253 lines
13 KiB
Plaintext
253 lines
13 KiB
Plaintext
{
|
|
"cells": [
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 1,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"Using matplotlib backend: MacOSX\n",
|
|
"Populating the interactive namespace from numpy and matplotlib\n"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"%pylab\n",
|
|
"%matplotlib inline\n",
|
|
"import pandas as pd\n",
|
|
"import numpy as np\n",
|
|
"import matplotlib.pyplot as plt\n",
|
|
"from scipy import stats\n",
|
|
"from matplotlib import colors\n",
|
|
"\n",
|
|
"data = pd.read_csv(\"Tennis players 2017-09.csv\")"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 2,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"data": {
|
|
"text/html": [
|
|
"<style type=\"text/css\" >\n",
|
|
" #T_7277b07a_4f3e_11e8_b8a3_787b8ab7acb2row0_col0 {\n",
|
|
" background-color: #fc7f00;\n",
|
|
" } #T_7277b07a_4f3e_11e8_b8a3_787b8ab7acb2row0_col1 {\n",
|
|
" background-color: #ffd20c;\n",
|
|
" } #T_7277b07a_4f3e_11e8_b8a3_787b8ab7acb2row0_col2 {\n",
|
|
" background-color: #ffe619;\n",
|
|
" } #T_7277b07a_4f3e_11e8_b8a3_787b8ab7acb2row0_col3 {\n",
|
|
" background-color: #f1f44d;\n",
|
|
" } #T_7277b07a_4f3e_11e8_b8a3_787b8ab7acb2row1_col0 {\n",
|
|
" background-color: #ffd20c;\n",
|
|
" } #T_7277b07a_4f3e_11e8_b8a3_787b8ab7acb2row1_col1 {\n",
|
|
" background-color: #fc7f00;\n",
|
|
" } #T_7277b07a_4f3e_11e8_b8a3_787b8ab7acb2row1_col2 {\n",
|
|
" background-color: #e4ff7a;\n",
|
|
" } #T_7277b07a_4f3e_11e8_b8a3_787b8ab7acb2row1_col3 {\n",
|
|
" background-color: #e8fc6c;\n",
|
|
" } #T_7277b07a_4f3e_11e8_b8a3_787b8ab7acb2row2_col0 {\n",
|
|
" background-color: #ffe619;\n",
|
|
" } #T_7277b07a_4f3e_11e8_b8a3_787b8ab7acb2row2_col1 {\n",
|
|
" background-color: #e4ff7a;\n",
|
|
" } #T_7277b07a_4f3e_11e8_b8a3_787b8ab7acb2row2_col2 {\n",
|
|
" background-color: #fc7f00;\n",
|
|
" } #T_7277b07a_4f3e_11e8_b8a3_787b8ab7acb2row2_col3 {\n",
|
|
" background-color: #fe9800;\n",
|
|
" } #T_7277b07a_4f3e_11e8_b8a3_787b8ab7acb2row3_col0 {\n",
|
|
" background-color: #f1f44d;\n",
|
|
" } #T_7277b07a_4f3e_11e8_b8a3_787b8ab7acb2row3_col1 {\n",
|
|
" background-color: #e8fc6c;\n",
|
|
" } #T_7277b07a_4f3e_11e8_b8a3_787b8ab7acb2row3_col2 {\n",
|
|
" background-color: #fe9800;\n",
|
|
" } #T_7277b07a_4f3e_11e8_b8a3_787b8ab7acb2row3_col3 {\n",
|
|
" background-color: #fc7f00;\n",
|
|
" }</style> \n",
|
|
"<table id=\"T_7277b07a_4f3e_11e8_b8a3_787b8ab7acb2\" > \n",
|
|
"<thead> <tr> \n",
|
|
" <th class=\"blank level0\" ></th> \n",
|
|
" <th class=\"col_heading level0 col0\" >DOB</th> \n",
|
|
" <th class=\"col_heading level0 col1\" >RANK</th> \n",
|
|
" <th class=\"col_heading level0 col2\" >HEIGHT</th> \n",
|
|
" <th class=\"col_heading level0 col3\" >Weight</th> \n",
|
|
" </tr></thead> \n",
|
|
"<tbody> <tr> \n",
|
|
" <th id=\"T_7277b07a_4f3e_11e8_b8a3_787b8ab7acb2level0_row0\" class=\"row_heading level0 row0\" >DOB</th> \n",
|
|
" <td id=\"T_7277b07a_4f3e_11e8_b8a3_787b8ab7acb2row0_col0\" class=\"data row0 col0\" >1</td> \n",
|
|
" <td id=\"T_7277b07a_4f3e_11e8_b8a3_787b8ab7acb2row0_col1\" class=\"data row0 col1\" >0.277766</td> \n",
|
|
" <td id=\"T_7277b07a_4f3e_11e8_b8a3_787b8ab7acb2row0_col2\" class=\"data row0 col2\" >0.139684</td> \n",
|
|
" <td id=\"T_7277b07a_4f3e_11e8_b8a3_787b8ab7acb2row0_col3\" class=\"data row0 col3\" >-0.030479</td> \n",
|
|
" </tr> <tr> \n",
|
|
" <th id=\"T_7277b07a_4f3e_11e8_b8a3_787b8ab7acb2level0_row1\" class=\"row_heading level0 row1\" >RANK</th> \n",
|
|
" <td id=\"T_7277b07a_4f3e_11e8_b8a3_787b8ab7acb2row1_col0\" class=\"data row1 col0\" >0.277766</td> \n",
|
|
" <td id=\"T_7277b07a_4f3e_11e8_b8a3_787b8ab7acb2row1_col1\" class=\"data row1 col1\" >1</td> \n",
|
|
" <td id=\"T_7277b07a_4f3e_11e8_b8a3_787b8ab7acb2row1_col2\" class=\"data row1 col2\" >-0.16755</td> \n",
|
|
" <td id=\"T_7277b07a_4f3e_11e8_b8a3_787b8ab7acb2row1_col3\" class=\"data row1 col3\" >-0.121946</td> \n",
|
|
" </tr> <tr> \n",
|
|
" <th id=\"T_7277b07a_4f3e_11e8_b8a3_787b8ab7acb2level0_row2\" class=\"row_heading level0 row2\" >HEIGHT</th> \n",
|
|
" <td id=\"T_7277b07a_4f3e_11e8_b8a3_787b8ab7acb2row2_col0\" class=\"data row2 col0\" >0.139684</td> \n",
|
|
" <td id=\"T_7277b07a_4f3e_11e8_b8a3_787b8ab7acb2row2_col1\" class=\"data row2 col1\" >-0.16755</td> \n",
|
|
" <td id=\"T_7277b07a_4f3e_11e8_b8a3_787b8ab7acb2row2_col2\" class=\"data row2 col2\" >1</td> \n",
|
|
" <td id=\"T_7277b07a_4f3e_11e8_b8a3_787b8ab7acb2row2_col3\" class=\"data row2 col3\" >0.779526</td> \n",
|
|
" </tr> <tr> \n",
|
|
" <th id=\"T_7277b07a_4f3e_11e8_b8a3_787b8ab7acb2level0_row3\" class=\"row_heading level0 row3\" >Weight</th> \n",
|
|
" <td id=\"T_7277b07a_4f3e_11e8_b8a3_787b8ab7acb2row3_col0\" class=\"data row3 col0\" >-0.030479</td> \n",
|
|
" <td id=\"T_7277b07a_4f3e_11e8_b8a3_787b8ab7acb2row3_col1\" class=\"data row3 col1\" >-0.121946</td> \n",
|
|
" <td id=\"T_7277b07a_4f3e_11e8_b8a3_787b8ab7acb2row3_col2\" class=\"data row3 col2\" >0.779526</td> \n",
|
|
" <td id=\"T_7277b07a_4f3e_11e8_b8a3_787b8ab7acb2row3_col3\" class=\"data row3 col3\" >1</td> \n",
|
|
" </tr></tbody> \n",
|
|
"</table> "
|
|
],
|
|
"text/plain": [
|
|
"<pandas.io.formats.style.Styler at 0x1a197d7b38>"
|
|
]
|
|
},
|
|
"execution_count": 2,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"def background_gradient(s, m, M, cmap='Wistia', low=0, high=0):\n",
|
|
" rng = M - m\n",
|
|
" norm = colors.Normalize(m - (rng * low),\n",
|
|
" M + (rng * high))\n",
|
|
" normed = norm(s.values)\n",
|
|
" c = [colors.rgb2hex(x) for x in plt.cm.get_cmap(cmap)(normed)]\n",
|
|
" return ['background-color: %s' % color for color in c]\n",
|
|
"\n",
|
|
"data = data[[\"SEX\", \"DOB\", \"RANK\", \"HANDED\", \"Country\", \"HEIGHT\", \"Weight\"]]\n",
|
|
"data.drop_duplicates\n",
|
|
"\n",
|
|
"pearson = data.corr()\n",
|
|
"pearson.style.apply(background_gradient,\n",
|
|
" cmap='Wistia',\n",
|
|
" m=pearson.min().min(),\n",
|
|
" M=pearson.max().max()\n",
|
|
")"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 3,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"data": {
|
|
"text/html": [
|
|
"<style type=\"text/css\" >\n",
|
|
" #T_727bef98_4f3e_11e8_a315_787b8ab7acb2row0_col0 {\n",
|
|
" background-color: #fc7f00;\n",
|
|
" } #T_727bef98_4f3e_11e8_a315_787b8ab7acb2row0_col1 {\n",
|
|
" background-color: #ffd20c;\n",
|
|
" } #T_727bef98_4f3e_11e8_a315_787b8ab7acb2row0_col2 {\n",
|
|
" background-color: #fee91d;\n",
|
|
" } #T_727bef98_4f3e_11e8_a315_787b8ab7acb2row0_col3 {\n",
|
|
" background-color: #f4f242;\n",
|
|
" } #T_727bef98_4f3e_11e8_a315_787b8ab7acb2row1_col0 {\n",
|
|
" background-color: #ffd20c;\n",
|
|
" } #T_727bef98_4f3e_11e8_a315_787b8ab7acb2row1_col1 {\n",
|
|
" background-color: #fc7f00;\n",
|
|
" } #T_727bef98_4f3e_11e8_a315_787b8ab7acb2row1_col2 {\n",
|
|
" background-color: #e4ff7a;\n",
|
|
" } #T_727bef98_4f3e_11e8_a315_787b8ab7acb2row1_col3 {\n",
|
|
" background-color: #eafa63;\n",
|
|
" } #T_727bef98_4f3e_11e8_a315_787b8ab7acb2row2_col0 {\n",
|
|
" background-color: #fee91d;\n",
|
|
" } #T_727bef98_4f3e_11e8_a315_787b8ab7acb2row2_col1 {\n",
|
|
" background-color: #e4ff7a;\n",
|
|
" } #T_727bef98_4f3e_11e8_a315_787b8ab7acb2row2_col2 {\n",
|
|
" background-color: #fc7f00;\n",
|
|
" } #T_727bef98_4f3e_11e8_a315_787b8ab7acb2row2_col3 {\n",
|
|
" background-color: #ff9d00;\n",
|
|
" } #T_727bef98_4f3e_11e8_a315_787b8ab7acb2row3_col0 {\n",
|
|
" background-color: #f4f242;\n",
|
|
" } #T_727bef98_4f3e_11e8_a315_787b8ab7acb2row3_col1 {\n",
|
|
" background-color: #eafa63;\n",
|
|
" } #T_727bef98_4f3e_11e8_a315_787b8ab7acb2row3_col2 {\n",
|
|
" background-color: #ff9d00;\n",
|
|
" } #T_727bef98_4f3e_11e8_a315_787b8ab7acb2row3_col3 {\n",
|
|
" background-color: #fc7f00;\n",
|
|
" }</style> \n",
|
|
"<table id=\"T_727bef98_4f3e_11e8_a315_787b8ab7acb2\" > \n",
|
|
"<thead> <tr> \n",
|
|
" <th class=\"blank level0\" ></th> \n",
|
|
" <th class=\"col_heading level0 col0\" >DOB</th> \n",
|
|
" <th class=\"col_heading level0 col1\" >RANK</th> \n",
|
|
" <th class=\"col_heading level0 col2\" >HEIGHT</th> \n",
|
|
" <th class=\"col_heading level0 col3\" >Weight</th> \n",
|
|
" </tr></thead> \n",
|
|
"<tbody> <tr> \n",
|
|
" <th id=\"T_727bef98_4f3e_11e8_a315_787b8ab7acb2level0_row0\" class=\"row_heading level0 row0\" >DOB</th> \n",
|
|
" <td id=\"T_727bef98_4f3e_11e8_a315_787b8ab7acb2row0_col0\" class=\"data row0 col0\" >1</td> \n",
|
|
" <td id=\"T_727bef98_4f3e_11e8_a315_787b8ab7acb2row0_col1\" class=\"data row0 col1\" >0.280386</td> \n",
|
|
" <td id=\"T_727bef98_4f3e_11e8_a315_787b8ab7acb2row0_col2\" class=\"data row0 col2\" >0.122412</td> \n",
|
|
" <td id=\"T_727bef98_4f3e_11e8_a315_787b8ab7acb2row0_col3\" class=\"data row0 col3\" >0.00769861</td> \n",
|
|
" </tr> <tr> \n",
|
|
" <th id=\"T_727bef98_4f3e_11e8_a315_787b8ab7acb2level0_row1\" class=\"row_heading level0 row1\" >RANK</th> \n",
|
|
" <td id=\"T_727bef98_4f3e_11e8_a315_787b8ab7acb2row1_col0\" class=\"data row1 col0\" >0.280386</td> \n",
|
|
" <td id=\"T_727bef98_4f3e_11e8_a315_787b8ab7acb2row1_col1\" class=\"data row1 col1\" >1</td> \n",
|
|
" <td id=\"T_727bef98_4f3e_11e8_a315_787b8ab7acb2row1_col2\" class=\"data row1 col2\" >-0.160006</td> \n",
|
|
" <td id=\"T_727bef98_4f3e_11e8_a315_787b8ab7acb2row1_col3\" class=\"data row1 col3\" >-0.0908714</td> \n",
|
|
" </tr> <tr> \n",
|
|
" <th id=\"T_727bef98_4f3e_11e8_a315_787b8ab7acb2level0_row2\" class=\"row_heading level0 row2\" >HEIGHT</th> \n",
|
|
" <td id=\"T_727bef98_4f3e_11e8_a315_787b8ab7acb2row2_col0\" class=\"data row2 col0\" >0.122412</td> \n",
|
|
" <td id=\"T_727bef98_4f3e_11e8_a315_787b8ab7acb2row2_col1\" class=\"data row2 col1\" >-0.160006</td> \n",
|
|
" <td id=\"T_727bef98_4f3e_11e8_a315_787b8ab7acb2row2_col2\" class=\"data row2 col2\" >1</td> \n",
|
|
" <td id=\"T_727bef98_4f3e_11e8_a315_787b8ab7acb2row2_col3\" class=\"data row2 col3\" >0.739246</td> \n",
|
|
" </tr> <tr> \n",
|
|
" <th id=\"T_727bef98_4f3e_11e8_a315_787b8ab7acb2level0_row3\" class=\"row_heading level0 row3\" >Weight</th> \n",
|
|
" <td id=\"T_727bef98_4f3e_11e8_a315_787b8ab7acb2row3_col0\" class=\"data row3 col0\" >0.00769861</td> \n",
|
|
" <td id=\"T_727bef98_4f3e_11e8_a315_787b8ab7acb2row3_col1\" class=\"data row3 col1\" >-0.0908714</td> \n",
|
|
" <td id=\"T_727bef98_4f3e_11e8_a315_787b8ab7acb2row3_col2\" class=\"data row3 col2\" >0.739246</td> \n",
|
|
" <td id=\"T_727bef98_4f3e_11e8_a315_787b8ab7acb2row3_col3\" class=\"data row3 col3\" >1</td> \n",
|
|
" </tr></tbody> \n",
|
|
"</table> "
|
|
],
|
|
"text/plain": [
|
|
"<pandas.io.formats.style.Styler at 0x111a3b198>"
|
|
]
|
|
},
|
|
"execution_count": 3,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"spearman = data.corr(method=\"spearman\")\n",
|
|
"spearman.style.apply(background_gradient,\n",
|
|
" cmap='Wistia',\n",
|
|
" m=spearman.min().min(),\n",
|
|
" M=spearman.max().max()\n",
|
|
")"
|
|
]
|
|
}
|
|
],
|
|
"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
|
|
}
|