{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "skip"
    }
   },
   "source": [
    "(c) 2016 - present. Enplus Advisors, Inc."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "slide"
    }
   },
   "source": [
    "# Programming with Data<br>Foundations of Python and Pandas\n",
    "\n",
    "# Lesson 3: Split, Apply, Combine"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "slideshow": {
     "slide_type": "skip"
    }
   },
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import pandas as pd\n",
    "\n",
    "pd.set_option('display.float_format', '{:,.2f}'.format)\n",
    "\n",
    "def image(name, **kwargs):\n",
    "    from IPython.display import Image\n",
    "    return Image(filename=f'assets/{name}', retina=True, **kwargs)\n",
    "\n",
    "# import matplotlib.pyplot as plt\n",
    "# %matplotlib inline\n",
    "# %config InlineBackend.figure_format='retina'"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "slideshow": {
     "slide_type": "skip"
    }
   },
   "outputs": [],
   "source": [
    "cols = ['year', 'month', 'day', 'hour', 'air_temp', 'dew_point',\n",
    "        'pressure', 'wind_dir', 'wind_speed', 'sky_code',\n",
    "        'precip1', 'precip6']\n",
    "dtypes = {\n",
    "    'year': 'int16',\n",
    "    'month': 'int8',\n",
    "    'day': 'int8',\n",
    "    'hour': 'int8',\n",
    "    'air_temp': 'Int32',\n",
    "    'dew_point': 'Int32',\n",
    "    'pressure': 'float64',\n",
    "    'wind_dir': 'Int32',\n",
    "    'wind_speed': 'float64',\n",
    "    'sky_code': 'Int32',\n",
    "    'precip1': 'Int32',\n",
    "    'precip6': 'Int32'\n",
    "}\n",
    "\n",
    "usecols = ['year', 'month', 'day', 'hour', 'air_temp', \n",
    "           'dew_point', 'wind_speed']\n",
    "\n",
    "dat = (pd.read_fwf(\n",
    "    'data/726505-04845-2009', header=None, names=cols,\n",
    "    dtype=dtypes, na_values='-9999', usecols=usecols)\n",
    "    .query(\"month <= 6\")\n",
    "    .assign(\n",
    "        air_temp=lambda df: df.air_temp / 10., # Celsius * 10\n",
    "        dew_point=lambda df: df.dew_point / 10. # Celsius * 10\n",
    "        # wind_speed=lambda df: df.wind_speed / 10. # meters/sec * 10\n",
    "))\n",
    "\n",
    "# dat.to_csv('data/weather-6m.csv', index=False, columns=usecols)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "slideshow": {
     "slide_type": "skip"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([2009], dtype=int16)"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "dat.year.unique()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "slideshow": {
     "slide_type": "skip"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "year            int16\n",
       "month            int8\n",
       "day              int8\n",
       "hour             int8\n",
       "air_temp      float64\n",
       "dew_point     float64\n",
       "wind_speed    float64\n",
       "dtype: object"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "dat.dtypes"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "slide"
    }
   },
   "source": [
    "# Weather Data from NOAA\n",
    "\n",
    "Hourly data for a single weather station in 2009."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "slideshow": {
     "slide_type": "fragment"
    }
   },
   "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>year</th>\n",
       "      <th>month</th>\n",
       "      <th>day</th>\n",
       "      <th>hour</th>\n",
       "      <th>air_temp</th>\n",
       "      <th>dew_point</th>\n",
       "      <th>wind_speed</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>2009</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>-13.30</td>\n",
       "      <td>-16.70</td>\n",
       "      <td>15.00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2009</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>-13.30</td>\n",
       "      <td>-16.10</td>\n",
       "      <td>26.00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2009</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>-12.20</td>\n",
       "      <td>-15.60</td>\n",
       "      <td>0.00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>2009</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>4</td>\n",
       "      <td>-11.70</td>\n",
       "      <td>-15.00</td>\n",
       "      <td>0.00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>2009</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>5</td>\n",
       "      <td>-11.10</td>\n",
       "      <td>-15.00</td>\n",
       "      <td>15.00</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   year  month  day  hour  air_temp  dew_point  wind_speed\n",
       "0  2009      1    1     1    -13.30     -16.70       15.00\n",
       "1  2009      1    1     2    -13.30     -16.10       26.00\n",
       "2  2009      1    1     3    -12.20     -15.60        0.00\n",
       "3  2009      1    1     4    -11.70     -15.00        0.00\n",
       "4  2009      1    1     5    -11.10     -15.00       15.00"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "dat.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "slide"
    }
   },
   "source": [
    "## Visualize Split, Aggregate, Combine"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "slideshow": {
     "slide_type": "fragment"
    }
   },
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<IPython.core.display.Image object>"
      ]
     },
     "execution_count": 6,
     "metadata": {
      "image/png": {
       "height": 410,
       "width": 600
      }
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "image('split-apply-combine.png')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "slide"
    }
   },
   "source": [
    "## As implemented by `pandas`\n",
    "\n",
    "* Split only\n",
    "* Return a single, aggregate value per group/column (`agg`)\n",
    "* Return one or more rows/columns per group (`apply`)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "slide"
    }
   },
   "source": [
    "## Split-Only\n",
    "\n",
    "* Iteration over the split `DataFrame`\n",
    "* You are responsible for applying functions and combining data\n",
    "* __BYOAC__ - Bring your own apply-combine"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "slideshow": {
     "slide_type": "fragment"
    }
   },
   "outputs": [],
   "source": [
    "grp = dat.groupby('month')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {
    "slideshow": {
     "slide_type": "fragment"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Month: 1\n"
     ]
    }
   ],
   "source": [
    "for month, month_df in grp:\n",
    "    print(f'Month: {month}')\n",
    "    break # stop the iteration"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {
    "slideshow": {
     "slide_type": "fragment"
    }
   },
   "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>year</th>\n",
       "      <th>month</th>\n",
       "      <th>day</th>\n",
       "      <th>hour</th>\n",
       "      <th>air_temp</th>\n",
       "      <th>dew_point</th>\n",
       "      <th>wind_speed</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>2009</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>-13.30</td>\n",
       "      <td>-16.70</td>\n",
       "      <td>15.00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2009</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>-13.30</td>\n",
       "      <td>-16.10</td>\n",
       "      <td>26.00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2009</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>-12.20</td>\n",
       "      <td>-15.60</td>\n",
       "      <td>0.00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>2009</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>4</td>\n",
       "      <td>-11.70</td>\n",
       "      <td>-15.00</td>\n",
       "      <td>0.00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>2009</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>5</td>\n",
       "      <td>-11.10</td>\n",
       "      <td>-15.00</td>\n",
       "      <td>15.00</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   year  month  day  hour  air_temp  dew_point  wind_speed\n",
       "0  2009      1    1     1    -13.30     -16.70       15.00\n",
       "1  2009      1    1     2    -13.30     -16.10       26.00\n",
       "2  2009      1    1     3    -12.20     -15.60        0.00\n",
       "3  2009      1    1     4    -11.70     -15.00        0.00\n",
       "4  2009      1    1     5    -11.10     -15.00       15.00"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "month_df.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "slide"
    }
   },
   "source": [
    "## Computing on the GroupBy object"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "fragment"
    }
   },
   "source": [
    "grp.groups is a dictionary of groups -> index elements"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {
    "slideshow": {
     "slide_type": "fragment"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "dict_keys([1, 2, 3, 4, 5, 6])"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Get the group names\n",
    "grp.groups.keys()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {
    "slideshow": {
     "slide_type": "fragment"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Int64Index([0, 1, 2, 3, 4], dtype='int64')"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "list(grp.groups.values())[0][:5]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "slide"
    }
   },
   "source": [
    "### Extract specific groups"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {
    "slideshow": {
     "slide_type": "fragment"
    }
   },
   "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>year</th>\n",
       "      <th>month</th>\n",
       "      <th>day</th>\n",
       "      <th>hour</th>\n",
       "      <th>air_temp</th>\n",
       "      <th>dew_point</th>\n",
       "      <th>wind_speed</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>2009</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>-13.30</td>\n",
       "      <td>-16.70</td>\n",
       "      <td>15.00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2009</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>-13.30</td>\n",
       "      <td>-16.10</td>\n",
       "      <td>26.00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2009</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>-12.20</td>\n",
       "      <td>-15.60</td>\n",
       "      <td>0.00</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   year  month  day  hour  air_temp  dew_point  wind_speed\n",
       "0  2009      1    1     1    -13.30     -16.70       15.00\n",
       "1  2009      1    1     2    -13.30     -16.10       26.00\n",
       "2  2009      1    1     3    -12.20     -15.60        0.00"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Retrieve a specific group\n",
    "\n",
    "grp.get_group(1)[:3] # first few rows"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "slide"
    }
   },
   "source": [
    "## One aggregate per column/group"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "fragment"
    }
   },
   "source": [
    "Default applies to all numeric columns."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {
    "scrolled": true,
    "slideshow": {
     "slide_type": "fragment"
    }
   },
   "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>year</th>\n",
       "      <th>day</th>\n",
       "      <th>hour</th>\n",
       "      <th>air_temp</th>\n",
       "      <th>dew_point</th>\n",
       "      <th>wind_speed</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>month</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>1</th>\n",
       "      <td>2009</td>\n",
       "      <td>16.02</td>\n",
       "      <td>11.52</td>\n",
       "      <td>-10.01</td>\n",
       "      <td>-14.11</td>\n",
       "      <td>42.85</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2009</td>\n",
       "      <td>14.50</td>\n",
       "      <td>11.50</td>\n",
       "      <td>-2.95</td>\n",
       "      <td>-7.25</td>\n",
       "      <td>47.96</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>2009</td>\n",
       "      <td>16.00</td>\n",
       "      <td>11.50</td>\n",
       "      <td>2.10</td>\n",
       "      <td>-3.42</td>\n",
       "      <td>44.69</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>2009</td>\n",
       "      <td>15.50</td>\n",
       "      <td>11.50</td>\n",
       "      <td>7.03</td>\n",
       "      <td>0.27</td>\n",
       "      <td>49.48</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>2009</td>\n",
       "      <td>16.00</td>\n",
       "      <td>11.50</td>\n",
       "      <td>13.98</td>\n",
       "      <td>6.24</td>\n",
       "      <td>42.60</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>2009</td>\n",
       "      <td>15.49</td>\n",
       "      <td>11.51</td>\n",
       "      <td>18.06</td>\n",
       "      <td>12.25</td>\n",
       "      <td>32.73</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       year   day  hour  air_temp  dew_point  wind_speed\n",
       "month                                                   \n",
       "1      2009 16.02 11.52    -10.01     -14.11       42.85\n",
       "2      2009 14.50 11.50     -2.95      -7.25       47.96\n",
       "3      2009 16.00 11.50      2.10      -3.42       44.69\n",
       "4      2009 15.50 11.50      7.03       0.27       49.48\n",
       "5      2009 16.00 11.50     13.98       6.24       42.60\n",
       "6      2009 15.49 11.51     18.06      12.25       32.73"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "grp.mean()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "slide"
    }
   },
   "source": [
    "### Select a single column"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "fragment"
    }
   },
   "source": [
    "Reduce over one column and return a `Series` or `DataFrame`"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {
    "slideshow": {
     "slide_type": "fragment"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "month\n",
       "1   -10.01\n",
       "2    -2.95\n",
       "3     2.10\n",
       "4     7.03\n",
       "5    13.98\n",
       "6    18.06\n",
       "Name: air_temp, dtype: float64"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Returns a Series\n",
    "grp['air_temp'].mean()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {
    "slideshow": {
     "slide_type": "fragment"
    }
   },
   "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>month</th>\n",
       "      <th>1</th>\n",
       "      <th>2</th>\n",
       "      <th>3</th>\n",
       "      <th>4</th>\n",
       "      <th>5</th>\n",
       "      <th>6</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>air_temp</th>\n",
       "      <td>-10.01</td>\n",
       "      <td>-2.95</td>\n",
       "      <td>2.10</td>\n",
       "      <td>7.03</td>\n",
       "      <td>13.98</td>\n",
       "      <td>18.06</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "month         1     2    3    4     5     6\n",
       "air_temp -10.01 -2.95 2.10 7.03 13.98 18.06"
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Returns a DataFrame\n",
    "grp[['air_temp']].mean().T"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "slide"
    }
   },
   "source": [
    "### One function, multiple columns"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "fragment"
    }
   },
   "source": [
    "Apply the same function to multiple *selected* columns."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {
    "slideshow": {
     "slide_type": "fragment"
    }
   },
   "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>air_temp</th>\n",
       "      <th>dew_point</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>month</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>-10.01</td>\n",
       "      <td>-14.11</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>-2.95</td>\n",
       "      <td>-7.25</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>2.10</td>\n",
       "      <td>-3.42</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>7.03</td>\n",
       "      <td>0.27</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>13.98</td>\n",
       "      <td>6.24</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>18.06</td>\n",
       "      <td>12.25</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       air_temp  dew_point\n",
       "month                     \n",
       "1        -10.01     -14.11\n",
       "2         -2.95      -7.25\n",
       "3          2.10      -3.42\n",
       "4          7.03       0.27\n",
       "5         13.98       6.24\n",
       "6         18.06      12.25"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "grp[['air_temp', 'dew_point']].mean()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "slide"
    }
   },
   "source": [
    "### Multiple functions, one or more columns"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "fragment"
    }
   },
   "source": [
    "Apply different functions to a single column.\n",
    "\n",
    "Use `agg` method (short for `aggregate`)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "fragment"
    }
   },
   "source": [
    "Apply different functions to a single column. Result columns have the same\n",
    "names as the functions, e.g. `mean`, `sum`, `std`."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {
    "scrolled": true,
    "slideshow": {
     "slide_type": "fragment"
    }
   },
   "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>mean</th>\n",
       "      <th>sum</th>\n",
       "      <th>std</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>month</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>-10.01</td>\n",
       "      <td>-7,125.40</td>\n",
       "      <td>6.16</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>-2.95</td>\n",
       "      <td>-1,900.70</td>\n",
       "      <td>6.78</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>2.10</td>\n",
       "      <td>1,498.70</td>\n",
       "      <td>6.70</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>7.03</td>\n",
       "      <td>4,855.30</td>\n",
       "      <td>5.96</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>13.98</td>\n",
       "      <td>9,965.90</td>\n",
       "      <td>5.11</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>18.06</td>\n",
       "      <td>12,424.80</td>\n",
       "      <td>6.00</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "        mean       sum  std\n",
       "month                      \n",
       "1     -10.01 -7,125.40 6.16\n",
       "2      -2.95 -1,900.70 6.78\n",
       "3       2.10  1,498.70 6.70\n",
       "4       7.03  4,855.30 5.96\n",
       "5      13.98  9,965.90 5.11\n",
       "6      18.06 12,424.80 6.00"
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "grp['air_temp'].agg([np.mean, np.sum, 'std'])"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "slide"
    }
   },
   "source": [
    "### Multiple functions, multiple columns\n",
    "\n",
    "Again, use the `agg` method. This parameterization gives the result `DataFrame` custom names."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {
    "slideshow": {
     "slide_type": "fragment"
    }
   },
   "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>mean_air_temp</th>\n",
       "      <th>mean_dew_point</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>month</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>-10.01</td>\n",
       "      <td>-14.11</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>-2.95</td>\n",
       "      <td>-7.25</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>2.10</td>\n",
       "      <td>-3.42</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>7.03</td>\n",
       "      <td>0.27</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>13.98</td>\n",
       "      <td>6.24</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>18.06</td>\n",
       "      <td>12.25</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       mean_air_temp  mean_dew_point\n",
       "month                               \n",
       "1             -10.01          -14.11\n",
       "2              -2.95           -7.25\n",
       "3               2.10           -3.42\n",
       "4               7.03            0.27\n",
       "5              13.98            6.24\n",
       "6              18.06           12.25"
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "grp.agg(\n",
    "    mean_air_temp=('air_temp', lambda x: x.mean()),\n",
    "    mean_dew_point=('dew_point', 'mean'),\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "slide"
    }
   },
   "source": [
    "#### Pandas < 0.25"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {
    "scrolled": true,
    "slideshow": {
     "slide_type": "fragment"
    }
   },
   "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>mean_air_temp</th>\n",
       "      <th>mean_dew_point</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>month</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>-10.01</td>\n",
       "      <td>-14.11</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>-2.95</td>\n",
       "      <td>-7.25</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>2.10</td>\n",
       "      <td>-3.42</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>7.03</td>\n",
       "      <td>0.27</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>13.98</td>\n",
       "      <td>6.24</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>18.06</td>\n",
       "      <td>12.25</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       mean_air_temp  mean_dew_point\n",
       "month                               \n",
       "1             -10.01          -14.11\n",
       "2              -2.95           -7.25\n",
       "3               2.10           -3.42\n",
       "4               7.03            0.27\n",
       "5              13.98            6.24\n",
       "6              18.06           12.25"
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "grp.agg({\n",
    "    'air_temp': lambda x: x.mean(),\n",
    "    'dew_point': 'mean'\n",
    "}).rename(columns={\n",
    "    'air_temp': 'mean_air_temp',\n",
    "    'dew_point': 'mean_dew_point'\n",
    "})"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "slide"
    }
   },
   "source": [
    "## Grouping by Multiple Variables"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "fragment"
    }
   },
   "source": [
    "Same idea as before, except our results now have a MultiIndex."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {
    "slideshow": {
     "slide_type": "fragment"
    }
   },
   "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></th>\n",
       "      <th>air_temp</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>month</th>\n",
       "      <th>hour</th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th rowspan=\"5\" valign=\"top\">1</th>\n",
       "      <th>0</th>\n",
       "      <td>-9.40</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>-9.96</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>-10.42</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>-10.70</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>-11.18</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th rowspan=\"5\" valign=\"top\">6</th>\n",
       "      <th>19</th>\n",
       "      <td>22.25</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>20</th>\n",
       "      <td>21.97</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>21</th>\n",
       "      <td>21.73</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>22</th>\n",
       "      <td>21.21</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>23</th>\n",
       "      <td>20.87</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>144 rows × 1 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "            air_temp\n",
       "month hour          \n",
       "1     0        -9.40\n",
       "      1        -9.96\n",
       "      2       -10.42\n",
       "      3       -10.70\n",
       "      4       -11.18\n",
       "...              ...\n",
       "6     19       22.25\n",
       "      20       21.97\n",
       "      21       21.73\n",
       "      22       21.21\n",
       "      23       20.87\n",
       "\n",
       "[144 rows x 1 columns]"
      ]
     },
     "execution_count": 20,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "grp2 = dat.groupby(['month', 'hour'])\n",
    "grp2[['air_temp']].mean()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "slide"
    }
   },
   "source": [
    "## One or more values per group"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "fragment"
    }
   },
   "source": [
    "Reduce/aggregate (`agg`) assumes we go from many observations to 1 result value"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "fragment"
    }
   },
   "source": [
    "To return multiple rows and/or columns per group, `agg` doesn't work"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "fragment"
    }
   },
   "source": [
    "Need a new method, `apply`"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "slide"
    }
   },
   "source": [
    "### Apply/Reduce returning one row, > 1 columns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {
    "slideshow": {
     "slide_type": "fragment"
    }
   },
   "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>air_temp</th>\n",
       "      <th>0.25</th>\n",
       "      <th>0.50</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>month</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>-13.30</td>\n",
       "      <td>-10.00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>-7.20</td>\n",
       "      <td>-2.20</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>-1.70</td>\n",
       "      <td>2.20</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>2.80</td>\n",
       "      <td>5.60</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>10.60</td>\n",
       "      <td>13.90</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>13.75</td>\n",
       "      <td>17.80</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "air_temp   0.25   0.50\n",
       "month                 \n",
       "1        -13.30 -10.00\n",
       "2         -7.20  -2.20\n",
       "3         -1.70   2.20\n",
       "4          2.80   5.60\n",
       "5         10.60  13.90\n",
       "6         13.75  17.80"
      ]
     },
     "execution_count": 21,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "grp3 = dat.groupby('month')\n",
    "grp3.apply(lambda df: df.air_temp.quantile([0.25, 0.5]))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "slide"
    }
   },
   "source": [
    "### Apply/Reduce returning > 1 rows, > 1 columns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {
    "slideshow": {
     "slide_type": "fragment"
    }
   },
   "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></th>\n",
       "      <th>year</th>\n",
       "      <th>month</th>\n",
       "      <th>day</th>\n",
       "      <th>hour</th>\n",
       "      <th>air_temp</th>\n",
       "      <th>dew_point</th>\n",
       "      <th>wind_speed</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>month</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\">1</th>\n",
       "      <th>0</th>\n",
       "      <td>2009</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>-13.30</td>\n",
       "      <td>-16.70</td>\n",
       "      <td>15.00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2009</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>-13.30</td>\n",
       "      <td>-16.10</td>\n",
       "      <td>26.00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th rowspan=\"2\" valign=\"top\">2</th>\n",
       "      <th>743</th>\n",
       "      <td>2009</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>2.80</td>\n",
       "      <td>-1.70</td>\n",
       "      <td>82.00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>744</th>\n",
       "      <td>2009</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>2.80</td>\n",
       "      <td>-1.70</td>\n",
       "      <td>82.00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th rowspan=\"2\" valign=\"top\">3</th>\n",
       "      <th>1415</th>\n",
       "      <td>2009</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>-7.20</td>\n",
       "      <td>-10.60</td>\n",
       "      <td>21.00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1416</th>\n",
       "      <td>2009</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>-7.20</td>\n",
       "      <td>-10.00</td>\n",
       "      <td>15.00</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "            year  month  day  hour  air_temp  dew_point  wind_speed\n",
       "month                                                              \n",
       "1     0     2009      1    1     1    -13.30     -16.70       15.00\n",
       "      1     2009      1    1     2    -13.30     -16.10       26.00\n",
       "2     743   2009      2    1     0      2.80      -1.70       82.00\n",
       "      744   2009      2    1     1      2.80      -1.70       82.00\n",
       "3     1415  2009      3    1     0     -7.20     -10.60       21.00\n",
       "      1416  2009      3    1     1     -7.20     -10.00       15.00"
      ]
     },
     "execution_count": 22,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "grp3.apply(lambda df: df.iloc[:2, ]).head(6)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "notes"
    }
   },
   "source": [
    "TODO: Add Filter, Transform\n",
    "\n",
    "\n",
    "\n",
    "SHOW: Combining index and group"
   ]
  }
 ],
 "metadata": {
  "celltoolbar": "Slideshow",
  "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": "3.8.3"
  },
  "toc": {
   "base_numbering": 1,
   "nav_menu": {},
   "number_sections": false,
   "sideBar": true,
   "skip_h1_title": true,
   "title_cell": "Table of Contents",
   "title_sidebar": "Contents",
   "toc_cell": false,
   "toc_position": {
    "height": "calc(100% - 180px)",
    "left": "10px",
    "top": "150px",
    "width": "288px"
   },
   "toc_section_display": true,
   "toc_window_display": true
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}