{
 "metadata": {
  "name": "",
  "signature": "sha256:709b15d88a623ba80d0ab8716c65ae256c10a527e942af98dec87f1131a36e3a"
 },
 "nbformat": 3,
 "nbformat_minor": 0,
 "worksheets": [
  {
   "cells": [
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "# Using List Comprehensions With Pandas\n",
      "\n",
      "- **Author:** [Chris Albon](http://www.chrisalbon.com/), [@ChrisAlbon](https://twitter.com/chrisalbon)\n",
      "- **Date:** -\n",
      "- **Repo:** [Python 3 code snippets for data science](https://github.com/chrisalbon/code_py)\n",
      "- **Note:**."
     ]
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "## Preliminaries"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "# Import modules\n",
      "import pandas as pd\n",
      "\n",
      "# Set ipython's max row display\n",
      "pd.set_option('display.max_row', 1000)\n",
      "\n",
      "# Set iPython's max column width to 50\n",
      "pd.set_option('display.max_columns', 50)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 1
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "## Create an example dataframe"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "data = {'name': ['Jason', 'Molly', 'Tina', 'Jake', 'Amy'], \n",
      "        'year': [2012, 2012, 2013, 2014, 2014], \n",
      "        'reports': [4, 24, 31, 2, 3]}\n",
      "df = pd.DataFrame(data, index = ['Cochice', 'Pima', 'Santa Cruz', 'Maricopa', 'Yuma'])\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>name</th>\n",
        "      <th>reports</th>\n",
        "      <th>year</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>Cochice</th>\n",
        "      <td> Jason</td>\n",
        "      <td>  4</td>\n",
        "      <td> 2012</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>Pima</th>\n",
        "      <td> Molly</td>\n",
        "      <td> 24</td>\n",
        "      <td> 2012</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>Santa Cruz</th>\n",
        "      <td>  Tina</td>\n",
        "      <td> 31</td>\n",
        "      <td> 2013</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>Maricopa</th>\n",
        "      <td>  Jake</td>\n",
        "      <td>  2</td>\n",
        "      <td> 2014</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>Yuma</th>\n",
        "      <td>   Amy</td>\n",
        "      <td>  3</td>\n",
        "      <td> 2014</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 3,
       "text": [
        "             name  reports  year\n",
        "Cochice     Jason        4  2012\n",
        "Pima        Molly       24  2012\n",
        "Santa Cruz   Tina       31  2013\n",
        "Maricopa     Jake        2  2014\n",
        "Yuma          Amy        3  2014"
       ]
      }
     ],
     "prompt_number": 3
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "## List Comprehensions"
     ]
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "### As a loop"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "# Create a variable\n",
      "next_year = []\n",
      "\n",
      "# For each row in df.years,\n",
      "for row in df['year']:\n",
      "    # Add 1 to the row and append it to next_year\n",
      "    next_year.append(row + 1)\n",
      "\n",
      "# Create df.next_year\n",
      "df['next_year'] = next_year\n",
      "\n",
      "# View the dataframe\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>name</th>\n",
        "      <th>reports</th>\n",
        "      <th>year</th>\n",
        "      <th>next_year</th>\n",
        "      <th>previous_year</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>Cochice</th>\n",
        "      <td> Jason</td>\n",
        "      <td>  4</td>\n",
        "      <td> 2012</td>\n",
        "      <td> 2013</td>\n",
        "      <td> 2011</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>Pima</th>\n",
        "      <td> Molly</td>\n",
        "      <td> 24</td>\n",
        "      <td> 2012</td>\n",
        "      <td> 2013</td>\n",
        "      <td> 2011</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>Santa Cruz</th>\n",
        "      <td>  Tina</td>\n",
        "      <td> 31</td>\n",
        "      <td> 2013</td>\n",
        "      <td> 2014</td>\n",
        "      <td> 2012</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>Maricopa</th>\n",
        "      <td>  Jake</td>\n",
        "      <td>  2</td>\n",
        "      <td> 2014</td>\n",
        "      <td> 2015</td>\n",
        "      <td> 2013</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>Yuma</th>\n",
        "      <td>   Amy</td>\n",
        "      <td>  3</td>\n",
        "      <td> 2014</td>\n",
        "      <td> 2015</td>\n",
        "      <td> 2013</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 14,
       "text": [
        "             name  reports  year  next_year  previous_year\n",
        "Cochice     Jason        4  2012       2013           2011\n",
        "Pima        Molly       24  2012       2013           2011\n",
        "Santa Cruz   Tina       31  2013       2014           2012\n",
        "Maricopa     Jake        2  2014       2015           2013\n",
        "Yuma          Amy        3  2014       2015           2013"
       ]
      }
     ],
     "prompt_number": 14
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "### As list comprehension"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "# Subtract 1 from row, for each row in df.year\n",
      "df['previous_year'] = [row-1 for row in df['year']]"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 11
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "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>name</th>\n",
        "      <th>reports</th>\n",
        "      <th>year</th>\n",
        "      <th>next_year</th>\n",
        "      <th>previous_year</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>Cochice</th>\n",
        "      <td> Jason</td>\n",
        "      <td>  4</td>\n",
        "      <td> 2012</td>\n",
        "      <td> 2013</td>\n",
        "      <td> 2011</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>Pima</th>\n",
        "      <td> Molly</td>\n",
        "      <td> 24</td>\n",
        "      <td> 2012</td>\n",
        "      <td> 2013</td>\n",
        "      <td> 2011</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>Santa Cruz</th>\n",
        "      <td>  Tina</td>\n",
        "      <td> 31</td>\n",
        "      <td> 2013</td>\n",
        "      <td> 2014</td>\n",
        "      <td> 2012</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>Maricopa</th>\n",
        "      <td>  Jake</td>\n",
        "      <td>  2</td>\n",
        "      <td> 2014</td>\n",
        "      <td> 2015</td>\n",
        "      <td> 2013</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>Yuma</th>\n",
        "      <td>   Amy</td>\n",
        "      <td>  3</td>\n",
        "      <td> 2014</td>\n",
        "      <td> 2015</td>\n",
        "      <td> 2013</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 13,
       "text": [
        "             name  reports  year  next_year  previous_year\n",
        "Cochice     Jason        4  2012       2013           2011\n",
        "Pima        Molly       24  2012       2013           2011\n",
        "Santa Cruz   Tina       31  2013       2014           2012\n",
        "Maricopa     Jake        2  2014       2015           2013\n",
        "Yuma          Amy        3  2014       2015           2013"
       ]
      }
     ],
     "prompt_number": 13
    }
   ],
   "metadata": {}
  }
 ]
}