Clustering/Boston Housing.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import pandas as pd\n",
    "from matplotlib import pyplot"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "%matplotlib inline"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "filename = 'housing.csv'\n",
    "names = ['CRIM', 'ZN', 'INDUS', 'CHAS', 'NOX', 'RM', 'AGE', 'DIS',  'RAD', 'TAX', 'PRTATIO', 'B', 'LSTAT', 'MEDV']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "df = pd.read_csv(filename, names=names, sep='\\s+')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(506, 14)"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style>\n",
       "    .dataframe thead tr:only-child th {\n",
       "        text-align: right;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\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>PRTATIO</th>\n",
       "      <th>B</th>\n",
       "      <th>LSTAT</th>\n",
       "      <th>MEDV</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>5.1e+02</td>\n",
       "      <td>506.0</td>\n",
       "      <td>506.0</td>\n",
       "      <td>5.1e+02</td>\n",
       "      <td>506.0</td>\n",
       "      <td>506.0</td>\n",
       "      <td>506.0</td>\n",
       "      <td>506.0</td>\n",
       "      <td>506.0</td>\n",
       "      <td>506.0</td>\n",
       "      <td>506.0</td>\n",
       "      <td>506.0</td>\n",
       "      <td>506.0</td>\n",
       "      <td>506.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>3.6e+00</td>\n",
       "      <td>11.4</td>\n",
       "      <td>11.1</td>\n",
       "      <td>6.9e-02</td>\n",
       "      <td>0.6</td>\n",
       "      <td>6.3</td>\n",
       "      <td>68.6</td>\n",
       "      <td>3.8</td>\n",
       "      <td>9.5</td>\n",
       "      <td>408.2</td>\n",
       "      <td>18.5</td>\n",
       "      <td>356.7</td>\n",
       "      <td>12.7</td>\n",
       "      <td>22.5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>8.6e+00</td>\n",
       "      <td>23.3</td>\n",
       "      <td>6.9</td>\n",
       "      <td>2.5e-01</td>\n",
       "      <td>0.1</td>\n",
       "      <td>0.7</td>\n",
       "      <td>28.1</td>\n",
       "      <td>2.1</td>\n",
       "      <td>8.7</td>\n",
       "      <td>168.5</td>\n",
       "      <td>2.2</td>\n",
       "      <td>91.3</td>\n",
       "      <td>7.1</td>\n",
       "      <td>9.2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>6.3e-03</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.5</td>\n",
       "      <td>0.0e+00</td>\n",
       "      <td>0.4</td>\n",
       "      <td>3.6</td>\n",
       "      <td>2.9</td>\n",
       "      <td>1.1</td>\n",
       "      <td>1.0</td>\n",
       "      <td>187.0</td>\n",
       "      <td>12.6</td>\n",
       "      <td>0.3</td>\n",
       "      <td>1.7</td>\n",
       "      <td>5.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>8.2e-02</td>\n",
       "      <td>0.0</td>\n",
       "      <td>5.2</td>\n",
       "      <td>0.0e+00</td>\n",
       "      <td>0.4</td>\n",
       "      <td>5.9</td>\n",
       "      <td>45.0</td>\n",
       "      <td>2.1</td>\n",
       "      <td>4.0</td>\n",
       "      <td>279.0</td>\n",
       "      <td>17.4</td>\n",
       "      <td>375.4</td>\n",
       "      <td>6.9</td>\n",
       "      <td>17.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>2.6e-01</td>\n",
       "      <td>0.0</td>\n",
       "      <td>9.7</td>\n",
       "      <td>0.0e+00</td>\n",
       "      <td>0.5</td>\n",
       "      <td>6.2</td>\n",
       "      <td>77.5</td>\n",
       "      <td>3.2</td>\n",
       "      <td>5.0</td>\n",
       "      <td>330.0</td>\n",
       "      <td>19.1</td>\n",
       "      <td>391.4</td>\n",
       "      <td>11.4</td>\n",
       "      <td>21.2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>3.7e+00</td>\n",
       "      <td>12.5</td>\n",
       "      <td>18.1</td>\n",
       "      <td>0.0e+00</td>\n",
       "      <td>0.6</td>\n",
       "      <td>6.6</td>\n",
       "      <td>94.1</td>\n",
       "      <td>5.2</td>\n",
       "      <td>24.0</td>\n",
       "      <td>666.0</td>\n",
       "      <td>20.2</td>\n",
       "      <td>396.2</td>\n",
       "      <td>17.0</td>\n",
       "      <td>25.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>8.9e+01</td>\n",
       "      <td>100.0</td>\n",
       "      <td>27.7</td>\n",
       "      <td>1.0e+00</td>\n",
       "      <td>0.9</td>\n",
       "      <td>8.8</td>\n",
       "      <td>100.0</td>\n",
       "      <td>12.1</td>\n",
       "      <td>24.0</td>\n",
       "      <td>711.0</td>\n",
       "      <td>22.0</td>\n",
       "      <td>396.9</td>\n",
       "      <td>38.0</td>\n",
       "      <td>50.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "          CRIM     ZN  INDUS     CHAS    NOX     RM    AGE    DIS    RAD    TAX  PRTATIO      B  LSTAT   MEDV\n",
       "count  5.1e+02  506.0  506.0  5.1e+02  506.0  506.0  506.0  506.0  506.0  506.0    506.0  506.0  506.0  506.0\n",
       "mean   3.6e+00   11.4   11.1  6.9e-02    0.6    6.3   68.6    3.8    9.5  408.2     18.5  356.7   12.7   22.5\n",
       "std    8.6e+00   23.3    6.9  2.5e-01    0.1    0.7   28.1    2.1    8.7  168.5      2.2   91.3    7.1    9.2\n",
       "min    6.3e-03    0.0    0.5  0.0e+00    0.4    3.6    2.9    1.1    1.0  187.0     12.6    0.3    1.7    5.0\n",
       "25%    8.2e-02    0.0    5.2  0.0e+00    0.4    5.9   45.0    2.1    4.0  279.0     17.4  375.4    6.9   17.0\n",
       "50%    2.6e-01    0.0    9.7  0.0e+00    0.5    6.2   77.5    3.2    5.0  330.0     19.1  391.4   11.4   21.2\n",
       "75%    3.7e+00   12.5   18.1  0.0e+00    0.6    6.6   94.1    5.2   24.0  666.0     20.2  396.2   17.0   25.0\n",
       "max    8.9e+01  100.0   27.7  1.0e+00    0.9    8.8  100.0   12.1   24.0  711.0     22.0  396.9   38.0   50.0"
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pd.set_option('precision', 1)\n",
    "df.describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "CRIM       float64\n",
       "ZN         float64\n",
       "INDUS      float64\n",
       "CHAS         int64\n",
       "NOX        float64\n",
       "RM         float64\n",
       "AGE        float64\n",
       "DIS        float64\n",
       "RAD          int64\n",
       "TAX        float64\n",
       "PRTATIO    float64\n",
       "B          float64\n",
       "LSTAT      float64\n",
       "MEDV       float64\n",
       "dtype: object"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.dtypes"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style>\n",
       "    .dataframe thead tr:only-child th {\n",
       "        text-align: right;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\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>PRTATIO</th>\n",
       "      <th>B</th>\n",
       "      <th>LSTAT</th>\n",
       "      <th>MEDV</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>476</th>\n",
       "      <td>4.87141</td>\n",
       "      <td>0.0</td>\n",
       "      <td>18.10</td>\n",
       "      <td>0</td>\n",
       "      <td>0.614</td>\n",
       "      <td>6.484</td>\n",
       "      <td>93.6</td>\n",
       "      <td>2.3053</td>\n",
       "      <td>24</td>\n",
       "      <td>666.0</td>\n",
       "      <td>20.2</td>\n",
       "      <td>396.21</td>\n",
       "      <td>18.68</td>\n",
       "      <td>16.7</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>477</th>\n",
       "      <td>15.02340</td>\n",
       "      <td>0.0</td>\n",
       "      <td>18.10</td>\n",
       "      <td>0</td>\n",
       "      <td>0.614</td>\n",
       "      <td>5.304</td>\n",
       "      <td>97.3</td>\n",
       "      <td>2.1007</td>\n",
       "      <td>24</td>\n",
       "      <td>666.0</td>\n",
       "      <td>20.2</td>\n",
       "      <td>349.48</td>\n",
       "      <td>24.91</td>\n",
       "      <td>12.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>478</th>\n",
       "      <td>10.23300</td>\n",
       "      <td>0.0</td>\n",
       "      <td>18.10</td>\n",
       "      <td>0</td>\n",
       "      <td>0.614</td>\n",
       "      <td>6.185</td>\n",
       "      <td>96.7</td>\n",
       "      <td>2.1705</td>\n",
       "      <td>24</td>\n",
       "      <td>666.0</td>\n",
       "      <td>20.2</td>\n",
       "      <td>379.70</td>\n",
       "      <td>18.03</td>\n",
       "      <td>14.6</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>479</th>\n",
       "      <td>14.33370</td>\n",
       "      <td>0.0</td>\n",
       "      <td>18.10</td>\n",
       "      <td>0</td>\n",
       "      <td>0.614</td>\n",
       "      <td>6.229</td>\n",
       "      <td>88.0</td>\n",
       "      <td>1.9512</td>\n",
       "      <td>24</td>\n",
       "      <td>666.0</td>\n",
       "      <td>20.2</td>\n",
       "      <td>383.32</td>\n",
       "      <td>13.11</td>\n",
       "      <td>21.4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>480</th>\n",
       "      <td>5.82401</td>\n",
       "      <td>0.0</td>\n",
       "      <td>18.10</td>\n",
       "      <td>0</td>\n",
       "      <td>0.532</td>\n",
       "      <td>6.242</td>\n",
       "      <td>64.7</td>\n",
       "      <td>3.4242</td>\n",
       "      <td>24</td>\n",
       "      <td>666.0</td>\n",
       "      <td>20.2</td>\n",
       "      <td>396.90</td>\n",
       "      <td>10.74</td>\n",
       "      <td>23.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>481</th>\n",
       "      <td>5.70818</td>\n",
       "      <td>0.0</td>\n",
       "      <td>18.10</td>\n",
       "      <td>0</td>\n",
       "      <td>0.532</td>\n",
       "      <td>6.750</td>\n",
       "      <td>74.9</td>\n",
       "      <td>3.3317</td>\n",
       "      <td>24</td>\n",
       "      <td>666.0</td>\n",
       "      <td>20.2</td>\n",
       "      <td>393.07</td>\n",
       "      <td>7.74</td>\n",
       "      <td>23.7</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>482</th>\n",
       "      <td>5.73116</td>\n",
       "      <td>0.0</td>\n",
       "      <td>18.10</td>\n",
       "      <td>0</td>\n",
       "      <td>0.532</td>\n",
       "      <td>7.061</td>\n",
       "      <td>77.0</td>\n",
       "      <td>3.4106</td>\n",
       "      <td>24</td>\n",
       "      <td>666.0</td>\n",
       "      <td>20.2</td>\n",
       "      <td>395.28</td>\n",
       "      <td>7.01</td>\n",
       "      <td>25.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>483</th>\n",
       "      <td>2.81838</td>\n",
       "      <td>0.0</td>\n",
       "      <td>18.10</td>\n",
       "      <td>0</td>\n",
       "      <td>0.532</td>\n",
       "      <td>5.762</td>\n",
       "      <td>40.3</td>\n",
       "      <td>4.0983</td>\n",
       "      <td>24</td>\n",
       "      <td>666.0</td>\n",
       "      <td>20.2</td>\n",
       "      <td>392.92</td>\n",
       "      <td>10.42</td>\n",
       "      <td>21.8</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>484</th>\n",
       "      <td>2.37857</td>\n",
       "      <td>0.0</td>\n",
       "      <td>18.10</td>\n",
       "      <td>0</td>\n",
       "      <td>0.583</td>\n",
       "      <td>5.871</td>\n",
       "      <td>41.9</td>\n",
       "      <td>3.7240</td>\n",
       "      <td>24</td>\n",
       "      <td>666.0</td>\n",
       "      <td>20.2</td>\n",
       "      <td>370.73</td>\n",
       "      <td>13.34</td>\n",
       "      <td>20.6</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>485</th>\n",
       "      <td>3.67367</td>\n",
       "      <td>0.0</td>\n",
       "      <td>18.10</td>\n",
       "      <td>0</td>\n",
       "      <td>0.583</td>\n",
       "      <td>6.312</td>\n",
       "      <td>51.9</td>\n",
       "      <td>3.9917</td>\n",
       "      <td>24</td>\n",
       "      <td>666.0</td>\n",
       "      <td>20.2</td>\n",
       "      <td>388.62</td>\n",
       "      <td>10.58</td>\n",
       "      <td>21.2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>486</th>\n",
       "      <td>5.69175</td>\n",
       "      <td>0.0</td>\n",
       "      <td>18.10</td>\n",
       "      <td>0</td>\n",
       "      <td>0.583</td>\n",
       "      <td>6.114</td>\n",
       "      <td>79.8</td>\n",
       "      <td>3.5459</td>\n",
       "      <td>24</td>\n",
       "      <td>666.0</td>\n",
       "      <td>20.2</td>\n",
       "      <td>392.68</td>\n",
       "      <td>14.98</td>\n",
       "      <td>19.1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>487</th>\n",
       "      <td>4.83567</td>\n",
       "      <td>0.0</td>\n",
       "      <td>18.10</td>\n",
       "      <td>0</td>\n",
       "      <td>0.583</td>\n",
       "      <td>5.905</td>\n",
       "      <td>53.2</td>\n",
       "      <td>3.1523</td>\n",
       "      <td>24</td>\n",
       "      <td>666.0</td>\n",
       "      <td>20.2</td>\n",
       "      <td>388.22</td>\n",
       "      <td>11.45</td>\n",
       "      <td>20.6</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>488</th>\n",
       "      <td>0.15086</td>\n",
       "      <td>0.0</td>\n",
       "      <td>27.74</td>\n",
       "      <td>0</td>\n",
       "      <td>0.609</td>\n",
       "      <td>5.454</td>\n",
       "      <td>92.7</td>\n",
       "      <td>1.8209</td>\n",
       "      <td>4</td>\n",
       "      <td>711.0</td>\n",
       "      <td>20.1</td>\n",
       "      <td>395.09</td>\n",
       "      <td>18.06</td>\n",
       "      <td>15.2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>489</th>\n",
       "      <td>0.18337</td>\n",
       "      <td>0.0</td>\n",
       "      <td>27.74</td>\n",
       "      <td>0</td>\n",
       "      <td>0.609</td>\n",
       "      <td>5.414</td>\n",
       "      <td>98.3</td>\n",
       "      <td>1.7554</td>\n",
       "      <td>4</td>\n",
       "      <td>711.0</td>\n",
       "      <td>20.1</td>\n",
       "      <td>344.05</td>\n",
       "      <td>23.97</td>\n",
       "      <td>7.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>490</th>\n",
       "      <td>0.20746</td>\n",
       "      <td>0.0</td>\n",
       "      <td>27.74</td>\n",
       "      <td>0</td>\n",
       "      <td>0.609</td>\n",
       "      <td>5.093</td>\n",
       "      <td>98.0</td>\n",
       "      <td>1.8226</td>\n",
       "      <td>4</td>\n",
       "      <td>711.0</td>\n",
       "      <td>20.1</td>\n",
       "      <td>318.43</td>\n",
       "      <td>29.68</td>\n",
       "      <td>8.1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>491</th>\n",
       "      <td>0.10574</td>\n",
       "      <td>0.0</td>\n",
       "      <td>27.74</td>\n",
       "      <td>0</td>\n",
       "      <td>0.609</td>\n",
       "      <td>5.983</td>\n",
       "      <td>98.8</td>\n",
       "      <td>1.8681</td>\n",
       "      <td>4</td>\n",
       "      <td>711.0</td>\n",
       "      <td>20.1</td>\n",
       "      <td>390.11</td>\n",
       "      <td>18.07</td>\n",
       "      <td>13.6</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>492</th>\n",
       "      <td>0.11132</td>\n",
       "      <td>0.0</td>\n",
       "      <td>27.74</td>\n",
       "      <td>0</td>\n",
       "      <td>0.609</td>\n",
       "      <td>5.983</td>\n",
       "      <td>83.5</td>\n",
       "      <td>2.1099</td>\n",
       "      <td>4</td>\n",
       "      <td>711.0</td>\n",
       "      <td>20.1</td>\n",
       "      <td>396.90</td>\n",
       "      <td>13.35</td>\n",
       "      <td>20.1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>493</th>\n",
       "      <td>0.17331</td>\n",
       "      <td>0.0</td>\n",
       "      <td>9.69</td>\n",
       "      <td>0</td>\n",
       "      <td>0.585</td>\n",
       "      <td>5.707</td>\n",
       "      <td>54.0</td>\n",
       "      <td>2.3817</td>\n",
       "      <td>6</td>\n",
       "      <td>391.0</td>\n",
       "      <td>19.2</td>\n",
       "      <td>396.90</td>\n",
       "      <td>12.01</td>\n",
       "      <td>21.8</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>494</th>\n",
       "      <td>0.27957</td>\n",
       "      <td>0.0</td>\n",
       "      <td>9.69</td>\n",
       "      <td>0</td>\n",
       "      <td>0.585</td>\n",
       "      <td>5.926</td>\n",
       "      <td>42.6</td>\n",
       "      <td>2.3817</td>\n",
       "      <td>6</td>\n",
       "      <td>391.0</td>\n",
       "      <td>19.2</td>\n",
       "      <td>396.90</td>\n",
       "      <td>13.59</td>\n",
       "      <td>24.5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>495</th>\n",
       "      <td>0.17899</td>\n",
       "      <td>0.0</td>\n",
       "      <td>9.69</td>\n",
       "      <td>0</td>\n",
       "      <td>0.585</td>\n",
       "      <td>5.670</td>\n",
       "      <td>28.8</td>\n",
       "      <td>2.7986</td>\n",
       "      <td>6</td>\n",
       "      <td>391.0</td>\n",
       "      <td>19.2</td>\n",
       "      <td>393.29</td>\n",
       "      <td>17.60</td>\n",
       "      <td>23.1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>496</th>\n",
       "      <td>0.28960</td>\n",
       "      <td>0.0</td>\n",
       "      <td>9.69</td>\n",
       "      <td>0</td>\n",
       "      <td>0.585</td>\n",
       "      <td>5.390</td>\n",
       "      <td>72.9</td>\n",
       "      <td>2.7986</td>\n",
       "      <td>6</td>\n",
       "      <td>391.0</td>\n",
       "      <td>19.2</td>\n",
       "      <td>396.90</td>\n",
       "      <td>21.14</td>\n",
       "      <td>19.7</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>497</th>\n",
       "      <td>0.26838</td>\n",
       "      <td>0.0</td>\n",
       "      <td>9.69</td>\n",
       "      <td>0</td>\n",
       "      <td>0.585</td>\n",
       "      <td>5.794</td>\n",
       "      <td>70.6</td>\n",
       "      <td>2.8927</td>\n",
       "      <td>6</td>\n",
       "      <td>391.0</td>\n",
       "      <td>19.2</td>\n",
       "      <td>396.90</td>\n",
       "      <td>14.10</td>\n",
       "      <td>18.3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>498</th>\n",
       "      <td>0.23912</td>\n",
       "      <td>0.0</td>\n",
       "      <td>9.69</td>\n",
       "      <td>0</td>\n",
       "      <td>0.585</td>\n",
       "      <td>6.019</td>\n",
       "      <td>65.3</td>\n",
       "      <td>2.4091</td>\n",
       "      <td>6</td>\n",
       "      <td>391.0</td>\n",
       "      <td>19.2</td>\n",
       "      <td>396.90</td>\n",
       "      <td>12.92</td>\n",
       "      <td>21.2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>499</th>\n",
       "      <td>0.17783</td>\n",
       "      <td>0.0</td>\n",
       "      <td>9.69</td>\n",
       "      <td>0</td>\n",
       "      <td>0.585</td>\n",
       "      <td>5.569</td>\n",
       "      <td>73.5</td>\n",
       "      <td>2.3999</td>\n",
       "      <td>6</td>\n",
       "      <td>391.0</td>\n",
       "      <td>19.2</td>\n",
       "      <td>395.77</td>\n",
       "      <td>15.10</td>\n",
       "      <td>17.5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>500</th>\n",
       "      <td>0.22438</td>\n",
       "      <td>0.0</td>\n",
       "      <td>9.69</td>\n",
       "      <td>0</td>\n",
       "      <td>0.585</td>\n",
       "      <td>6.027</td>\n",
       "      <td>79.7</td>\n",
       "      <td>2.4982</td>\n",
       "      <td>6</td>\n",
       "      <td>391.0</td>\n",
       "      <td>19.2</td>\n",
       "      <td>396.90</td>\n",
       "      <td>14.33</td>\n",
       "      <td>16.8</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>501</th>\n",
       "      <td>0.06263</td>\n",
       "      <td>0.0</td>\n",
       "      <td>11.93</td>\n",
       "      <td>0</td>\n",
       "      <td>0.573</td>\n",
       "      <td>6.593</td>\n",
       "      <td>69.1</td>\n",
       "      <td>2.4786</td>\n",
       "      <td>1</td>\n",
       "      <td>273.0</td>\n",
       "      <td>21.0</td>\n",
       "      <td>391.99</td>\n",
       "      <td>9.67</td>\n",
       "      <td>22.4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>502</th>\n",
       "      <td>0.04527</td>\n",
       "      <td>0.0</td>\n",
       "      <td>11.93</td>\n",
       "      <td>0</td>\n",
       "      <td>0.573</td>\n",
       "      <td>6.120</td>\n",
       "      <td>76.7</td>\n",
       "      <td>2.2875</td>\n",
       "      <td>1</td>\n",
       "      <td>273.0</td>\n",
       "      <td>21.0</td>\n",
       "      <td>396.90</td>\n",
       "      <td>9.08</td>\n",
       "      <td>20.6</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>503</th>\n",
       "      <td>0.06076</td>\n",
       "      <td>0.0</td>\n",
       "      <td>11.93</td>\n",
       "      <td>0</td>\n",
       "      <td>0.573</td>\n",
       "      <td>6.976</td>\n",
       "      <td>91.0</td>\n",
       "      <td>2.1675</td>\n",
       "      <td>1</td>\n",
       "      <td>273.0</td>\n",
       "      <td>21.0</td>\n",
       "      <td>396.90</td>\n",
       "      <td>5.64</td>\n",
       "      <td>23.9</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>504</th>\n",
       "      <td>0.10959</td>\n",
       "      <td>0.0</td>\n",
       "      <td>11.93</td>\n",
       "      <td>0</td>\n",
       "      <td>0.573</td>\n",
       "      <td>6.794</td>\n",
       "      <td>89.3</td>\n",
       "      <td>2.3889</td>\n",
       "      <td>1</td>\n",
       "      <td>273.0</td>\n",
       "      <td>21.0</td>\n",
       "      <td>393.45</td>\n",
       "      <td>6.48</td>\n",
       "      <td>22.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>505</th>\n",
       "      <td>0.04741</td>\n",
       "      <td>0.0</td>\n",
       "      <td>11.93</td>\n",
       "      <td>0</td>\n",
       "      <td>0.573</td>\n",
       "      <td>6.030</td>\n",
       "      <td>80.8</td>\n",
       "      <td>2.5050</td>\n",
       "      <td>1</td>\n",
       "      <td>273.0</td>\n",
       "      <td>21.0</td>\n",
       "      <td>396.90</td>\n",
       "      <td>7.88</td>\n",
       "      <td>11.9</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "         CRIM   ZN  INDUS  CHAS    NOX     RM   AGE     DIS  RAD    TAX  PRTATIO       B  LSTAT  MEDV\n",
       "476   4.87141  0.0  18.10     0  0.614  6.484  93.6  2.3053   24  666.0     20.2  396.21  18.68  16.7\n",
       "477  15.02340  0.0  18.10     0  0.614  5.304  97.3  2.1007   24  666.0     20.2  349.48  24.91  12.0\n",
       "478  10.23300  0.0  18.10     0  0.614  6.185  96.7  2.1705   24  666.0     20.2  379.70  18.03  14.6\n",
       "479  14.33370  0.0  18.10     0  0.614  6.229  88.0  1.9512   24  666.0     20.2  383.32  13.11  21.4\n",
       "480   5.82401  0.0  18.10     0  0.532  6.242  64.7  3.4242   24  666.0     20.2  396.90  10.74  23.0\n",
       "481   5.70818  0.0  18.10     0  0.532  6.750  74.9  3.3317   24  666.0     20.2  393.07   7.74  23.7\n",
       "482   5.73116  0.0  18.10     0  0.532  7.061  77.0  3.4106   24  666.0     20.2  395.28   7.01  25.0\n",
       "483   2.81838  0.0  18.10     0  0.532  5.762  40.3  4.0983   24  666.0     20.2  392.92  10.42  21.8\n",
       "484   2.37857  0.0  18.10     0  0.583  5.871  41.9  3.7240   24  666.0     20.2  370.73  13.34  20.6\n",
       "485   3.67367  0.0  18.10     0  0.583  6.312  51.9  3.9917   24  666.0     20.2  388.62  10.58  21.2\n",
       "486   5.69175  0.0  18.10     0  0.583  6.114  79.8  3.5459   24  666.0     20.2  392.68  14.98  19.1\n",
       "487   4.83567  0.0  18.10     0  0.583  5.905  53.2  3.1523   24  666.0     20.2  388.22  11.45  20.6\n",
       "488   0.15086  0.0  27.74     0  0.609  5.454  92.7  1.8209    4  711.0     20.1  395.09  18.06  15.2\n",
       "489   0.18337  0.0  27.74     0  0.609  5.414  98.3  1.7554    4  711.0     20.1  344.05  23.97   7.0\n",
       "490   0.20746  0.0  27.74     0  0.609  5.093  98.0  1.8226    4  711.0     20.1  318.43  29.68   8.1\n",
       "491   0.10574  0.0  27.74     0  0.609  5.983  98.8  1.8681    4  711.0     20.1  390.11  18.07  13.6\n",
       "492   0.11132  0.0  27.74     0  0.609  5.983  83.5  2.1099    4  711.0     20.1  396.90  13.35  20.1\n",
       "493   0.17331  0.0   9.69     0  0.585  5.707  54.0  2.3817    6  391.0     19.2  396.90  12.01  21.8\n",
       "494   0.27957  0.0   9.69     0  0.585  5.926  42.6  2.3817    6  391.0     19.2  396.90  13.59  24.5\n",
       "495   0.17899  0.0   9.69     0  0.585  5.670  28.8  2.7986    6  391.0     19.2  393.29  17.60  23.1\n",
       "496   0.28960  0.0   9.69     0  0.585  5.390  72.9  2.7986    6  391.0     19.2  396.90  21.14  19.7\n",
       "497   0.26838  0.0   9.69     0  0.585  5.794  70.6  2.8927    6  391.0     19.2  396.90  14.10  18.3\n",
       "498   0.23912  0.0   9.69     0  0.585  6.019  65.3  2.4091    6  391.0     19.2  396.90  12.92  21.2\n",
       "499   0.17783  0.0   9.69     0  0.585  5.569  73.5  2.3999    6  391.0     19.2  395.77  15.10  17.5\n",
       "500   0.22438  0.0   9.69     0  0.585  6.027  79.7  2.4982    6  391.0     19.2  396.90  14.33  16.8\n",
       "501   0.06263  0.0  11.93     0  0.573  6.593  69.1  2.4786    1  273.0     21.0  391.99   9.67  22.4\n",
       "502   0.04527  0.0  11.93     0  0.573  6.120  76.7  2.2875    1  273.0     21.0  396.90   9.08  20.6\n",
       "503   0.06076  0.0  11.93     0  0.573  6.976  91.0  2.1675    1  273.0     21.0  396.90   5.64  23.9\n",
       "504   0.10959  0.0  11.93     0  0.573  6.794  89.3  2.3889    1  273.0     21.0  393.45   6.48  22.0\n",
       "505   0.04741  0.0  11.93     0  0.573  6.030  80.8  2.5050    1  273.0     21.0  396.90   7.88  11.9"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pd.set_option('display.width', 120)\n",
    "df.tail(30)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "CRIM       0\n",
       "ZN         0\n",
       "INDUS      0\n",
       "CHAS       0\n",
       "NOX        0\n",
       "RM         0\n",
       "AGE        0\n",
       "DIS        0\n",
       "RAD        0\n",
       "TAX        0\n",
       "PRTATIO    0\n",
       "B          0\n",
       "LSTAT      0\n",
       "MEDV       0\n",
       "dtype: int64"
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.isnull().sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style>\n",
       "    .dataframe thead tr:only-child th {\n",
       "        text-align: right;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\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>PRTATIO</th>\n",
       "      <th>B</th>\n",
       "      <th>LSTAT</th>\n",
       "      <th>MEDV</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>CRIM</th>\n",
       "      <td>1.00</td>\n",
       "      <td>-0.20</td>\n",
       "      <td>0.41</td>\n",
       "      <td>-5.59e-02</td>\n",
       "      <td>0.42</td>\n",
       "      <td>-0.22</td>\n",
       "      <td>0.35</td>\n",
       "      <td>-0.38</td>\n",
       "      <td>6.26e-01</td>\n",
       "      <td>0.58</td>\n",
       "      <td>0.29</td>\n",
       "      <td>-0.39</td>\n",
       "      <td>0.46</td>\n",
       "      <td>-0.39</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>ZN</th>\n",
       "      <td>-0.20</td>\n",
       "      <td>1.00</td>\n",
       "      <td>-0.53</td>\n",
       "      <td>-4.27e-02</td>\n",
       "      <td>-0.52</td>\n",
       "      <td>0.31</td>\n",
       "      <td>-0.57</td>\n",
       "      <td>0.66</td>\n",
       "      <td>-3.12e-01</td>\n",
       "      <td>-0.31</td>\n",
       "      <td>-0.39</td>\n",
       "      <td>0.18</td>\n",
       "      <td>-0.41</td>\n",
       "      <td>0.36</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>INDUS</th>\n",
       "      <td>0.41</td>\n",
       "      <td>-0.53</td>\n",
       "      <td>1.00</td>\n",
       "      <td>6.29e-02</td>\n",
       "      <td>0.76</td>\n",
       "      <td>-0.39</td>\n",
       "      <td>0.64</td>\n",
       "      <td>-0.71</td>\n",
       "      <td>5.95e-01</td>\n",
       "      <td>0.72</td>\n",
       "      <td>0.38</td>\n",
       "      <td>-0.36</td>\n",
       "      <td>0.60</td>\n",
       "      <td>-0.48</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>CHAS</th>\n",
       "      <td>-0.06</td>\n",
       "      <td>-0.04</td>\n",
       "      <td>0.06</td>\n",
       "      <td>1.00e+00</td>\n",
       "      <td>0.09</td>\n",
       "      <td>0.09</td>\n",
       "      <td>0.09</td>\n",
       "      <td>-0.10</td>\n",
       "      <td>-7.37e-03</td>\n",
       "      <td>-0.04</td>\n",
       "      <td>-0.12</td>\n",
       "      <td>0.05</td>\n",
       "      <td>-0.05</td>\n",
       "      <td>0.18</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>NOX</th>\n",
       "      <td>0.42</td>\n",
       "      <td>-0.52</td>\n",
       "      <td>0.76</td>\n",
       "      <td>9.12e-02</td>\n",
       "      <td>1.00</td>\n",
       "      <td>-0.30</td>\n",
       "      <td>0.73</td>\n",
       "      <td>-0.77</td>\n",
       "      <td>6.11e-01</td>\n",
       "      <td>0.67</td>\n",
       "      <td>0.19</td>\n",
       "      <td>-0.38</td>\n",
       "      <td>0.59</td>\n",
       "      <td>-0.43</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>RM</th>\n",
       "      <td>-0.22</td>\n",
       "      <td>0.31</td>\n",
       "      <td>-0.39</td>\n",
       "      <td>9.13e-02</td>\n",
       "      <td>-0.30</td>\n",
       "      <td>1.00</td>\n",
       "      <td>-0.24</td>\n",
       "      <td>0.21</td>\n",
       "      <td>-2.10e-01</td>\n",
       "      <td>-0.29</td>\n",
       "      <td>-0.36</td>\n",
       "      <td>0.13</td>\n",
       "      <td>-0.61</td>\n",
       "      <td>0.70</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>AGE</th>\n",
       "      <td>0.35</td>\n",
       "      <td>-0.57</td>\n",
       "      <td>0.64</td>\n",
       "      <td>8.65e-02</td>\n",
       "      <td>0.73</td>\n",
       "      <td>-0.24</td>\n",
       "      <td>1.00</td>\n",
       "      <td>-0.75</td>\n",
       "      <td>4.56e-01</td>\n",
       "      <td>0.51</td>\n",
       "      <td>0.26</td>\n",
       "      <td>-0.27</td>\n",
       "      <td>0.60</td>\n",
       "      <td>-0.38</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>DIS</th>\n",
       "      <td>-0.38</td>\n",
       "      <td>0.66</td>\n",
       "      <td>-0.71</td>\n",
       "      <td>-9.92e-02</td>\n",
       "      <td>-0.77</td>\n",
       "      <td>0.21</td>\n",
       "      <td>-0.75</td>\n",
       "      <td>1.00</td>\n",
       "      <td>-4.95e-01</td>\n",
       "      <td>-0.53</td>\n",
       "      <td>-0.23</td>\n",
       "      <td>0.29</td>\n",
       "      <td>-0.50</td>\n",
       "      <td>0.25</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>RAD</th>\n",
       "      <td>0.63</td>\n",
       "      <td>-0.31</td>\n",
       "      <td>0.60</td>\n",
       "      <td>-7.37e-03</td>\n",
       "      <td>0.61</td>\n",
       "      <td>-0.21</td>\n",
       "      <td>0.46</td>\n",
       "      <td>-0.49</td>\n",
       "      <td>1.00e+00</td>\n",
       "      <td>0.91</td>\n",
       "      <td>0.46</td>\n",
       "      <td>-0.44</td>\n",
       "      <td>0.49</td>\n",
       "      <td>-0.38</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>TAX</th>\n",
       "      <td>0.58</td>\n",
       "      <td>-0.31</td>\n",
       "      <td>0.72</td>\n",
       "      <td>-3.56e-02</td>\n",
       "      <td>0.67</td>\n",
       "      <td>-0.29</td>\n",
       "      <td>0.51</td>\n",
       "      <td>-0.53</td>\n",
       "      <td>9.10e-01</td>\n",
       "      <td>1.00</td>\n",
       "      <td>0.46</td>\n",
       "      <td>-0.44</td>\n",
       "      <td>0.54</td>\n",
       "      <td>-0.47</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>PRTATIO</th>\n",
       "      <td>0.29</td>\n",
       "      <td>-0.39</td>\n",
       "      <td>0.38</td>\n",
       "      <td>-1.22e-01</td>\n",
       "      <td>0.19</td>\n",
       "      <td>-0.36</td>\n",
       "      <td>0.26</td>\n",
       "      <td>-0.23</td>\n",
       "      <td>4.65e-01</td>\n",
       "      <td>0.46</td>\n",
       "      <td>1.00</td>\n",
       "      <td>-0.18</td>\n",
       "      <td>0.37</td>\n",
       "      <td>-0.51</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>B</th>\n",
       "      <td>-0.39</td>\n",
       "      <td>0.18</td>\n",
       "      <td>-0.36</td>\n",
       "      <td>4.88e-02</td>\n",
       "      <td>-0.38</td>\n",
       "      <td>0.13</td>\n",
       "      <td>-0.27</td>\n",
       "      <td>0.29</td>\n",
       "      <td>-4.44e-01</td>\n",
       "      <td>-0.44</td>\n",
       "      <td>-0.18</td>\n",
       "      <td>1.00</td>\n",
       "      <td>-0.37</td>\n",
       "      <td>0.33</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>LSTAT</th>\n",
       "      <td>0.46</td>\n",
       "      <td>-0.41</td>\n",
       "      <td>0.60</td>\n",
       "      <td>-5.39e-02</td>\n",
       "      <td>0.59</td>\n",
       "      <td>-0.61</td>\n",
       "      <td>0.60</td>\n",
       "      <td>-0.50</td>\n",
       "      <td>4.89e-01</td>\n",
       "      <td>0.54</td>\n",
       "      <td>0.37</td>\n",
       "      <td>-0.37</td>\n",
       "      <td>1.00</td>\n",
       "      <td>-0.74</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>MEDV</th>\n",
       "      <td>-0.39</td>\n",
       "      <td>0.36</td>\n",
       "      <td>-0.48</td>\n",
       "      <td>1.75e-01</td>\n",
       "      <td>-0.43</td>\n",
       "      <td>0.70</td>\n",
       "      <td>-0.38</td>\n",
       "      <td>0.25</td>\n",
       "      <td>-3.82e-01</td>\n",
       "      <td>-0.47</td>\n",
       "      <td>-0.51</td>\n",
       "      <td>0.33</td>\n",
       "      <td>-0.74</td>\n",
       "      <td>1.00</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "         CRIM    ZN  INDUS      CHAS   NOX    RM   AGE   DIS       RAD   TAX  PRTATIO     B  LSTAT  MEDV\n",
       "CRIM     1.00 -0.20   0.41 -5.59e-02  0.42 -0.22  0.35 -0.38  6.26e-01  0.58     0.29 -0.39   0.46 -0.39\n",
       "ZN      -0.20  1.00  -0.53 -4.27e-02 -0.52  0.31 -0.57  0.66 -3.12e-01 -0.31    -0.39  0.18  -0.41  0.36\n",
       "INDUS    0.41 -0.53   1.00  6.29e-02  0.76 -0.39  0.64 -0.71  5.95e-01  0.72     0.38 -0.36   0.60 -0.48\n",
       "CHAS    -0.06 -0.04   0.06  1.00e+00  0.09  0.09  0.09 -0.10 -7.37e-03 -0.04    -0.12  0.05  -0.05  0.18\n",
       "NOX      0.42 -0.52   0.76  9.12e-02  1.00 -0.30  0.73 -0.77  6.11e-01  0.67     0.19 -0.38   0.59 -0.43\n",
       "RM      -0.22  0.31  -0.39  9.13e-02 -0.30  1.00 -0.24  0.21 -2.10e-01 -0.29    -0.36  0.13  -0.61  0.70\n",
       "AGE      0.35 -0.57   0.64  8.65e-02  0.73 -0.24  1.00 -0.75  4.56e-01  0.51     0.26 -0.27   0.60 -0.38\n",
       "DIS     -0.38  0.66  -0.71 -9.92e-02 -0.77  0.21 -0.75  1.00 -4.95e-01 -0.53    -0.23  0.29  -0.50  0.25\n",
       "RAD      0.63 -0.31   0.60 -7.37e-03  0.61 -0.21  0.46 -0.49  1.00e+00  0.91     0.46 -0.44   0.49 -0.38\n",
       "TAX      0.58 -0.31   0.72 -3.56e-02  0.67 -0.29  0.51 -0.53  9.10e-01  1.00     0.46 -0.44   0.54 -0.47\n",
       "PRTATIO  0.29 -0.39   0.38 -1.22e-01  0.19 -0.36  0.26 -0.23  4.65e-01  0.46     1.00 -0.18   0.37 -0.51\n",
       "B       -0.39  0.18  -0.36  4.88e-02 -0.38  0.13 -0.27  0.29 -4.44e-01 -0.44    -0.18  1.00  -0.37  0.33\n",
       "LSTAT    0.46 -0.41   0.60 -5.39e-02  0.59 -0.61  0.60 -0.50  4.89e-01  0.54     0.37 -0.37   1.00 -0.74\n",
       "MEDV    -0.39  0.36  -0.48  1.75e-01 -0.43  0.70 -0.38  0.25 -3.82e-01 -0.47    -0.51  0.33  -0.74  1.00"
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "## correlation\n",
    "pd.set_option('precision', 2)\n",
    "df.corr(method = 'pearson')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAWkAAAD/CAYAAAAzMyekAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\njGwAAAAASUVORK5CYII=\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x7f0798cd3490>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "df.hist(sharex=False, sharey=False, xlabelsize=1, ylabelsize=1)\n",
    "pyplot.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAXcAAADzCAYAAAB9llaEAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nwV0+H1UAAAAASUVORK5CYII=\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x7f0798c8a850>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "df.plot(kind='density', subplots=True, layout=(4,4), sharex=False, fontsize=1)\n",
    "pyplot.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAsMAAAKuCAYAAABE5hHGAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nrkJggg==\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x7fd644951fd0>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "df.plot(kind='box', subplots=True, layout=(4,4), sharex=False,  sharey=False, fontsize=8, figsize=(12,12))\n",
    "pyplot.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAUkAAAD8CAYAAAD6+lbaAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x7fd617595150>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "fig = pyplot.figure()\n",
    "ax = fig.add_subplot(111)\n",
    "cax = ax.matshow(df.corr())\n",
    "fig.colorbar(cax)\n",
    "ax.set_xticklabels(names)\n",
    "ax.set_yticklabels(names)\n",
    "pyplot.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(506,)\n",
      "(506, 13)\n"
     ]
    }
   ],
   "source": [
    "y = df[names[-1]]\n",
    "X = df[names[:-1]]\n",
    "print y.shape\n",
    "print X.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "from sklearn.model_selection import train_test_split, KFold, cross_val_score, GridSearchCV"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "X_train, X_test, y_train, y_test = train_test_split( X, y, test_size=0.2, random_state=7)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "num_folds = 10\n",
    "seed = 7\n",
    "scoring = 'neg_mean_squared_error'"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "from sklearn.linear_model import LinearRegression\n",
    "\n",
    "from sklearn.linear_model import Lasso\n",
    "\n",
    "from sklearn.linear_model import ElasticNet\n",
    "\n",
    "from sklearn.tree import DecisionTreeRegressor\n",
    "\n",
    "from sklearn.neighbors import KNeighborsRegressor\n",
    "\n",
    "from sklearn.svm import SVR\n",
    "\n",
    "from sklearn.pipeline import Pipeline\n",
    "\n",
    "from sklearn.ensemble import RandomForestRegressor\n",
    "\n",
    "from sklearn.ensemble import GradientBoostingRegressor\n",
    "\n",
    "from sklearn.ensemble import ExtraTreesRegressor\n",
    "\n",
    "from sklearn.ensemble import AdaBoostRegressor\n",
    "\n",
    "from sklearn.metrics import mean_squared_error"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "models = {}\n",
    "\n",
    "models['LR'] = LinearRegression()\n",
    "\n",
    "models['LASSO'] = Lasso()\n",
    "\n",
    "models['EN'] = ElasticNet()\n",
    "\n",
    "models['KNN']  = KNeighborsRegressor()\n",
    "\n",
    "models['CART'] = DecisionTreeRegressor()\n",
    "\n",
    "models['SVM'] = SVR()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "KNN: -41.896488 (13.901688)\n",
      "SVM: -85.518342 (31.994798)\n",
      "CART: -27.830154 (11.994918)\n",
      "EN: -27.502259 (12.305022)\n",
      "LR: -21.379856 (9.414264)\n",
      "LASSO: -26.423561 (11.651110)\n"
     ]
    }
   ],
   "source": [
    "results = {}\n",
    "\n",
    "for key in models:\n",
    "\n",
    "    kfold = KFold(n_splits=num_folds, random_state=seed)\n",
    "\n",
    "    cv_result = cross_val_score(models[key], X_train, y_train, cv=kfold, scoring=scoring)\n",
    "\n",
    "    results[key] = cv_result\n",
    "\n",
    "    print('%s: %f (%f)' % (key, cv_result.mean(), cv_result.std()))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYMAAAD8CAYAAACVZ8iyAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nSUVORK5CYII=\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x7fd60b818890>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "fig = pyplot.figure()\n",
    "ax = fig.add_subplot(111)\n",
    "ax.boxplot(results.values())\n",
    "ax.set_xticklabels(results.keys())\n",
    "pyplot.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 39,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "from sklearn.preprocessing import StandardScaler"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "ScalerCART: -24.623580 (13.503302)\n",
      "ScalerSVM: -29.633086 (17.009186)\n",
      "ScalerKNN: -20.107620 (12.376949)\n",
      "ScalerLASSO: -26.607314 (8.978761)\n",
      "ScalerEN: -27.932372 (10.587490)\n",
      "ScalerLR: -21.379856 (9.414264)\n"
     ]
    }
   ],
   "source": [
    "pipelines = {}\n",
    "pipelines['ScalerLR'] = Pipeline([('Scaler', StandardScaler()), ('LR', LinearRegression())])\n",
    "\n",
    "pipelines['ScalerLASSO'] = Pipeline([('Scaler', StandardScaler()), ('LASSO', Lasso())])\n",
    "\n",
    "pipelines['ScalerEN'] = Pipeline([('Scaler', StandardScaler()), ('EN', ElasticNet())])\n",
    "\n",
    "pipelines['ScalerKNN'] = Pipeline([('Scaler', StandardScaler()), ('KNN', KNeighborsRegressor())])\n",
    "\n",
    "pipelines['ScalerCART'] = Pipeline([('Scaler', StandardScaler()), ('CART', DecisionTreeRegressor())])\n",
    "\n",
    "pipelines['ScalerSVM'] = Pipeline([('Scaler', StandardScaler()), ('SVM', SVR())])\n",
    "\n",
    "results = {}\n",
    "\n",
    "for key in pipelines:\n",
    "\n",
    "    kfold = KFold(n_splits=num_folds, random_state=seed)\n",
    "\n",
    "    cv_result = cross_val_score(pipelines[key], X_train, y_train, cv=kfold, scoring=scoring)\n",
    "\n",
    "    results[key] = cv_result\n",
    "\n",
    "    print('%s: %f (%f)' % (key, cv_result.mean(), cv_result.std()))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAXwAAAD8CAYAAAB0IB+mAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n1BL/HwR1BDGD7iLWAAAAAElFTkSuQmCC\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x7fd60b95b790>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "fig = pyplot.figure()\n",
    "ax = fig.add_subplot(111)\n",
    "ax.boxplot(results.values())\n",
    "ax.set_xticklabels(results.keys())\n",
    "pyplot.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 43,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "s_k = Pipeline([('Scaler', StandardScaler()), ('KNN', KNeighborsRegressor())])\n",
    "\n",
    "param_grid = {'KNN__n_neighbors':  [1, 3, 5, 7, 9, 11, 13, 15, 17, 19, 21]}\n",
    "\n",
    "kfold = KFold(n_splits=num_folds, random_state=seed)\n",
    "\n",
    "grid = GridSearchCV(estimator=s_k, param_grid=param_grid, cv=kfold, scoring=scoring)\n",
    "grid_result = grid.fit(X=X_train, y=y_train)\n",
    "\n",
    "print('最优：%s 使用%s' % (grid_result.best_score_, grid_result.best_params_))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 53,
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0.0 1\n",
      "-8.72121935976 3\n",
      "-12.7354948482 5\n",
      "-15.7113632473 7\n",
      "-16.7747066501 9\n",
      "-17.8059637546 11\n",
      "-18.5498163019 13\n",
      "-19.2884405979 15\n",
      "-20.2389037149 17\n",
      "-21.2455064052 19\n",
      "-22.0803859781 21\n"
     ]
    }
   ],
   "source": [
    "res= zip(grid_result.cv_results_['mean_train_score'], grid_result.cv_results_['param_KNN__n_neighbors'])\n",
    "for a,b in res:\n",
    "    print a, b"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 54,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "from sklearn.ensemble import RandomForestRegressor\n",
    "\n",
    "from sklearn.ensemble import GradientBoostingRegressor\n",
    "\n",
    "from sklearn.ensemble import ExtraTreesRegressor\n",
    "\n",
    "from sklearn.ensemble import AdaBoostRegressor\n",
    "\n",
    "from sklearn.metrics import mean_squared_error"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 56,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "ScaledAB-LR: -23.780579 (9.029614)\n",
      "ScaledAB: -15.283989 (6.713950)\n",
      "ScaledAB-KNN: -16.446338 (10.290478)\n",
      "ScaledETR: -10.296758 (5.517486)\n",
      "ScaledRFR: -13.708249 (6.847397)\n",
      "ScaledGBR: -10.379358 (4.633832)\n"
     ]
    }
   ],
   "source": [
    "ensembles = {}\n",
    "\n",
    "ensembles['ScaledAB'] = Pipeline([('Scaler',StandardScaler()), ('AB', AdaBoostRegressor())])\n",
    "\n",
    "ensembles['ScaledAB-KNN'] = Pipeline([('Scaler', StandardScaler()), ('ABKNN', AdaBoostRegressor(base_estimator= KNeighborsRegressor(n_neighbors=3)))])\n",
    "\n",
    "ensembles['ScaledAB-LR'] = Pipeline([('Scaler', StandardScaler()), ('ABLR', AdaBoostRegressor(LinearRegression()))])\n",
    "\n",
    "ensembles['ScaledRFR'] = Pipeline([('Scaler', StandardScaler()), ('RFR', RandomForestRegressor())])\n",
    "\n",
    "ensembles['ScaledETR'] = Pipeline([('Scaler', StandardScaler()), ('ETR', ExtraTreesRegressor())])\n",
    "\n",
    "ensembles['ScaledGBR'] = Pipeline([('Scaler', StandardScaler()), ('RBR', GradientBoostingRegressor())])\n",
    "\n",
    "\n",
    "\n",
    "results = {}\n",
    "\n",
    "for key in ensembles:\n",
    "\n",
    "    kfold = KFold(n_splits=num_folds, random_state=seed)\n",
    "\n",
    "    cv_result = cross_val_score(ensembles[key], X_train, y_train, cv=kfold, scoring=scoring)\n",
    "\n",
    "    results[key] = cv_result\n",
    "\n",
    "    print('%s: %f (%f)' % (key, cv_result.mean(), cv_result.std()))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 57,
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAXwAAAD8CAYAAAB0IB+mAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nB3wzs5z4f6OBRnafa3bKAAAAAElFTkSuQmCC\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x7fd6179d4690>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "fig = pyplot.figure()\n",
    "ax = fig.add_subplot(111)\n",
    "ax.boxplot(results.values())\n",
    "ax.set_xticklabels(results.keys())\n",
    "pyplot.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 58,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "最优：-9.28708798401 使用{'GBR__n_estimators': 500}\n"
     ]
    }
   ],
   "source": [
    "s_gbr = Pipeline([('Scaler', StandardScaler()), ('GBR', GradientBoostingRegressor())])\n",
    "\n",
    "param_grid = {'GBR__n_estimators': [10, 50, 100, 200, 300, 400, 500, 600, 700, 800, 900]}\n",
    "\n",
    "kfold = KFold(n_splits=num_folds, random_state=seed)\n",
    "\n",
    "grid = GridSearchCV(estimator=s_gbr, param_grid=param_grid, cv=kfold, scoring=scoring)\n",
    "grid_result = grid.fit(X=X_train, y=y_train)\n",
    "\n",
    "print('最优：%s 使用%s' % (grid_result.best_score_, grid_result.best_params_))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "s_gbr = Pipeline([('Scaler', StandardScaler()), ('GBR', GradientBoostingRegressor())])\n",
    "s_gbr.set_params(GBR__n_estimators=500).fit(X=X_train, y=y_train)\n",
    "predictions = s_gbr.predict(X_test)\n",
    "\n",
    "print mean_squared_error(y_test, )"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 2",
   "language": "python",
   "name": "python2"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 2
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython2",
   "version": "2.7.13"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}