{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Data Summary"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import datetime\n",
    "from data_describe import data_summary\n",
    "from datetime import datetime"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>CRIM</th>\n",
       "      <th>ZN</th>\n",
       "      <th>INDUS</th>\n",
       "      <th>CHAS</th>\n",
       "      <th>NOX</th>\n",
       "      <th>RM</th>\n",
       "      <th>AGE</th>\n",
       "      <th>DIS</th>\n",
       "      <th>RAD</th>\n",
       "      <th>TAX</th>\n",
       "      <th>PTRATIO</th>\n",
       "      <th>B</th>\n",
       "      <th>LSTAT</th>\n",
       "      <th>target</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0.00632</td>\n",
       "      <td>18.0</td>\n",
       "      <td>2.31</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.538</td>\n",
       "      <td>6.575</td>\n",
       "      <td>65.2</td>\n",
       "      <td>4.09</td>\n",
       "      <td>1.0</td>\n",
       "      <td>296.0</td>\n",
       "      <td>15.3</td>\n",
       "      <td>396.9</td>\n",
       "      <td>4.98</td>\n",
       "      <td>24.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "      CRIM    ZN  INDUS  CHAS    NOX     RM   AGE   DIS  RAD    TAX  PTRATIO  \\\n",
       "0  0.00632  18.0   2.31   0.0  0.538  6.575  65.2  4.09  1.0  296.0     15.3   \n",
       "\n",
       "       B  LSTAT  target  \n",
       "0  396.9   4.98    24.0  "
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from sklearn.datasets import load_boston\n",
    "data = load_boston()\n",
    "df = pd.DataFrame(data.data, columns=list(data.feature_names))\n",
    "df['target'] = data.target\n",
    "df.head(1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Change data types to demonstrate data summary\n",
    "df['AGE'] = df['AGE'].map(lambda x: \"young\" if x < 29 else \"old\")\n",
    "df[\"AgeFlag\"] = df['AGE'].astype(bool)\n",
    "df['ZN'] = df['ZN'].astype(int)\n",
    "df['Date'] = datetime.strptime('1/1/2008 1:30 PM', '%m/%d/%Y %I:%M %p')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>CRIM</th>\n",
       "      <th>ZN</th>\n",
       "      <th>INDUS</th>\n",
       "      <th>CHAS</th>\n",
       "      <th>NOX</th>\n",
       "      <th>RM</th>\n",
       "      <th>AGE</th>\n",
       "      <th>DIS</th>\n",
       "      <th>RAD</th>\n",
       "      <th>TAX</th>\n",
       "      <th>PTRATIO</th>\n",
       "      <th>B</th>\n",
       "      <th>LSTAT</th>\n",
       "      <th>target</th>\n",
       "      <th>AgeFlag</th>\n",
       "      <th>Date</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>Data Type</th>\n",
       "      <td>float64</td>\n",
       "      <td>int32</td>\n",
       "      <td>float64</td>\n",
       "      <td>float64</td>\n",
       "      <td>float64</td>\n",
       "      <td>float64</td>\n",
       "      <td>object</td>\n",
       "      <td>float64</td>\n",
       "      <td>float64</td>\n",
       "      <td>float64</td>\n",
       "      <td>float64</td>\n",
       "      <td>float64</td>\n",
       "      <td>float64</td>\n",
       "      <td>float64</td>\n",
       "      <td>bool</td>\n",
       "      <td>datetime64[ns]</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Mean</th>\n",
       "      <td>3.61352</td>\n",
       "      <td>11.3478</td>\n",
       "      <td>11.1368</td>\n",
       "      <td>0.06917</td>\n",
       "      <td>0.554695</td>\n",
       "      <td>6.28463</td>\n",
       "      <td></td>\n",
       "      <td>3.79504</td>\n",
       "      <td>9.54941</td>\n",
       "      <td>408.237</td>\n",
       "      <td>18.4555</td>\n",
       "      <td>356.674</td>\n",
       "      <td>12.6531</td>\n",
       "      <td>22.5328</td>\n",
       "      <td>1</td>\n",
       "      <td>2008-01-01 13:30:00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Standard Deviation</th>\n",
       "      <td>8.60155</td>\n",
       "      <td>23.3106</td>\n",
       "      <td>6.86035</td>\n",
       "      <td>0.253994</td>\n",
       "      <td>0.115878</td>\n",
       "      <td>0.702617</td>\n",
       "      <td></td>\n",
       "      <td>2.10571</td>\n",
       "      <td>8.70726</td>\n",
       "      <td>168.537</td>\n",
       "      <td>2.16495</td>\n",
       "      <td>91.2949</td>\n",
       "      <td>7.14106</td>\n",
       "      <td>9.1971</td>\n",
       "      <td>0</td>\n",
       "      <td></td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Median</th>\n",
       "      <td>0.25651</td>\n",
       "      <td>0</td>\n",
       "      <td>9.69</td>\n",
       "      <td>0</td>\n",
       "      <td>0.538</td>\n",
       "      <td>6.2085</td>\n",
       "      <td></td>\n",
       "      <td>3.20745</td>\n",
       "      <td>5</td>\n",
       "      <td>330</td>\n",
       "      <td>19.05</td>\n",
       "      <td>391.44</td>\n",
       "      <td>11.36</td>\n",
       "      <td>21.2</td>\n",
       "      <td>1</td>\n",
       "      <td></td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Min</th>\n",
       "      <td>0.00632</td>\n",
       "      <td>0</td>\n",
       "      <td>0.46</td>\n",
       "      <td>0</td>\n",
       "      <td>0.385</td>\n",
       "      <td>3.561</td>\n",
       "      <td></td>\n",
       "      <td>1.1296</td>\n",
       "      <td>1</td>\n",
       "      <td>187</td>\n",
       "      <td>12.6</td>\n",
       "      <td>0.32</td>\n",
       "      <td>1.73</td>\n",
       "      <td>5</td>\n",
       "      <td></td>\n",
       "      <td></td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Max</th>\n",
       "      <td>88.9762</td>\n",
       "      <td>100</td>\n",
       "      <td>27.74</td>\n",
       "      <td>1</td>\n",
       "      <td>0.871</td>\n",
       "      <td>8.78</td>\n",
       "      <td></td>\n",
       "      <td>12.1265</td>\n",
       "      <td>24</td>\n",
       "      <td>711</td>\n",
       "      <td>22</td>\n",
       "      <td>396.9</td>\n",
       "      <td>37.97</td>\n",
       "      <td>50</td>\n",
       "      <td></td>\n",
       "      <td></td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th># Zeros</th>\n",
       "      <td>0</td>\n",
       "      <td>372</td>\n",
       "      <td>0</td>\n",
       "      <td>471</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td></td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td></td>\n",
       "      <td></td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th># Nulls</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>% Most Frequent Value</th>\n",
       "      <td>0.4</td>\n",
       "      <td>73.52</td>\n",
       "      <td>26.09</td>\n",
       "      <td>93.08</td>\n",
       "      <td>4.55</td>\n",
       "      <td>0.59</td>\n",
       "      <td>88.14</td>\n",
       "      <td>0.99</td>\n",
       "      <td>26.09</td>\n",
       "      <td>26.09</td>\n",
       "      <td>27.67</td>\n",
       "      <td>23.91</td>\n",
       "      <td>0.59</td>\n",
       "      <td>3.16</td>\n",
       "      <td>100</td>\n",
       "      <td>100</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                          CRIM       ZN    INDUS      CHAS       NOX  \\\n",
       "Data Type              float64    int32  float64   float64   float64   \n",
       "Mean                   3.61352  11.3478  11.1368   0.06917  0.554695   \n",
       "Standard Deviation     8.60155  23.3106  6.86035  0.253994  0.115878   \n",
       "Median                 0.25651        0     9.69         0     0.538   \n",
       "Min                    0.00632        0     0.46         0     0.385   \n",
       "Max                    88.9762      100    27.74         1     0.871   \n",
       "# Zeros                      0      372        0       471         0   \n",
       "# Nulls                      0        0        0         0         0   \n",
       "% Most Frequent Value      0.4    73.52    26.09     93.08      4.55   \n",
       "\n",
       "                             RM     AGE      DIS      RAD      TAX  PTRATIO  \\\n",
       "Data Type               float64  object  float64  float64  float64  float64   \n",
       "Mean                    6.28463          3.79504  9.54941  408.237  18.4555   \n",
       "Standard Deviation     0.702617          2.10571  8.70726  168.537  2.16495   \n",
       "Median                   6.2085          3.20745        5      330    19.05   \n",
       "Min                       3.561           1.1296        1      187     12.6   \n",
       "Max                        8.78          12.1265       24      711       22   \n",
       "# Zeros                       0                0        0        0        0   \n",
       "# Nulls                       0       0        0        0        0        0   \n",
       "% Most Frequent Value      0.59   88.14     0.99    26.09    26.09    27.67   \n",
       "\n",
       "                             B    LSTAT   target AgeFlag                 Date  \n",
       "Data Type              float64  float64  float64    bool       datetime64[ns]  \n",
       "Mean                   356.674  12.6531  22.5328       1  2008-01-01 13:30:00  \n",
       "Standard Deviation     91.2949  7.14106   9.1971       0                       \n",
       "Median                  391.44    11.36     21.2       1                       \n",
       "Min                       0.32     1.73        5                               \n",
       "Max                      396.9    37.97       50                               \n",
       "# Zeros                      0        0        0                               \n",
       "# Nulls                      0        0        0       0                    0  \n",
       "% Most Frequent Value    23.91     0.59     3.16     100                  100  "
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data_summary(df)"
   ]
  }
 ],
 "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": "3.7.7"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}