{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Data Aggregation and Group Operations"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## GroupBy"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import numpy as np"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style>\n",
       "    .dataframe thead tr:only-child th {\n",
       "        text-align: right;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>data1</th>\n",
       "      <th>data2</th>\n",
       "      <th>key1</th>\n",
       "      <th>key2</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>20</td>\n",
       "      <td>1.993315</td>\n",
       "      <td>a</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>21</td>\n",
       "      <td>1.132069</td>\n",
       "      <td>b</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>22</td>\n",
       "      <td>0.135880</td>\n",
       "      <td>a</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>23</td>\n",
       "      <td>-1.071349</td>\n",
       "      <td>b</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>100</td>\n",
       "      <td>-0.585936</td>\n",
       "      <td>a</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>200</td>\n",
       "      <td>-1.501368</td>\n",
       "      <td>b</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>300</td>\n",
       "      <td>-0.688437</td>\n",
       "      <td>a</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>400</td>\n",
       "      <td>0.926304</td>\n",
       "      <td>a</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   data1     data2 key1 key2\n",
       "0     20  1.993315    a    1\n",
       "1     21  1.132069    b    2\n",
       "2     22  0.135880    a    3\n",
       "3     23 -1.071349    b    4\n",
       "4    100 -0.585936    a    1\n",
       "5    200 -1.501368    b    2\n",
       "6    300 -0.688437    a    3\n",
       "7    400  0.926304    a    4"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df = pd.DataFrame({\"key1\" : [\"a\", \"b\", \"a\", \"b\", \"a\", \"b\", \"a\", \"a\"], \n",
    "                  \"key2\" : [\"1\", \"2\", \"3\", \"4\", \"1\", \"2\", \"3\", \"4\"], \n",
    "                  \"data1\" : [20, 21, 22, 23, 100, 200, 300, 400], \n",
    "                  \"data2\" : np.random.randn(8)})\n",
    "df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style>\n",
       "    .dataframe thead tr:only-child th {\n",
       "        text-align: right;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>data1</th>\n",
       "      <th>data2</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>key1</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>a</th>\n",
       "      <td>168.400000</td>\n",
       "      <td>0.356225</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>b</th>\n",
       "      <td>81.333333</td>\n",
       "      <td>-0.480216</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "           data1     data2\n",
       "key1                      \n",
       "a     168.400000  0.356225\n",
       "b      81.333333 -0.480216"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.groupby(df[\"key1\"]).mean()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style>\n",
       "    .dataframe thead tr:only-child th {\n",
       "        text-align: right;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>data1</th>\n",
       "      <th>data2</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>key1</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>a</th>\n",
       "      <td>168.400000</td>\n",
       "      <td>0.356225</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>b</th>\n",
       "      <td>81.333333</td>\n",
       "      <td>-0.480216</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "           data1     data2\n",
       "key1                      \n",
       "a     168.400000  0.356225\n",
       "b      81.333333 -0.480216"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.groupby(\"key1\").mean()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style>\n",
       "    .dataframe thead tr:only-child th {\n",
       "        text-align: right;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th>data1</th>\n",
       "      <th>data2</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>key1</th>\n",
       "      <th>key2</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th rowspan=\"3\" valign=\"top\">a</th>\n",
       "      <th>1</th>\n",
       "      <td>60.0</td>\n",
       "      <td>0.703689</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>161.0</td>\n",
       "      <td>-0.276278</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>400.0</td>\n",
       "      <td>0.926304</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th rowspan=\"2\" valign=\"top\">b</th>\n",
       "      <th>2</th>\n",
       "      <td>110.5</td>\n",
       "      <td>-0.184649</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>23.0</td>\n",
       "      <td>-1.071349</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "           data1     data2\n",
       "key1 key2                 \n",
       "a    1      60.0  0.703689\n",
       "     3     161.0 -0.276278\n",
       "     4     400.0  0.926304\n",
       "b    2     110.5 -0.184649\n",
       "     4      23.0 -1.071349"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "means = df.groupby([df[\"key1\"], df[\"key2\"]]).mean()\n",
    "means"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style>\n",
       "    .dataframe thead tr:only-child th {\n",
       "        text-align: right;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th>data1</th>\n",
       "      <th>data2</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>key1</th>\n",
       "      <th>key2</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th rowspan=\"3\" valign=\"top\">a</th>\n",
       "      <th>1</th>\n",
       "      <td>60.0</td>\n",
       "      <td>0.703689</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>161.0</td>\n",
       "      <td>-0.276278</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>400.0</td>\n",
       "      <td>0.926304</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th rowspan=\"2\" valign=\"top\">b</th>\n",
       "      <th>2</th>\n",
       "      <td>110.5</td>\n",
       "      <td>-0.184649</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>23.0</td>\n",
       "      <td>-1.071349</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "           data1     data2\n",
       "key1 key2                 \n",
       "a    1      60.0  0.703689\n",
       "     3     161.0 -0.276278\n",
       "     4     400.0  0.926304\n",
       "b    2     110.5 -0.184649\n",
       "     4      23.0 -1.071349"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.groupby([\"key1\", \"key2\"]).mean()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style>\n",
       "    .dataframe thead tr:only-child th {\n",
       "        text-align: right;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr>\n",
       "      <th></th>\n",
       "      <th colspan=\"4\" halign=\"left\">data1</th>\n",
       "      <th colspan=\"4\" halign=\"left\">data2</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>key2</th>\n",
       "      <th>1</th>\n",
       "      <th>2</th>\n",
       "      <th>3</th>\n",
       "      <th>4</th>\n",
       "      <th>1</th>\n",
       "      <th>2</th>\n",
       "      <th>3</th>\n",
       "      <th>4</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>key1</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>a</th>\n",
       "      <td>60.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>161.0</td>\n",
       "      <td>400.0</td>\n",
       "      <td>0.703689</td>\n",
       "      <td>NaN</td>\n",
       "      <td>-0.276278</td>\n",
       "      <td>0.926304</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>b</th>\n",
       "      <td>NaN</td>\n",
       "      <td>110.5</td>\n",
       "      <td>NaN</td>\n",
       "      <td>23.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>-0.184649</td>\n",
       "      <td>NaN</td>\n",
       "      <td>-1.071349</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "     data1                          data2                              \n",
       "key2     1      2      3      4         1         2         3         4\n",
       "key1                                                                   \n",
       "a     60.0    NaN  161.0  400.0  0.703689       NaN -0.276278  0.926304\n",
       "b      NaN  110.5    NaN   23.0       NaN -0.184649       NaN -1.071349"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "means.unstack()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "key1  key2\n",
       "a     1       2\n",
       "      3       2\n",
       "      4       1\n",
       "b     2       2\n",
       "      4       1\n",
       "dtype: int64"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.groupby([\"key1\", \"key2\"]).size()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "a\n",
      "   data1     data2 key1 key2\n",
      "0     20  1.993315    a    1\n",
      "2     22  0.135880    a    3\n",
      "4    100 -0.585936    a    1\n",
      "6    300 -0.688437    a    3\n",
      "7    400  0.926304    a    4\n",
      "b\n",
      "   data1     data2 key1 key2\n",
      "1     21  1.132069    b    2\n",
      "3     23 -1.071349    b    4\n",
      "5    200 -1.501368    b    2\n"
     ]
    }
   ],
   "source": [
    "# iterating over groups\n",
    "for name, group in df.groupby(\"key1\"):\n",
    "    print(name)\n",
    "    print(group)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "data1      int64\n",
       "data2    float64\n",
       "key1      object\n",
       "key2      object\n",
       "dtype: object"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.dtypes"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{dtype('int64'):    data1\n",
       " 0     20\n",
       " 1     21\n",
       " 2     22\n",
       " 3     23\n",
       " 4    100\n",
       " 5    200\n",
       " 6    300\n",
       " 7    400, dtype('float64'):       data2\n",
       " 0  1.993315\n",
       " 1  1.132069\n",
       " 2  0.135880\n",
       " 3 -1.071349\n",
       " 4 -0.585936\n",
       " 5 -1.501368\n",
       " 6 -0.688437\n",
       " 7  0.926304, dtype('O'):   key1 key2\n",
       " 0    a    1\n",
       " 1    b    2\n",
       " 2    a    3\n",
       " 3    b    4\n",
       " 4    a    1\n",
       " 5    b    2\n",
       " 6    a    3\n",
       " 7    a    4}"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df2 = df.groupby(df.dtypes, axis = 1)\n",
    "dict(list(df2))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Select a Column"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style>\n",
       "    .dataframe thead tr:only-child th {\n",
       "        text-align: right;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>data1</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>key1</th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>a</th>\n",
       "      <td>168.400000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>b</th>\n",
       "      <td>81.333333</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "           data1\n",
       "key1            \n",
       "a     168.400000\n",
       "b      81.333333"
      ]
     },
     "execution_count": 20,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.groupby('key1')[['data1']].mean()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0    a\n",
       "1    b\n",
       "2    a\n",
       "3    b\n",
       "4    a\n",
       "5    b\n",
       "6    a\n",
       "7    a\n",
       "Name: key1, dtype: object"
      ]
     },
     "execution_count": 21,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df[\"key1\"]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "data1    8\n",
       "data2    8\n",
       "key1     8\n",
       "key2     8\n",
       "dtype: int64"
      ]
     },
     "execution_count": 22,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.count()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style>\n",
       "    .dataframe thead tr:only-child th {\n",
       "        text-align: right;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>data1</th>\n",
       "      <th>data2</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>key1</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>a</th>\n",
       "      <td>380</td>\n",
       "      <td>2.681751</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>b</th>\n",
       "      <td>179</td>\n",
       "      <td>2.633437</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "      data1     data2\n",
       "key1                 \n",
       "a       380  2.681751\n",
       "b       179  2.633437"
      ]
     },
     "execution_count": 23,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "def my_range(arr):\n",
    "    return arr.max() - arr.min()\n",
    "\n",
    "df.groupby(\"key1\").aggregate(my_range)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 74,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style>\n",
       "    .dataframe thead tr:only-child th {\n",
       "        text-align: right;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr>\n",
       "      <th></th>\n",
       "      <th colspan=\"8\" halign=\"left\">data1</th>\n",
       "      <th colspan=\"8\" halign=\"left\">data2</th>\n",
       "    </tr>\n",
       "    <tr>\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",
       "      <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",
       "    <tr>\n",
       "      <th>key1</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>a</th>\n",
       "      <td>5.0</td>\n",
       "      <td>168.400000</td>\n",
       "      <td>172.547964</td>\n",
       "      <td>20.0</td>\n",
       "      <td>22.0</td>\n",
       "      <td>100.0</td>\n",
       "      <td>300.0</td>\n",
       "      <td>400.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>0.304734</td>\n",
       "      <td>0.896221</td>\n",
       "      <td>-1.090432</td>\n",
       "      <td>0.270046</td>\n",
       "      <td>0.392229</td>\n",
       "      <td>0.553693</td>\n",
       "      <td>1.398133</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>b</th>\n",
       "      <td>3.0</td>\n",
       "      <td>81.333333</td>\n",
       "      <td>102.773213</td>\n",
       "      <td>21.0</td>\n",
       "      <td>22.0</td>\n",
       "      <td>23.0</td>\n",
       "      <td>111.5</td>\n",
       "      <td>200.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>0.553255</td>\n",
       "      <td>0.466006</td>\n",
       "      <td>0.064604</td>\n",
       "      <td>0.333526</td>\n",
       "      <td>0.602447</td>\n",
       "      <td>0.797580</td>\n",
       "      <td>0.992713</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "     data1                                                          data2  \\\n",
       "     count        mean         std   min   25%    50%    75%    max count   \n",
       "key1                                                                        \n",
       "a      5.0  168.400000  172.547964  20.0  22.0  100.0  300.0  400.0   5.0   \n",
       "b      3.0   81.333333  102.773213  21.0  22.0   23.0  111.5  200.0   3.0   \n",
       "\n",
       "                                                                            \n",
       "          mean       std       min       25%       50%       75%       max  \n",
       "key1                                                                        \n",
       "a     0.304734  0.896221 -1.090432  0.270046  0.392229  0.553693  1.398133  \n",
       "b     0.553255  0.466006  0.064604  0.333526  0.602447  0.797580  0.992713  "
      ]
     },
     "execution_count": 74,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.groupby(\"key1\").describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style>\n",
       "    .dataframe thead tr:only-child th {\n",
       "        text-align: right;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr>\n",
       "      <th></th>\n",
       "      <th colspan=\"8\" halign=\"left\">data1</th>\n",
       "      <th colspan=\"8\" halign=\"left\">data2</th>\n",
       "    </tr>\n",
       "    <tr>\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",
       "      <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",
       "    <tr>\n",
       "      <th>key1</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>a</th>\n",
       "      <td>5.0</td>\n",
       "      <td>168.400000</td>\n",
       "      <td>172.547964</td>\n",
       "      <td>20.0</td>\n",
       "      <td>22.0</td>\n",
       "      <td>100.0</td>\n",
       "      <td>300.0</td>\n",
       "      <td>400.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>0.356225</td>\n",
       "      <td>1.121672</td>\n",
       "      <td>-0.688437</td>\n",
       "      <td>-0.585936</td>\n",
       "      <td>0.135880</td>\n",
       "      <td>0.926304</td>\n",
       "      <td>1.993315</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>b</th>\n",
       "      <td>3.0</td>\n",
       "      <td>81.333333</td>\n",
       "      <td>102.773213</td>\n",
       "      <td>21.0</td>\n",
       "      <td>22.0</td>\n",
       "      <td>23.0</td>\n",
       "      <td>111.5</td>\n",
       "      <td>200.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>-0.480216</td>\n",
       "      <td>1.412737</td>\n",
       "      <td>-1.501368</td>\n",
       "      <td>-1.286358</td>\n",
       "      <td>-1.071349</td>\n",
       "      <td>0.030360</td>\n",
       "      <td>1.132069</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "     data1                                                          data2  \\\n",
       "     count        mean         std   min   25%    50%    75%    max count   \n",
       "key1                                                                        \n",
       "a      5.0  168.400000  172.547964  20.0  22.0  100.0  300.0  400.0   5.0   \n",
       "b      3.0   81.333333  102.773213  21.0  22.0   23.0  111.5  200.0   3.0   \n",
       "\n",
       "                                                                            \n",
       "          mean       std       min       25%       50%       75%       max  \n",
       "key1                                                                        \n",
       "a     0.356225  1.121672 -0.688437 -0.585936  0.135880  0.926304  1.993315  \n",
       "b    -0.480216  1.412737 -1.501368 -1.286358 -1.071349  0.030360  1.132069  "
      ]
     },
     "execution_count": 30,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.groupby(\"key1\").aggregate(\"describe\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Data aggregation"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style>\n",
       "    .dataframe thead tr:only-child th {\n",
       "        text-align: right;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>total_bill</th>\n",
       "      <th>tip</th>\n",
       "      <th>smoker</th>\n",
       "      <th>day</th>\n",
       "      <th>time</th>\n",
       "      <th>size</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>16.99</td>\n",
       "      <td>1.01</td>\n",
       "      <td>No</td>\n",
       "      <td>Sun</td>\n",
       "      <td>Dinner</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>10.34</td>\n",
       "      <td>1.66</td>\n",
       "      <td>No</td>\n",
       "      <td>Sun</td>\n",
       "      <td>Dinner</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>21.01</td>\n",
       "      <td>3.50</td>\n",
       "      <td>No</td>\n",
       "      <td>Sun</td>\n",
       "      <td>Dinner</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>23.68</td>\n",
       "      <td>3.31</td>\n",
       "      <td>No</td>\n",
       "      <td>Sun</td>\n",
       "      <td>Dinner</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>24.59</td>\n",
       "      <td>3.61</td>\n",
       "      <td>No</td>\n",
       "      <td>Sun</td>\n",
       "      <td>Dinner</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   total_bill   tip smoker  day    time  size\n",
       "0       16.99  1.01     No  Sun  Dinner     2\n",
       "1       10.34  1.66     No  Sun  Dinner     3\n",
       "2       21.01  3.50     No  Sun  Dinner     3\n",
       "3       23.68  3.31     No  Sun  Dinner     2\n",
       "4       24.59  3.61     No  Sun  Dinner     4"
      ]
     },
     "execution_count": 32,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df = pd.read_csv(\"examples/tips.csv\")\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style>\n",
       "    .dataframe thead tr:only-child th {\n",
       "        text-align: right;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>total_bill</th>\n",
       "      <th>tip</th>\n",
       "      <th>smoker</th>\n",
       "      <th>day</th>\n",
       "      <th>time</th>\n",
       "      <th>size</th>\n",
       "      <th>tip_pct</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>16.99</td>\n",
       "      <td>1.01</td>\n",
       "      <td>No</td>\n",
       "      <td>Sun</td>\n",
       "      <td>Dinner</td>\n",
       "      <td>2</td>\n",
       "      <td>5.944673</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>10.34</td>\n",
       "      <td>1.66</td>\n",
       "      <td>No</td>\n",
       "      <td>Sun</td>\n",
       "      <td>Dinner</td>\n",
       "      <td>3</td>\n",
       "      <td>16.054159</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>21.01</td>\n",
       "      <td>3.50</td>\n",
       "      <td>No</td>\n",
       "      <td>Sun</td>\n",
       "      <td>Dinner</td>\n",
       "      <td>3</td>\n",
       "      <td>16.658734</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>23.68</td>\n",
       "      <td>3.31</td>\n",
       "      <td>No</td>\n",
       "      <td>Sun</td>\n",
       "      <td>Dinner</td>\n",
       "      <td>2</td>\n",
       "      <td>13.978041</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>24.59</td>\n",
       "      <td>3.61</td>\n",
       "      <td>No</td>\n",
       "      <td>Sun</td>\n",
       "      <td>Dinner</td>\n",
       "      <td>4</td>\n",
       "      <td>14.680765</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   total_bill   tip smoker  day    time  size    tip_pct\n",
       "0       16.99  1.01     No  Sun  Dinner     2   5.944673\n",
       "1       10.34  1.66     No  Sun  Dinner     3  16.054159\n",
       "2       21.01  3.50     No  Sun  Dinner     3  16.658734\n",
       "3       23.68  3.31     No  Sun  Dinner     2  13.978041\n",
       "4       24.59  3.61     No  Sun  Dinner     4  14.680765"
      ]
     },
     "execution_count": 33,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df[\"tip_pct\"] = df.tip / df.total_bill * 100\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style>\n",
       "    .dataframe thead tr:only-child th {\n",
       "        text-align: right;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th>tip_pct</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>day</th>\n",
       "      <th>smoker</th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th rowspan=\"2\" valign=\"top\">Fri</th>\n",
       "      <th>No</th>\n",
       "      <td>15.165044</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Yes</th>\n",
       "      <td>17.478305</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th rowspan=\"2\" valign=\"top\">Sat</th>\n",
       "      <th>No</th>\n",
       "      <td>15.804766</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Yes</th>\n",
       "      <td>14.790607</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th rowspan=\"2\" valign=\"top\">Sun</th>\n",
       "      <th>No</th>\n",
       "      <td>16.011294</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Yes</th>\n",
       "      <td>18.725032</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th rowspan=\"2\" valign=\"top\">Thur</th>\n",
       "      <th>No</th>\n",
       "      <td>16.029808</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Yes</th>\n",
       "      <td>16.386327</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "               tip_pct\n",
       "day  smoker           \n",
       "Fri  No      15.165044\n",
       "     Yes     17.478305\n",
       "Sat  No      15.804766\n",
       "     Yes     14.790607\n",
       "Sun  No      16.011294\n",
       "     Yes     18.725032\n",
       "Thur No      16.029808\n",
       "     Yes     16.386327"
      ]
     },
     "execution_count": 34,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.groupby([\"day\", \"smoker\"])[[\"tip_pct\"]].mean()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 93,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style>\n",
       "    .dataframe thead tr:only-child th {\n",
       "        text-align: right;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th></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",
       "    <tr>\n",
       "      <th>day</th>\n",
       "      <th>smoker</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th rowspan=\"2\" valign=\"top\">Fri</th>\n",
       "      <th>No</th>\n",
       "      <td>4.0</td>\n",
       "      <td>15.165044</td>\n",
       "      <td>2.812295</td>\n",
       "      <td>12.038523</td>\n",
       "      <td>13.723917</td>\n",
       "      <td>14.924093</td>\n",
       "      <td>16.365221</td>\n",
       "      <td>18.773467</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Yes</th>\n",
       "      <td>15.0</td>\n",
       "      <td>17.478305</td>\n",
       "      <td>5.129267</td>\n",
       "      <td>10.355540</td>\n",
       "      <td>13.373871</td>\n",
       "      <td>17.391304</td>\n",
       "      <td>20.924019</td>\n",
       "      <td>26.348039</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th rowspan=\"2\" valign=\"top\">Sat</th>\n",
       "      <th>No</th>\n",
       "      <td>45.0</td>\n",
       "      <td>15.804766</td>\n",
       "      <td>3.976730</td>\n",
       "      <td>5.679667</td>\n",
       "      <td>13.623978</td>\n",
       "      <td>15.015198</td>\n",
       "      <td>18.391451</td>\n",
       "      <td>29.198966</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Yes</th>\n",
       "      <td>42.0</td>\n",
       "      <td>14.790607</td>\n",
       "      <td>6.137495</td>\n",
       "      <td>3.563814</td>\n",
       "      <td>9.179713</td>\n",
       "      <td>15.362439</td>\n",
       "      <td>19.050216</td>\n",
       "      <td>32.573290</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th rowspan=\"2\" valign=\"top\">Sun</th>\n",
       "      <th>No</th>\n",
       "      <td>57.0</td>\n",
       "      <td>16.011294</td>\n",
       "      <td>4.234723</td>\n",
       "      <td>5.944673</td>\n",
       "      <td>13.978041</td>\n",
       "      <td>16.166505</td>\n",
       "      <td>18.518519</td>\n",
       "      <td>25.267250</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Yes</th>\n",
       "      <td>19.0</td>\n",
       "      <td>18.725032</td>\n",
       "      <td>15.413424</td>\n",
       "      <td>6.565988</td>\n",
       "      <td>9.772265</td>\n",
       "      <td>13.812155</td>\n",
       "      <td>21.532480</td>\n",
       "      <td>71.034483</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th rowspan=\"2\" valign=\"top\">Thur</th>\n",
       "      <th>No</th>\n",
       "      <td>45.0</td>\n",
       "      <td>16.029808</td>\n",
       "      <td>3.877420</td>\n",
       "      <td>7.296137</td>\n",
       "      <td>13.774105</td>\n",
       "      <td>15.349194</td>\n",
       "      <td>18.484288</td>\n",
       "      <td>26.631158</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Yes</th>\n",
       "      <td>17.0</td>\n",
       "      <td>16.386327</td>\n",
       "      <td>3.938881</td>\n",
       "      <td>9.001406</td>\n",
       "      <td>14.803849</td>\n",
       "      <td>15.384615</td>\n",
       "      <td>19.483682</td>\n",
       "      <td>24.125452</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "             count       mean        std        min        25%        50%  \\\n",
       "day  smoker                                                                 \n",
       "Fri  No        4.0  15.165044   2.812295  12.038523  13.723917  14.924093   \n",
       "     Yes      15.0  17.478305   5.129267  10.355540  13.373871  17.391304   \n",
       "Sat  No       45.0  15.804766   3.976730   5.679667  13.623978  15.015198   \n",
       "     Yes      42.0  14.790607   6.137495   3.563814   9.179713  15.362439   \n",
       "Sun  No       57.0  16.011294   4.234723   5.944673  13.978041  16.166505   \n",
       "     Yes      19.0  18.725032  15.413424   6.565988   9.772265  13.812155   \n",
       "Thur No       45.0  16.029808   3.877420   7.296137  13.774105  15.349194   \n",
       "     Yes      17.0  16.386327   3.938881   9.001406  14.803849  15.384615   \n",
       "\n",
       "                   75%        max  \n",
       "day  smoker                        \n",
       "Fri  No      16.365221  18.773467  \n",
       "     Yes     20.924019  26.348039  \n",
       "Sat  No      18.391451  29.198966  \n",
       "     Yes     19.050216  32.573290  \n",
       "Sun  No      18.518519  25.267250  \n",
       "     Yes     21.532480  71.034483  \n",
       "Thur No      18.484288  26.631158  \n",
       "     Yes     19.483682  24.125452  "
      ]
     },
     "execution_count": 93,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.groupby([\"day\", \"smoker\"]).tip_pct.aggregate('describe')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style>\n",
       "    .dataframe thead tr:only-child th {\n",
       "        text-align: right;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th>mean</th>\n",
       "      <th>sum</th>\n",
       "      <th>std</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>day</th>\n",
       "      <th>smoker</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th rowspan=\"2\" valign=\"top\">Fri</th>\n",
       "      <th>No</th>\n",
       "      <td>15.165044</td>\n",
       "      <td>60.660177</td>\n",
       "      <td>2.812295</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Yes</th>\n",
       "      <td>17.478305</td>\n",
       "      <td>262.174578</td>\n",
       "      <td>5.129267</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th rowspan=\"2\" valign=\"top\">Sat</th>\n",
       "      <th>No</th>\n",
       "      <td>15.804766</td>\n",
       "      <td>711.214459</td>\n",
       "      <td>3.976730</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Yes</th>\n",
       "      <td>14.790607</td>\n",
       "      <td>621.205474</td>\n",
       "      <td>6.137495</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th rowspan=\"2\" valign=\"top\">Sun</th>\n",
       "      <th>No</th>\n",
       "      <td>16.011294</td>\n",
       "      <td>912.643775</td>\n",
       "      <td>4.234723</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Yes</th>\n",
       "      <td>18.725032</td>\n",
       "      <td>355.775601</td>\n",
       "      <td>15.413424</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th rowspan=\"2\" valign=\"top\">Thur</th>\n",
       "      <th>No</th>\n",
       "      <td>16.029808</td>\n",
       "      <td>721.341368</td>\n",
       "      <td>3.877420</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Yes</th>\n",
       "      <td>16.386327</td>\n",
       "      <td>278.567563</td>\n",
       "      <td>3.938881</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                  mean         sum        std\n",
       "day  smoker                                  \n",
       "Fri  No      15.165044   60.660177   2.812295\n",
       "     Yes     17.478305  262.174578   5.129267\n",
       "Sat  No      15.804766  711.214459   3.976730\n",
       "     Yes     14.790607  621.205474   6.137495\n",
       "Sun  No      16.011294  912.643775   4.234723\n",
       "     Yes     18.725032  355.775601  15.413424\n",
       "Thur No      16.029808  721.341368   3.877420\n",
       "     Yes     16.386327  278.567563   3.938881"
      ]
     },
     "execution_count": 36,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.groupby([\"day\", \"smoker\"]).tip_pct.agg([\"mean\", \"sum\", np.std])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style>\n",
       "    .dataframe thead tr:only-child th {\n",
       "        text-align: right;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th>average</th>\n",
       "      <th>summation</th>\n",
       "      <th>standar dev</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>day</th>\n",
       "      <th>smoker</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th rowspan=\"2\" valign=\"top\">Fri</th>\n",
       "      <th>No</th>\n",
       "      <td>15.165044</td>\n",
       "      <td>60.660177</td>\n",
       "      <td>2.812295</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Yes</th>\n",
       "      <td>17.478305</td>\n",
       "      <td>262.174578</td>\n",
       "      <td>5.129267</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th rowspan=\"2\" valign=\"top\">Sat</th>\n",
       "      <th>No</th>\n",
       "      <td>15.804766</td>\n",
       "      <td>711.214459</td>\n",
       "      <td>3.976730</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Yes</th>\n",
       "      <td>14.790607</td>\n",
       "      <td>621.205474</td>\n",
       "      <td>6.137495</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th rowspan=\"2\" valign=\"top\">Sun</th>\n",
       "      <th>No</th>\n",
       "      <td>16.011294</td>\n",
       "      <td>912.643775</td>\n",
       "      <td>4.234723</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Yes</th>\n",
       "      <td>18.725032</td>\n",
       "      <td>355.775601</td>\n",
       "      <td>15.413424</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th rowspan=\"2\" valign=\"top\">Thur</th>\n",
       "      <th>No</th>\n",
       "      <td>16.029808</td>\n",
       "      <td>721.341368</td>\n",
       "      <td>3.877420</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Yes</th>\n",
       "      <td>16.386327</td>\n",
       "      <td>278.567563</td>\n",
       "      <td>3.938881</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "               average   summation  standar dev\n",
       "day  smoker                                    \n",
       "Fri  No      15.165044   60.660177     2.812295\n",
       "     Yes     17.478305  262.174578     5.129267\n",
       "Sat  No      15.804766  711.214459     3.976730\n",
       "     Yes     14.790607  621.205474     6.137495\n",
       "Sun  No      16.011294  912.643775     4.234723\n",
       "     Yes     18.725032  355.775601    15.413424\n",
       "Thur No      16.029808  721.341368     3.877420\n",
       "     Yes     16.386327  278.567563     3.938881"
      ]
     },
     "execution_count": 41,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import warnings\n",
    "warnings.filterwarnings(action = \"ignore\")\n",
    "df.groupby([\"day\", \"smoker\"]).tip_pct.agg({\"average\" : \"mean\",\n",
    "                                           \"summation\": \"sum\", \n",
    "                                           \"standar dev\" : np.std})"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 43,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style>\n",
       "    .dataframe thead tr:only-child th {\n",
       "        text-align: right;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th colspan=\"3\" halign=\"left\">tip_pct</th>\n",
       "      <th colspan=\"3\" halign=\"left\">total_bill</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th>count</th>\n",
       "      <th>mean</th>\n",
       "      <th>max</th>\n",
       "      <th>count</th>\n",
       "      <th>mean</th>\n",
       "      <th>max</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>day</th>\n",
       "      <th>smoker</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th rowspan=\"2\" valign=\"top\">Fri</th>\n",
       "      <th>No</th>\n",
       "      <td>4</td>\n",
       "      <td>15.165044</td>\n",
       "      <td>18.773467</td>\n",
       "      <td>4</td>\n",
       "      <td>18.420000</td>\n",
       "      <td>22.75</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Yes</th>\n",
       "      <td>15</td>\n",
       "      <td>17.478305</td>\n",
       "      <td>26.348039</td>\n",
       "      <td>15</td>\n",
       "      <td>16.813333</td>\n",
       "      <td>40.17</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th rowspan=\"2\" valign=\"top\">Sat</th>\n",
       "      <th>No</th>\n",
       "      <td>45</td>\n",
       "      <td>15.804766</td>\n",
       "      <td>29.198966</td>\n",
       "      <td>45</td>\n",
       "      <td>19.661778</td>\n",
       "      <td>48.33</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Yes</th>\n",
       "      <td>42</td>\n",
       "      <td>14.790607</td>\n",
       "      <td>32.573290</td>\n",
       "      <td>42</td>\n",
       "      <td>21.276667</td>\n",
       "      <td>50.81</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th rowspan=\"2\" valign=\"top\">Sun</th>\n",
       "      <th>No</th>\n",
       "      <td>57</td>\n",
       "      <td>16.011294</td>\n",
       "      <td>25.267250</td>\n",
       "      <td>57</td>\n",
       "      <td>20.506667</td>\n",
       "      <td>48.17</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Yes</th>\n",
       "      <td>19</td>\n",
       "      <td>18.725032</td>\n",
       "      <td>71.034483</td>\n",
       "      <td>19</td>\n",
       "      <td>24.120000</td>\n",
       "      <td>45.35</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th rowspan=\"2\" valign=\"top\">Thur</th>\n",
       "      <th>No</th>\n",
       "      <td>45</td>\n",
       "      <td>16.029808</td>\n",
       "      <td>26.631158</td>\n",
       "      <td>45</td>\n",
       "      <td>17.113111</td>\n",
       "      <td>41.19</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Yes</th>\n",
       "      <td>17</td>\n",
       "      <td>16.386327</td>\n",
       "      <td>24.125452</td>\n",
       "      <td>17</td>\n",
       "      <td>19.190588</td>\n",
       "      <td>43.11</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "            tip_pct                       total_bill                  \n",
       "              count       mean        max      count       mean    max\n",
       "day  smoker                                                           \n",
       "Fri  No           4  15.165044  18.773467          4  18.420000  22.75\n",
       "     Yes         15  17.478305  26.348039         15  16.813333  40.17\n",
       "Sat  No          45  15.804766  29.198966         45  19.661778  48.33\n",
       "     Yes         42  14.790607  32.573290         42  21.276667  50.81\n",
       "Sun  No          57  16.011294  25.267250         57  20.506667  48.17\n",
       "     Yes         19  18.725032  71.034483         19  24.120000  45.35\n",
       "Thur No          45  16.029808  26.631158         45  17.113111  41.19\n",
       "     Yes         17  16.386327  24.125452         17  19.190588  43.11"
      ]
     },
     "execution_count": 43,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "functions = [\"count\", \"mean\", \"max\"]\n",
    "df.groupby([\"day\", \"smoker\"])[\"tip_pct\", \"total_bill\"].agg(functions)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Apply\n",
    "apply splits an object into pieces, invokes the epassed function on each piece, and then attempts to concatenate the pieces together"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 45,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style>\n",
       "    .dataframe thead tr:only-child th {\n",
       "        text-align: right;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>total_bill</th>\n",
       "      <th>tip</th>\n",
       "      <th>smoker</th>\n",
       "      <th>day</th>\n",
       "      <th>time</th>\n",
       "      <th>size</th>\n",
       "      <th>tip_pct</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>183</th>\n",
       "      <td>23.17</td>\n",
       "      <td>6.50</td>\n",
       "      <td>Yes</td>\n",
       "      <td>Sun</td>\n",
       "      <td>Dinner</td>\n",
       "      <td>4</td>\n",
       "      <td>28.053517</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>232</th>\n",
       "      <td>11.61</td>\n",
       "      <td>3.39</td>\n",
       "      <td>No</td>\n",
       "      <td>Sat</td>\n",
       "      <td>Dinner</td>\n",
       "      <td>2</td>\n",
       "      <td>29.198966</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>67</th>\n",
       "      <td>3.07</td>\n",
       "      <td>1.00</td>\n",
       "      <td>Yes</td>\n",
       "      <td>Sat</td>\n",
       "      <td>Dinner</td>\n",
       "      <td>1</td>\n",
       "      <td>32.573290</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>178</th>\n",
       "      <td>9.60</td>\n",
       "      <td>4.00</td>\n",
       "      <td>Yes</td>\n",
       "      <td>Sun</td>\n",
       "      <td>Dinner</td>\n",
       "      <td>2</td>\n",
       "      <td>41.666667</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>172</th>\n",
       "      <td>7.25</td>\n",
       "      <td>5.15</td>\n",
       "      <td>Yes</td>\n",
       "      <td>Sun</td>\n",
       "      <td>Dinner</td>\n",
       "      <td>2</td>\n",
       "      <td>71.034483</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "     total_bill   tip smoker  day    time  size    tip_pct\n",
       "183       23.17  6.50    Yes  Sun  Dinner     4  28.053517\n",
       "232       11.61  3.39     No  Sat  Dinner     2  29.198966\n",
       "67         3.07  1.00    Yes  Sat  Dinner     1  32.573290\n",
       "178        9.60  4.00    Yes  Sun  Dinner     2  41.666667\n",
       "172        7.25  5.15    Yes  Sun  Dinner     2  71.034483"
      ]
     },
     "execution_count": 45,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "def top_five(data = df, n = 5, column = \"tip_pct\" ):\n",
    "    return df.sort_values(by = column)[-n:]\n",
    "\n",
    "top_five(data = df)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 48,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style>\n",
       "    .dataframe thead tr:only-child th {\n",
       "        text-align: right;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th>total_bill</th>\n",
       "      <th>tip</th>\n",
       "      <th>smoker</th>\n",
       "      <th>day</th>\n",
       "      <th>time</th>\n",
       "      <th>size</th>\n",
       "      <th>tip_pct</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>smoker</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th rowspan=\"5\" valign=\"top\">No</th>\n",
       "      <th>183</th>\n",
       "      <td>23.17</td>\n",
       "      <td>6.50</td>\n",
       "      <td>Yes</td>\n",
       "      <td>Sun</td>\n",
       "      <td>Dinner</td>\n",
       "      <td>4</td>\n",
       "      <td>28.053517</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>232</th>\n",
       "      <td>11.61</td>\n",
       "      <td>3.39</td>\n",
       "      <td>No</td>\n",
       "      <td>Sat</td>\n",
       "      <td>Dinner</td>\n",
       "      <td>2</td>\n",
       "      <td>29.198966</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>67</th>\n",
       "      <td>3.07</td>\n",
       "      <td>1.00</td>\n",
       "      <td>Yes</td>\n",
       "      <td>Sat</td>\n",
       "      <td>Dinner</td>\n",
       "      <td>1</td>\n",
       "      <td>32.573290</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>178</th>\n",
       "      <td>9.60</td>\n",
       "      <td>4.00</td>\n",
       "      <td>Yes</td>\n",
       "      <td>Sun</td>\n",
       "      <td>Dinner</td>\n",
       "      <td>2</td>\n",
       "      <td>41.666667</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>172</th>\n",
       "      <td>7.25</td>\n",
       "      <td>5.15</td>\n",
       "      <td>Yes</td>\n",
       "      <td>Sun</td>\n",
       "      <td>Dinner</td>\n",
       "      <td>2</td>\n",
       "      <td>71.034483</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th rowspan=\"5\" valign=\"top\">Yes</th>\n",
       "      <th>183</th>\n",
       "      <td>23.17</td>\n",
       "      <td>6.50</td>\n",
       "      <td>Yes</td>\n",
       "      <td>Sun</td>\n",
       "      <td>Dinner</td>\n",
       "      <td>4</td>\n",
       "      <td>28.053517</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>232</th>\n",
       "      <td>11.61</td>\n",
       "      <td>3.39</td>\n",
       "      <td>No</td>\n",
       "      <td>Sat</td>\n",
       "      <td>Dinner</td>\n",
       "      <td>2</td>\n",
       "      <td>29.198966</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>67</th>\n",
       "      <td>3.07</td>\n",
       "      <td>1.00</td>\n",
       "      <td>Yes</td>\n",
       "      <td>Sat</td>\n",
       "      <td>Dinner</td>\n",
       "      <td>1</td>\n",
       "      <td>32.573290</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>178</th>\n",
       "      <td>9.60</td>\n",
       "      <td>4.00</td>\n",
       "      <td>Yes</td>\n",
       "      <td>Sun</td>\n",
       "      <td>Dinner</td>\n",
       "      <td>2</td>\n",
       "      <td>41.666667</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>172</th>\n",
       "      <td>7.25</td>\n",
       "      <td>5.15</td>\n",
       "      <td>Yes</td>\n",
       "      <td>Sun</td>\n",
       "      <td>Dinner</td>\n",
       "      <td>2</td>\n",
       "      <td>71.034483</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "            total_bill   tip smoker  day    time  size    tip_pct\n",
       "smoker                                                           \n",
       "No     183       23.17  6.50    Yes  Sun  Dinner     4  28.053517\n",
       "       232       11.61  3.39     No  Sat  Dinner     2  29.198966\n",
       "       67         3.07  1.00    Yes  Sat  Dinner     1  32.573290\n",
       "       178        9.60  4.00    Yes  Sun  Dinner     2  41.666667\n",
       "       172        7.25  5.15    Yes  Sun  Dinner     2  71.034483\n",
       "Yes    183       23.17  6.50    Yes  Sun  Dinner     4  28.053517\n",
       "       232       11.61  3.39     No  Sat  Dinner     2  29.198966\n",
       "       67         3.07  1.00    Yes  Sat  Dinner     1  32.573290\n",
       "       178        9.60  4.00    Yes  Sun  Dinner     2  41.666667\n",
       "       172        7.25  5.15    Yes  Sun  Dinner     2  71.034483"
      ]
     },
     "execution_count": 48,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.groupby(\"smoker\").apply(top_five)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "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": "3.6.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}