add dataset for machine learning

Author: gkarwchan

Machine_Learning.ipynb

@@ -1,5 +1,168 @@
 {
  "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>CRIM</th>\n",
+       "      <th>ZN</th>\n",
+       "      <th>INDUS</th>\n",
+       "      <th>CHAS</th>\n",
+       "      <th>NOX</th>\n",
+       "      <th>RM</th>\n",
+       "      <th>AGE</th>\n",
+       "      <th>DIS</th>\n",
+       "      <th>RAD</th>\n",
+       "      <th>TAX</th>\n",
+       "      <th>PTRATIO</th>\n",
+       "      <th>B</th>\n",
+       "      <th>LSTAT</th>\n",
+       "      <th>MEDV</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>0.00632</td>\n",
+       "      <td>18.0</td>\n",
+       "      <td>2.31</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0.538</td>\n",
+       "      <td>6.575</td>\n",
+       "      <td>65.2</td>\n",
+       "      <td>4.0900</td>\n",
+       "      <td>1</td>\n",
+       "      <td>296.0</td>\n",
+       "      <td>15.3</td>\n",
+       "      <td>396.90</td>\n",
+       "      <td>4.98</td>\n",
+       "      <td>24.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>0.02731</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>7.07</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0.469</td>\n",
+       "      <td>6.421</td>\n",
+       "      <td>78.9</td>\n",
+       "      <td>4.9671</td>\n",
+       "      <td>2</td>\n",
+       "      <td>242.0</td>\n",
+       "      <td>17.8</td>\n",
+       "      <td>396.90</td>\n",
+       "      <td>9.14</td>\n",
+       "      <td>21.6</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>0.02729</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>7.07</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0.469</td>\n",
+       "      <td>7.185</td>\n",
+       "      <td>61.1</td>\n",
+       "      <td>4.9671</td>\n",
+       "      <td>2</td>\n",
+       "      <td>242.0</td>\n",
+       "      <td>17.8</td>\n",
+       "      <td>392.83</td>\n",
+       "      <td>4.03</td>\n",
+       "      <td>34.7</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>0.03237</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>2.18</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0.458</td>\n",
+       "      <td>6.998</td>\n",
+       "      <td>45.8</td>\n",
+       "      <td>6.0622</td>\n",
+       "      <td>3</td>\n",
+       "      <td>222.0</td>\n",
+       "      <td>18.7</td>\n",
+       "      <td>394.63</td>\n",
+       "      <td>2.94</td>\n",
+       "      <td>33.4</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>0.06905</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>2.18</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0.458</td>\n",
+       "      <td>7.147</td>\n",
+       "      <td>54.2</td>\n",
+       "      <td>6.0622</td>\n",
+       "      <td>3</td>\n",
+       "      <td>222.0</td>\n",
+       "      <td>18.7</td>\n",
+       "      <td>396.90</td>\n",
+       "      <td>5.33</td>\n",
+       "      <td>36.2</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "      CRIM    ZN  INDUS  CHAS    NOX     RM   AGE     DIS  RAD    TAX  \\\n",
+       "0  0.00632  18.0   2.31     0  0.538  6.575  65.2  4.0900    1  296.0   \n",
+       "1  0.02731   0.0   7.07     0  0.469  6.421  78.9  4.9671    2  242.0   \n",
+       "2  0.02729   0.0   7.07     0  0.469  7.185  61.1  4.9671    2  242.0   \n",
+       "3  0.03237   0.0   2.18     0  0.458  6.998  45.8  6.0622    3  222.0   \n",
+       "4  0.06905   0.0   2.18     0  0.458  7.147  54.2  6.0622    3  222.0   \n",
+       "\n",
+       "   PTRATIO       B  LSTAT  MEDV  \n",
+       "0     15.3  396.90   4.98  24.0  \n",
+       "1     17.8  396.90   9.14  21.6  \n",
+       "2     17.8  392.83   4.03  34.7  \n",
+       "3     18.7  394.63   2.94  33.4  \n",
+       "4     18.7  396.90   5.33  36.2  "
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "import pandas as pd\n",
+    "homes = pd.read_fwf('./data/housing.data', \n",
+    "            names=['CRIM', 'ZN', 'INDUS', 'CHAS', 'NOX', 'RM', \n",
+    "                   'AGE', 'DIS', 'RAD', 'TAX', 'PTRATIO', 'B',\n",
+    "                   'LSTAT', 'MEDV'\n",
+    "                  ])\n",
+    "homes.head()"
+   ]
+  },
   {
    "cell_type": "markdown",
    "metadata": {},