" class=\"data row4 col7\" >0.14</td> \n",
" <td id=\"T_227be366_dadb_11e8_b9d7_f48e38ee2210row4_col8\" class=\"data row4 col8\" >0.21</td> \n",
" </tr> <tr> \n",
" <th id=\"T_227be366_dadb_11e8_b9d7_f48e38ee2210level0_row5\" class=\"row_heading level0 row5\" >5</th> \n",
" <td id=\"T_227be366_dadb_11e8_b9d7_f48e38ee2210row5_col0\" class=\"data row5 col0\" >0.022</td> \n",
" <td id=\"T_227be366_dadb_11e8_b9d7_f48e38ee2210row5_col1\" class=\"data row5 col1\" >0.23</td> \n",
" <td id=\"T_227be366_dadb_11e8_b9d7_f48e38ee2210row5_col2\" class=\"data row5 col2\" >0.28</td> \n",
" <td id=\"T_227be366_dadb_11e8_b9d7_f48e38ee2210row5_col3\" class=\"data row5 col3\" >0.54</td> \n",
" <td id=\"T_227be366_dadb_11e8_b9d7_f48e38ee2210row5_col4\" class=\"data row5 col4\" >0.17</td> \n",
" <td id=\"T_227be366_dadb_11e8_b9d7_f48e38ee2210row5_col5\" class=\"data row5 col5\" >1.0</td> \n",
" <td id=\"T_227be366_dadb_11e8_b9d7_f48e38ee2210row5_col6\" class=\"data row5 col6\" >0.15</td> \n",
" <td id=\"T_227be366_dadb_11e8_b9d7_f48e38ee2210row5_col7\" class=\"data row5 col7\" >0.026</td> \n",
" <td id=\"T_227be366_dadb_11e8_b9d7_f48e38ee2210row5_col8\" class=\"data row5 col8\" >0.31</td> \n",
" </tr> <tr> \n",
" <th id=\"T_227be366_dadb_11e8_b9d7_f48e38ee2210level0_row6\" class=\"row_heading level0 row6\" >6</th> \n",
" <td id=\"T_227be366_dadb_11e8_b9d7_f48e38ee2210row6_col0\" class=\"data row6 col0\" >-0.034</td> \n",
" <td id=\"T_227be366_dadb_11e8_b9d7_f48e38ee2210row6_col1\" class=\"data row6 col1\" >0.14</td> \n",
" <td id=\"T_227be366_dadb_11e8_b9d7_f48e38ee2210row6_col2\" class=\"data row6 col2\" >-0.0028</td> \n",
" <td id=\"T_227be366_dadb_11e8_b9d7_f48e38ee2210row6_col3\" class=\"data row6 col3\" >0.1</td> \n",
" <td id=\"T_227be366_dadb_11e8_b9d7_f48e38ee2210row6_col4\" class=\"data row6 col4\" >0.099</td> \n",
" <td id=\"T_227be366_dadb_11e8_b9d7_f48e38ee2210row6_col5\" class=\"data row6 col5\" >0.15</td> \n",
" <td id=\"T_227be366_dadb_11e8_b9d7_f48e38ee2210row6_col6\" class=\"data row6 col6\" >1.0</td> \n",
" <td id=\"T_227be366_dadb_11e8_b9d7_f48e38ee2210row6_col7\" class=\"data row6 col7\" >0.034</td> \n",
" <td id=\"T_227be366_dadb_11e8_b9d7_f48e38ee2210row6_col8\" class=\"data row6 col8\" >0.17</td> \n",
" </tr> <tr> \n",
" <th id=\"T_227be366_dadb_11e8_b9d7_f48e38ee2210level0_row7\" class=\"row_heading level0 row7\" >7</th> \n",
" <td id=\"T_227be366_dadb_11e8_b9d7_f48e38ee2210row7_col0\" class=\"data row7 col0\" >0.54</td> \n",
" <td id=\"T_227be366_dadb_11e8_b9d7_f48e38ee2210row7_col1\" class=\"data row7 col1\" >0.27</td> \n",
" <td id=\"T_227be366_dadb_11e8_b9d7_f48e38ee2210row7_col2\" class=\"data row7 col2\" >0.32</td> \n",
" <td id=\"T_227be366_dadb_11e8_b9d7_f48e38ee2210row7_col3\" class=\"data row7 col3\" >0.13</td> \n",
" <td id=\"T_227be366_dadb_11e8_b9d7_f48e38ee2210row7_col4\" class=\"data row7 col4\" >0.14</td> \n",
" <td id=\"T_227be366_dadb_11e8_b9d7_f48e38ee2210row7_col5\" class=\"data row7 col5\" >0.026</td> \n",
" <td id=\"T_227be366_dadb_11e8_b9d7_f48e38ee2210row7_col6\" class=\"data row7 col6\" >0.034</td> \n",
" <td id=\"T_227be366_dadb_11e8_b9d7_f48e38ee2210row7_col7\" class=\"data row7 col7\" >1.0</td> \n",
" <td id=\"T_227be366_dadb_11e8_b9d7_f48e38ee2210row7_col8\" class=\"data row7 col8\" >0.24</td> \n",
" </tr> <tr> \n",
" <th id=\"T_227be366_dadb_11e8_b9d7_f48e38ee2210level0_row8\" class=\"row_heading level0 row8\" >8</th> \n",
" <td id=\"T_227be366_dadb_11e8_b9d7_f48e38ee2210row8_col0\" class=\"data row8 col0\" >0.22</td> \n",
" <td id=\"T_227be366_dadb_11e8_b9d7_f48e38ee2210row8_col1\" class=\"data row8 col1\" >0.49</td> \n",
" <td id=\"T_227be366_dadb_11e8_b9d7_f48e38ee2210row8_col2\" class=\"data row8 col2\" >0.17</td> \n",
" <td id=\"T_227be366_dadb_11e8_b9d7_f48e38ee2210row8_col3\" class=\"data row8 col3\" >0.22</td> \n",
" <td id=\"T_227be366_dadb_11e8_b9d7_f48e38ee2210row8_col4\" class=\"data row8 col4\" >0.21</td> \n",
" <td id=\"T_227be366_dadb_11e8_b9d7_f48e38ee2210row8_col5\" class=\"data row8 col5\" >0.31</td> \n",
" <td id=\"T_227be366_dadb_11e8_b9d7_f48e38ee2210row8_col6\" class=\"data row8 col6\" >0.17</td> \n",
" <td id=\"T_227be366_dadb_11e8_b9d7_f48e38ee2210row8_col7\" class=\"data row8 col7\" >0.24</td> \n",
" <td id=\"T_227be366_dadb_11e8_b9d7_f48e38ee2210row8_col8\" class=\"data row8 col8\" >1.0</td> \n",
" </tr></tbody> \n",
"</table> "
],
"text/plain": [
"<pandas.io.formats.style.Styler at 0x26c78f6d438>"
]
},
"execution_count": 4,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"data = pd.read_csv(\"https://raw.githubusercontent.com/jbrownlee/Datasets/master/pima-indians-diabetes.data.csv\",header=None)\n",
"print(data.describe())\n",
"\n",
"# Step -2: Mark zero values as missing or NaN\n",
"data[[1,2,3,4,5]] = data[[1,2,3,4,5]].replace(0, np.NaN)\n",
"\n",
"# Count the number of NaN values in each column\n",
"print(data.isnull().sum())\n",
"\n",
"# Step 5: Call the fillna() function with the imputation strategy\n",
"data.fillna(data.mean(), inplace=True)\n",
"\n",
"# Count the number of NaN values in each column to verify\n",
"print(data.isnull().sum())\n",
"\n",
"# Create the matrix of correlation score between the features and the label\n",
"scoreTable = data.corr(method='pearson')\n",
"\n",
"# Visulaize the matrix\n",
"data.corr(method='pearson').style.format(\"{:.2}\").background_gradient(cmap=plt.get_cmap('coolwarm'), axis=1)"
]
},
{
"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": "3.6.4"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment