{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Exploring Dataset"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "# import pandas\n",
    "import pandas as pd "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "# read a dataset \n",
    "df = pd.read_csv(\"../data/framingham.csv\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Head "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "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>male</th>\n",
       "      <th>age</th>\n",
       "      <th>education</th>\n",
       "      <th>currentSmoker</th>\n",
       "      <th>cigsPerDay</th>\n",
       "      <th>BPMeds</th>\n",
       "      <th>prevalentStroke</th>\n",
       "      <th>prevalentHyp</th>\n",
       "      <th>diabetes</th>\n",
       "      <th>totChol</th>\n",
       "      <th>sysBP</th>\n",
       "      <th>diaBP</th>\n",
       "      <th>BMI</th>\n",
       "      <th>heartRate</th>\n",
       "      <th>glucose</th>\n",
       "      <th>TenYearCHD</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>39</td>\n",
       "      <td>4.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>195.0</td>\n",
       "      <td>106.0</td>\n",
       "      <td>70.0</td>\n",
       "      <td>26.97</td>\n",
       "      <td>80.0</td>\n",
       "      <td>77.0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0</td>\n",
       "      <td>46</td>\n",
       "      <td>2.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>250.0</td>\n",
       "      <td>121.0</td>\n",
       "      <td>81.0</td>\n",
       "      <td>28.73</td>\n",
       "      <td>95.0</td>\n",
       "      <td>76.0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1</td>\n",
       "      <td>48</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1</td>\n",
       "      <td>20.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>245.0</td>\n",
       "      <td>127.5</td>\n",
       "      <td>80.0</td>\n",
       "      <td>25.34</td>\n",
       "      <td>75.0</td>\n",
       "      <td>70.0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0</td>\n",
       "      <td>61</td>\n",
       "      <td>3.0</td>\n",
       "      <td>1</td>\n",
       "      <td>30.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>225.0</td>\n",
       "      <td>150.0</td>\n",
       "      <td>95.0</td>\n",
       "      <td>28.58</td>\n",
       "      <td>65.0</td>\n",
       "      <td>103.0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0</td>\n",
       "      <td>46</td>\n",
       "      <td>3.0</td>\n",
       "      <td>1</td>\n",
       "      <td>23.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>285.0</td>\n",
       "      <td>130.0</td>\n",
       "      <td>84.0</td>\n",
       "      <td>23.10</td>\n",
       "      <td>85.0</td>\n",
       "      <td>85.0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   male  age  education  currentSmoker  cigsPerDay  BPMeds  prevalentStroke  \\\n",
       "0     1   39        4.0              0         0.0     0.0                0   \n",
       "1     0   46        2.0              0         0.0     0.0                0   \n",
       "2     1   48        1.0              1        20.0     0.0                0   \n",
       "3     0   61        3.0              1        30.0     0.0                0   \n",
       "4     0   46        3.0              1        23.0     0.0                0   \n",
       "\n",
       "   prevalentHyp  diabetes  totChol  sysBP  diaBP    BMI  heartRate  glucose  \\\n",
       "0             0         0    195.0  106.0   70.0  26.97       80.0     77.0   \n",
       "1             0         0    250.0  121.0   81.0  28.73       95.0     76.0   \n",
       "2             0         0    245.0  127.5   80.0  25.34       75.0     70.0   \n",
       "3             1         0    225.0  150.0   95.0  28.58       65.0    103.0   \n",
       "4             0         0    285.0  130.0   84.0  23.10       85.0     85.0   \n",
       "\n",
       "   TenYearCHD  \n",
       "0           0  \n",
       "1           0  \n",
       "2           0  \n",
       "3           1  \n",
       "4           0  "
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# head: by default shows first 5 rows \n",
    "df.head() "
   ]
  },
  {
   "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>male</th>\n",
       "      <th>age</th>\n",
       "      <th>education</th>\n",
       "      <th>currentSmoker</th>\n",
       "      <th>cigsPerDay</th>\n",
       "      <th>BPMeds</th>\n",
       "      <th>prevalentStroke</th>\n",
       "      <th>prevalentHyp</th>\n",
       "      <th>diabetes</th>\n",
       "      <th>totChol</th>\n",
       "      <th>sysBP</th>\n",
       "      <th>diaBP</th>\n",
       "      <th>BMI</th>\n",
       "      <th>heartRate</th>\n",
       "      <th>glucose</th>\n",
       "      <th>TenYearCHD</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>39</td>\n",
       "      <td>4.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>195.0</td>\n",
       "      <td>106.0</td>\n",
       "      <td>70.0</td>\n",
       "      <td>26.97</td>\n",
       "      <td>80.0</td>\n",
       "      <td>77.0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0</td>\n",
       "      <td>46</td>\n",
       "      <td>2.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>250.0</td>\n",
       "      <td>121.0</td>\n",
       "      <td>81.0</td>\n",
       "      <td>28.73</td>\n",
       "      <td>95.0</td>\n",
       "      <td>76.0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1</td>\n",
       "      <td>48</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1</td>\n",
       "      <td>20.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>245.0</td>\n",
       "      <td>127.5</td>\n",
       "      <td>80.0</td>\n",
       "      <td>25.34</td>\n",
       "      <td>75.0</td>\n",
       "      <td>70.0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0</td>\n",
       "      <td>61</td>\n",
       "      <td>3.0</td>\n",
       "      <td>1</td>\n",
       "      <td>30.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>225.0</td>\n",
       "      <td>150.0</td>\n",
       "      <td>95.0</td>\n",
       "      <td>28.58</td>\n",
       "      <td>65.0</td>\n",
       "      <td>103.0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0</td>\n",
       "      <td>46</td>\n",
       "      <td>3.0</td>\n",
       "      <td>1</td>\n",
       "      <td>23.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>285.0</td>\n",
       "      <td>130.0</td>\n",
       "      <td>84.0</td>\n",
       "      <td>23.10</td>\n",
       "      <td>85.0</td>\n",
       "      <td>85.0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>0</td>\n",
       "      <td>43</td>\n",
       "      <td>2.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>228.0</td>\n",
       "      <td>180.0</td>\n",
       "      <td>110.0</td>\n",
       "      <td>30.30</td>\n",
       "      <td>77.0</td>\n",
       "      <td>99.0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>0</td>\n",
       "      <td>63</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>205.0</td>\n",
       "      <td>138.0</td>\n",
       "      <td>71.0</td>\n",
       "      <td>33.11</td>\n",
       "      <td>60.0</td>\n",
       "      <td>85.0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>0</td>\n",
       "      <td>45</td>\n",
       "      <td>2.0</td>\n",
       "      <td>1</td>\n",
       "      <td>20.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>313.0</td>\n",
       "      <td>100.0</td>\n",
       "      <td>71.0</td>\n",
       "      <td>21.68</td>\n",
       "      <td>79.0</td>\n",
       "      <td>78.0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   male  age  education  currentSmoker  cigsPerDay  BPMeds  prevalentStroke  \\\n",
       "0     1   39        4.0              0         0.0     0.0                0   \n",
       "1     0   46        2.0              0         0.0     0.0                0   \n",
       "2     1   48        1.0              1        20.0     0.0                0   \n",
       "3     0   61        3.0              1        30.0     0.0                0   \n",
       "4     0   46        3.0              1        23.0     0.0                0   \n",
       "5     0   43        2.0              0         0.0     0.0                0   \n",
       "6     0   63        1.0              0         0.0     0.0                0   \n",
       "7     0   45        2.0              1        20.0     0.0                0   \n",
       "\n",
       "   prevalentHyp  diabetes  totChol  sysBP  diaBP    BMI  heartRate  glucose  \\\n",
       "0             0         0    195.0  106.0   70.0  26.97       80.0     77.0   \n",
       "1             0         0    250.0  121.0   81.0  28.73       95.0     76.0   \n",
       "2             0         0    245.0  127.5   80.0  25.34       75.0     70.0   \n",
       "3             1         0    225.0  150.0   95.0  28.58       65.0    103.0   \n",
       "4             0         0    285.0  130.0   84.0  23.10       85.0     85.0   \n",
       "5             1         0    228.0  180.0  110.0  30.30       77.0     99.0   \n",
       "6             0         0    205.0  138.0   71.0  33.11       60.0     85.0   \n",
       "7             0         0    313.0  100.0   71.0  21.68       79.0     78.0   \n",
       "\n",
       "   TenYearCHD  \n",
       "0           0  \n",
       "1           0  \n",
       "2           0  \n",
       "3           1  \n",
       "4           0  \n",
       "5           0  \n",
       "6           1  \n",
       "7           0  "
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# head(n); n = 1, 2, 3, 4, ....\n",
    "df.head(8)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Tail\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "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>male</th>\n",
       "      <th>age</th>\n",
       "      <th>education</th>\n",
       "      <th>currentSmoker</th>\n",
       "      <th>cigsPerDay</th>\n",
       "      <th>BPMeds</th>\n",
       "      <th>prevalentStroke</th>\n",
       "      <th>prevalentHyp</th>\n",
       "      <th>diabetes</th>\n",
       "      <th>totChol</th>\n",
       "      <th>sysBP</th>\n",
       "      <th>diaBP</th>\n",
       "      <th>BMI</th>\n",
       "      <th>heartRate</th>\n",
       "      <th>glucose</th>\n",
       "      <th>TenYearCHD</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>4235</th>\n",
       "      <td>0</td>\n",
       "      <td>48</td>\n",
       "      <td>2.0</td>\n",
       "      <td>1</td>\n",
       "      <td>20.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>248.0</td>\n",
       "      <td>131.0</td>\n",
       "      <td>72.0</td>\n",
       "      <td>22.00</td>\n",
       "      <td>84.0</td>\n",
       "      <td>86.0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4236</th>\n",
       "      <td>0</td>\n",
       "      <td>44</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1</td>\n",
       "      <td>15.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>210.0</td>\n",
       "      <td>126.5</td>\n",
       "      <td>87.0</td>\n",
       "      <td>19.16</td>\n",
       "      <td>86.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4237</th>\n",
       "      <td>0</td>\n",
       "      <td>52</td>\n",
       "      <td>2.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>269.0</td>\n",
       "      <td>133.5</td>\n",
       "      <td>83.0</td>\n",
       "      <td>21.47</td>\n",
       "      <td>80.0</td>\n",
       "      <td>107.0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4238</th>\n",
       "      <td>1</td>\n",
       "      <td>40</td>\n",
       "      <td>3.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>185.0</td>\n",
       "      <td>141.0</td>\n",
       "      <td>98.0</td>\n",
       "      <td>25.60</td>\n",
       "      <td>67.0</td>\n",
       "      <td>72.0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4239</th>\n",
       "      <td>0</td>\n",
       "      <td>39</td>\n",
       "      <td>3.0</td>\n",
       "      <td>1</td>\n",
       "      <td>30.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>196.0</td>\n",
       "      <td>133.0</td>\n",
       "      <td>86.0</td>\n",
       "      <td>20.91</td>\n",
       "      <td>85.0</td>\n",
       "      <td>80.0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "      male  age  education  currentSmoker  cigsPerDay  BPMeds  \\\n",
       "4235     0   48        2.0              1        20.0     NaN   \n",
       "4236     0   44        1.0              1        15.0     0.0   \n",
       "4237     0   52        2.0              0         0.0     0.0   \n",
       "4238     1   40        3.0              0         0.0     0.0   \n",
       "4239     0   39        3.0              1        30.0     0.0   \n",
       "\n",
       "      prevalentStroke  prevalentHyp  diabetes  totChol  sysBP  diaBP    BMI  \\\n",
       "4235                0             0         0    248.0  131.0   72.0  22.00   \n",
       "4236                0             0         0    210.0  126.5   87.0  19.16   \n",
       "4237                0             0         0    269.0  133.5   83.0  21.47   \n",
       "4238                0             1         0    185.0  141.0   98.0  25.60   \n",
       "4239                0             0         0    196.0  133.0   86.0  20.91   \n",
       "\n",
       "      heartRate  glucose  TenYearCHD  \n",
       "4235       84.0     86.0           0  \n",
       "4236       86.0      NaN           0  \n",
       "4237       80.0    107.0           0  \n",
       "4238       67.0     72.0           0  \n",
       "4239       85.0     80.0           0  "
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# tail: by default shows last 5 rows \n",
    "df.tail() "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "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>male</th>\n",
       "      <th>age</th>\n",
       "      <th>education</th>\n",
       "      <th>currentSmoker</th>\n",
       "      <th>cigsPerDay</th>\n",
       "      <th>BPMeds</th>\n",
       "      <th>prevalentStroke</th>\n",
       "      <th>prevalentHyp</th>\n",
       "      <th>diabetes</th>\n",
       "      <th>totChol</th>\n",
       "      <th>sysBP</th>\n",
       "      <th>diaBP</th>\n",
       "      <th>BMI</th>\n",
       "      <th>heartRate</th>\n",
       "      <th>glucose</th>\n",
       "      <th>TenYearCHD</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>4232</th>\n",
       "      <td>1</td>\n",
       "      <td>68</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>176.0</td>\n",
       "      <td>168.0</td>\n",
       "      <td>97.0</td>\n",
       "      <td>23.14</td>\n",
       "      <td>60.0</td>\n",
       "      <td>79.0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4233</th>\n",
       "      <td>1</td>\n",
       "      <td>50</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>313.0</td>\n",
       "      <td>179.0</td>\n",
       "      <td>92.0</td>\n",
       "      <td>25.97</td>\n",
       "      <td>66.0</td>\n",
       "      <td>86.0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4234</th>\n",
       "      <td>1</td>\n",
       "      <td>51</td>\n",
       "      <td>3.0</td>\n",
       "      <td>1</td>\n",
       "      <td>43.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>207.0</td>\n",
       "      <td>126.5</td>\n",
       "      <td>80.0</td>\n",
       "      <td>19.71</td>\n",
       "      <td>65.0</td>\n",
       "      <td>68.0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4235</th>\n",
       "      <td>0</td>\n",
       "      <td>48</td>\n",
       "      <td>2.0</td>\n",
       "      <td>1</td>\n",
       "      <td>20.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>248.0</td>\n",
       "      <td>131.0</td>\n",
       "      <td>72.0</td>\n",
       "      <td>22.00</td>\n",
       "      <td>84.0</td>\n",
       "      <td>86.0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4236</th>\n",
       "      <td>0</td>\n",
       "      <td>44</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1</td>\n",
       "      <td>15.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>210.0</td>\n",
       "      <td>126.5</td>\n",
       "      <td>87.0</td>\n",
       "      <td>19.16</td>\n",
       "      <td>86.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4237</th>\n",
       "      <td>0</td>\n",
       "      <td>52</td>\n",
       "      <td>2.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>269.0</td>\n",
       "      <td>133.5</td>\n",
       "      <td>83.0</td>\n",
       "      <td>21.47</td>\n",
       "      <td>80.0</td>\n",
       "      <td>107.0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4238</th>\n",
       "      <td>1</td>\n",
       "      <td>40</td>\n",
       "      <td>3.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>185.0</td>\n",
       "      <td>141.0</td>\n",
       "      <td>98.0</td>\n",
       "      <td>25.60</td>\n",
       "      <td>67.0</td>\n",
       "      <td>72.0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4239</th>\n",
       "      <td>0</td>\n",
       "      <td>39</td>\n",
       "      <td>3.0</td>\n",
       "      <td>1</td>\n",
       "      <td>30.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>196.0</td>\n",
       "      <td>133.0</td>\n",
       "      <td>86.0</td>\n",
       "      <td>20.91</td>\n",
       "      <td>85.0</td>\n",
       "      <td>80.0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "      male  age  education  currentSmoker  cigsPerDay  BPMeds  \\\n",
       "4232     1   68        1.0              0         0.0     0.0   \n",
       "4233     1   50        1.0              1         1.0     0.0   \n",
       "4234     1   51        3.0              1        43.0     0.0   \n",
       "4235     0   48        2.0              1        20.0     NaN   \n",
       "4236     0   44        1.0              1        15.0     0.0   \n",
       "4237     0   52        2.0              0         0.0     0.0   \n",
       "4238     1   40        3.0              0         0.0     0.0   \n",
       "4239     0   39        3.0              1        30.0     0.0   \n",
       "\n",
       "      prevalentStroke  prevalentHyp  diabetes  totChol  sysBP  diaBP    BMI  \\\n",
       "4232                0             1         0    176.0  168.0   97.0  23.14   \n",
       "4233                0             1         0    313.0  179.0   92.0  25.97   \n",
       "4234                0             0         0    207.0  126.5   80.0  19.71   \n",
       "4235                0             0         0    248.0  131.0   72.0  22.00   \n",
       "4236                0             0         0    210.0  126.5   87.0  19.16   \n",
       "4237                0             0         0    269.0  133.5   83.0  21.47   \n",
       "4238                0             1         0    185.0  141.0   98.0  25.60   \n",
       "4239                0             0         0    196.0  133.0   86.0  20.91   \n",
       "\n",
       "      heartRate  glucose  TenYearCHD  \n",
       "4232       60.0     79.0           1  \n",
       "4233       66.0     86.0           1  \n",
       "4234       65.0     68.0           0  \n",
       "4235       84.0     86.0           0  \n",
       "4236       86.0      NaN           0  \n",
       "4237       80.0    107.0           0  \n",
       "4238       67.0     72.0           0  \n",
       "4239       85.0     80.0           0  "
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# tail(n); n=1, 2, 3, 4...\n",
    "df.tail(8)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Columns Names "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Index(['male', 'age', 'education', 'currentSmoker', 'cigsPerDay', 'BPMeds',\n",
       "       'prevalentStroke', 'prevalentHyp', 'diabetes', 'totChol', 'sysBP',\n",
       "       'diaBP', 'BMI', 'heartRate', 'glucose', 'TenYearCHD'],\n",
       "      dtype='object')"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Columns \n",
    "df.columns"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Observations and Variables(Rows and Columns)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(4240, 16)"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# shape(rows x columns)\n",
    "df.shape"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Data Types "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "male                 int64\n",
       "age                  int64\n",
       "education          float64\n",
       "currentSmoker        int64\n",
       "cigsPerDay         float64\n",
       "BPMeds             float64\n",
       "prevalentStroke      int64\n",
       "prevalentHyp         int64\n",
       "diabetes             int64\n",
       "totChol            float64\n",
       "sysBP              float64\n",
       "diaBP              float64\n",
       "BMI                float64\n",
       "heartRate          float64\n",
       "glucose            float64\n",
       "TenYearCHD           int64\n",
       "dtype: object"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# check datatypes \n",
    "df.dtypes"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Basic Information"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 4240 entries, 0 to 4239\n",
      "Data columns (total 16 columns):\n",
      " #   Column           Non-Null Count  Dtype  \n",
      "---  ------           --------------  -----  \n",
      " 0   male             4240 non-null   int64  \n",
      " 1   age              4240 non-null   int64  \n",
      " 2   education        4135 non-null   float64\n",
      " 3   currentSmoker    4240 non-null   int64  \n",
      " 4   cigsPerDay       4211 non-null   float64\n",
      " 5   BPMeds           4187 non-null   float64\n",
      " 6   prevalentStroke  4240 non-null   int64  \n",
      " 7   prevalentHyp     4240 non-null   int64  \n",
      " 8   diabetes         4240 non-null   int64  \n",
      " 9   totChol          4190 non-null   float64\n",
      " 10  sysBP            4240 non-null   float64\n",
      " 11  diaBP            4240 non-null   float64\n",
      " 12  BMI              4221 non-null   float64\n",
      " 13  heartRate        4239 non-null   float64\n",
      " 14  glucose          3852 non-null   float64\n",
      " 15  TenYearCHD       4240 non-null   int64  \n",
      "dtypes: float64(9), int64(7)\n",
      "memory usage: 530.1 KB\n"
     ]
    }
   ],
   "source": [
    "# info: it gives an overview of datasets \n",
    "df.info() "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Numerical Summary of a Dataset"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "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>male</th>\n",
       "      <th>age</th>\n",
       "      <th>education</th>\n",
       "      <th>currentSmoker</th>\n",
       "      <th>cigsPerDay</th>\n",
       "      <th>BPMeds</th>\n",
       "      <th>prevalentStroke</th>\n",
       "      <th>prevalentHyp</th>\n",
       "      <th>diabetes</th>\n",
       "      <th>totChol</th>\n",
       "      <th>sysBP</th>\n",
       "      <th>diaBP</th>\n",
       "      <th>BMI</th>\n",
       "      <th>heartRate</th>\n",
       "      <th>glucose</th>\n",
       "      <th>TenYearCHD</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>4240.000000</td>\n",
       "      <td>4240.000000</td>\n",
       "      <td>4135.000000</td>\n",
       "      <td>4240.000000</td>\n",
       "      <td>4211.000000</td>\n",
       "      <td>4187.000000</td>\n",
       "      <td>4240.000000</td>\n",
       "      <td>4240.000000</td>\n",
       "      <td>4240.000000</td>\n",
       "      <td>4190.000000</td>\n",
       "      <td>4240.000000</td>\n",
       "      <td>4240.000000</td>\n",
       "      <td>4221.000000</td>\n",
       "      <td>4239.000000</td>\n",
       "      <td>3852.000000</td>\n",
       "      <td>4240.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>0.429245</td>\n",
       "      <td>49.580189</td>\n",
       "      <td>1.979444</td>\n",
       "      <td>0.494104</td>\n",
       "      <td>9.005937</td>\n",
       "      <td>0.029615</td>\n",
       "      <td>0.005896</td>\n",
       "      <td>0.310613</td>\n",
       "      <td>0.025708</td>\n",
       "      <td>236.699523</td>\n",
       "      <td>132.354599</td>\n",
       "      <td>82.897759</td>\n",
       "      <td>25.800801</td>\n",
       "      <td>75.878981</td>\n",
       "      <td>81.963655</td>\n",
       "      <td>0.151887</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>0.495027</td>\n",
       "      <td>8.572942</td>\n",
       "      <td>1.019791</td>\n",
       "      <td>0.500024</td>\n",
       "      <td>11.922462</td>\n",
       "      <td>0.169544</td>\n",
       "      <td>0.076569</td>\n",
       "      <td>0.462799</td>\n",
       "      <td>0.158280</td>\n",
       "      <td>44.591284</td>\n",
       "      <td>22.033300</td>\n",
       "      <td>11.910394</td>\n",
       "      <td>4.079840</td>\n",
       "      <td>12.025348</td>\n",
       "      <td>23.954335</td>\n",
       "      <td>0.358953</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>0.000000</td>\n",
       "      <td>32.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>107.000000</td>\n",
       "      <td>83.500000</td>\n",
       "      <td>48.000000</td>\n",
       "      <td>15.540000</td>\n",
       "      <td>44.000000</td>\n",
       "      <td>40.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>0.000000</td>\n",
       "      <td>42.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>206.000000</td>\n",
       "      <td>117.000000</td>\n",
       "      <td>75.000000</td>\n",
       "      <td>23.070000</td>\n",
       "      <td>68.000000</td>\n",
       "      <td>71.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>0.000000</td>\n",
       "      <td>49.000000</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>234.000000</td>\n",
       "      <td>128.000000</td>\n",
       "      <td>82.000000</td>\n",
       "      <td>25.400000</td>\n",
       "      <td>75.000000</td>\n",
       "      <td>78.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>1.000000</td>\n",
       "      <td>56.000000</td>\n",
       "      <td>3.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>20.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>263.000000</td>\n",
       "      <td>144.000000</td>\n",
       "      <td>90.000000</td>\n",
       "      <td>28.040000</td>\n",
       "      <td>83.000000</td>\n",
       "      <td>87.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>1.000000</td>\n",
       "      <td>70.000000</td>\n",
       "      <td>4.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>70.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>696.000000</td>\n",
       "      <td>295.000000</td>\n",
       "      <td>142.500000</td>\n",
       "      <td>56.800000</td>\n",
       "      <td>143.000000</td>\n",
       "      <td>394.000000</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "              male          age    education  currentSmoker   cigsPerDay  \\\n",
       "count  4240.000000  4240.000000  4135.000000    4240.000000  4211.000000   \n",
       "mean      0.429245    49.580189     1.979444       0.494104     9.005937   \n",
       "std       0.495027     8.572942     1.019791       0.500024    11.922462   \n",
       "min       0.000000    32.000000     1.000000       0.000000     0.000000   \n",
       "25%       0.000000    42.000000     1.000000       0.000000     0.000000   \n",
       "50%       0.000000    49.000000     2.000000       0.000000     0.000000   \n",
       "75%       1.000000    56.000000     3.000000       1.000000    20.000000   \n",
       "max       1.000000    70.000000     4.000000       1.000000    70.000000   \n",
       "\n",
       "            BPMeds  prevalentStroke  prevalentHyp     diabetes      totChol  \\\n",
       "count  4187.000000      4240.000000   4240.000000  4240.000000  4190.000000   \n",
       "mean      0.029615         0.005896      0.310613     0.025708   236.699523   \n",
       "std       0.169544         0.076569      0.462799     0.158280    44.591284   \n",
       "min       0.000000         0.000000      0.000000     0.000000   107.000000   \n",
       "25%       0.000000         0.000000      0.000000     0.000000   206.000000   \n",
       "50%       0.000000         0.000000      0.000000     0.000000   234.000000   \n",
       "75%       0.000000         0.000000      1.000000     0.000000   263.000000   \n",
       "max       1.000000         1.000000      1.000000     1.000000   696.000000   \n",
       "\n",
       "             sysBP        diaBP          BMI    heartRate      glucose  \\\n",
       "count  4240.000000  4240.000000  4221.000000  4239.000000  3852.000000   \n",
       "mean    132.354599    82.897759    25.800801    75.878981    81.963655   \n",
       "std      22.033300    11.910394     4.079840    12.025348    23.954335   \n",
       "min      83.500000    48.000000    15.540000    44.000000    40.000000   \n",
       "25%     117.000000    75.000000    23.070000    68.000000    71.000000   \n",
       "50%     128.000000    82.000000    25.400000    75.000000    78.000000   \n",
       "75%     144.000000    90.000000    28.040000    83.000000    87.000000   \n",
       "max     295.000000   142.500000    56.800000   143.000000   394.000000   \n",
       "\n",
       "        TenYearCHD  \n",
       "count  4240.000000  \n",
       "mean      0.151887  \n",
       "std       0.358953  \n",
       "min       0.000000  \n",
       "25%       0.000000  \n",
       "50%       0.000000  \n",
       "75%       0.000000  \n",
       "max       1.000000  "
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# describe: it gives summary statistics or five number summary \n",
    "df.describe() "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "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>count</th>\n",
       "      <th>mean</th>\n",
       "      <th>std</th>\n",
       "      <th>min</th>\n",
       "      <th>25%</th>\n",
       "      <th>50%</th>\n",
       "      <th>75%</th>\n",
       "      <th>max</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>male</th>\n",
       "      <td>4240.0</td>\n",
       "      <td>0.429245</td>\n",
       "      <td>0.495027</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.00</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>age</th>\n",
       "      <td>4240.0</td>\n",
       "      <td>49.580189</td>\n",
       "      <td>8.572942</td>\n",
       "      <td>32.00</td>\n",
       "      <td>42.00</td>\n",
       "      <td>49.0</td>\n",
       "      <td>56.00</td>\n",
       "      <td>70.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>education</th>\n",
       "      <td>4135.0</td>\n",
       "      <td>1.979444</td>\n",
       "      <td>1.019791</td>\n",
       "      <td>1.00</td>\n",
       "      <td>1.00</td>\n",
       "      <td>2.0</td>\n",
       "      <td>3.00</td>\n",
       "      <td>4.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>currentSmoker</th>\n",
       "      <td>4240.0</td>\n",
       "      <td>0.494104</td>\n",
       "      <td>0.500024</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.00</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>cigsPerDay</th>\n",
       "      <td>4211.0</td>\n",
       "      <td>9.005937</td>\n",
       "      <td>11.922462</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>20.00</td>\n",
       "      <td>70.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>BPMeds</th>\n",
       "      <td>4187.0</td>\n",
       "      <td>0.029615</td>\n",
       "      <td>0.169544</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.00</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>prevalentStroke</th>\n",
       "      <td>4240.0</td>\n",
       "      <td>0.005896</td>\n",
       "      <td>0.076569</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.00</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>prevalentHyp</th>\n",
       "      <td>4240.0</td>\n",
       "      <td>0.310613</td>\n",
       "      <td>0.462799</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.00</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>diabetes</th>\n",
       "      <td>4240.0</td>\n",
       "      <td>0.025708</td>\n",
       "      <td>0.158280</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.00</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>totChol</th>\n",
       "      <td>4190.0</td>\n",
       "      <td>236.699523</td>\n",
       "      <td>44.591284</td>\n",
       "      <td>107.00</td>\n",
       "      <td>206.00</td>\n",
       "      <td>234.0</td>\n",
       "      <td>263.00</td>\n",
       "      <td>696.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>sysBP</th>\n",
       "      <td>4240.0</td>\n",
       "      <td>132.354599</td>\n",
       "      <td>22.033300</td>\n",
       "      <td>83.50</td>\n",
       "      <td>117.00</td>\n",
       "      <td>128.0</td>\n",
       "      <td>144.00</td>\n",
       "      <td>295.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>diaBP</th>\n",
       "      <td>4240.0</td>\n",
       "      <td>82.897759</td>\n",
       "      <td>11.910394</td>\n",
       "      <td>48.00</td>\n",
       "      <td>75.00</td>\n",
       "      <td>82.0</td>\n",
       "      <td>90.00</td>\n",
       "      <td>142.5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>BMI</th>\n",
       "      <td>4221.0</td>\n",
       "      <td>25.800801</td>\n",
       "      <td>4.079840</td>\n",
       "      <td>15.54</td>\n",
       "      <td>23.07</td>\n",
       "      <td>25.4</td>\n",
       "      <td>28.04</td>\n",
       "      <td>56.8</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>heartRate</th>\n",
       "      <td>4239.0</td>\n",
       "      <td>75.878981</td>\n",
       "      <td>12.025348</td>\n",
       "      <td>44.00</td>\n",
       "      <td>68.00</td>\n",
       "      <td>75.0</td>\n",
       "      <td>83.00</td>\n",
       "      <td>143.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>glucose</th>\n",
       "      <td>3852.0</td>\n",
       "      <td>81.963655</td>\n",
       "      <td>23.954335</td>\n",
       "      <td>40.00</td>\n",
       "      <td>71.00</td>\n",
       "      <td>78.0</td>\n",
       "      <td>87.00</td>\n",
       "      <td>394.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>TenYearCHD</th>\n",
       "      <td>4240.0</td>\n",
       "      <td>0.151887</td>\n",
       "      <td>0.358953</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.00</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                  count        mean        std     min     25%    50%     75%  \\\n",
       "male             4240.0    0.429245   0.495027    0.00    0.00    0.0    1.00   \n",
       "age              4240.0   49.580189   8.572942   32.00   42.00   49.0   56.00   \n",
       "education        4135.0    1.979444   1.019791    1.00    1.00    2.0    3.00   \n",
       "currentSmoker    4240.0    0.494104   0.500024    0.00    0.00    0.0    1.00   \n",
       "cigsPerDay       4211.0    9.005937  11.922462    0.00    0.00    0.0   20.00   \n",
       "BPMeds           4187.0    0.029615   0.169544    0.00    0.00    0.0    0.00   \n",
       "prevalentStroke  4240.0    0.005896   0.076569    0.00    0.00    0.0    0.00   \n",
       "prevalentHyp     4240.0    0.310613   0.462799    0.00    0.00    0.0    1.00   \n",
       "diabetes         4240.0    0.025708   0.158280    0.00    0.00    0.0    0.00   \n",
       "totChol          4190.0  236.699523  44.591284  107.00  206.00  234.0  263.00   \n",
       "sysBP            4240.0  132.354599  22.033300   83.50  117.00  128.0  144.00   \n",
       "diaBP            4240.0   82.897759  11.910394   48.00   75.00   82.0   90.00   \n",
       "BMI              4221.0   25.800801   4.079840   15.54   23.07   25.4   28.04   \n",
       "heartRate        4239.0   75.878981  12.025348   44.00   68.00   75.0   83.00   \n",
       "glucose          3852.0   81.963655  23.954335   40.00   71.00   78.0   87.00   \n",
       "TenYearCHD       4240.0    0.151887   0.358953    0.00    0.00    0.0    0.00   \n",
       "\n",
       "                   max  \n",
       "male               1.0  \n",
       "age               70.0  \n",
       "education          4.0  \n",
       "currentSmoker      1.0  \n",
       "cigsPerDay        70.0  \n",
       "BPMeds             1.0  \n",
       "prevalentStroke    1.0  \n",
       "prevalentHyp       1.0  \n",
       "diabetes           1.0  \n",
       "totChol          696.0  \n",
       "sysBP            295.0  \n",
       "diaBP            142.5  \n",
       "BMI               56.8  \n",
       "heartRate        143.0  \n",
       "glucose          394.0  \n",
       "TenYearCHD         1.0  "
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# transpose table\n",
    "df.describe().T"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "count    4240.000000\n",
       "mean       49.580189\n",
       "std         8.572942\n",
       "min        32.000000\n",
       "25%        42.000000\n",
       "50%        49.000000\n",
       "75%        56.000000\n",
       "max        70.000000\n",
       "Name: age, dtype: float64"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# for specific column \n",
    "df['age'].describe() "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "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>age</th>\n",
       "      <th>BMI</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>4240.000000</td>\n",
       "      <td>4221.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>49.580189</td>\n",
       "      <td>25.800801</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>8.572942</td>\n",
       "      <td>4.079840</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>32.000000</td>\n",
       "      <td>15.540000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>42.000000</td>\n",
       "      <td>23.070000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>49.000000</td>\n",
       "      <td>25.400000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>56.000000</td>\n",
       "      <td>28.040000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>70.000000</td>\n",
       "      <td>56.800000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "               age          BMI\n",
       "count  4240.000000  4221.000000\n",
       "mean     49.580189    25.800801\n",
       "std       8.572942     4.079840\n",
       "min      32.000000    15.540000\n",
       "25%      42.000000    23.070000\n",
       "50%      49.000000    25.400000\n",
       "75%      56.000000    28.040000\n",
       "max      70.000000    56.800000"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# for multiple columns \n",
    "df[['age', 'BMI']].describe() "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Exploring Series "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# read another dataset \n",
    "titanic = pd.read_csv('http://bit.ly/kaggletrain')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# examine first few rows \n",
    "titanic.head() "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Value Counts "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# value_counts()\n",
    "titanic['Sex'].value_counts() "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# value_counts() in percent\n",
    "titanic['Sex'].value_counts(normalize=True) "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# returns a series \n",
    "type(titanic['Sex'].value_counts(normalize=True))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Unique() "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# unique() \n",
    "titanic['Fare'].unique() "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# return a numpy.ndarray\n",
    "type(titanic['Fare'].unique())"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Cross Tabulation"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# crosstab \n",
    "pd.crosstab(titanic['Sex'], titanic['Survived'])"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Describe "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# describe a categorical column \n",
    "titanic['Age'].describe() "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Basic Statistics"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# mean()\n",
    "titanic.Age.mean() "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# max()\n",
    "titanic.Age.max() "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# min() \n",
    "titanic.Age.min() "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# median() \n",
    "titanic.Age.median() "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Visualization"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "%matplotlib inline "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# barplot\n",
    "titanic.Sex.value_counts().plot(kind=\"bar\") "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# histogram\n",
    "titanic.Age.plot(kind=\"hist\")"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.7.4"
  },
  "latex_envs": {
   "LaTeX_envs_menu_present": true,
   "autoclose": false,
   "autocomplete": true,
   "bibliofile": "biblio.bib",
   "cite_by": "apalike",
   "current_citInitial": 1,
   "eqLabelWithNumbers": true,
   "eqNumInitial": 1,
   "hotkeys": {
    "equation": "Ctrl-E",
    "itemize": "Ctrl-I"
   },
   "labels_anchors": false,
   "latex_user_defs": false,
   "report_style_numbering": false,
   "user_envs_cfg": false
  },
  "toc": {
   "base_numbering": 1,
   "nav_menu": {},
   "number_sections": true,
   "sideBar": true,
   "skip_h1_title": false,
   "title_cell": "Table of Contents",
   "title_sidebar": "Contents",
   "toc_cell": true,
   "toc_position": {},
   "toc_section_display": true,
   "toc_window_display": false
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}