{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Pandas\n",
    "\n",
    "[Pandas](http://pandas.pydata.org/) is a an open source library providing high-performance, easy-to-use data structures and data analysis tools. Pandas is particularly suited to the analysis of _tabular_ data, i.e. data that can can go into a table. In other words, if you can imagine the data in an Excel spreadsheet, then Pandas is the tool for the job.\n",
    "\n",
    "A [recent analysis](https://stackoverflow.blog/2017/09/06/incredible-growth-python/) of questions from Stack Overflow showed that python is the fastest growing and most widely used programming language in the world (in developed countries).\n",
    "\n",
    "![python growth](https://zgab33vy595fw5zq-zippykid.netdna-ssl.com/wp-content/uploads/2017/09/growth_major_languages-1-1024x878.png)\n",
    "\n",
    "A [follow-up analysis](https://stackoverflow.blog/2017/09/14/python-growing-quickly/) showed that this growth is driven by the data science packages such as numpy, matplotlib, and especially pandas.\n",
    "\n",
    "![pandas growth](https://zgab33vy595fw5zq-zippykid.netdna-ssl.com/wp-content/uploads/2017/09/related_tags_over_time-1-1024x1024.png)\n",
    "\n",
    "The exponential growth of pandas is due to the fact that it _just works_. It saves you time and helps you do science more efficiently and effictively.\n",
    "\n",
    "### Pandas capabilities (from the Pandas website):\n",
    "\n",
    "* A fast and efficient DataFrame object for data manipulation with integrated indexing;\n",
    "* Tools for reading and writing data between in-memory data structures and different formats: CSV and text files, Microsoft Excel, SQL databases, and the fast HDF5 format;\n",
    "* Intelligent data alignment and integrated handling of missing data: gain automatic label-based alignment in computations and easily manipulate messy data into an orderly form;\n",
    "* Flexible reshaping and pivoting of data sets;\n",
    "* Intelligent label-based slicing, fancy indexing, and subsetting of large data sets;\n",
    "* Columns can be inserted and deleted from data structures for size mutability;\n",
    "* Aggregating or transforming data with a powerful group by engine allowing split-apply-combine operations on data sets;\n",
    "* High performance merging and joining of data sets;\n",
    "* Hierarchical axis indexing provides an intuitive way of working with high-dimensional data in a lower-dimensional data structure;\n",
    "* Time series-functionality: date range generation and frequency conversion, moving window statistics, moving window linear regressions, date shifting and lagging. Even create domain-specific time offsets and join time series without losing data;\n",
    "* Highly optimized for performance, with critical code paths written in Cython or C.\n",
    "* Python with pandas is in use in a wide variety of academic and commercial domains, including Finance, Neuroscience, Economics, Statistics, Advertising, Web Analytics, and more.\n",
    "\n",
    "In this lecture, we will go over the basic capabilities of Pandas. It is a very deep library, and you will need to dig into the [documentation](http://pandas.pydata.org/pandas-docs/stable/) for more advanced usage.\n",
    "\n",
    "Pandas was created by [Wes McKinney](http://wesmckinney.com/). Many of the examples here are drawn from Wes McKinney's book [Python for Data Analysis](http://shop.oreilly.com/product/0636920023784.do), which includes a github repo of [code samples](https://github.com/wesm/pydata-book)."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "from matplotlib import pyplot as plt\n",
    "%matplotlib inline"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Pandas Data Structures: Series\n",
    "\n",
    "A Series represents a one-dimensional array of data. The main difference between a Series and numpy array is that a Series has an _index_. The index contains the labels that we use to access the data.\n",
    "\n",
    "There are many ways to [create a Series](https://pandas.pydata.org/pandas-docs/stable/dsintro.html#series). We will just show a few."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Ryan      35.0\n",
       "Chiara    36.0\n",
       "Johnny     1.8\n",
       "dtype: float64"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "names = ['Ryan', 'Chiara', 'Johnny']\n",
    "values = [35, 36, 1.8]\n",
    "ages = pd.Series(values, index=names)\n",
    "ages"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Series have built in plotting methods."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.axes._subplots.AxesSubplot at 0x7fa9e3ea7510>"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "ages.plot(kind='bar')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Arithmetic operations and most numpy function can be applied to Series.\n",
    "An important point is that the Series keep their index during such operations."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Ryan      0.002902\n",
       "Chiara    0.002765\n",
       "Johnny    0.181416\n",
       "dtype: float64"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "np.log(ages) / ages**2"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "We can access the underlying index object if we need to:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Index([u'Ryan', u'Chiara', u'Johnny'], dtype='object')"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "ages.index"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "We can get values back out using the index via the `.loc` attribute"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "1.8"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "ages.loc['Johnny']"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Or by raw position using `.iloc`"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "1.8"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "ages.iloc[2]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "If we need to, we can always get the raw data back out as well"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([35. , 36. ,  1.8])"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "ages.values"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Index([u'Ryan', u'Chiara', u'Johnny'], dtype='object')"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "ages.index"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Pandas Data Structures: DataFrame\n",
    "\n",
    "There is a lot more to Series, but they are limit to a single \"column\". A more useful Pandas data structure is the DataFrame. A DataFrame is basically a bunch of series that share the same index. It's a lot like a table in a spreadsheet.\n",
    "\n",
    "Below we create a DataFrame."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>age</th>\n",
       "      <th>height</th>\n",
       "      <th>weight</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>Ryan</th>\n",
       "      <td>35.0</td>\n",
       "      <td>180</td>\n",
       "      <td>72.5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Chiara</th>\n",
       "      <td>36.0</td>\n",
       "      <td>155</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Johnny</th>\n",
       "      <td>1.8</td>\n",
       "      <td>83</td>\n",
       "      <td>11.3</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "         age  height  weight\n",
       "Ryan    35.0     180    72.5\n",
       "Chiara  36.0     155     NaN\n",
       "Johnny   1.8      83    11.3"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# first we create a dictionary\n",
    "data = {'age': [35, 36, 1.8],\n",
    "        'height': [180, 155, 83],\n",
    "        'weight': [72.5, np.nan, 11.3]}\n",
    "df = pd.DataFrame(data, index=['Ryan', 'Chiara', 'Johnny'])\n",
    "df"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Pandas handles missing data very elegantly, keeping track of it through all calculations."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "Index: 3 entries, Ryan to Johnny\n",
      "Data columns (total 3 columns):\n",
      "age       3 non-null float64\n",
      "height    3 non-null int64\n",
      "weight    2 non-null float64\n",
      "dtypes: float64(2), int64(1)\n",
      "memory usage: 96.0+ bytes\n"
     ]
    }
   ],
   "source": [
    "df.info()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "A wide range of statistical functions are available on both Series and DataFrames."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "age        1.8\n",
       "height    83.0\n",
       "weight    11.3\n",
       "dtype: float64"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.min()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "age        24.266667\n",
       "height    139.333333\n",
       "weight     41.900000\n",
       "dtype: float64"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.mean()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "age       19.463128\n",
       "height    50.362023\n",
       "weight    43.274935\n",
       "dtype: float64"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.std()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>age</th>\n",
       "      <th>height</th>\n",
       "      <th>weight</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>3.000000</td>\n",
       "      <td>3.000000</td>\n",
       "      <td>2.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>24.266667</td>\n",
       "      <td>139.333333</td>\n",
       "      <td>41.900000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>19.463128</td>\n",
       "      <td>50.362023</td>\n",
       "      <td>43.274935</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>1.800000</td>\n",
       "      <td>83.000000</td>\n",
       "      <td>11.300000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>18.400000</td>\n",
       "      <td>119.000000</td>\n",
       "      <td>26.600000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>35.000000</td>\n",
       "      <td>155.000000</td>\n",
       "      <td>41.900000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>35.500000</td>\n",
       "      <td>167.500000</td>\n",
       "      <td>57.200000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>36.000000</td>\n",
       "      <td>180.000000</td>\n",
       "      <td>72.500000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "             age      height     weight\n",
       "count   3.000000    3.000000   2.000000\n",
       "mean   24.266667  139.333333  41.900000\n",
       "std    19.463128   50.362023  43.274935\n",
       "min     1.800000   83.000000  11.300000\n",
       "25%    18.400000  119.000000  26.600000\n",
       "50%    35.000000  155.000000  41.900000\n",
       "75%    35.500000  167.500000  57.200000\n",
       "max    36.000000  180.000000  72.500000"
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.describe()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "We can get a single column as a Series using python's getitem syntax on the DataFrame object."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Ryan      180\n",
       "Chiara    155\n",
       "Johnny     83\n",
       "Name: height, dtype: int64"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df['height']"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "...or using attribute syntax."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Ryan      180\n",
       "Chiara    155\n",
       "Johnny     83\n",
       "Name: height, dtype: int64"
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.height"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "New columns can easily be added to DataFrames"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>age</th>\n",
       "      <th>height</th>\n",
       "      <th>weight</th>\n",
       "      <th>density</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>Ryan</th>\n",
       "      <td>35.0</td>\n",
       "      <td>180</td>\n",
       "      <td>72.5</td>\n",
       "      <td>0.402778</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Chiara</th>\n",
       "      <td>36.0</td>\n",
       "      <td>155</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Johnny</th>\n",
       "      <td>1.8</td>\n",
       "      <td>83</td>\n",
       "      <td>11.3</td>\n",
       "      <td>0.136145</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "         age  height  weight   density\n",
       "Ryan    35.0     180    72.5  0.402778\n",
       "Chiara  36.0     155     NaN       NaN\n",
       "Johnny   1.8      83    11.3  0.136145"
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df['density'] = df.weight / df.height\n",
    "df"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Merging Data\n",
    "\n",
    "Pandas supports a wide range of methods for merging different datasets. These are described extensively in the [documentation](https://pandas.pydata.org/pandas-docs/stable/merging.html). Here we just give a few examples."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>age</th>\n",
       "      <th>height</th>\n",
       "      <th>weight</th>\n",
       "      <th>density</th>\n",
       "      <th>education</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>Ryan</th>\n",
       "      <td>35.0</td>\n",
       "      <td>180</td>\n",
       "      <td>72.5</td>\n",
       "      <td>0.402778</td>\n",
       "      <td>PhD</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Chiara</th>\n",
       "      <td>36.0</td>\n",
       "      <td>155</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>PhD</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Johnny</th>\n",
       "      <td>1.8</td>\n",
       "      <td>83</td>\n",
       "      <td>11.3</td>\n",
       "      <td>0.136145</td>\n",
       "      <td>None</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "         age  height  weight   density education\n",
       "Ryan    35.0     180    72.5  0.402778       PhD\n",
       "Chiara  36.0     155     NaN       NaN       PhD\n",
       "Johnny   1.8      83    11.3  0.136145      None"
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "education = pd.Series(['PhD', 'PhD', None, 'masters'],\n",
    "                     index=['Ryan', 'Chiara', 'Johnny', 'Takaya'],\n",
    "                     name='education')\n",
    "# returns a new DataFrame\n",
    "df.join(education)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>age</th>\n",
       "      <th>height</th>\n",
       "      <th>weight</th>\n",
       "      <th>density</th>\n",
       "      <th>education</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>Ryan</th>\n",
       "      <td>35.0</td>\n",
       "      <td>180.0</td>\n",
       "      <td>72.5</td>\n",
       "      <td>0.402778</td>\n",
       "      <td>PhD</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Chiara</th>\n",
       "      <td>36.0</td>\n",
       "      <td>155.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>PhD</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Johnny</th>\n",
       "      <td>1.8</td>\n",
       "      <td>83.0</td>\n",
       "      <td>11.3</td>\n",
       "      <td>0.136145</td>\n",
       "      <td>None</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Takaya</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>masters</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "         age  height  weight   density education\n",
       "Ryan    35.0   180.0    72.5  0.402778       PhD\n",
       "Chiara  36.0   155.0     NaN       NaN       PhD\n",
       "Johnny   1.8    83.0    11.3  0.136145      None\n",
       "Takaya   NaN     NaN     NaN       NaN   masters"
      ]
     },
     "execution_count": 20,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# returns a new DataFrame\n",
    "df.join(education, how='right')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>age</th>\n",
       "      <th>height</th>\n",
       "      <th>weight</th>\n",
       "      <th>density</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>Ryan</th>\n",
       "      <td>35.0</td>\n",
       "      <td>180.0</td>\n",
       "      <td>72.5</td>\n",
       "      <td>0.402778</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Chiara</th>\n",
       "      <td>36.0</td>\n",
       "      <td>155.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Johnny</th>\n",
       "      <td>1.8</td>\n",
       "      <td>83.0</td>\n",
       "      <td>11.3</td>\n",
       "      <td>0.136145</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Takaya</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Kerry</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "         age  height  weight   density\n",
       "Ryan    35.0   180.0    72.5  0.402778\n",
       "Chiara  36.0   155.0     NaN       NaN\n",
       "Johnny   1.8    83.0    11.3  0.136145\n",
       "Takaya   NaN     NaN     NaN       NaN\n",
       "Kerry    NaN     NaN     NaN       NaN"
      ]
     },
     "execution_count": 21,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# returns a new DataFrame\n",
    "df.reindex(['Ryan', 'Chiara', 'Johnny', 'Takaya', 'Kerry'])"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "We can also index using a boolean series. This is very useful"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>age</th>\n",
       "      <th>height</th>\n",
       "      <th>weight</th>\n",
       "      <th>density</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>Ryan</th>\n",
       "      <td>35.0</td>\n",
       "      <td>180</td>\n",
       "      <td>72.5</td>\n",
       "      <td>0.402778</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Chiara</th>\n",
       "      <td>36.0</td>\n",
       "      <td>155</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "         age  height  weight   density\n",
       "Ryan    35.0     180    72.5  0.402778\n",
       "Chiara  36.0     155     NaN       NaN"
      ]
     },
     "execution_count": 22,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "adults = df[df.age > 18]\n",
    "adults"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>age</th>\n",
       "      <th>height</th>\n",
       "      <th>weight</th>\n",
       "      <th>density</th>\n",
       "      <th>is_adult</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>Ryan</th>\n",
       "      <td>35.0</td>\n",
       "      <td>180</td>\n",
       "      <td>72.5</td>\n",
       "      <td>0.402778</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Chiara</th>\n",
       "      <td>36.0</td>\n",
       "      <td>155</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Johnny</th>\n",
       "      <td>1.8</td>\n",
       "      <td>83</td>\n",
       "      <td>11.3</td>\n",
       "      <td>0.136145</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "         age  height  weight   density  is_adult\n",
       "Ryan    35.0     180    72.5  0.402778      True\n",
       "Chiara  36.0     155     NaN       NaN      True\n",
       "Johnny   1.8      83    11.3  0.136145     False"
      ]
     },
     "execution_count": 23,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df['is_adult'] = df.age > 18\n",
    "df"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Plotting\n",
    "\n",
    "DataFrames have all kinds of [useful plotting](https://pandas.pydata.org/pandas-docs/stable/visualization.html) built in."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.axes._subplots.AxesSubplot at 0x7faa50920c50>"
      ]
     },
     "execution_count": 24,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "df.plot(kind='scatter', x='age', y='height', grid=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.axes._subplots.AxesSubplot at 0x7faa508b0850>"
      ]
     },
     "execution_count": 25,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "df.plot(kind='bar')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Time Indexes\n",
    "\n",
    "Indexes are very powerful. They are a big part of why Pandas is so useful. There are different indices for different types of data. Time Indexes are especially great!"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.axes._subplots.AxesSubplot at 0x7faa50852f50>"
      ]
     },
     "execution_count": 26,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "two_years = pd.date_range(start='2014-01-01', end='2016-01-01', freq='D')\n",
    "timeseries = pd.Series(np.sin(2 *np.pi *two_years.dayofyear / 365),\n",
    "                       index=two_years)\n",
    "timeseries.plot()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "We can use python's slicing notation inside `.loc` to select a date range."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.axes._subplots.AxesSubplot at 0x7faa50836ad0>"
      ]
     },
     "execution_count": 27,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "timeseries.loc['2015-01-01':'2015-07-01'].plot()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Stock Market Data\n",
    "\n",
    "* oops - Ryan's links don't work, so we will use static files\n",
    "\n",
    "Now we read some stock market data from Google finance. I have created direct links to Google and Apple stock price data."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {},
   "outputs": [],
   "source": [
    "#!curl -L -o goog.csv http://tinyurl.com/rces-goog\n",
    "#!curl -L -o aapl.csv http://tinyurl.com/rces-aapl-csv\n",
    "! cp /home/pangeo/notebooks/GOOGL.csv goog.csv\n",
    "! cp /home/pangeo/notebooks/AAPL.csv aapl.csv"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Date,Open,High,Low,Close,Adj Close,Volume\n",
      "2006-01-03,211.471466,218.053055,209.319321,217.832840,217.832840,26216100\n",
      "2006-01-04,222.172165,224.704712,220.095093,222.842850,222.842850,30542200\n",
      "2006-01-05,223.223221,226.001007,220.970978,225.845840,225.845840,21594900\n",
      "2006-01-06,228.663666,235.485489,226.846848,233.063065,233.063065,35478200\n",
      "2006-01-09,233.438446,236.936935,230.700699,233.683685,233.683685,25558200\n",
      "2006-01-10,232.442444,235.360367,231.251251,235.115112,235.115112,18176000\n",
      "2006-01-11,235.870865,237.792786,234.824829,236.051056,236.051056,17996700\n",
      "2006-01-12,237.097092,237.732727,230.980988,232.047043,232.047043,20230300\n",
      "2006-01-13,232.387390,233.678680,231.036041,233.358353,233.358353,15297800\n"
     ]
    }
   ],
   "source": [
    "! head goog.csv"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "We can see that this is well-formated, tidy CSV data, ready for immediate ingestion into Pandas.\n",
    "We use Pandas' amazing [read_csv](https://pandas.pydata.org/pandas-docs/stable/generated/pandas.read_csv.html) function to do this."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Date</th>\n",
       "      <th>Open</th>\n",
       "      <th>High</th>\n",
       "      <th>Low</th>\n",
       "      <th>Close</th>\n",
       "      <th>Adj Close</th>\n",
       "      <th>Volume</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>2006-01-03</td>\n",
       "      <td>211.471466</td>\n",
       "      <td>218.053055</td>\n",
       "      <td>209.319321</td>\n",
       "      <td>217.832840</td>\n",
       "      <td>217.832840</td>\n",
       "      <td>26216100</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2006-01-04</td>\n",
       "      <td>222.172165</td>\n",
       "      <td>224.704712</td>\n",
       "      <td>220.095093</td>\n",
       "      <td>222.842850</td>\n",
       "      <td>222.842850</td>\n",
       "      <td>30542200</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2006-01-05</td>\n",
       "      <td>223.223221</td>\n",
       "      <td>226.001007</td>\n",
       "      <td>220.970978</td>\n",
       "      <td>225.845840</td>\n",
       "      <td>225.845840</td>\n",
       "      <td>21594900</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>2006-01-06</td>\n",
       "      <td>228.663666</td>\n",
       "      <td>235.485489</td>\n",
       "      <td>226.846848</td>\n",
       "      <td>233.063065</td>\n",
       "      <td>233.063065</td>\n",
       "      <td>35478200</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>2006-01-09</td>\n",
       "      <td>233.438446</td>\n",
       "      <td>236.936935</td>\n",
       "      <td>230.700699</td>\n",
       "      <td>233.683685</td>\n",
       "      <td>233.683685</td>\n",
       "      <td>25558200</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "         Date        Open        High         Low       Close   Adj Close  \\\n",
       "0  2006-01-03  211.471466  218.053055  209.319321  217.832840  217.832840   \n",
       "1  2006-01-04  222.172165  224.704712  220.095093  222.842850  222.842850   \n",
       "2  2006-01-05  223.223221  226.001007  220.970978  225.845840  225.845840   \n",
       "3  2006-01-06  228.663666  235.485489  226.846848  233.063065  233.063065   \n",
       "4  2006-01-09  233.438446  236.936935  230.700699  233.683685  233.683685   \n",
       "\n",
       "     Volume  \n",
       "0  26216100  \n",
       "1  30542200  \n",
       "2  21594900  \n",
       "3  35478200  \n",
       "4  25558200  "
      ]
     },
     "execution_count": 30,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "goog = pd.read_csv('goog.csv')\n",
    "goog.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Not bad! But we can do better by giving read_csv some hints."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Open</th>\n",
       "      <th>High</th>\n",
       "      <th>Low</th>\n",
       "      <th>Close</th>\n",
       "      <th>Adj Close</th>\n",
       "      <th>Volume</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Date</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>2006-01-03</th>\n",
       "      <td>211.471466</td>\n",
       "      <td>218.053055</td>\n",
       "      <td>209.319321</td>\n",
       "      <td>217.832840</td>\n",
       "      <td>217.832840</td>\n",
       "      <td>26216100</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2006-01-04</th>\n",
       "      <td>222.172165</td>\n",
       "      <td>224.704712</td>\n",
       "      <td>220.095093</td>\n",
       "      <td>222.842850</td>\n",
       "      <td>222.842850</td>\n",
       "      <td>30542200</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2006-01-05</th>\n",
       "      <td>223.223221</td>\n",
       "      <td>226.001007</td>\n",
       "      <td>220.970978</td>\n",
       "      <td>225.845840</td>\n",
       "      <td>225.845840</td>\n",
       "      <td>21594900</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2006-01-06</th>\n",
       "      <td>228.663666</td>\n",
       "      <td>235.485489</td>\n",
       "      <td>226.846848</td>\n",
       "      <td>233.063065</td>\n",
       "      <td>233.063065</td>\n",
       "      <td>35478200</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2006-01-09</th>\n",
       "      <td>233.438446</td>\n",
       "      <td>236.936935</td>\n",
       "      <td>230.700699</td>\n",
       "      <td>233.683685</td>\n",
       "      <td>233.683685</td>\n",
       "      <td>25558200</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                  Open        High         Low       Close   Adj Close  \\\n",
       "Date                                                                     \n",
       "2006-01-03  211.471466  218.053055  209.319321  217.832840  217.832840   \n",
       "2006-01-04  222.172165  224.704712  220.095093  222.842850  222.842850   \n",
       "2006-01-05  223.223221  226.001007  220.970978  225.845840  225.845840   \n",
       "2006-01-06  228.663666  235.485489  226.846848  233.063065  233.063065   \n",
       "2006-01-09  233.438446  236.936935  230.700699  233.683685  233.683685   \n",
       "\n",
       "              Volume  \n",
       "Date                  \n",
       "2006-01-03  26216100  \n",
       "2006-01-04  30542200  \n",
       "2006-01-05  21594900  \n",
       "2006-01-06  35478200  \n",
       "2006-01-09  25558200  "
      ]
     },
     "execution_count": 31,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "goog = pd.read_csv('goog.csv', parse_dates=[0], index_col=0)\n",
    "goog.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "DatetimeIndex: 3091 entries, 2006-01-03 to 2018-04-13\n",
      "Data columns (total 6 columns):\n",
      "Open         3091 non-null float64\n",
      "High         3091 non-null float64\n",
      "Low          3091 non-null float64\n",
      "Close        3091 non-null float64\n",
      "Adj Close    3091 non-null float64\n",
      "Volume       3091 non-null int64\n",
      "dtypes: float64(5), int64(1)\n",
      "memory usage: 169.0 KB\n"
     ]
    }
   ],
   "source": [
    "goog.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.axes._subplots.AxesSubplot at 0x7faa50852f90>"
      ]
     },
     "execution_count": 33,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "goog.Close.plot()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "DatetimeIndex: 3091 entries, 2006-01-03 to 2018-04-13\n",
      "Data columns (total 6 columns):\n",
      "Open         3091 non-null float64\n",
      "High         3091 non-null float64\n",
      "Low          3091 non-null float64\n",
      "Close        3091 non-null float64\n",
      "Adj Close    3091 non-null float64\n",
      "Volume       3091 non-null int64\n",
      "dtypes: float64(5), int64(1)\n",
      "memory usage: 169.0 KB\n"
     ]
    }
   ],
   "source": [
    "aapl = pd.read_csv('aapl.csv', parse_dates=[0], index_col=0)\n",
    "aapl.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>aapl</th>\n",
       "      <th>goog</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Date</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>2006-01-03</th>\n",
       "      <td>10.678572</td>\n",
       "      <td>217.832840</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2006-01-04</th>\n",
       "      <td>10.710000</td>\n",
       "      <td>222.842850</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2006-01-05</th>\n",
       "      <td>10.625714</td>\n",
       "      <td>225.845840</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2006-01-06</th>\n",
       "      <td>10.900000</td>\n",
       "      <td>233.063065</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2006-01-09</th>\n",
       "      <td>10.864285</td>\n",
       "      <td>233.683685</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                 aapl        goog\n",
       "Date                             \n",
       "2006-01-03  10.678572  217.832840\n",
       "2006-01-04  10.710000  222.842850\n",
       "2006-01-05  10.625714  225.845840\n",
       "2006-01-06  10.900000  233.063065\n",
       "2006-01-09  10.864285  233.683685"
      ]
     },
     "execution_count": 35,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "aapl_close = aapl.Close.rename('aapl')\n",
    "goog_close = goog.Close.rename('goog')\n",
    "stocks = pd.concat([aapl_close, goog_close], axis=1)\n",
    "stocks.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.axes._subplots.AxesSubplot at 0x7faa51141cd0>"
      ]
     },
     "execution_count": 36,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "stocks.plot()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Pandas knows how to take correlations. And [tons of other computations](https://pandas.pydata.org/pandas-docs/stable/computation.html)."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>aapl</th>\n",
       "      <th>goog</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>aapl</th>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.922954</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>goog</th>\n",
       "      <td>0.922954</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "          aapl      goog\n",
       "aapl  1.000000  0.922954\n",
       "goog  0.922954  1.000000"
      ]
     },
     "execution_count": 37,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "stocks.corr()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Because it understands times, it can do really cool stuff like resampling."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/home2/nhn2/miniconda3/envs/python2.7/lib/python2.7/site-packages/pandas/plotting/_core.py:186: UserWarning: 'colors' is being deprecated. Please use 'color'instead of 'colors'\n",
      "  warnings.warn((\"'colors' is being deprecated. Please use 'color'\"\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "<matplotlib.axes._subplots.AxesSubplot at 0x7faa5106b1d0>"
      ]
     },
     "execution_count": 38,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# resample by taking the mean over each month\n",
    "\n",
    "fig, ax = plt.subplots()\n",
    "stocks.resample('MS').mean().plot(ax=ax, colors=['r', 'b'])\n",
    "# and each year\n",
    "stocks.resample('AS').mean().plot(ax=ax, colors=['r', 'b'])"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "The string `QS` means \"month start. The string `AS` mean \"year start\". There is a long list of possible [frequency aliases](https://pandas.pydata.org/pandas-docs/stable/timeseries.html#timeseries-offset-aliases).\n",
    "\n",
    "We can also apply other reduction operations with resample. These are described in the [resample docs](https://pandas.pydata.org/pandas-docs/stable/timeseries.html#resampling)."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 39,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.axes._subplots.AxesSubplot at 0x7faa50fc9250>"
      ]
     },
     "execution_count": 39,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# get resample object\n",
    "rs = stocks.goog.resample('MS')\n",
    "# standard deviation of each month\n",
    "rs.std().plot()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Temperature Data\n",
    "\n",
    "We download some timeseries data from the [Berkeley Earth(http://berkeleyearth.org/) surface temperature dataset. This is timeseries data from various locations around earth. Let's get our local temperatures."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 40,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "  % Total    % Received % Xferd  Average Speed   Time    Time     Time  Current\n",
      "                                 Dload  Upload   Total   Spent    Left  Speed\n",
      "100  313k  100  313k    0     0   450k      0 --:--:-- --:--:-- --:--:--  450k\n"
     ]
    }
   ],
   "source": [
    "! curl -o nyc_temp.txt http://berkeleyearth.lbl.gov/auto/Local/TAVG/Text/40.99N-74.56W-TAVG-Trend.txt"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "If we examine this data, we see it is NOT a well formated CSV file. Loading it will be a bit painful, but Pandas makes the job retatively easy."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "% \n",
      "%                  Monthly          Annual          Five-year        Ten-year        Twenty-year\n",
      "% Year, Month,  Anomaly, Unc.,   Anomaly, Unc.,   Anomaly, Unc.,   Anomaly, Unc.,   Anomaly, Unc.\n",
      " \n",
      "  1743    11    -2.276  1.665       NaN    NaN       NaN    NaN       NaN    NaN       NaN    NaN\n",
      "  1743    12       NaN    NaN       NaN    NaN       NaN    NaN       NaN    NaN       NaN    NaN\n",
      "  1744     1       NaN    NaN       NaN    NaN       NaN    NaN       NaN    NaN       NaN    NaN\n",
      "  1744     2       NaN    NaN       NaN    NaN       NaN    NaN       NaN    NaN       NaN    NaN\n"
     ]
    }
   ],
   "source": [
    "! head -72 nyc_temp.txt | tail -8"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>year</th>\n",
       "      <th>month</th>\n",
       "      <th>monthly_anom</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1743</td>\n",
       "      <td>11</td>\n",
       "      <td>-2.276</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1743</td>\n",
       "      <td>12</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1744</td>\n",
       "      <td>1</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1744</td>\n",
       "      <td>2</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1744</td>\n",
       "      <td>3</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   year  month  monthly_anom\n",
       "0  1743     11        -2.276\n",
       "1  1743     12           NaN\n",
       "2  1744      1           NaN\n",
       "3  1744      2           NaN\n",
       "4  1744      3           NaN"
      ]
     },
     "execution_count": 42,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "##### http://berkeleyearth.lbl.gov/locations/40.99N-74.56W\n",
    "# http://berkeleyearth.lbl.gov/auto/Local/TAVG/Text/40.99N-74.56W-TAVG-Trend.txt\n",
    "\n",
    "\n",
    "#temp = pd.read_csv('nyc_temp.txt')\n",
    "\n",
    "col_names = ['year', 'month', 'monthly_anom'] + 10*[]\n",
    "temp = pd.read_csv('nyc_temp.txt',\n",
    "                   header=None, usecols=[0, 1, 2], names=col_names,\n",
    "                   delim_whitespace=True, comment='%')\n",
    "\n",
    "temp.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 43,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>monthly_anom</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1743-11-01 00:00:00</th>\n",
       "      <td>-2.276</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1743-12-01 00:00:00</th>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1744-01-01 00:00:00</th>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1744-02-01 00:00:00</th>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1744-03-01 00:00:00</th>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                     monthly_anom\n",
       "1743-11-01 00:00:00        -2.276\n",
       "1743-12-01 00:00:00           NaN\n",
       "1744-01-01 00:00:00           NaN\n",
       "1744-02-01 00:00:00           NaN\n",
       "1744-03-01 00:00:00           NaN"
      ]
     },
     "execution_count": 43,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# need a day\n",
    "date_df = temp.drop('monthly_anom', axis=1)\n",
    "date_df['day'] = 1\n",
    "date_index = pd.DatetimeIndex(pd.to_datetime(date_df))\n",
    "temp = temp.set_index(date_index).drop(['year', 'month'], axis=1)\n",
    "temp.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 44,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.axes._subplots.AxesSubplot at 0x7faa50f1c810>"
      ]
     },
     "execution_count": 44,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "temp.plot()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 45,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.axes._subplots.AxesSubplot at 0x7faa50db6810>"
      ]
     },
     "execution_count": 45,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "fig, ax = plt.subplots()\n",
    "temp.plot(ax=ax)\n",
    "temp.resample('AS').mean().plot(ax=ax)\n",
    "temp.resample('10AS').mean().plot(ax=ax)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Pandas can do both time-based resampling and operation over fixed-length rolling windows. These are very similar but distinct; see [discussion in Pandas docs](https://pandas.pydata.org/pandas-docs/stable/computation.html#time-aware-rolling-vs-resampling)."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 46,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.axes._subplots.AxesSubplot at 0x7faa50b47fd0>"
      ]
     },
     "execution_count": 46,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# more advanced operation on rolling windows\n",
    "def difference_max_min(data):\n",
    "    return data.max() - data.min()\n",
    "\n",
    "rw = temp.rolling('365D')\n",
    "rw.apply(difference_max_min).plot()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "To create a \"climatology\" (i.e. the average of all same months), we can use Pandas' [groupby](https://pandas.pydata.org/pandas-docs/stable/groupby.html) functionality."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 47,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.axes._subplots.AxesSubplot at 0x7faa50a55d50>"
      ]
     },
     "execution_count": 47,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# diurnal cycle has been removed!\n",
    "temp.groupby(temp.index.month).mean().plot()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 48,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>monthly_anom</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>2012</th>\n",
       "      <td>2.009833</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1998</th>\n",
       "      <td>1.862250</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2006</th>\n",
       "      <td>1.557583</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1949</th>\n",
       "      <td>1.424500</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2010</th>\n",
       "      <td>1.395917</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1991</th>\n",
       "      <td>1.395583</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1990</th>\n",
       "      <td>1.360833</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2011</th>\n",
       "      <td>1.310583</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2002</th>\n",
       "      <td>1.290500</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1953</th>\n",
       "      <td>1.212833</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "      monthly_anom\n",
       "2012      2.009833\n",
       "1998      1.862250\n",
       "2006      1.557583\n",
       "1949      1.424500\n",
       "2010      1.395917\n",
       "1991      1.395583\n",
       "1990      1.360833\n",
       "2011      1.310583\n",
       "2002      1.290500\n",
       "1953      1.212833"
      ]
     },
     "execution_count": 48,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# find the hottest years\n",
    "temp.groupby(temp.index.year).mean().sort_values('monthly_anom', ascending=False).head(10)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Groupby\n",
    "\n",
    "Now we will explore groupby's capabilities more in a public dataset from the City of New York: the [Rat Information Portal](The Rat Information Portal)!"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 49,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "# https://data.cityofnewyork.us/Health/Rats/amyk-xiv9\n",
    "rats = pd.read_csv('https://data.cityofnewyork.us/api/views/amyk-xiv9/rows.csv',\n",
    "                  parse_dates=['APPROVED_DATE', 'INSPECTION_DATE'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 50,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 218231 entries, 0 to 218230\n",
      "Data columns (total 20 columns):\n",
      "INSPECTION_TYPE                218231 non-null object\n",
      "JOB_TICKET_OR_WORK_ORDER_ID    218231 non-null int64\n",
      "JOB_ID                         218231 non-null object\n",
      "JOB_PROGRESS                   218231 non-null int64\n",
      "BBL                            218231 non-null int64\n",
      "BORO_CODE                      218231 non-null int64\n",
      "BLOCK                          215548 non-null float64\n",
      "LOT                            215548 non-null float64\n",
      "HOUSE_NUMBER                   214304 non-null object\n",
      "STREET_NAME                    218175 non-null object\n",
      "ZIP_CODE                       217023 non-null float64\n",
      "X_COORD                        216907 non-null float64\n",
      "Y_COORD                        216907 non-null float64\n",
      "LATITUDE                       218092 non-null float64\n",
      "LONGITUDE                      218092 non-null float64\n",
      "BOROUGH                        218231 non-null object\n",
      "INSPECTION_DATE                218231 non-null datetime64[ns]\n",
      "RESULT                         218231 non-null object\n",
      "APPROVED_DATE                  218231 non-null datetime64[ns]\n",
      "LOCATION                       217985 non-null object\n",
      "dtypes: datetime64[ns](2), float64(7), int64(4), object(7)\n",
      "memory usage: 33.3+ MB\n"
     ]
    }
   ],
   "source": [
    "rats.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 51,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>INSPECTION_TYPE</th>\n",
       "      <th>JOB_TICKET_OR_WORK_ORDER_ID</th>\n",
       "      <th>JOB_ID</th>\n",
       "      <th>JOB_PROGRESS</th>\n",
       "      <th>BBL</th>\n",
       "      <th>BORO_CODE</th>\n",
       "      <th>BLOCK</th>\n",
       "      <th>LOT</th>\n",
       "      <th>HOUSE_NUMBER</th>\n",
       "      <th>STREET_NAME</th>\n",
       "      <th>ZIP_CODE</th>\n",
       "      <th>X_COORD</th>\n",
       "      <th>Y_COORD</th>\n",
       "      <th>LATITUDE</th>\n",
       "      <th>LONGITUDE</th>\n",
       "      <th>BOROUGH</th>\n",
       "      <th>INSPECTION_DATE</th>\n",
       "      <th>RESULT</th>\n",
       "      <th>APPROVED_DATE</th>\n",
       "      <th>LOCATION</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>COMPLIANCE</td>\n",
       "      <td>2110773</td>\n",
       "      <td>PO2090711</td>\n",
       "      <td>2</td>\n",
       "      <td>3013040024</td>\n",
       "      <td>3</td>\n",
       "      <td>1304.0</td>\n",
       "      <td>24.0</td>\n",
       "      <td>2</td>\n",
       "      <td>STODDARD PLACE</td>\n",
       "      <td>11225.0</td>\n",
       "      <td>996474.0</td>\n",
       "      <td>181731.0</td>\n",
       "      <td>40.665471</td>\n",
       "      <td>-73.955938</td>\n",
       "      <td>Brooklyn</td>\n",
       "      <td>2019-11-04 15:40:49</td>\n",
       "      <td>Active Rat Signs</td>\n",
       "      <td>2019-11-06 10:03:51</td>\n",
       "      <td>(40.665470953232, -73.955937552675)</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>COMPLIANCE</td>\n",
       "      <td>2127558</td>\n",
       "      <td>PO2113817</td>\n",
       "      <td>2</td>\n",
       "      <td>1004020036</td>\n",
       "      <td>1</td>\n",
       "      <td>402.0</td>\n",
       "      <td>36.0</td>\n",
       "      <td>106</td>\n",
       "      <td>AVENUE B</td>\n",
       "      <td>10009.0</td>\n",
       "      <td>989368.0</td>\n",
       "      <td>203405.0</td>\n",
       "      <td>40.724924</td>\n",
       "      <td>-73.981326</td>\n",
       "      <td>Manhattan</td>\n",
       "      <td>2019-11-01 12:45:19</td>\n",
       "      <td>Active Rat Signs</td>\n",
       "      <td>2019-11-06 09:11:47</td>\n",
       "      <td>(40.72492418461, -73.981325959827)</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>INITIAL</td>\n",
       "      <td>2131358</td>\n",
       "      <td>PO2131358</td>\n",
       "      <td>1</td>\n",
       "      <td>2024470064</td>\n",
       "      <td>2</td>\n",
       "      <td>2447.0</td>\n",
       "      <td>64.0</td>\n",
       "      <td>257</td>\n",
       "      <td>EAST 164 STREET</td>\n",
       "      <td>10456.0</td>\n",
       "      <td>1007105.0</td>\n",
       "      <td>241255.0</td>\n",
       "      <td>40.828618</td>\n",
       "      <td>-73.917451</td>\n",
       "      <td>Bronx</td>\n",
       "      <td>2019-11-04 16:17:38</td>\n",
       "      <td>Active Rat Signs</td>\n",
       "      <td>2019-11-06 10:58:07</td>\n",
       "      <td>(40.828617551661, -73.917450560229)</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>INITIAL</td>\n",
       "      <td>2150812</td>\n",
       "      <td>PO2150812</td>\n",
       "      <td>1</td>\n",
       "      <td>2037420001</td>\n",
       "      <td>2</td>\n",
       "      <td>3742.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1101</td>\n",
       "      <td>MANOR AVENUE</td>\n",
       "      <td>10472.0</td>\n",
       "      <td>1018617.0</td>\n",
       "      <td>240398.0</td>\n",
       "      <td>40.826439</td>\n",
       "      <td>-73.875820</td>\n",
       "      <td>Bronx</td>\n",
       "      <td>2019-11-04 11:56:05</td>\n",
       "      <td>Active Rat Signs</td>\n",
       "      <td>2019-11-06 14:55:42</td>\n",
       "      <td>(40.826439194567, -73.875820359062)</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>COMPLIANCE</td>\n",
       "      <td>2128102</td>\n",
       "      <td>PO2115246</td>\n",
       "      <td>2</td>\n",
       "      <td>3033920005</td>\n",
       "      <td>3</td>\n",
       "      <td>3392.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>723</td>\n",
       "      <td>KNICKERBOCKER AVENUE</td>\n",
       "      <td>11221.0</td>\n",
       "      <td>1009221.0</td>\n",
       "      <td>192146.0</td>\n",
       "      <td>40.694031</td>\n",
       "      <td>-73.909951</td>\n",
       "      <td>Brooklyn</td>\n",
       "      <td>2019-10-29 10:16:56</td>\n",
       "      <td>Active Rat Signs</td>\n",
       "      <td>2019-11-06 16:08:23</td>\n",
       "      <td>(40.694030894349, -73.90995119043)</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  INSPECTION_TYPE  JOB_TICKET_OR_WORK_ORDER_ID     JOB_ID  JOB_PROGRESS  \\\n",
       "0      COMPLIANCE                      2110773  PO2090711             2   \n",
       "1      COMPLIANCE                      2127558  PO2113817             2   \n",
       "2         INITIAL                      2131358  PO2131358             1   \n",
       "3         INITIAL                      2150812  PO2150812             1   \n",
       "4      COMPLIANCE                      2128102  PO2115246             2   \n",
       "\n",
       "          BBL  BORO_CODE   BLOCK   LOT HOUSE_NUMBER           STREET_NAME  \\\n",
       "0  3013040024          3  1304.0  24.0            2        STODDARD PLACE   \n",
       "1  1004020036          1   402.0  36.0          106              AVENUE B   \n",
       "2  2024470064          2  2447.0  64.0          257       EAST 164 STREET   \n",
       "3  2037420001          2  3742.0   1.0         1101          MANOR AVENUE   \n",
       "4  3033920005          3  3392.0   5.0          723  KNICKERBOCKER AVENUE   \n",
       "\n",
       "   ZIP_CODE    X_COORD   Y_COORD   LATITUDE  LONGITUDE    BOROUGH  \\\n",
       "0   11225.0   996474.0  181731.0  40.665471 -73.955938   Brooklyn   \n",
       "1   10009.0   989368.0  203405.0  40.724924 -73.981326  Manhattan   \n",
       "2   10456.0  1007105.0  241255.0  40.828618 -73.917451      Bronx   \n",
       "3   10472.0  1018617.0  240398.0  40.826439 -73.875820      Bronx   \n",
       "4   11221.0  1009221.0  192146.0  40.694031 -73.909951   Brooklyn   \n",
       "\n",
       "      INSPECTION_DATE            RESULT       APPROVED_DATE  \\\n",
       "0 2019-11-04 15:40:49  Active Rat Signs 2019-11-06 10:03:51   \n",
       "1 2019-11-01 12:45:19  Active Rat Signs 2019-11-06 09:11:47   \n",
       "2 2019-11-04 16:17:38  Active Rat Signs 2019-11-06 10:58:07   \n",
       "3 2019-11-04 11:56:05  Active Rat Signs 2019-11-06 14:55:42   \n",
       "4 2019-10-29 10:16:56  Active Rat Signs 2019-11-06 16:08:23   \n",
       "\n",
       "                              LOCATION  \n",
       "0  (40.665470953232, -73.955937552675)  \n",
       "1   (40.72492418461, -73.981325959827)  \n",
       "2  (40.828617551661, -73.917450560229)  \n",
       "3  (40.826439194567, -73.875820359062)  \n",
       "4   (40.694030894349, -73.90995119043)  "
      ]
     },
     "execution_count": 51,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "rats.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Let's do some grouping to explore the data."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 52,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "INSPECTION_TYPE\n",
       "COMPLIANCE     73364\n",
       "INITIAL       144867\n",
       "Name: INSPECTION_TYPE, dtype: int64"
      ]
     },
     "execution_count": 52,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "rats.groupby('INSPECTION_TYPE')['INSPECTION_TYPE'].count()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 53,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "BORO_CODE\n",
       "1    66716\n",
       "2    74417\n",
       "3    61477\n",
       "4    13151\n",
       "5     2470\n",
       "Name: BORO_CODE, dtype: int64"
      ]
     },
     "execution_count": 53,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "rats.groupby('BORO_CODE')['BORO_CODE'].count().head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 54,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "STREET_NAME\n",
       "                                    1\n",
       "  11 AVENUE                         1\n",
       "  20 LANE                           2\n",
       "  32 PLACE                          2\n",
       "  33 STREET                         1\n",
       "  34 STREET                         1\n",
       "  39 ROAD                           2\n",
       "  53 ROAD                           1\n",
       "  55 DRIVE                          3\n",
       "  72 ROAD                           1\n",
       " 136 STREET                         1\n",
       " 35 STREET                          1\n",
       " 36 AVENUE                          1\n",
       " 60 STREET                          3\n",
       " ADELPHI STREET                     1\n",
       " BAILEY AVENUE                      1\n",
       " BEDFORD STREET                     1\n",
       " BERGEN STREET                      1\n",
       " BOERUM STREET                      1\n",
       " BOGART STREET                      1\n",
       "Name: STREET_NAME, dtype: int64"
      ]
     },
     "execution_count": 54,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "rats.groupby('STREET_NAME')['STREET_NAME'].count().head(20)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "This dataset clearly needs some cleaning. We can Pandas' [text features](https://pandas.pydata.org/pandas-docs/stable/text.html) to strip the whitespace out of the data."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 55,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "STREET_NAME\n",
       "                          1\n",
       "********************    113\n",
       "0000                      1\n",
       "1 AVENUE                939\n",
       "1 PLACE                   6\n",
       "1 STREET                 25\n",
       "1/2 2 AVENUE              1\n",
       "1/2 5 AVENUE              2\n",
       "1/2 7 AVENUE SOUTH        4\n",
       "1/2 BEDFORD STREET        1\n",
       "1/2 BRIGGS AVENUE         1\n",
       "1/2 CATHERINE STREET      1\n",
       "1/2 DOWNING STREET        1\n",
       "1/2 EAST 115 STREET       6\n",
       "1/2 EAST 7 STREET         3\n",
       "1/2 EAST 9 STREET         1\n",
       "1/2 KING STREET           1\n",
       "1/2 MULBERRY STREET       3\n",
       "1/2 ROGERS AVENUE         5\n",
       "1/2 ST MARKS PLACE        1\n",
       "Name: STREET_NAME, dtype: int64"
      ]
     },
     "execution_count": 55,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# clean up street name\n",
    "street_names_cleaned = rats.STREET_NAME.str.strip()\n",
    "street_names_cleaned.groupby(street_names_cleaned).count().head(20)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 56,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "STREET_NAME\n",
       "BROADWAY              3386\n",
       "GRAND CONCOURSE       2904\n",
       "AMSTERDAM AVENUE      1683\n",
       "WEBSTER AVENUE        1655\n",
       "3 AVENUE              1551\n",
       "LAFAYETTE AVENUE      1549\n",
       "PARK AVENUE           1418\n",
       "MORRIS AVENUE         1410\n",
       "JEROME AVENUE         1390\n",
       "BEDFORD AVENUE        1354\n",
       "ST NICHOLAS AVENUE    1313\n",
       "WALTON AVENUE         1280\n",
       "GREENE AVENUE         1259\n",
       "LEXINGTON AVENUE      1190\n",
       "2 AVENUE              1189\n",
       "EASTERN PARKWAY       1177\n",
       "VALENTINE AVENUE      1067\n",
       "WILLOUGHBY AVENUE     1047\n",
       "WASHINGTON AVENUE     1010\n",
       "MADISON STREET        1002\n",
       "Name: STREET_NAME, dtype: int64"
      ]
     },
     "execution_count": 56,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "count = street_names_cleaned.groupby(street_names_cleaned).count()\n",
    "count.sort_values(ascending=False).head(20)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "To get a better idea of the geography, let's plot the locations of the inspections. But first let's look at the statistics."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 57,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>LATITUDE</th>\n",
       "      <th>LONGITUDE</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>218092.000000</td>\n",
       "      <td>218092.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>40.545938</td>\n",
       "      <td>-73.523365</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>3.025624</td>\n",
       "      <td>5.485032</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>0.000000</td>\n",
       "      <td>-74.249307</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>40.700123</td>\n",
       "      <td>-73.956776</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>40.783610</td>\n",
       "      <td>-73.930537</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>40.839360</td>\n",
       "      <td>-73.902904</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>40.912863</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "            LATITUDE      LONGITUDE\n",
       "count  218092.000000  218092.000000\n",
       "mean       40.545938     -73.523365\n",
       "std         3.025624       5.485032\n",
       "min         0.000000     -74.249307\n",
       "25%        40.700123     -73.956776\n",
       "50%        40.783610     -73.930537\n",
       "75%        40.839360     -73.902904\n",
       "max        40.912863       0.000000"
      ]
     },
     "execution_count": 57,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "rats[['LATITUDE', 'LONGITUDE']].describe()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "There are clearly some weird outliers in the location data. We need to strip these out before plotting."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 58,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.axes._subplots.AxesSubplot at 0x7fa9d83b02d0>"
      ]
     },
     "execution_count": 58,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "valid_latlon = rats[(rats.LATITUDE > 30) & (rats.LONGITUDE < -70)]\n",
    "valid_latlon.plot.hexbin('LONGITUDE', 'LATITUDE', C='BORO_CODE', cmap='Set1')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 59,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.axes._subplots.AxesSubplot at 0x7fa9d9443810>"
      ]
     },
     "execution_count": 59,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# https://github.com/pandas-dev/pandas/issues/10678\n",
    "valid_latlon.plot.hexbin('LONGITUDE', 'LATITUDE', sharex=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 60,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.axes._subplots.AxesSubplot at 0x7fa9d9443ed0>"
      ]
     },
     "execution_count": 60,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "valid_latlon.plot.hexbin('LONGITUDE', 'LATITUDE', sharex=False, bins='log', cmap='magma')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 61,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.axes._subplots.AxesSubplot at 0x7fa9d8614610>"
      ]
     },
     "execution_count": 61,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "manhattan_rats = valid_latlon[valid_latlon.BORO_CODE==1]\n",
    "manhattan_rats.plot.hexbin('LONGITUDE', 'LATITUDE', sharex=False, bins='log', cmap='magma')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 62,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "inspection_date = pd.DatetimeIndex(rats.INSPECTION_DATE)\n",
    "\n",
    "fig, ax = plt.subplots()\n",
    "rats.groupby(inspection_date.weekday)['JOB_ID'].count().plot(kind='bar', ax=ax)\n",
    "ax.set_xlabel('weekday');"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 63,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "fig, ax = plt.subplots()\n",
    "rats.groupby(inspection_date.hour)['JOB_ID'].count().plot(kind='bar', ax=ax)\n",
    "ax.set_xlabel('hour');"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 64,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Text(0.5,0,'month')"
      ]
     },
     "execution_count": 64,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "fig, ax = plt.subplots()\n",
    "rats.groupby(inspection_date.month)['JOB_ID'].count().plot(kind='bar', ax=ax)\n",
    "ax.set_xlabel('month')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Py2 PyNGL",
   "language": "python",
   "name": "python2.7"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 2
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython2",
   "version": "2.7.14"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}