{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": false
   },
   "source": [
    "# Визуальный анализ данных"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": false
   },
   "source": [
    "Подключаем необходимые библиотеки."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
   ],
   "source": [
    "import numpy as np\n",
    "import scipy as sp\n",
    "import pandas as pd\n",
    "import matplotlib.pyplot as plt\n",
    "%matplotlib inline\n",
    "import seaborn as sns"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": false
   },
   "source": [
    "Считываем датасет."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
   ],
   "source": [
    "data = pd.read_csv(\"telecom-churn.csv\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": false
   },
   "source": [
    "Проверяем, всё ли правильно считалось и \"распарсилось\"."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "collapsed": false
   },
   "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>state</th>\n",
       "      <th>account length</th>\n",
       "      <th>area code</th>\n",
       "      <th>phone number</th>\n",
       "      <th>international plan</th>\n",
       "      <th>voice mail plan</th>\n",
       "      <th>number vmail messages</th>\n",
       "      <th>total day minutes</th>\n",
       "      <th>total day calls</th>\n",
       "      <th>total day charge</th>\n",
       "      <th>...</th>\n",
       "      <th>total eve calls</th>\n",
       "      <th>total eve charge</th>\n",
       "      <th>total night minutes</th>\n",
       "      <th>total night calls</th>\n",
       "      <th>total night charge</th>\n",
       "      <th>total intl minutes</th>\n",
       "      <th>total intl calls</th>\n",
       "      <th>total intl charge</th>\n",
       "      <th>customer service calls</th>\n",
       "      <th>churn</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>KS</td>\n",
       "      <td>128</td>\n",
       "      <td>415</td>\n",
       "      <td>382-4657</td>\n",
       "      <td>no</td>\n",
       "      <td>yes</td>\n",
       "      <td>25</td>\n",
       "      <td>265.1</td>\n",
       "      <td>110</td>\n",
       "      <td>45.07</td>\n",
       "      <td>...</td>\n",
       "      <td>99</td>\n",
       "      <td>16.78</td>\n",
       "      <td>244.7</td>\n",
       "      <td>91</td>\n",
       "      <td>11.01</td>\n",
       "      <td>10.0</td>\n",
       "      <td>3</td>\n",
       "      <td>2.70</td>\n",
       "      <td>1</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>OH</td>\n",
       "      <td>107</td>\n",
       "      <td>415</td>\n",
       "      <td>371-7191</td>\n",
       "      <td>no</td>\n",
       "      <td>yes</td>\n",
       "      <td>26</td>\n",
       "      <td>161.6</td>\n",
       "      <td>123</td>\n",
       "      <td>27.47</td>\n",
       "      <td>...</td>\n",
       "      <td>103</td>\n",
       "      <td>16.62</td>\n",
       "      <td>254.4</td>\n",
       "      <td>103</td>\n",
       "      <td>11.45</td>\n",
       "      <td>13.7</td>\n",
       "      <td>3</td>\n",
       "      <td>3.70</td>\n",
       "      <td>1</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>NJ</td>\n",
       "      <td>137</td>\n",
       "      <td>415</td>\n",
       "      <td>358-1921</td>\n",
       "      <td>no</td>\n",
       "      <td>no</td>\n",
       "      <td>0</td>\n",
       "      <td>243.4</td>\n",
       "      <td>114</td>\n",
       "      <td>41.38</td>\n",
       "      <td>...</td>\n",
       "      <td>110</td>\n",
       "      <td>10.30</td>\n",
       "      <td>162.6</td>\n",
       "      <td>104</td>\n",
       "      <td>7.32</td>\n",
       "      <td>12.2</td>\n",
       "      <td>5</td>\n",
       "      <td>3.29</td>\n",
       "      <td>0</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>OH</td>\n",
       "      <td>84</td>\n",
       "      <td>408</td>\n",
       "      <td>375-9999</td>\n",
       "      <td>yes</td>\n",
       "      <td>no</td>\n",
       "      <td>0</td>\n",
       "      <td>299.4</td>\n",
       "      <td>71</td>\n",
       "      <td>50.90</td>\n",
       "      <td>...</td>\n",
       "      <td>88</td>\n",
       "      <td>5.26</td>\n",
       "      <td>196.9</td>\n",
       "      <td>89</td>\n",
       "      <td>8.86</td>\n",
       "      <td>6.6</td>\n",
       "      <td>7</td>\n",
       "      <td>1.78</td>\n",
       "      <td>2</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>OK</td>\n",
       "      <td>75</td>\n",
       "      <td>415</td>\n",
       "      <td>330-6626</td>\n",
       "      <td>yes</td>\n",
       "      <td>no</td>\n",
       "      <td>0</td>\n",
       "      <td>166.7</td>\n",
       "      <td>113</td>\n",
       "      <td>28.34</td>\n",
       "      <td>...</td>\n",
       "      <td>122</td>\n",
       "      <td>12.61</td>\n",
       "      <td>186.9</td>\n",
       "      <td>121</td>\n",
       "      <td>8.41</td>\n",
       "      <td>10.1</td>\n",
       "      <td>3</td>\n",
       "      <td>2.73</td>\n",
       "      <td>3</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 21 columns</p>\n",
       "</div>"
      ]
     },
     "execution_count": 3,
     "metadata": {
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": false
   },
   "source": [
    "Можно получить сводку и общее представление о типах данных."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 3333 entries, 0 to 3332\n",
      "Data columns (total 21 columns):\n",
      "state                     3333 non-null object\n",
      "account length            3333 non-null int64\n",
      "area code                 3333 non-null int64\n",
      "phone number              3333 non-null object\n",
      "international plan        3333 non-null object\n",
      "voice mail plan           3333 non-null object\n",
      "number vmail messages     3333 non-null int64\n",
      "total day minutes         3333 non-null float64\n",
      "total day calls           3333 non-null int64\n",
      "total day charge          3333 non-null float64\n",
      "total eve minutes         3333 non-null float64\n",
      "total eve calls           3333 non-null int64\n",
      "total eve charge          3333 non-null float64\n",
      "total night minutes       3333 non-null float64\n",
      "total night calls         3333 non-null int64\n",
      "total night charge        3333 non-null float64\n",
      "total intl minutes        3333 non-null float64\n",
      "total intl calls          3333 non-null int64\n",
      "total intl charge         3333 non-null float64\n",
      "customer service calls    3333 non-null int64\n",
      "churn                     3333 non-null bool\n",
      "dtypes: bool(1), float64(8), int64(8), object(4)\n",
      "memory usage: 524.1+ KB\n"
     ]
    }
   ],
   "source": [
    "data.info()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": false
   },
   "source": [
    "Целевая переменная: churn (лояльность абонента). Это категориальный (более конкретно &mdash; бинарный) признак. Попробуем узнать, как распределены его значения."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "False    2850\n",
       "True      483\n",
       "Name: churn, dtype: int64"
      ]
     },
     "execution_count": 5,
     "metadata": {
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data['churn'].value_counts()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": false
   },
   "source": [
    "Видим, что 2850 из 3333 абонентов &mdash; лояльные. А сколько это в процентах?.."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "False    0.855086\n",
       "True     0.144914\n",
       "Name: churn, dtype: float64"
      ]
     },
     "execution_count": 6,
     "metadata": {
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data['churn'].value_counts(normalize=True)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": false
   },
   "source": [
    "Визуализируем это."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "image/png": "eb58c1303680f70e0c840b8024b3cd7c2294f3a2"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "data['churn'].value_counts(normalize=True).plot(kind='bar', \n",
    "                                                title='Признак churn');"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": false
   },
   "source": [
    "Нам также может быть интересно, у скольких наших клиентов подключён роуминг."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "image/png": "1b30217f75cfba5c7c0f37dd809752b3e089062b"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "data['international plan'].value_counts(normalize=True).plot(kind='bar');"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": false
   },
   "source": [
    "А как обстоят дела у нелояльных пользователей (churn=1)?"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "image/png": "bf924362d8de0d0b916bc5413e923970540953ce"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "churn_users = data[data['churn'] == True]\n",
    "churn_users['international plan'].value_counts(normalize=True).plot(kind='bar');"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": false
   },
   "source": [
    "Видим, что процент клиентов с роумингом выше, чем в общей выборке. \n",
    "\n",
    "Можем предположить, что бинарные признаки **international plan** и **churn** коррелируют. Нарисуем теперь их вместе."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {
    "collapsed": false
   },
   "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>international plan</th>\n",
       "      <th>no</th>\n",
       "      <th>yes</th>\n",
       "      <th>All</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>churn</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>False</th>\n",
       "      <td>2664</td>\n",
       "      <td>186</td>\n",
       "      <td>2850</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>True</th>\n",
       "      <td>346</td>\n",
       "      <td>137</td>\n",
       "      <td>483</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>All</th>\n",
       "      <td>3010</td>\n",
       "      <td>323</td>\n",
       "      <td>3333</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ]
     },
     "execution_count": 19,
     "metadata": {
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pd.crosstab(data['churn'], data['international plan'], margins=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "image/png": "5739f5954f8d9545ddac940d39ad0f001ea9422f"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "sns.countplot(x='international plan', hue='churn', data=data);"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": false
   },
   "source": [
    "Большинство клиентов, у которых был подключён роуминг, от нас ушли!"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "international plan\n",
       "no     3010\n",
       "yes     323\n",
       "Name: churn, dtype: int64"
      ]
     },
     "execution_count": 25,
     "metadata": {
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data.groupby('international plan')['churn'].count()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": false
   },
   "source": [
    "Посмотрим на распределение признака **account length**."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "image/png": "52816f2fd37519b286aea91df17b0cdcad6892c3"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "sns.distplot(data['account length']);"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": false
   },
   "source": [
    "Похоже на нормальное распределение!"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": false
   },
   "source": [
    "Что можно сказать о связи между **account length** и лояльностью?"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "churn\n",
       "False    100.793684\n",
       "True     102.664596\n",
       "Name: account length, dtype: float64"
      ]
     },
     "execution_count": 28,
     "metadata": {
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data.groupby('churn')['account length'].mean()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "churn\n",
       "False    39.88235\n",
       "True     39.46782\n",
       "Name: account length, dtype: float64"
      ]
     },
     "execution_count": 29,
     "metadata": {
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data.groupby('churn')['account length'].std()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "churn\n",
       "False    100\n",
       "True     103\n",
       "Name: account length, dtype: int64"
      ]
     },
     "execution_count": 30,
     "metadata": {
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data.groupby('churn')['account length'].median()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": false
   },
   "source": [
    "На первый взгляд, никак не связаны."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "image/png": "963212841239ba8b9f8b019138180325d0ed8199"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "fig, ax = plt.subplots(1, 2, sharey=True)\n",
    "sns.distplot(data[data['churn'] == False]['account length'], \n",
    "             ax=ax[0]).set_title('Лояльные');\n",
    "sns.distplot(churn_users['account length'], \n",
    "             ax=ax[1]).set_title('Ушедшие');"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": false
   },
   "source": [
    "На второй взгляд тоже."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": false
   },
   "source": [
    "Теперь посмотрим, связаны ли длительности дневных и ночных звонков."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "image/png": "8fa7b65953d6716500a10aa52d0d816da03e9b9b"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "sns.regplot(data['total day minutes'], data['total night minutes']);"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": false
   },
   "source": [
    "А как насчёт количества звонков?"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "image/png": "7f444c1709be3b358ed668456f53846126753f2d"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "sns.regplot(data['total day calls'], data['total night calls']);"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": false
   },
   "source": [
    "Пока никакой связи не видно."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": false
   },
   "source": [
    "Построим корреляционную матрицу для числовых признаков."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 54,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
   ],
   "source": [
    "numeric_data = data.select_dtypes(['int64', 'float64'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 45,
   "metadata": {
    "collapsed": false
   },
   "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>account length</th>\n",
       "      <th>area code</th>\n",
       "      <th>number vmail messages</th>\n",
       "      <th>total day minutes</th>\n",
       "      <th>total day calls</th>\n",
       "      <th>total day charge</th>\n",
       "      <th>total eve minutes</th>\n",
       "      <th>total eve calls</th>\n",
       "      <th>total eve charge</th>\n",
       "      <th>total night minutes</th>\n",
       "      <th>total night calls</th>\n",
       "      <th>total night charge</th>\n",
       "      <th>total intl minutes</th>\n",
       "      <th>total intl calls</th>\n",
       "      <th>total intl charge</th>\n",
       "      <th>customer service calls</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>128</td>\n",
       "      <td>415</td>\n",
       "      <td>25</td>\n",
       "      <td>265.1</td>\n",
       "      <td>110</td>\n",
       "      <td>45.07</td>\n",
       "      <td>197.4</td>\n",
       "      <td>99</td>\n",
       "      <td>16.78</td>\n",
       "      <td>244.7</td>\n",
       "      <td>91</td>\n",
       "      <td>11.01</td>\n",
       "      <td>10.0</td>\n",
       "      <td>3</td>\n",
       "      <td>2.70</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>107</td>\n",
       "      <td>415</td>\n",
       "      <td>26</td>\n",
       "      <td>161.6</td>\n",
       "      <td>123</td>\n",
       "      <td>27.47</td>\n",
       "      <td>195.5</td>\n",
       "      <td>103</td>\n",
       "      <td>16.62</td>\n",
       "      <td>254.4</td>\n",
       "      <td>103</td>\n",
       "      <td>11.45</td>\n",
       "      <td>13.7</td>\n",
       "      <td>3</td>\n",
       "      <td>3.70</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>137</td>\n",
       "      <td>415</td>\n",
       "      <td>0</td>\n",
       "      <td>243.4</td>\n",
       "      <td>114</td>\n",
       "      <td>41.38</td>\n",
       "      <td>121.2</td>\n",
       "      <td>110</td>\n",
       "      <td>10.30</td>\n",
       "      <td>162.6</td>\n",
       "      <td>104</td>\n",
       "      <td>7.32</td>\n",
       "      <td>12.2</td>\n",
       "      <td>5</td>\n",
       "      <td>3.29</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>84</td>\n",
       "      <td>408</td>\n",
       "      <td>0</td>\n",
       "      <td>299.4</td>\n",
       "      <td>71</td>\n",
       "      <td>50.90</td>\n",
       "      <td>61.9</td>\n",
       "      <td>88</td>\n",
       "      <td>5.26</td>\n",
       "      <td>196.9</td>\n",
       "      <td>89</td>\n",
       "      <td>8.86</td>\n",
       "      <td>6.6</td>\n",
       "      <td>7</td>\n",
       "      <td>1.78</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>75</td>\n",
       "      <td>415</td>\n",
       "      <td>0</td>\n",
       "      <td>166.7</td>\n",
       "      <td>113</td>\n",
       "      <td>28.34</td>\n",
       "      <td>148.3</td>\n",
       "      <td>122</td>\n",
       "      <td>12.61</td>\n",
       "      <td>186.9</td>\n",
       "      <td>121</td>\n",
       "      <td>8.41</td>\n",
       "      <td>10.1</td>\n",
       "      <td>3</td>\n",
       "      <td>2.73</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ]
     },
     "execution_count": 45,
     "metadata": {
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "numeric_data.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 60,
   "metadata": {
    "collapsed": false
   },
   "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>account length</th>\n",
       "      <th>number vmail messages</th>\n",
       "      <th>total day minutes</th>\n",
       "      <th>total day calls</th>\n",
       "      <th>total day charge</th>\n",
       "      <th>total eve minutes</th>\n",
       "      <th>total eve calls</th>\n",
       "      <th>total eve charge</th>\n",
       "      <th>total night minutes</th>\n",
       "      <th>total night calls</th>\n",
       "      <th>total night charge</th>\n",
       "      <th>total intl minutes</th>\n",
       "      <th>total intl calls</th>\n",
       "      <th>total intl charge</th>\n",
       "      <th>customer service calls</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>account length</th>\n",
       "      <td>1.000000</td>\n",
       "      <td>-0.004628</td>\n",
       "      <td>0.006216</td>\n",
       "      <td>0.038470</td>\n",
       "      <td>0.006214</td>\n",
       "      <td>-0.006757</td>\n",
       "      <td>0.019260</td>\n",
       "      <td>-0.006745</td>\n",
       "      <td>-0.008955</td>\n",
       "      <td>-0.013176</td>\n",
       "      <td>-0.008960</td>\n",
       "      <td>0.009514</td>\n",
       "      <td>0.020661</td>\n",
       "      <td>0.009546</td>\n",
       "      <td>-0.003796</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>number vmail messages</th>\n",
       "      <td>-0.004628</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000778</td>\n",
       "      <td>-0.009548</td>\n",
       "      <td>0.000776</td>\n",
       "      <td>0.017562</td>\n",
       "      <td>-0.005864</td>\n",
       "      <td>0.017578</td>\n",
       "      <td>0.007681</td>\n",
       "      <td>0.007123</td>\n",
       "      <td>0.007663</td>\n",
       "      <td>0.002856</td>\n",
       "      <td>0.013957</td>\n",
       "      <td>0.002884</td>\n",
       "      <td>-0.013263</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>total day minutes</th>\n",
       "      <td>0.006216</td>\n",
       "      <td>0.000778</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.006750</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.007043</td>\n",
       "      <td>0.015769</td>\n",
       "      <td>0.007029</td>\n",
       "      <td>0.004323</td>\n",
       "      <td>0.022972</td>\n",
       "      <td>0.004300</td>\n",
       "      <td>-0.010155</td>\n",
       "      <td>0.008033</td>\n",
       "      <td>-0.010092</td>\n",
       "      <td>-0.013423</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>total day calls</th>\n",
       "      <td>0.038470</td>\n",
       "      <td>-0.009548</td>\n",
       "      <td>0.006750</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.006753</td>\n",
       "      <td>-0.021451</td>\n",
       "      <td>0.006462</td>\n",
       "      <td>-0.021449</td>\n",
       "      <td>0.022938</td>\n",
       "      <td>-0.019557</td>\n",
       "      <td>0.022927</td>\n",
       "      <td>0.021565</td>\n",
       "      <td>0.004574</td>\n",
       "      <td>0.021666</td>\n",
       "      <td>-0.018942</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>total day charge</th>\n",
       "      <td>0.006214</td>\n",
       "      <td>0.000776</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.006753</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.007050</td>\n",
       "      <td>0.015769</td>\n",
       "      <td>0.007036</td>\n",
       "      <td>0.004324</td>\n",
       "      <td>0.022972</td>\n",
       "      <td>0.004301</td>\n",
       "      <td>-0.010157</td>\n",
       "      <td>0.008032</td>\n",
       "      <td>-0.010094</td>\n",
       "      <td>-0.013427</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>total eve minutes</th>\n",
       "      <td>-0.006757</td>\n",
       "      <td>0.017562</td>\n",
       "      <td>0.007043</td>\n",
       "      <td>-0.021451</td>\n",
       "      <td>0.007050</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>-0.011430</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>-0.012584</td>\n",
       "      <td>0.007586</td>\n",
       "      <td>-0.012593</td>\n",
       "      <td>-0.011035</td>\n",
       "      <td>0.002541</td>\n",
       "      <td>-0.011067</td>\n",
       "      <td>-0.012985</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>total eve calls</th>\n",
       "      <td>0.019260</td>\n",
       "      <td>-0.005864</td>\n",
       "      <td>0.015769</td>\n",
       "      <td>0.006462</td>\n",
       "      <td>0.015769</td>\n",
       "      <td>-0.011430</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>-0.011423</td>\n",
       "      <td>-0.002093</td>\n",
       "      <td>0.007710</td>\n",
       "      <td>-0.002056</td>\n",
       "      <td>0.008703</td>\n",
       "      <td>0.017434</td>\n",
       "      <td>0.008674</td>\n",
       "      <td>0.002423</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>total eve charge</th>\n",
       "      <td>-0.006745</td>\n",
       "      <td>0.017578</td>\n",
       "      <td>0.007029</td>\n",
       "      <td>-0.021449</td>\n",
       "      <td>0.007036</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>-0.011423</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>-0.012592</td>\n",
       "      <td>0.007596</td>\n",
       "      <td>-0.012601</td>\n",
       "      <td>-0.011043</td>\n",
       "      <td>0.002541</td>\n",
       "      <td>-0.011074</td>\n",
       "      <td>-0.012987</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>total night minutes</th>\n",
       "      <td>-0.008955</td>\n",
       "      <td>0.007681</td>\n",
       "      <td>0.004323</td>\n",
       "      <td>0.022938</td>\n",
       "      <td>0.004324</td>\n",
       "      <td>-0.012584</td>\n",
       "      <td>-0.002093</td>\n",
       "      <td>-0.012592</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.011204</td>\n",
       "      <td>0.999999</td>\n",
       "      <td>-0.015207</td>\n",
       "      <td>-0.012353</td>\n",
       "      <td>-0.015180</td>\n",
       "      <td>-0.009288</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>total night calls</th>\n",
       "      <td>-0.013176</td>\n",
       "      <td>0.007123</td>\n",
       "      <td>0.022972</td>\n",
       "      <td>-0.019557</td>\n",
       "      <td>0.022972</td>\n",
       "      <td>0.007586</td>\n",
       "      <td>0.007710</td>\n",
       "      <td>0.007596</td>\n",
       "      <td>0.011204</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.011188</td>\n",
       "      <td>-0.013605</td>\n",
       "      <td>0.000305</td>\n",
       "      <td>-0.013630</td>\n",
       "      <td>-0.012802</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>total night charge</th>\n",
       "      <td>-0.008960</td>\n",
       "      <td>0.007663</td>\n",
       "      <td>0.004300</td>\n",
       "      <td>0.022927</td>\n",
       "      <td>0.004301</td>\n",
       "      <td>-0.012593</td>\n",
       "      <td>-0.002056</td>\n",
       "      <td>-0.012601</td>\n",
       "      <td>0.999999</td>\n",
       "      <td>0.011188</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>-0.015214</td>\n",
       "      <td>-0.012329</td>\n",
       "      <td>-0.015186</td>\n",
       "      <td>-0.009277</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>total intl minutes</th>\n",
       "      <td>0.009514</td>\n",
       "      <td>0.002856</td>\n",
       "      <td>-0.010155</td>\n",
       "      <td>0.021565</td>\n",
       "      <td>-0.010157</td>\n",
       "      <td>-0.011035</td>\n",
       "      <td>0.008703</td>\n",
       "      <td>-0.011043</td>\n",
       "      <td>-0.015207</td>\n",
       "      <td>-0.013605</td>\n",
       "      <td>-0.015214</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.032304</td>\n",
       "      <td>0.999993</td>\n",
       "      <td>-0.009640</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>total intl calls</th>\n",
       "      <td>0.020661</td>\n",
       "      <td>0.013957</td>\n",
       "      <td>0.008033</td>\n",
       "      <td>0.004574</td>\n",
       "      <td>0.008032</td>\n",
       "      <td>0.002541</td>\n",
       "      <td>0.017434</td>\n",
       "      <td>0.002541</td>\n",
       "      <td>-0.012353</td>\n",
       "      <td>0.000305</td>\n",
       "      <td>-0.012329</td>\n",
       "      <td>0.032304</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.032372</td>\n",
       "      <td>-0.017561</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>total intl charge</th>\n",
       "      <td>0.009546</td>\n",
       "      <td>0.002884</td>\n",
       "      <td>-0.010092</td>\n",
       "      <td>0.021666</td>\n",
       "      <td>-0.010094</td>\n",
       "      <td>-0.011067</td>\n",
       "      <td>0.008674</td>\n",
       "      <td>-0.011074</td>\n",
       "      <td>-0.015180</td>\n",
       "      <td>-0.013630</td>\n",
       "      <td>-0.015186</td>\n",
       "      <td>0.999993</td>\n",
       "      <td>0.032372</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>-0.009675</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>customer service calls</th>\n",
       "      <td>-0.003796</td>\n",
       "      <td>-0.013263</td>\n",
       "      <td>-0.013423</td>\n",
       "      <td>-0.018942</td>\n",
       "      <td>-0.013427</td>\n",
       "      <td>-0.012985</td>\n",
       "      <td>0.002423</td>\n",
       "      <td>-0.012987</td>\n",
       "      <td>-0.009288</td>\n",
       "      <td>-0.012802</td>\n",
       "      <td>-0.009277</td>\n",
       "      <td>-0.009640</td>\n",
       "      <td>-0.017561</td>\n",
       "      <td>-0.009675</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ]
     },
     "execution_count": 60,
     "metadata": {
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "corr_matrix = numeric_data.drop('area code', axis=1).corr()\n",
    "corr_matrix"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 62,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "image/png": "c6aa458fc6fdd72653818dc98b9a432ae6bd0cb6"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "sns.heatmap(corr_matrix);"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 58,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "image/png": "2601088f3e858ef8830a07e5b3e531d36c72eeb4"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "sns.pairplot(numeric_data[['total day minutes', \n",
    "                           'total day calls', \n",
    "                           'total day charge']]);"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 0,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
   ],
   "source": [
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (Ubuntu Linux)",
   "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": "3.6.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 0
}