{
 "metadata": {
  "name": "",
  "signature": "sha256:a832e123bc2b6617ac3a3a1aa8c3dc25f27637ab20f18b8b01a34ff854510192"
 },
 "nbformat": 3,
 "nbformat_minor": 0,
 "worksheets": [
  {
   "cells": [
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "from __future__ import division, print_function"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 3
    },
    {
     "cell_type": "code",
     "collapsed": true,
     "input": [
      "from IPython.display import HTML, Image, display as disp"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 4
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "with open(\"../css/css.css\", \"r\") as f:\n",
      "    style = f.read()\n",
      "HTML(style)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "html": [
        "<link href='http://fonts.googleapis.com/css?family=Source+Code+Pro' rel='stylesheet' type='text/css'>\n",
        "<link href='http://fonts.googleapis.com/css?family=Raleway' rel='stylesheet' type='text/css'>\n",
        "<style>\n",
        "/*\n",
        "Rob's custom notebook CSS\n",
        "*/\n",
        "\n",
        "/*Fonts*/\n",
        "\n",
        "\n",
        "/*\n",
        "\n",
        "    Name:       Base16 Ocean Dark\n",
        "    Author:     Chris Kempson (http://chriskempson.com)\n",
        "\n",
        "    CodeMirror template adapted for IPython Notebook by Nikhil Sonnad (https://github.com/nsonnad/base16-ipython-notebook)\n",
        "    CodeMirror template by Jan T. Sott (https://github.com/idleberg/base16-chrome-devtools)\n",
        "    Original Base16 color scheme by Chris Kempson (https://github.com/chriskempson/base16)\n",
        "\n",
        "*/\n",
        "\n",
        "/* Uncomment to use a custom font\n",
        "div#notebook, div.CodeMirror, div.output_area pre, div.output_wrapper, div.prompt {\n",
        "  font-family: 'Custom Font Name', monospace !important;\n",
        "}\n",
        "*/\n",
        "body {\n",
        "    font-family: 'Raleway', sans-serif;\n",
        "}\n",
        "\n",
        ".rendered_html pre, .rendered_html code {\n",
        "    background-color: #2b303b;\n",
        "    color: #8fb1bf;\n",
        "    font-weight: bold:\n",
        "}\n",
        "\n",
        "\n",
        ".rendered_html table, .rendered_html th, .rendered_html tr, .rendered_html td {\n",
        "border: 1px #4f5b66 solid;\n",
        "white-space: nowrap;\n",
        "}\n",
        ".rendered_html thead {\n",
        "background-color: #43515c;\n",
        "color: white;\n",
        "}\n",
        ".rendered_html th {font-weight: bold;}\n",
        "table.dataframe tr {border: 1px #4f5b66;}\n",
        "\n",
        "/* GLOBALS */\n",
        "body {background-color: #2b303b;}\n",
        "a {color: #8fa1b3;}\n",
        "\n",
        "/* INTRO PAGE */\n",
        ".toolbar_info, .list_container {color: #dfe1e8;}\n",
        "\n",
        "/* NOTEBOOK */\n",
        "\n",
        "/* comment out this line to bring the toolbar back */\n",
        "div#maintoolbar, div#header {display: none !important;}\n",
        "\n",
        "div#notebook {border-top: none;}\n",
        "\n",
        "div.input_prompt {color: #ab7967;}\n",
        "div.output_prompt {color: #b48ead;}\n",
        "div.input_area {\n",
        "\n",
        "  font-size: 16px !important;\n",
        "  border-radius: 0px;\n",
        "  border: 1px solid #4f5b66;\n",
        "}\n",
        "div.output_area pre {font-weight: normal; color: #c0c5ce;}\n",
        "\n",
        ".rendered_html table, .rendered_html th, .rendered_html tr, .rendered_html td {\n",
        "  border: 1px  #c0c5ce solid;\n",
        "  color: #c0c5ce;\n",
        "}\n",
        "div.output_html { font-family: sans-serif; }\n",
        "table.dataframe tr {border: 1px #c0c5ce;}\n",
        "\n",
        "div.cell.selected {border-radius: 0px;}\n",
        "div.cell.edit_mode {border-radius: 0px; border: thin solid #b48ead;}\n",
        "div.text_cell_render, div.output_html {color: #c0c5ce;}\n",
        "\n",
        "span.ansiblack {color: #343d46;}\n",
        "span.ansiblue {color: #96b5b4;}\n",
        "span.ansigray {color: #a7adba;}\n",
        "span.ansigreen {color: #a3be8c;}\n",
        "span.ansipurple {color: #b48ead;}\n",
        "span.ansired {color: #bf616a;}\n",
        "span.ansiyellow {color: #ebcb8b;}\n",
        "\n",
        "div.output_stderr {background-color: #bf616a;}\n",
        "div.output_stderr pre {color: #dfe1e8;}\n",
        "\n",
        ".cm-s-ipython.CodeMirror {background: #2b303b; color: #dfe1e8;}\n",
        ".cm-s-ipython div.CodeMirror-selected {background: #343d46 !important;}\n",
        ".cm-s-ipython .CodeMirror-gutters {background: #2b303b; border-right: 0px;}\n",
        ".cm-s-ipython .CodeMirror-linenumber {color: #65737e;}\n",
        ".cm-s-ipython .CodeMirror-cursor {border-left: 1px solid #a7adba !important;}\n",
        "\n",
        ".cm-s-ipython span.cm-comment {color: #ab7967;}\n",
        ".cm-s-ipython span.cm-atom {color: #b48ead;}\n",
        ".cm-s-ipython span.cm-number {color: #b48ead;}\n",
        "\n",
        ".cm-s-ipython span.cm-property, .cm-s-ipython span.cm-attribute {color: #a3be8c;}\n",
        ".cm-s-ipython span.cm-keyword {color: #bf616a;}\n",
        ".cm-s-ipython span.cm-string {color: #ebcb8b;}\n",
        ".cm-s-ipython span.cm-operator {color: #ab7967;}\n",
        ".cm-s-ipython span.cm-builtin {color: #b48ead;}\n",
        "\n",
        ".cm-s-ipython span.cm-variable {color: #a3be8c;}\n",
        ".cm-s-ipython span.cm-variable-2 {color: #8fa1b3;}\n",
        ".cm-s-ipython span.cm-def {color: #d08770;}\n",
        ".cm-s-ipython span.cm-error {background: #bf616a; color: #a7adba;}\n",
        ".cm-s-ipython span.cm-bracket {color: #c0c5ce;}\n",
        ".cm-s-ipython span.cm-tag {color: #bf616a;}\n",
        ".cm-s-ipython span.cm-link {color: #b48ead;}\n",
        ".cm-s-ipython span.cm-meta {color: #b49391;}\n",
        "\n",
        ".cm-s-ipython .CodeMirror-matchingbracket { text-decoration: underline; color: #dfe1e8 !important;}\n",
        "</style>\n"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 5,
       "text": [
        "<IPython.core.display.HTML object>"
       ]
      }
     ],
     "prompt_number": 5
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "# Whirlwind Introduction to [Pandas](http://pandas.pydata.org)!\n",
      "---------------\n",
      "\n",
      "### About me: Phillip Cloud\n",
      "\n",
      "## Past:\n",
      "* MA Psychology from CUNY CCNY (analysis of rat spike train data)\n",
      "* Started using pandas/numpy for loading data from proprietary formats\n",
      "* Decided I should contribute\n",
      "\n",
      "## Now:\n",
      "* Data infrastructure/research/development @ neuromatters (neurotechnology R & D company)\n",
      "* Core contributer to pandas for a little over 1 year"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": true,
     "input": [
      "!./shortlog.sh ../../pandas"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "  2985\tWes McKinney\r\n",
        "  1149\tjreback\r\n",
        "   765\ty-p\r\n",
        "   607\tChang She\r\n",
        "   323\tPhillip Cloud\r\n",
        "   315\tAdam Klein\r\n",
        "   120\tJeffrey Tratner\r\n",
        "   109\tVytautas Jancauskas\r\n",
        "    89\tJoris Van den Bossche\r\n",
        "    84\tAndy Hayden\r\n"
       ]
      }
     ],
     "prompt_number": 6
    },
    {
     "cell_type": "heading",
     "level": 1,
     "metadata": {},
     "source": [
      "Why pandas?"
     ]
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "pandas fills the need for a Python library that is awesome at data munging. With pandas you don't need to go outside of Python to do data analysis. You can write a web app using django and have data dashboards that are backed by pandas."
     ]
    },
    {
     "cell_type": "heading",
     "level": 1,
     "metadata": {},
     "source": [
      "What is pandas?"
     ]
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "#### Strengths:\n",
      "``pandas`` is *the* library for tabular you've always wished you had. It supports operations such as\n",
      "\n",
      "* ``groupby``\n",
      "* ``merge``\n",
      "* aggregations (``mean``, ``sum``, ``any``, `all`, etc.)\n",
      "* advanced indexing capabilities\n",
      "* automatic data alignment during e.g., arithmetic operations\n",
      "* powerful vectorized text manipulation\n",
      "* missing data handling\n",
      "* comprehensive and extremely flexible IO (e.g., CSV, Excel, HDF5, HTML)\n",
      "\n",
      "#### Limitations:\n",
      "\n",
      "* ``pandas`` was designed to work with \"medium\" data, i.e., data that fit into memory.\n",
      "* That said, I routinely work with $\\approx$ 20-100M row datasets fairly easily with pandas."
     ]
    },
    {
     "cell_type": "heading",
     "level": 2,
     "metadata": {},
     "source": [
      "My reaction after discovering pandas:"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "disp(Image(\"../img/m.jpg\"))"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "jpeg": "/9j/4AAQSkZJRgABAQEASABIAAD/2wBDAAEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEB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\nwGMjhq1bFWcsOoUasVZtRdSlKs3PX2sp8taElacf/9k=\n",
       "metadata": {},
       "output_type": "display_data",
       "text": [
        "<IPython.core.display.Image object>"
       ]
      }
     ],
     "prompt_number": 7
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "disp(Image(\"../img/u.jpg\"))"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "jpeg": "/9j/4AAQSkZJRgABAgAAZABkAAD/7AARRHVja3kAAQAEAAAANwAA/+4ADkFkb2JlAGTAAAAAAf/b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\nQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBB/9k=\n",
       "metadata": {},
       "output_type": "display_data",
       "text": [
        "<IPython.core.display.Image object>"
       ]
      }
     ],
     "prompt_number": 8
    },
    {
     "cell_type": "heading",
     "level": 2,
     "metadata": {},
     "source": [
      "First rule of pandas talks: they aren't complete without a meme."
     ]
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "### Deps for the talk\n",
      "\n",
      "* [These notebooks](http://github.com/cpcloud/nypug-pandas-features)\n",
      "* [pandas](http://pandas.pydata.org/pandas-docs/stable/install.html#installation) with *all* [optional deps](http://pandas.pydata.org/pandas-docs/stable/install.html#recommended-dependencies) (Anaconda provides most if not all of these)\n",
      "* [sh](http://amoffat.github.io/sh): ``pip install sh``\n",
      "* [jq](http://stedolan.github.io/jq)\n",
      "* [requests](http://docs.python-requests.org/en/latest) because `urllib` et al are less than desirable\n",
      "\n",
      "### Optional\n",
      "* [mpltools](http://tonysyu.github.io/mpltools) (for nice looking plots by default)"
     ]
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "### Enough talking, let's see some code."
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "# imports that I'll use throughout the talk\n",
      "import numpy as np\n",
      "import pandas as pd\n",
      "from pandas import DataFrame, Series, Index\n",
      "from numpy.random import randn, randint, rand, choice\n",
      "import matplotlib.pyplot as plt\n",
      "\n",
      "pd.options.display.max_rows = 10\n",
      "\n",
      "try:\n",
      "    from mpltools import style\n",
      "    style.use('ggplot')\n",
      "except ImportError:\n",
      "    pass\n",
      "\n",
      "\n",
      "# because of our bg color\n",
      "plt.rc('text', color='white')\n",
      "plt.rc('axes', labelcolor='white')\n",
      "plt.rc('xtick', color='white')\n",
      "plt.rc('ytick', color='white')"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 9
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "%matplotlib inline"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 10
    },
    {
     "cell_type": "heading",
     "level": 1,
     "metadata": {},
     "source": [
      "[``pandas.DataFrame``](http://pandas.pydata.org/pandas-docs/stable/dsintro.html#dataframe)"
     ]
    },
    {
     "cell_type": "heading",
     "level": 3,
     "metadata": {},
     "source": [
      "``DataFrame`` is the flagship data structure in ``pandas``"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "df = pd.DataFrame(randn(10, 2), columns=list('ab'))\n",
      "df"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "html": [
        "<div style=\"max-height:1000px;max-width:1500px;overflow:auto;\">\n",
        "<table border=\"1\" class=\"dataframe\">\n",
        "  <thead>\n",
        "    <tr style=\"text-align: right;\">\n",
        "      <th></th>\n",
        "      <th>a</th>\n",
        "      <th>b</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>0</th>\n",
        "      <td> 1.525911</td>\n",
        "      <td>-1.536062</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>1</th>\n",
        "      <td>-0.773639</td>\n",
        "      <td> 0.786538</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2</th>\n",
        "      <td> 0.673406</td>\n",
        "      <td> 0.336026</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>3</th>\n",
        "      <td>-0.778567</td>\n",
        "      <td> 0.557999</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>4</th>\n",
        "      <td> 0.932137</td>\n",
        "      <td>-1.204426</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>5</th>\n",
        "      <td> 0.139991</td>\n",
        "      <td> 0.406078</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>6</th>\n",
        "      <td>-0.687879</td>\n",
        "      <td>-0.497632</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>7</th>\n",
        "      <td> 0.271935</td>\n",
        "      <td>-0.287440</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>8</th>\n",
        "      <td> 0.240098</td>\n",
        "      <td> 1.125080</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>9</th>\n",
        "      <td> 0.235167</td>\n",
        "      <td>-0.532541</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 11,
       "text": [
        "          a         b\n",
        "0  1.525911 -1.536062\n",
        "1 -0.773639  0.786538\n",
        "2  0.673406  0.336026\n",
        "3 -0.778567  0.557999\n",
        "4  0.932137 -1.204426\n",
        "5  0.139991  0.406078\n",
        "6 -0.687879 -0.497632\n",
        "7  0.271935 -0.287440\n",
        "8  0.240098  1.125080\n",
        "9  0.235167 -0.532541"
       ]
      }
     ],
     "prompt_number": 11
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "# if you have boto installed and have set up credentials\n",
      "# df = pd.read_csv('s3://nypug/tips.csv')"
     ],
     "language": "python",
     "metadata": {},
     "outputs": []
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "df = pd.read_csv('https://s3.amazonaws.com/nyqpug/tips.csv')\n",
      "df"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "html": [
        "<div style=\"max-height:1000px;max-width:1500px;overflow:auto;\">\n",
        "<table border=\"1\" class=\"dataframe\">\n",
        "  <thead>\n",
        "    <tr style=\"text-align: right;\">\n",
        "      <th></th>\n",
        "      <th>total_bill</th>\n",
        "      <th>tip</th>\n",
        "      <th>sex</th>\n",
        "      <th>smoker</th>\n",
        "      <th>day</th>\n",
        "      <th>time</th>\n",
        "      <th>size</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>0  </th>\n",
        "      <td> 16.99</td>\n",
        "      <td> 1.01</td>\n",
        "      <td> Female</td>\n",
        "      <td>  No</td>\n",
        "      <td>  Sun</td>\n",
        "      <td> Dinner</td>\n",
        "      <td> 2</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>1  </th>\n",
        "      <td> 10.34</td>\n",
        "      <td> 1.66</td>\n",
        "      <td>   Male</td>\n",
        "      <td>  No</td>\n",
        "      <td>  Sun</td>\n",
        "      <td> Dinner</td>\n",
        "      <td> 3</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2  </th>\n",
        "      <td> 21.01</td>\n",
        "      <td> 3.50</td>\n",
        "      <td>   Male</td>\n",
        "      <td>  No</td>\n",
        "      <td>  Sun</td>\n",
        "      <td> Dinner</td>\n",
        "      <td> 3</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>3  </th>\n",
        "      <td> 23.68</td>\n",
        "      <td> 3.31</td>\n",
        "      <td>   Male</td>\n",
        "      <td>  No</td>\n",
        "      <td>  Sun</td>\n",
        "      <td> Dinner</td>\n",
        "      <td> 2</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>4  </th>\n",
        "      <td> 24.59</td>\n",
        "      <td> 3.61</td>\n",
        "      <td> Female</td>\n",
        "      <td>  No</td>\n",
        "      <td>  Sun</td>\n",
        "      <td> Dinner</td>\n",
        "      <td> 4</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>...</th>\n",
        "      <td>...</td>\n",
        "      <td>...</td>\n",
        "      <td>...</td>\n",
        "      <td>...</td>\n",
        "      <td>...</td>\n",
        "      <td>...</td>\n",
        "      <td>...</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>239</th>\n",
        "      <td> 29.03</td>\n",
        "      <td> 5.92</td>\n",
        "      <td>   Male</td>\n",
        "      <td>  No</td>\n",
        "      <td>  Sat</td>\n",
        "      <td> Dinner</td>\n",
        "      <td> 3</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>240</th>\n",
        "      <td> 27.18</td>\n",
        "      <td> 2.00</td>\n",
        "      <td> Female</td>\n",
        "      <td> Yes</td>\n",
        "      <td>  Sat</td>\n",
        "      <td> Dinner</td>\n",
        "      <td> 2</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>241</th>\n",
        "      <td> 22.67</td>\n",
        "      <td> 2.00</td>\n",
        "      <td>   Male</td>\n",
        "      <td> Yes</td>\n",
        "      <td>  Sat</td>\n",
        "      <td> Dinner</td>\n",
        "      <td> 2</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>242</th>\n",
        "      <td> 17.82</td>\n",
        "      <td> 1.75</td>\n",
        "      <td>   Male</td>\n",
        "      <td>  No</td>\n",
        "      <td>  Sat</td>\n",
        "      <td> Dinner</td>\n",
        "      <td> 2</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>243</th>\n",
        "      <td> 18.78</td>\n",
        "      <td> 3.00</td>\n",
        "      <td> Female</td>\n",
        "      <td>  No</td>\n",
        "      <td> Thur</td>\n",
        "      <td> Dinner</td>\n",
        "      <td> 2</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "<p>244 rows \u00d7 7 columns</p>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 12,
       "text": [
        "     total_bill   tip     sex smoker   day    time  size\n",
        "0         16.99  1.01  Female     No   Sun  Dinner     2\n",
        "1         10.34  1.66    Male     No   Sun  Dinner     3\n",
        "2         21.01  3.50    Male     No   Sun  Dinner     3\n",
        "3         23.68  3.31    Male     No   Sun  Dinner     2\n",
        "4         24.59  3.61  Female     No   Sun  Dinner     4\n",
        "..          ...   ...     ...    ...   ...     ...   ...\n",
        "239       29.03  5.92    Male     No   Sat  Dinner     3\n",
        "240       27.18  2.00  Female    Yes   Sat  Dinner     2\n",
        "241       22.67  2.00    Male    Yes   Sat  Dinner     2\n",
        "242       17.82  1.75    Male     No   Sat  Dinner     2\n",
        "243       18.78  3.00  Female     No  Thur  Dinner     2\n",
        "\n",
        "[244 rows x 7 columns]"
       ]
      }
     ],
     "prompt_number": 12
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "df.dtypes"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 13,
       "text": [
        "total_bill    float64\n",
        "tip           float64\n",
        "sex            object\n",
        "smoker         object\n",
        "day            object\n",
        "time           object\n",
        "size            int64\n",
        "dtype: object"
       ]
      }
     ],
     "prompt_number": 13
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "### One of ``pandas``' most useful and powerful features is its ability to slice and dice data in almost any way you can think of. "
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "# column access by name\n",
      "df['day']  # \u27f5 that's a Series object"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 14,
       "text": [
        "0    Sun\n",
        "1    Sun\n",
        "2    Sun\n",
        "...\n",
        "241     Sat\n",
        "242     Sat\n",
        "243    Thur\n",
        "Name: day, Length: 244, dtype: object"
       ]
      }
     ],
     "prompt_number": 14
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "# by attribute\n",
      "df.time"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 15,
       "text": [
        "0    Dinner\n",
        "1    Dinner\n",
        "2    Dinner\n",
        "...\n",
        "241    Dinner\n",
        "242    Dinner\n",
        "243    Dinner\n",
        "Name: time, Length: 244, dtype: object"
       ]
      }
     ],
     "prompt_number": 15
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "df.time.value_counts()"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 16,
       "text": [
        "Dinner    176\n",
        "Lunch      68\n",
        "dtype: int64"
       ]
      }
     ],
     "prompt_number": 16
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "# multiple columns\n",
      "df[['tip', 'sex']]"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "html": [
        "<div style=\"max-height:1000px;max-width:1500px;overflow:auto;\">\n",
        "<table border=\"1\" class=\"dataframe\">\n",
        "  <thead>\n",
        "    <tr style=\"text-align: right;\">\n",
        "      <th></th>\n",
        "      <th>tip</th>\n",
        "      <th>sex</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>0  </th>\n",
        "      <td> 1.01</td>\n",
        "      <td> Female</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>1  </th>\n",
        "      <td> 1.66</td>\n",
        "      <td>   Male</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2  </th>\n",
        "      <td> 3.50</td>\n",
        "      <td>   Male</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>3  </th>\n",
        "      <td> 3.31</td>\n",
        "      <td>   Male</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>4  </th>\n",
        "      <td> 3.61</td>\n",
        "      <td> Female</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>...</th>\n",
        "      <td>...</td>\n",
        "      <td>...</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>239</th>\n",
        "      <td> 5.92</td>\n",
        "      <td>   Male</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>240</th>\n",
        "      <td> 2.00</td>\n",
        "      <td> Female</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>241</th>\n",
        "      <td> 2.00</td>\n",
        "      <td>   Male</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>242</th>\n",
        "      <td> 1.75</td>\n",
        "      <td>   Male</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>243</th>\n",
        "      <td> 3.00</td>\n",
        "      <td> Female</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "<p>244 rows \u00d7 2 columns</p>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 17,
       "text": [
        "      tip     sex\n",
        "0    1.01  Female\n",
        "1    1.66    Male\n",
        "2    3.50    Male\n",
        "3    3.31    Male\n",
        "4    3.61  Female\n",
        "..    ...     ...\n",
        "239  5.92    Male\n",
        "240  2.00  Female\n",
        "241  2.00    Male\n",
        "242  1.75    Male\n",
        "243  3.00  Female\n",
        "\n",
        "[244 rows x 2 columns]"
       ]
      }
     ],
     "prompt_number": 17
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "t = df.set_index('day')\n",
      "t.head()"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "html": [
        "<div style=\"max-height:1000px;max-width:1500px;overflow:auto;\">\n",
        "<table border=\"1\" class=\"dataframe\">\n",
        "  <thead>\n",
        "    <tr style=\"text-align: right;\">\n",
        "      <th></th>\n",
        "      <th>total_bill</th>\n",
        "      <th>tip</th>\n",
        "      <th>sex</th>\n",
        "      <th>smoker</th>\n",
        "      <th>time</th>\n",
        "      <th>size</th>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>day</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>Sun</th>\n",
        "      <td> 16.99</td>\n",
        "      <td> 1.01</td>\n",
        "      <td> Female</td>\n",
        "      <td> No</td>\n",
        "      <td> Dinner</td>\n",
        "      <td> 2</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>Sun</th>\n",
        "      <td> 10.34</td>\n",
        "      <td> 1.66</td>\n",
        "      <td>   Male</td>\n",
        "      <td> No</td>\n",
        "      <td> Dinner</td>\n",
        "      <td> 3</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>Sun</th>\n",
        "      <td> 21.01</td>\n",
        "      <td> 3.50</td>\n",
        "      <td>   Male</td>\n",
        "      <td> No</td>\n",
        "      <td> Dinner</td>\n",
        "      <td> 3</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>Sun</th>\n",
        "      <td> 23.68</td>\n",
        "      <td> 3.31</td>\n",
        "      <td>   Male</td>\n",
        "      <td> No</td>\n",
        "      <td> Dinner</td>\n",
        "      <td> 2</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>Sun</th>\n",
        "      <td> 24.59</td>\n",
        "      <td> 3.61</td>\n",
        "      <td> Female</td>\n",
        "      <td> No</td>\n",
        "      <td> Dinner</td>\n",
        "      <td> 4</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 18,
       "text": [
        "     total_bill   tip     sex smoker    time  size\n",
        "day                                               \n",
        "Sun       16.99  1.01  Female     No  Dinner     2\n",
        "Sun       10.34  1.66    Male     No  Dinner     3\n",
        "Sun       21.01  3.50    Male     No  Dinner     3\n",
        "Sun       23.68  3.31    Male     No  Dinner     2\n",
        "Sun       24.59  3.61  Female     No  Dinner     4"
       ]
      }
     ],
     "prompt_number": 18
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "t.loc['Sun']"
     ],
     "language": "python",
     "metadata": {},
     "outputs": []
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "df.loc[df.day == 'Sun']"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "html": [
        "<div style=\"max-height:1000px;max-width:1500px;overflow:auto;\">\n",
        "<table border=\"1\" class=\"dataframe\">\n",
        "  <thead>\n",
        "    <tr style=\"text-align: right;\">\n",
        "      <th></th>\n",
        "      <th>total_bill</th>\n",
        "      <th>tip</th>\n",
        "      <th>sex</th>\n",
        "      <th>smoker</th>\n",
        "      <th>day</th>\n",
        "      <th>time</th>\n",
        "      <th>size</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>0  </th>\n",
        "      <td> 16.99</td>\n",
        "      <td> 1.01</td>\n",
        "      <td> Female</td>\n",
        "      <td>  No</td>\n",
        "      <td> Sun</td>\n",
        "      <td> Dinner</td>\n",
        "      <td> 2</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>1  </th>\n",
        "      <td> 10.34</td>\n",
        "      <td> 1.66</td>\n",
        "      <td>   Male</td>\n",
        "      <td>  No</td>\n",
        "      <td> Sun</td>\n",
        "      <td> Dinner</td>\n",
        "      <td> 3</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2  </th>\n",
        "      <td> 21.01</td>\n",
        "      <td> 3.50</td>\n",
        "      <td>   Male</td>\n",
        "      <td>  No</td>\n",
        "      <td> Sun</td>\n",
        "      <td> Dinner</td>\n",
        "      <td> 3</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>3  </th>\n",
        "      <td> 23.68</td>\n",
        "      <td> 3.31</td>\n",
        "      <td>   Male</td>\n",
        "      <td>  No</td>\n",
        "      <td> Sun</td>\n",
        "      <td> Dinner</td>\n",
        "      <td> 2</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>4  </th>\n",
        "      <td> 24.59</td>\n",
        "      <td> 3.61</td>\n",
        "      <td> Female</td>\n",
        "      <td>  No</td>\n",
        "      <td> Sun</td>\n",
        "      <td> Dinner</td>\n",
        "      <td> 4</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>...</th>\n",
        "      <td>...</td>\n",
        "      <td>...</td>\n",
        "      <td>...</td>\n",
        "      <td>...</td>\n",
        "      <td>...</td>\n",
        "      <td>...</td>\n",
        "      <td>...</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>186</th>\n",
        "      <td> 20.90</td>\n",
        "      <td> 3.50</td>\n",
        "      <td> Female</td>\n",
        "      <td> Yes</td>\n",
        "      <td> Sun</td>\n",
        "      <td> Dinner</td>\n",
        "      <td> 3</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>187</th>\n",
        "      <td> 30.46</td>\n",
        "      <td> 2.00</td>\n",
        "      <td>   Male</td>\n",
        "      <td> Yes</td>\n",
        "      <td> Sun</td>\n",
        "      <td> Dinner</td>\n",
        "      <td> 5</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>188</th>\n",
        "      <td> 18.15</td>\n",
        "      <td> 3.50</td>\n",
        "      <td> Female</td>\n",
        "      <td> Yes</td>\n",
        "      <td> Sun</td>\n",
        "      <td> Dinner</td>\n",
        "      <td> 3</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>189</th>\n",
        "      <td> 23.10</td>\n",
        "      <td> 4.00</td>\n",
        "      <td>   Male</td>\n",
        "      <td> Yes</td>\n",
        "      <td> Sun</td>\n",
        "      <td> Dinner</td>\n",
        "      <td> 3</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>190</th>\n",
        "      <td> 15.69</td>\n",
        "      <td> 1.50</td>\n",
        "      <td>   Male</td>\n",
        "      <td> Yes</td>\n",
        "      <td> Sun</td>\n",
        "      <td> Dinner</td>\n",
        "      <td> 2</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "<p>76 rows \u00d7 7 columns</p>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 19,
       "text": [
        "     total_bill   tip     sex smoker  day    time  size\n",
        "0         16.99  1.01  Female     No  Sun  Dinner     2\n",
        "1         10.34  1.66    Male     No  Sun  Dinner     3\n",
        "2         21.01  3.50    Male     No  Sun  Dinner     3\n",
        "3         23.68  3.31    Male     No  Sun  Dinner     2\n",
        "4         24.59  3.61  Female     No  Sun  Dinner     4\n",
        "..          ...   ...     ...    ...  ...     ...   ...\n",
        "186       20.90  3.50  Female    Yes  Sun  Dinner     3\n",
        "187       30.46  2.00    Male    Yes  Sun  Dinner     5\n",
        "188       18.15  3.50  Female    Yes  Sun  Dinner     3\n",
        "189       23.10  4.00    Male    Yes  Sun  Dinner     3\n",
        "190       15.69  1.50    Male    Yes  Sun  Dinner     2\n",
        "\n",
        "[76 rows x 7 columns]"
       ]
      }
     ],
     "prompt_number": 19
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "df.loc[:, 'smoker']"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 21,
       "text": [
        "0    No\n",
        "1    No\n",
        "2    No\n",
        "...\n",
        "241    Yes\n",
        "242     No\n",
        "243     No\n",
        "Name: smoker, Length: 244, dtype: object"
       ]
      }
     ],
     "prompt_number": 21
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "df.iloc[:, 3]  # same as df.loc[:, 'smoker']"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 22,
       "text": [
        "0    No\n",
        "1    No\n",
        "2    No\n",
        "...\n",
        "241    Yes\n",
        "242     No\n",
        "243     No\n",
        "Name: smoker, Length: 244, dtype: object"
       ]
      }
     ],
     "prompt_number": 22
    },
    {
     "cell_type": "heading",
     "level": 3,
     "metadata": {},
     "source": [
      "Add and delete columns as you please"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "df['pct_tip'] = df.tip / df.total_bill\n",
      "df['avg_price'] = df.total_bill / df.size"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 23
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "df.avg_price.hist(bins=20)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 24,
       "text": [
        "<matplotlib.axes._subplots.AxesSubplot at 0x4ae7a50>"
       ]
      },
      {
       "metadata": {},
       "output_type": "display_data",
       "png": "iVBORw0KGgoAAAANSUhEUgAAAXYAAAEECAYAAAA8tB+vAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nAcX+Du5tMSL3AAAAAElFTkSuQmCC\n",
       "text": [
        "<matplotlib.figure.Figure at 0x4ae7ed0>"
       ]
      }
     ],
     "prompt_number": 24
    },
    {
     "cell_type": "code",
     "collapsed": true,
     "input": [
      "del df['avg_price']\n",
      "del df['pct_tip']"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 25
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "# multiple columns, multiple rows\n",
      "df.loc[[0, 2], ['sex', 'tip']]"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "html": [
        "<div style=\"max-height:1000px;max-width:1500px;overflow:auto;\">\n",
        "<table border=\"1\" class=\"dataframe\">\n",
        "  <thead>\n",
        "    <tr style=\"text-align: right;\">\n",
        "      <th></th>\n",
        "      <th>sex</th>\n",
        "      <th>tip</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>0</th>\n",
        "      <td> Female</td>\n",
        "      <td> 1.01</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2</th>\n",
        "      <td>   Male</td>\n",
        "      <td> 3.50</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 26,
       "text": [
        "      sex   tip\n",
        "0  Female  1.01\n",
        "2    Male  3.50"
       ]
      }
     ],
     "prompt_number": 26
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "df.loc[:10, ['total_bill', 'tip']]  # note this is inclusive"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "html": [
        "<div style=\"max-height:1000px;max-width:1500px;overflow:auto;\">\n",
        "<table border=\"1\" class=\"dataframe\">\n",
        "  <thead>\n",
        "    <tr style=\"text-align: right;\">\n",
        "      <th></th>\n",
        "      <th>total_bill</th>\n",
        "      <th>tip</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>0 </th>\n",
        "      <td> 16.99</td>\n",
        "      <td> 1.01</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>1 </th>\n",
        "      <td> 10.34</td>\n",
        "      <td> 1.66</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2 </th>\n",
        "      <td> 21.01</td>\n",
        "      <td> 3.50</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>3 </th>\n",
        "      <td> 23.68</td>\n",
        "      <td> 3.31</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>4 </th>\n",
        "      <td> 24.59</td>\n",
        "      <td> 3.61</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>...</th>\n",
        "      <td>...</td>\n",
        "      <td>...</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>6 </th>\n",
        "      <td>  8.77</td>\n",
        "      <td> 2.00</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>7 </th>\n",
        "      <td> 26.88</td>\n",
        "      <td> 3.12</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>8 </th>\n",
        "      <td> 15.04</td>\n",
        "      <td> 1.96</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>9 </th>\n",
        "      <td> 14.78</td>\n",
        "      <td> 3.23</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>10</th>\n",
        "      <td> 10.27</td>\n",
        "      <td> 1.71</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "<p>11 rows \u00d7 2 columns</p>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 27,
       "text": [
        "    total_bill   tip\n",
        "0        16.99  1.01\n",
        "1        10.34  1.66\n",
        "2        21.01  3.50\n",
        "3        23.68  3.31\n",
        "4        24.59  3.61\n",
        "..         ...   ...\n",
        "6         8.77  2.00\n",
        "7        26.88  3.12\n",
        "8        15.04  1.96\n",
        "9        14.78  3.23\n",
        "10       10.27  1.71\n",
        "\n",
        "[11 rows x 2 columns]"
       ]
      }
     ],
     "prompt_number": 27
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "# and with iloc\n",
      "df.iloc[:5]  # exclusive endpoints"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "html": [
        "<div style=\"max-height:1000px;max-width:1500px;overflow:auto;\">\n",
        "<table border=\"1\" class=\"dataframe\">\n",
        "  <thead>\n",
        "    <tr style=\"text-align: right;\">\n",
        "      <th></th>\n",
        "      <th>total_bill</th>\n",
        "      <th>tip</th>\n",
        "      <th>sex</th>\n",
        "      <th>smoker</th>\n",
        "      <th>day</th>\n",
        "      <th>time</th>\n",
        "      <th>size</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>0</th>\n",
        "      <td> 16.99</td>\n",
        "      <td> 1.01</td>\n",
        "      <td> Female</td>\n",
        "      <td> No</td>\n",
        "      <td> Sun</td>\n",
        "      <td> Dinner</td>\n",
        "      <td> 2</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>1</th>\n",
        "      <td> 10.34</td>\n",
        "      <td> 1.66</td>\n",
        "      <td>   Male</td>\n",
        "      <td> No</td>\n",
        "      <td> Sun</td>\n",
        "      <td> Dinner</td>\n",
        "      <td> 3</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2</th>\n",
        "      <td> 21.01</td>\n",
        "      <td> 3.50</td>\n",
        "      <td>   Male</td>\n",
        "      <td> No</td>\n",
        "      <td> Sun</td>\n",
        "      <td> Dinner</td>\n",
        "      <td> 3</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>3</th>\n",
        "      <td> 23.68</td>\n",
        "      <td> 3.31</td>\n",
        "      <td>   Male</td>\n",
        "      <td> No</td>\n",
        "      <td> Sun</td>\n",
        "      <td> Dinner</td>\n",
        "      <td> 2</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>4</th>\n",
        "      <td> 24.59</td>\n",
        "      <td> 3.61</td>\n",
        "      <td> Female</td>\n",
        "      <td> No</td>\n",
        "      <td> Sun</td>\n",
        "      <td> Dinner</td>\n",
        "      <td> 4</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 28,
       "text": [
        "   total_bill   tip     sex smoker  day    time  size\n",
        "0       16.99  1.01  Female     No  Sun  Dinner     2\n",
        "1       10.34  1.66    Male     No  Sun  Dinner     3\n",
        "2       21.01  3.50    Male     No  Sun  Dinner     3\n",
        "3       23.68  3.31    Male     No  Sun  Dinner     2\n",
        "4       24.59  3.61  Female     No  Sun  Dinner     4"
       ]
      }
     ],
     "prompt_number": 28
    },
    {
     "cell_type": "heading",
     "level": 2,
     "metadata": {},
     "source": [
      "Applying Functions to Pandas Objects"
     ]
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "Apply a function over the columns of a ``DataFrame``"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": true,
     "input": [
      "# np.ptp is peak-to-peak difference, i.e., range\n",
      "df[['total_bill', 'tip', 'size']].apply(np.ptp)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 29,
       "text": [
        "total_bill    47.74\n",
        "tip            9.00\n",
        "size           5.00\n",
        "dtype: float64"
       ]
      }
     ],
     "prompt_number": 29
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "days = ['Sun', 'Mon', 'Tues', 'Wed', 'Thur', 'Fri', 'Sat']"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 31
    },
    {
     "cell_type": "code",
     "collapsed": true,
     "input": [
      "df.day.map(days.index)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 32,
       "text": [
        "0    0\n",
        "1    0\n",
        "2    0\n",
        "...\n",
        "241    6\n",
        "242    6\n",
        "243    4\n",
        "Name: day, Length: 244, dtype: int64"
       ]
      }
     ],
     "prompt_number": 32
    },
    {
     "cell_type": "heading",
     "level": 2,
     "metadata": {},
     "source": [
      "[Reductions](http://pandas.pydata.org/pandas-docs/stable/basics.html#descriptive-statistics)"
     ]
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "For example, the ``DataFrame.sum()`` method results in a ``Series`` object and by default sums across the rows. If you want to sum across the columns pass ``axis=1``, similar to the ``numpy`` convention"
     ]
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "In general, reduction operations result in a ``Series`` object.\n",
      "\n",
      "Some example reduction functions:\n",
      "\n",
      "* ``mean``, ``median``, and ``mode``\n",
      "* ``count``\n",
      "* ``std``, ``var``\n",
      "\n",
      "*NOTE:* **These ignore ``NaN``s**"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "df.sum()  # whoa! + is defined for strings"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 33,
       "text": [
        "total_bill                                              4827.77\n",
        "tip                                                      731.58\n",
        "sex           FemaleMaleMaleMaleFemaleMaleMaleMaleMaleMaleMa...\n",
        "smoker        NoNoNoNoNoNoNoNoNoNoNoNoNoNoNoNoNoNoNoNoNoNoNo...\n",
        "day           SunSunSunSunSunSunSunSunSunSunSunSunSunSunSunS...\n",
        "time          DinnerDinnerDinnerDinnerDinnerDinnerDinnerDinn...\n",
        "size                                                        627\n",
        "dtype: object"
       ]
      }
     ],
     "prompt_number": 33
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "df.sum(numeric_only=True)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 34,
       "text": [
        "total_bill    4827.77\n",
        "tip            731.58\n",
        "size           627.00\n",
        "dtype: float64"
       ]
      }
     ],
     "prompt_number": 34
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "df.count() / df.shape[0]  # we don't have any nans"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 37,
       "text": [
        "total_bill    1\n",
        "tip           1\n",
        "sex           1\n",
        "smoker        1\n",
        "day           1\n",
        "time          1\n",
        "size          1\n",
        "dtype: float64"
       ]
      }
     ],
     "prompt_number": 37
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "df.var()"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 35,
       "text": [
        "total_bill    79.252939\n",
        "tip            1.914455\n",
        "size           0.904591\n",
        "dtype: float64"
       ]
      }
     ],
     "prompt_number": 35
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "df.mean()"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 36,
       "text": [
        "total_bill    19.785943\n",
        "tip            2.998279\n",
        "size           2.569672\n",
        "dtype: float64"
       ]
      }
     ],
     "prompt_number": 36
    },
    {
     "cell_type": "heading",
     "level": 2,
     "metadata": {},
     "source": [
      "[``GroupBy``](http://pandas.pydata.org/pandas-docs/stable/groupby.html)"
     ]
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "``pandas``' ``GroupBy`` functionality allows you to perform operations on subsets of a ``DataFrame`` and then  combines the results for you at the end"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "df.head()"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "html": [
        "<div style=\"max-height:1000px;max-width:1500px;overflow:auto;\">\n",
        "<table border=\"1\" class=\"dataframe\">\n",
        "  <thead>\n",
        "    <tr style=\"text-align: right;\">\n",
        "      <th></th>\n",
        "      <th>total_bill</th>\n",
        "      <th>tip</th>\n",
        "      <th>sex</th>\n",
        "      <th>smoker</th>\n",
        "      <th>day</th>\n",
        "      <th>time</th>\n",
        "      <th>size</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>0</th>\n",
        "      <td> 16.99</td>\n",
        "      <td> 1.01</td>\n",
        "      <td> Female</td>\n",
        "      <td> No</td>\n",
        "      <td> Sun</td>\n",
        "      <td> Dinner</td>\n",
        "      <td> 2</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>1</th>\n",
        "      <td> 10.34</td>\n",
        "      <td> 1.66</td>\n",
        "      <td>   Male</td>\n",
        "      <td> No</td>\n",
        "      <td> Sun</td>\n",
        "      <td> Dinner</td>\n",
        "      <td> 3</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2</th>\n",
        "      <td> 21.01</td>\n",
        "      <td> 3.50</td>\n",
        "      <td>   Male</td>\n",
        "      <td> No</td>\n",
        "      <td> Sun</td>\n",
        "      <td> Dinner</td>\n",
        "      <td> 3</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>3</th>\n",
        "      <td> 23.68</td>\n",
        "      <td> 3.31</td>\n",
        "      <td>   Male</td>\n",
        "      <td> No</td>\n",
        "      <td> Sun</td>\n",
        "      <td> Dinner</td>\n",
        "      <td> 2</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>4</th>\n",
        "      <td> 24.59</td>\n",
        "      <td> 3.61</td>\n",
        "      <td> Female</td>\n",
        "      <td> No</td>\n",
        "      <td> Sun</td>\n",
        "      <td> Dinner</td>\n",
        "      <td> 4</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 38,
       "text": [
        "   total_bill   tip     sex smoker  day    time  size\n",
        "0       16.99  1.01  Female     No  Sun  Dinner     2\n",
        "1       10.34  1.66    Male     No  Sun  Dinner     3\n",
        "2       21.01  3.50    Male     No  Sun  Dinner     3\n",
        "3       23.68  3.31    Male     No  Sun  Dinner     2\n",
        "4       24.59  3.61  Female     No  Sun  Dinner     4"
       ]
      }
     ],
     "prompt_number": 38
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "gb = df.groupby('sex')\n",
      "gb.mean()"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "html": [
        "<div style=\"max-height:1000px;max-width:1500px;overflow:auto;\">\n",
        "<table border=\"1\" class=\"dataframe\">\n",
        "  <thead>\n",
        "    <tr style=\"text-align: right;\">\n",
        "      <th></th>\n",
        "      <th>total_bill</th>\n",
        "      <th>tip</th>\n",
        "      <th>size</th>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>sex</th>\n",
        "      <th></th>\n",
        "      <th></th>\n",
        "      <th></th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>Female</th>\n",
        "      <td> 18.056897</td>\n",
        "      <td> 2.833448</td>\n",
        "      <td> 2.459770</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>Male</th>\n",
        "      <td> 20.744076</td>\n",
        "      <td> 3.089618</td>\n",
        "      <td> 2.630573</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 39,
       "text": [
        "        total_bill       tip      size\n",
        "sex                                   \n",
        "Female   18.056897  2.833448  2.459770\n",
        "Male     20.744076  3.089618  2.630573"
       ]
      }
     ],
     "prompt_number": 39
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "gb = df.groupby(['sex', 'smoker'])\n",
      "gb.std()"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "html": [
        "<div style=\"max-height:1000px;max-width:1500px;overflow:auto;\">\n",
        "<table border=\"1\" class=\"dataframe\">\n",
        "  <thead>\n",
        "    <tr style=\"text-align: right;\">\n",
        "      <th></th>\n",
        "      <th></th>\n",
        "      <th>total_bill</th>\n",
        "      <th>tip</th>\n",
        "      <th>size</th>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>sex</th>\n",
        "      <th>smoker</th>\n",
        "      <th></th>\n",
        "      <th></th>\n",
        "      <th></th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th rowspan=\"2\" valign=\"top\">Female</th>\n",
        "      <th>No</th>\n",
        "      <td> 7.286455</td>\n",
        "      <td> 1.128425</td>\n",
        "      <td> 1.073146</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>Yes</th>\n",
        "      <td> 9.189751</td>\n",
        "      <td> 1.219916</td>\n",
        "      <td> 0.613917</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th rowspan=\"2\" valign=\"top\">Male</th>\n",
        "      <th>No</th>\n",
        "      <td> 8.726566</td>\n",
        "      <td> 1.489559</td>\n",
        "      <td> 0.989094</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>Yes</th>\n",
        "      <td> 9.911845</td>\n",
        "      <td> 1.500120</td>\n",
        "      <td> 0.892530</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 40,
       "text": [
        "               total_bill       tip      size\n",
        "sex    smoker                                \n",
        "Female No        7.286455  1.128425  1.073146\n",
        "       Yes       9.189751  1.219916  0.613917\n",
        "Male   No        8.726566  1.489559  0.989094\n",
        "       Yes       9.911845  1.500120  0.892530"
       ]
      }
     ],
     "prompt_number": 40
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "# can pass multiple reducers to agg\n",
      "gb.agg(['mean', 'std', 'median'])"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "html": [
        "<div style=\"max-height:1000px;max-width:1500px;overflow:auto;\">\n",
        "<table border=\"1\" class=\"dataframe\">\n",
        "  <thead>\n",
        "    <tr>\n",
        "      <th></th>\n",
        "      <th></th>\n",
        "      <th colspan=\"3\" halign=\"left\">total_bill</th>\n",
        "      <th colspan=\"3\" halign=\"left\">tip</th>\n",
        "      <th colspan=\"3\" halign=\"left\">size</th>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th></th>\n",
        "      <th></th>\n",
        "      <th>mean</th>\n",
        "      <th>std</th>\n",
        "      <th>median</th>\n",
        "      <th>mean</th>\n",
        "      <th>std</th>\n",
        "      <th>median</th>\n",
        "      <th>mean</th>\n",
        "      <th>std</th>\n",
        "      <th>median</th>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>sex</th>\n",
        "      <th>smoker</th>\n",
        "      <th></th>\n",
        "      <th></th>\n",
        "      <th></th>\n",
        "      <th></th>\n",
        "      <th></th>\n",
        "      <th></th>\n",
        "      <th></th>\n",
        "      <th></th>\n",
        "      <th></th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th rowspan=\"2\" valign=\"top\">Female</th>\n",
        "      <th>No</th>\n",
        "      <td> 18.105185</td>\n",
        "      <td> 7.286455</td>\n",
        "      <td> 16.69</td>\n",
        "      <td> 2.773519</td>\n",
        "      <td> 1.128425</td>\n",
        "      <td> 2.68</td>\n",
        "      <td> 2.592593</td>\n",
        "      <td> 1.073146</td>\n",
        "      <td> 2</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>Yes</th>\n",
        "      <td> 17.977879</td>\n",
        "      <td> 9.189751</td>\n",
        "      <td> 16.27</td>\n",
        "      <td> 2.931515</td>\n",
        "      <td> 1.219916</td>\n",
        "      <td> 2.88</td>\n",
        "      <td> 2.242424</td>\n",
        "      <td> 0.613917</td>\n",
        "      <td> 2</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th rowspan=\"2\" valign=\"top\">Male</th>\n",
        "      <th>No</th>\n",
        "      <td> 19.791237</td>\n",
        "      <td> 8.726566</td>\n",
        "      <td> 18.24</td>\n",
        "      <td> 3.113402</td>\n",
        "      <td> 1.489559</td>\n",
        "      <td> 2.74</td>\n",
        "      <td> 2.711340</td>\n",
        "      <td> 0.989094</td>\n",
        "      <td> 2</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>Yes</th>\n",
        "      <td> 22.284500</td>\n",
        "      <td> 9.911845</td>\n",
        "      <td> 20.39</td>\n",
        "      <td> 3.051167</td>\n",
        "      <td> 1.500120</td>\n",
        "      <td> 3.00</td>\n",
        "      <td> 2.500000</td>\n",
        "      <td> 0.892530</td>\n",
        "      <td> 2</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 41,
       "text": [
        "               total_bill                         tip                    \\\n",
        "                     mean       std  median      mean       std  median   \n",
        "sex    smoker                                                             \n",
        "Female No       18.105185  7.286455   16.69  2.773519  1.128425    2.68   \n",
        "       Yes      17.977879  9.189751   16.27  2.931515  1.219916    2.88   \n",
        "Male   No       19.791237  8.726566   18.24  3.113402  1.489559    2.74   \n",
        "       Yes      22.284500  9.911845   20.39  3.051167  1.500120    3.00   \n",
        "\n",
        "                   size                    \n",
        "                   mean       std  median  \n",
        "sex    smoker                              \n",
        "Female No      2.592593  1.073146       2  \n",
        "       Yes     2.242424  0.613917       2  \n",
        "Male   No      2.711340  0.989094       2  \n",
        "       Yes     2.500000  0.892530       2  "
       ]
      }
     ],
     "prompt_number": 41
    },
    {
     "cell_type": "heading",
     "level": 3,
     "metadata": {},
     "source": [
      "``apply``"
     ]
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "``GroupBy.apply()`` take a `callable` and calls it on each group"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "def stdize(x):\n",
      "    return (x - x.mean()) / x.std()\n",
      "    \n",
      "df['tb_std'] = gb.total_bill.apply(stdize)\n",
      "df"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "html": [
        "<div style=\"max-height:1000px;max-width:1500px;overflow:auto;\">\n",
        "<table border=\"1\" class=\"dataframe\">\n",
        "  <thead>\n",
        "    <tr style=\"text-align: right;\">\n",
        "      <th></th>\n",
        "      <th>total_bill</th>\n",
        "      <th>tip</th>\n",
        "      <th>sex</th>\n",
        "      <th>smoker</th>\n",
        "      <th>day</th>\n",
        "      <th>time</th>\n",
        "      <th>size</th>\n",
        "      <th>tb_std</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>0  </th>\n",
        "      <td> 16.99</td>\n",
        "      <td> 1.01</td>\n",
        "      <td> Female</td>\n",
        "      <td>  No</td>\n",
        "      <td>  Sun</td>\n",
        "      <td> Dinner</td>\n",
        "      <td> 2</td>\n",
        "      <td>-0.153049</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>1  </th>\n",
        "      <td> 10.34</td>\n",
        "      <td> 1.66</td>\n",
        "      <td>   Male</td>\n",
        "      <td>  No</td>\n",
        "      <td>  Sun</td>\n",
        "      <td> Dinner</td>\n",
        "      <td> 3</td>\n",
        "      <td>-1.083042</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2  </th>\n",
        "      <td> 21.01</td>\n",
        "      <td> 3.50</td>\n",
        "      <td>   Male</td>\n",
        "      <td>  No</td>\n",
        "      <td>  Sun</td>\n",
        "      <td> Dinner</td>\n",
        "      <td> 3</td>\n",
        "      <td> 0.139661</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>3  </th>\n",
        "      <td> 23.68</td>\n",
        "      <td> 3.31</td>\n",
        "      <td>   Male</td>\n",
        "      <td>  No</td>\n",
        "      <td>  Sun</td>\n",
        "      <td> Dinner</td>\n",
        "      <td> 2</td>\n",
        "      <td> 0.445623</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>4  </th>\n",
        "      <td> 24.59</td>\n",
        "      <td> 3.61</td>\n",
        "      <td> Female</td>\n",
        "      <td>  No</td>\n",
        "      <td>  Sun</td>\n",
        "      <td> Dinner</td>\n",
        "      <td> 4</td>\n",
        "      <td> 0.889982</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>...</th>\n",
        "      <td>...</td>\n",
        "      <td>...</td>\n",
        "      <td>...</td>\n",
        "      <td>...</td>\n",
        "      <td>...</td>\n",
        "      <td>...</td>\n",
        "      <td>...</td>\n",
        "      <td>...</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>239</th>\n",
        "      <td> 29.03</td>\n",
        "      <td> 5.92</td>\n",
        "      <td>   Male</td>\n",
        "      <td>  No</td>\n",
        "      <td>  Sat</td>\n",
        "      <td> Dinner</td>\n",
        "      <td> 3</td>\n",
        "      <td> 1.058694</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>240</th>\n",
        "      <td> 27.18</td>\n",
        "      <td> 2.00</td>\n",
        "      <td> Female</td>\n",
        "      <td> Yes</td>\n",
        "      <td>  Sat</td>\n",
        "      <td> Dinner</td>\n",
        "      <td> 2</td>\n",
        "      <td> 1.001346</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>241</th>\n",
        "      <td> 22.67</td>\n",
        "      <td> 2.00</td>\n",
        "      <td>   Male</td>\n",
        "      <td> Yes</td>\n",
        "      <td>  Sat</td>\n",
        "      <td> Dinner</td>\n",
        "      <td> 2</td>\n",
        "      <td> 0.038893</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>242</th>\n",
        "      <td> 17.82</td>\n",
        "      <td> 1.75</td>\n",
        "      <td>   Male</td>\n",
        "      <td>  No</td>\n",
        "      <td>  Sat</td>\n",
        "      <td> Dinner</td>\n",
        "      <td> 2</td>\n",
        "      <td>-0.225889</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>243</th>\n",
        "      <td> 18.78</td>\n",
        "      <td> 3.00</td>\n",
        "      <td> Female</td>\n",
        "      <td>  No</td>\n",
        "      <td> Thur</td>\n",
        "      <td> Dinner</td>\n",
        "      <td> 2</td>\n",
        "      <td> 0.092612</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "<p>244 rows \u00d7 8 columns</p>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 42,
       "text": [
        "     total_bill   tip     sex smoker   day    time  size    tb_std\n",
        "0         16.99  1.01  Female     No   Sun  Dinner     2 -0.153049\n",
        "1         10.34  1.66    Male     No   Sun  Dinner     3 -1.083042\n",
        "2         21.01  3.50    Male     No   Sun  Dinner     3  0.139661\n",
        "3         23.68  3.31    Male     No   Sun  Dinner     2  0.445623\n",
        "4         24.59  3.61  Female     No   Sun  Dinner     4  0.889982\n",
        "..          ...   ...     ...    ...   ...     ...   ...       ...\n",
        "239       29.03  5.92    Male     No   Sat  Dinner     3  1.058694\n",
        "240       27.18  2.00  Female    Yes   Sat  Dinner     2  1.001346\n",
        "241       22.67  2.00    Male    Yes   Sat  Dinner     2  0.038893\n",
        "242       17.82  1.75    Male     No   Sat  Dinner     2 -0.225889\n",
        "243       18.78  3.00  Female     No  Thur  Dinner     2  0.092612\n",
        "\n",
        "[244 rows x 8 columns]"
       ]
      }
     ],
     "prompt_number": 42
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "ax = df.tb_std.plot(kind='kde', lw=3)\n",
      "df.tb_std.hist(ax=ax, normed=True)\n",
      "\n",
      "ax.set_xlabel('$z$-score', fontsize=20)\n",
      "ax.set_title(r'Total Bill Stdized Across Sex$\\times$ Smoker')\n",
      "\n",
      "ax.axis('tight')\n",
      "plt.gcf().tight_layout()"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "display_data",
       "png": "iVBORw0KGgoAAAANSUhEUgAAAakAAAEYCAYAAADmugmLAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nAAAASUVORK5CYII=\n",
       "text": [
        "<matplotlib.figure.Figure at 0x4d5d190>"
       ]
      }
     ],
     "prompt_number": 43
    },
    {
     "cell_type": "heading",
     "level": 2,
     "metadata": {},
     "source": [
      "[``merge``](http://pandas.pydata.org/pandas-docs/stable/merging.html)"
     ]
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "Often times you have data sets of different shapes with a common column that you want to join on\n",
      "\n",
      "``pandas`` does this a couple of ways, but the main entry point is ``pandas.merge``"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "# create some frames\n",
      "n = 2000\n",
      "n2 = n // 2\n",
      "visits = DataFrame({'page_visits_per_day': np.random.poisson(10, size=n),\n",
      "                 'user_id': randint(9, size=n)})\n",
      "likes = DataFrame({'likes_per_day': np.random.poisson(30, size=n2),\n",
      "                   'user_id': randint(6, size=n2)})\n",
      "visits"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "html": [
        "<div style=\"max-height:1000px;max-width:1500px;overflow:auto;\">\n",
        "<table border=\"1\" class=\"dataframe\">\n",
        "  <thead>\n",
        "    <tr style=\"text-align: right;\">\n",
        "      <th></th>\n",
        "      <th>page_visits_per_day</th>\n",
        "      <th>user_id</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>0   </th>\n",
        "      <td>  6</td>\n",
        "      <td> 4</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>1   </th>\n",
        "      <td> 12</td>\n",
        "      <td> 1</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2   </th>\n",
        "      <td> 13</td>\n",
        "      <td> 5</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>3   </th>\n",
        "      <td>  7</td>\n",
        "      <td> 1</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>4   </th>\n",
        "      <td>  6</td>\n",
        "      <td> 7</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>...</th>\n",
        "      <td>...</td>\n",
        "      <td>...</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>1995</th>\n",
        "      <td>  7</td>\n",
        "      <td> 1</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>1996</th>\n",
        "      <td>  8</td>\n",
        "      <td> 5</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>1997</th>\n",
        "      <td>  9</td>\n",
        "      <td> 3</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>1998</th>\n",
        "      <td> 10</td>\n",
        "      <td> 6</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>1999</th>\n",
        "      <td>  8</td>\n",
        "      <td> 4</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "<p>2000 rows \u00d7 2 columns</p>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 45,
       "text": [
        "      page_visits_per_day  user_id\n",
        "0                       6        4\n",
        "1                      12        1\n",
        "2                      13        5\n",
        "3                       7        1\n",
        "4                       6        7\n",
        "...                   ...      ...\n",
        "1995                    7        1\n",
        "1996                    8        5\n",
        "1997                    9        3\n",
        "1998                   10        6\n",
        "1999                    8        4\n",
        "\n",
        "[2000 rows x 2 columns]"
       ]
      }
     ],
     "prompt_number": 45
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "likes"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "html": [
        "<div style=\"max-height:1000px;max-width:1500px;overflow:auto;\">\n",
        "<table border=\"1\" class=\"dataframe\">\n",
        "  <thead>\n",
        "    <tr style=\"text-align: right;\">\n",
        "      <th></th>\n",
        "      <th>likes_per_day</th>\n",
        "      <th>user_id</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>0  </th>\n",
        "      <td> 27</td>\n",
        "      <td> 0</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>1  </th>\n",
        "      <td> 33</td>\n",
        "      <td> 4</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2  </th>\n",
        "      <td> 23</td>\n",
        "      <td> 1</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>3  </th>\n",
        "      <td> 31</td>\n",
        "      <td> 5</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>4  </th>\n",
        "      <td> 26</td>\n",
        "      <td> 0</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>...</th>\n",
        "      <td>...</td>\n",
        "      <td>...</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>995</th>\n",
        "      <td> 28</td>\n",
        "      <td> 5</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>996</th>\n",
        "      <td> 30</td>\n",
        "      <td> 3</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>997</th>\n",
        "      <td> 33</td>\n",
        "      <td> 4</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>998</th>\n",
        "      <td> 29</td>\n",
        "      <td> 0</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>999</th>\n",
        "      <td> 27</td>\n",
        "      <td> 5</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "<p>1000 rows \u00d7 2 columns</p>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 46,
       "text": [
        "     likes_per_day  user_id\n",
        "0               27        0\n",
        "1               33        4\n",
        "2               23        1\n",
        "3               31        5\n",
        "4               26        0\n",
        "..             ...      ...\n",
        "995             28        5\n",
        "996             30        3\n",
        "997             33        4\n",
        "998             29        0\n",
        "999             27        5\n",
        "\n",
        "[1000 rows x 2 columns]"
       ]
      }
     ],
     "prompt_number": 46
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "merg = pd.merge(visits, likes)\n",
      "merg.sort('user_id')"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "html": [
        "<div style=\"max-height:1000px;max-width:1500px;overflow:auto;\">\n",
        "<table border=\"1\" class=\"dataframe\">\n",
        "  <thead>\n",
        "    <tr style=\"text-align: right;\">\n",
        "      <th></th>\n",
        "      <th>page_visits_per_day</th>\n",
        "      <th>user_id</th>\n",
        "      <th>likes_per_day</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>152516</th>\n",
        "      <td> 15</td>\n",
        "      <td> 0</td>\n",
        "      <td> 22</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>174447</th>\n",
        "      <td> 11</td>\n",
        "      <td> 0</td>\n",
        "      <td> 21</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>174446</th>\n",
        "      <td> 11</td>\n",
        "      <td> 0</td>\n",
        "      <td> 25</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>174445</th>\n",
        "      <td> 11</td>\n",
        "      <td> 0</td>\n",
        "      <td> 25</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>174444</th>\n",
        "      <td> 11</td>\n",
        "      <td> 0</td>\n",
        "      <td> 26</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>...</th>\n",
        "      <td>...</td>\n",
        "      <td>...</td>\n",
        "      <td>...</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>85623 </th>\n",
        "      <td> 17</td>\n",
        "      <td> 5</td>\n",
        "      <td> 24</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>85624 </th>\n",
        "      <td> 17</td>\n",
        "      <td> 5</td>\n",
        "      <td> 35</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>85625 </th>\n",
        "      <td> 17</td>\n",
        "      <td> 5</td>\n",
        "      <td> 34</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>85645 </th>\n",
        "      <td> 17</td>\n",
        "      <td> 5</td>\n",
        "      <td> 25</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>73182 </th>\n",
        "      <td> 10</td>\n",
        "      <td> 5</td>\n",
        "      <td> 34</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "<p>227153 rows \u00d7 3 columns</p>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 47,
       "text": [
        "        page_visits_per_day  user_id  likes_per_day\n",
        "152516                   15        0             22\n",
        "174447                   11        0             21\n",
        "174446                   11        0             25\n",
        "174445                   11        0             25\n",
        "174444                   11        0             26\n",
        "...                     ...      ...            ...\n",
        "85623                    17        5             24\n",
        "85624                    17        5             35\n",
        "85625                    17        5             34\n",
        "85645                    17        5             25\n",
        "73182                    10        5             34\n",
        "\n",
        "[227153 rows x 3 columns]"
       ]
      }
     ],
     "prompt_number": 47
    },
    {
     "cell_type": "heading",
     "level": 2,
     "metadata": {},
     "source": [
      "[String Manipulation](http://pandas.pydata.org/pandas-docs/stable/basics.html#vectorized-string-methods)"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "s = df.day\n",
      "s"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 48,
       "text": [
        "0    Sun\n",
        "1    Sun\n",
        "2    Sun\n",
        "...\n",
        "241     Sat\n",
        "242     Sat\n",
        "243    Thur\n",
        "Name: day, Length: 244, dtype: object"
       ]
      }
     ],
     "prompt_number": 48
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "is_weekend = s.str.startswith('S')\n",
      "is_weekend"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 49,
       "text": [
        "0    True\n",
        "1    True\n",
        "2    True\n",
        "...\n",
        "241     True\n",
        "242     True\n",
        "243    False\n",
        "Name: day, Length: 244, dtype: bool"
       ]
      }
     ],
     "prompt_number": 49
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "correct = s[is_weekend].str.contains(r'^(?:Sat|Sun)$')\n",
      "correct.all()"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 50,
       "text": [
        "True"
       ]
      }
     ],
     "prompt_number": 50
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "s.str.len()"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 51,
       "text": [
        "0    3\n",
        "1    3\n",
        "2    3\n",
        "...\n",
        "241    3\n",
        "242    3\n",
        "243    4\n",
        "Name: day, Length: 244, dtype: int64"
       ]
      }
     ],
     "prompt_number": 51
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "s.str[:2]"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 52,
       "text": [
        "0    Su\n",
        "1    Su\n",
        "2    Su\n",
        "...\n",
        "241    Sa\n",
        "242    Sa\n",
        "243    Th\n",
        "Name: day, Length: 244, dtype: object"
       ]
      }
     ],
     "prompt_number": 52
    },
    {
     "cell_type": "heading",
     "level": 2,
     "metadata": {},
     "source": [
      "[Time Series Functionality](http://pandas.pydata.org/pandas-docs/stable/timeseries.html)"
     ]
    },
    {
     "cell_type": "heading",
     "level": 3,
     "metadata": {},
     "source": [
      "Construction"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "n = 10000\n",
      "idx = pd.date_range(start='today', periods=n, freq='D')\n",
      "idx"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 53,
       "text": [
        "<class 'pandas.tseries.index.DatetimeIndex'>\n",
        "[2014-05-28, ..., 2041-10-12]\n",
        "Length: 10000, Freq: D, Timezone: None"
       ]
      }
     ],
     "prompt_number": 53
    },
    {
     "cell_type": "code",
     "collapsed": true,
     "input": [
      "s = Series(np.random.poisson(10, size=n), index=idx, name='login_count')\n",
      "s"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 55,
       "text": [
        "2014-05-28     6\n",
        "2014-05-29    12\n",
        "2014-05-30    11\n",
        "...\n",
        "2041-10-10     6\n",
        "2041-10-11    14\n",
        "2041-10-12     8\n",
        "Freq: D, Name: login_count, Length: 10000"
       ]
      }
     ],
     "prompt_number": 55
    },
    {
     "cell_type": "heading",
     "level": 3,
     "metadata": {},
     "source": [
      "``resample``"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "s.resample('W', how='sum')"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 56,
       "text": [
        "2014-06-01    46\n",
        "2014-06-08    56\n",
        "2014-06-15    74\n",
        "...\n",
        "2041-09-29    66\n",
        "2041-10-06    77\n",
        "2041-10-13    59\n",
        "Freq: W-SUN, Name: login_count, Length: 1429"
       ]
      }
     ],
     "prompt_number": 56
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "# multiple functions\n",
      "rs = s.resample('W', how=['mean', 'std', 'count'])\n",
      "rs"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "html": [
        "<div style=\"max-height:1000px;max-width:1500px;overflow:auto;\">\n",
        "<table border=\"1\" class=\"dataframe\">\n",
        "  <thead>\n",
        "    <tr style=\"text-align: right;\">\n",
        "      <th></th>\n",
        "      <th>mean</th>\n",
        "      <th>std</th>\n",
        "      <th>count</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>2014-06-01</th>\n",
        "      <td>  9.200000</td>\n",
        "      <td> 2.387467</td>\n",
        "      <td> 5</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2014-06-08</th>\n",
        "      <td>  8.000000</td>\n",
        "      <td> 2.768875</td>\n",
        "      <td> 7</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2014-06-15</th>\n",
        "      <td> 10.571429</td>\n",
        "      <td> 4.755949</td>\n",
        "      <td> 7</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2014-06-22</th>\n",
        "      <td> 10.857143</td>\n",
        "      <td> 3.132016</td>\n",
        "      <td> 7</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2014-06-29</th>\n",
        "      <td>  9.285714</td>\n",
        "      <td> 2.927700</td>\n",
        "      <td> 7</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>...</th>\n",
        "      <td>...</td>\n",
        "      <td>...</td>\n",
        "      <td>...</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2041-09-15</th>\n",
        "      <td>  8.285714</td>\n",
        "      <td> 2.984085</td>\n",
        "      <td> 7</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2041-09-22</th>\n",
        "      <td> 10.000000</td>\n",
        "      <td> 2.000000</td>\n",
        "      <td> 7</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2041-09-29</th>\n",
        "      <td>  9.428571</td>\n",
        "      <td> 3.154739</td>\n",
        "      <td> 7</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2041-10-06</th>\n",
        "      <td> 11.000000</td>\n",
        "      <td> 2.828427</td>\n",
        "      <td> 7</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2041-10-13</th>\n",
        "      <td>  9.833333</td>\n",
        "      <td> 2.857738</td>\n",
        "      <td> 6</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "<p>1429 rows \u00d7 3 columns</p>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 57,
       "text": [
        "                 mean       std  count\n",
        "2014-06-01   9.200000  2.387467      5\n",
        "2014-06-08   8.000000  2.768875      7\n",
        "2014-06-15  10.571429  4.755949      7\n",
        "2014-06-22  10.857143  3.132016      7\n",
        "2014-06-29   9.285714  2.927700      7\n",
        "...               ...       ...    ...\n",
        "2041-09-15   8.285714  2.984085      7\n",
        "2041-09-22  10.000000  2.000000      7\n",
        "2041-09-29   9.428571  3.154739      7\n",
        "2041-10-06  11.000000  2.828427      7\n",
        "2041-10-13   9.833333  2.857738      6\n",
        "\n",
        "[1429 rows x 3 columns]"
       ]
      }
     ],
     "prompt_number": 57
    },
    {
     "cell_type": "heading",
     "level": 2,
     "metadata": {},
     "source": [
      "[Plotting](http://pandas.pydata.org/pandas-docs/stable/visualization.html)"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "mu = rs['mean']\n",
      "fig, ax = plt.subplots(figsize=(12, 6))\n",
      "ax.step(mu.index[:50], mu.iloc[:50], lw=3, where='post')\n",
      "fig.tight_layout()\n",
      "ax.set_xlabel('Time')\n",
      "ax.set_ylabel('Average Count / Week')\n",
      "ax.set_title('Count vs. Time')"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 58,
       "text": [
        "<matplotlib.text.Text at 0x58f0550>"
       ]
      },
      {
       "metadata": {},
       "output_type": "display_data",
       "png": "iVBORw0KGgoAAAANSUhEUgAAA2cAAAHHCAYAAAA7yCCiAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nFmeSJEmSFAGLM0mSJEmKwP8HjQ1kLPi6diIAAAAASUVORK5CYII=\n",
       "text": [
        "<matplotlib.figure.Figure at 0x58991d0>"
       ]
      }
     ],
     "prompt_number": 58
    },
    {
     "cell_type": "heading",
     "level": 2,
     "metadata": {},
     "source": [
      "Basic IO"
     ]
    },
    {
     "cell_type": "heading",
     "level": 3,
     "metadata": {},
     "source": [
      "CSV: [``read_csv``](http://pandas.pydata.org/pandas-docs/stable/io.html#io-read-csv-table)/[``to_csv``](http://pandas.pydata.org/pandas-docs/stable/io.html#io-store-in-csv)"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "%%writefile tmp.csv\n",
      "a,b,c\n",
      "1,d,3.0\n",
      "4,e,6.28\n",
      "2,f,4.4"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "Overwriting tmp.csv\n"
       ]
      }
     ],
     "prompt_number": 59
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "df = pd.read_csv('tmp.csv')\n",
      "df"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "html": [
        "<div style=\"max-height:1000px;max-width:1500px;overflow:auto;\">\n",
        "<table border=\"1\" class=\"dataframe\">\n",
        "  <thead>\n",
        "    <tr style=\"text-align: right;\">\n",
        "      <th></th>\n",
        "      <th>a</th>\n",
        "      <th>b</th>\n",
        "      <th>c</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>0</th>\n",
        "      <td> 1</td>\n",
        "      <td> d</td>\n",
        "      <td> 3.00</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>1</th>\n",
        "      <td> 4</td>\n",
        "      <td> e</td>\n",
        "      <td> 6.28</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2</th>\n",
        "      <td> 2</td>\n",
        "      <td> f</td>\n",
        "      <td> 4.40</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 60,
       "text": [
        "   a  b     c\n",
        "0  1  d  3.00\n",
        "1  4  e  6.28\n",
        "2  2  f  4.40"
       ]
      }
     ],
     "prompt_number": 60
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "df.dtypes"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 61,
       "text": [
        "a      int64\n",
        "b     object\n",
        "c    float64\n",
        "dtype: object"
       ]
      }
     ],
     "prompt_number": 61
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "df.to_csv('tmp.csv')"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 62
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "%cat tmp.csv # saves the index created by default"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        ",a,b,c\r\n",
        "0,1,d,3.0\r\n",
        "1,4,e,6.28\r\n",
        "2,2,f,4.4\r\n"
       ]
      }
     ],
     "prompt_number": 63
    },
    {
     "cell_type": "heading",
     "level": 3,
     "metadata": {},
     "source": [
      "HDF5: [``read_hdf``](http://pandas.pydata.org/pandas-docs/stable/io.html#io-hdf5)/[``to_hdf``](http://pandas.pydata.org/pandas-docs/stable/io.html#io-hdf5)"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "df = DataFrame(dict(a=randn(10), b=randint(10, size=10),\n",
      "                    c=choice(list('abc'), size=10)))\n",
      "df"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "html": [
        "<div style=\"max-height:1000px;max-width:1500px;overflow:auto;\">\n",
        "<table border=\"1\" class=\"dataframe\">\n",
        "  <thead>\n",
        "    <tr style=\"text-align: right;\">\n",
        "      <th></th>\n",
        "      <th>a</th>\n",
        "      <th>b</th>\n",
        "      <th>c</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>0</th>\n",
        "      <td> 0.311531</td>\n",
        "      <td> 2</td>\n",
        "      <td> a</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>1</th>\n",
        "      <td> 0.466764</td>\n",
        "      <td> 3</td>\n",
        "      <td> b</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2</th>\n",
        "      <td>-0.134696</td>\n",
        "      <td> 9</td>\n",
        "      <td> a</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>3</th>\n",
        "      <td>-1.227535</td>\n",
        "      <td> 4</td>\n",
        "      <td> c</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>4</th>\n",
        "      <td>-0.572367</td>\n",
        "      <td> 8</td>\n",
        "      <td> a</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>5</th>\n",
        "      <td> 0.330043</td>\n",
        "      <td> 7</td>\n",
        "      <td> a</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>6</th>\n",
        "      <td>-0.684184</td>\n",
        "      <td> 4</td>\n",
        "      <td> c</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>7</th>\n",
        "      <td>-1.097351</td>\n",
        "      <td> 9</td>\n",
        "      <td> c</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>8</th>\n",
        "      <td>-0.694465</td>\n",
        "      <td> 1</td>\n",
        "      <td> b</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>9</th>\n",
        "      <td>-1.376861</td>\n",
        "      <td> 5</td>\n",
        "      <td> b</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 64,
       "text": [
        "          a  b  c\n",
        "0  0.311531  2  a\n",
        "1  0.466764  3  b\n",
        "2 -0.134696  9  a\n",
        "3 -1.227535  4  c\n",
        "4 -0.572367  8  a\n",
        "5  0.330043  7  a\n",
        "6 -0.684184  4  c\n",
        "7 -1.097351  9  c\n",
        "8 -0.694465  1  b\n",
        "9 -1.376861  5  b"
       ]
      }
     ],
     "prompt_number": 64
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "df.to_hdf('tmp.h5', 'df', format='table')"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 65
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "pd.read_hdf('tmp.h5', 'df')"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "html": [
        "<div style=\"max-height:1000px;max-width:1500px;overflow:auto;\">\n",
        "<table border=\"1\" class=\"dataframe\">\n",
        "  <thead>\n",
        "    <tr style=\"text-align: right;\">\n",
        "      <th></th>\n",
        "      <th>a</th>\n",
        "      <th>b</th>\n",
        "      <th>c</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>0</th>\n",
        "      <td> 0.311531</td>\n",
        "      <td> 2</td>\n",
        "      <td> a</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>1</th>\n",
        "      <td> 0.466764</td>\n",
        "      <td> 3</td>\n",
        "      <td> b</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2</th>\n",
        "      <td>-0.134696</td>\n",
        "      <td> 9</td>\n",
        "      <td> a</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>3</th>\n",
        "      <td>-1.227535</td>\n",
        "      <td> 4</td>\n",
        "      <td> c</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>4</th>\n",
        "      <td>-0.572367</td>\n",
        "      <td> 8</td>\n",
        "      <td> a</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>5</th>\n",
        "      <td> 0.330043</td>\n",
        "      <td> 7</td>\n",
        "      <td> a</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>6</th>\n",
        "      <td>-0.684184</td>\n",
        "      <td> 4</td>\n",
        "      <td> c</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>7</th>\n",
        "      <td>-1.097351</td>\n",
        "      <td> 9</td>\n",
        "      <td> c</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>8</th>\n",
        "      <td>-0.694465</td>\n",
        "      <td> 1</td>\n",
        "      <td> b</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>9</th>\n",
        "      <td>-1.376861</td>\n",
        "      <td> 5</td>\n",
        "      <td> b</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 66,
       "text": [
        "          a  b  c\n",
        "0  0.311531  2  a\n",
        "1  0.466764  3  b\n",
        "2 -0.134696  9  a\n",
        "3 -1.227535  4  c\n",
        "4 -0.572367  8  a\n",
        "5  0.330043  7  a\n",
        "6 -0.684184  4  c\n",
        "7 -1.097351  9  c\n",
        "8 -0.694465  1  b\n",
        "9 -1.376861  5  b"
       ]
      }
     ],
     "prompt_number": 66
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "!ptdump tmp.h5"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "/ (RootGroup) ''\r\n",
        "/df (Group) ''\r\n",
        "/df/table (Table(10,)) ''\r\n"
       ]
      }
     ],
     "prompt_number": 68
    },
    {
     "cell_type": "heading",
     "level": 1,
     "metadata": {},
     "source": [
      "Next Up:\n",
      "\n",
      "[Features!](Features.ipynb)"
     ]
    }
   ],
   "metadata": {}
  }
 ]
}