{
 "metadata": {
  "name": "",
  "signature": "sha256:2a61c11fc4cfaa8c34ade4ea86130ce85b4a74c7f26da063290965df33b40f69"
 },
 "nbformat": 3,
 "nbformat_minor": 0,
 "worksheets": [
  {
   "cells": [
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "# Convert A Categorical Variable Into Dummy Variables\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": [
      "### import modules"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "import pandas as pd"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 14
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "### Create a dataframe"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "raw_data = {'first_name': ['Jason', 'Molly', 'Tina', 'Jake', 'Amy'], \n",
      "        'last_name': ['Miller', 'Jacobson', 'Ali', 'Milner', 'Cooze'], \n",
      "        'sex': ['male', 'female', 'male', 'female', 'female']}\n",
      "df = pd.DataFrame(raw_data, columns = ['first_name', 'last_name', 'sex'])\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>first_name</th>\n",
        "      <th>last_name</th>\n",
        "      <th>sex</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>0</th>\n",
        "      <td> Jason</td>\n",
        "      <td>   Miller</td>\n",
        "      <td>   male</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>1</th>\n",
        "      <td> Molly</td>\n",
        "      <td> Jacobson</td>\n",
        "      <td> female</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2</th>\n",
        "      <td>  Tina</td>\n",
        "      <td>      Ali</td>\n",
        "      <td>   male</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>3</th>\n",
        "      <td>  Jake</td>\n",
        "      <td>   Milner</td>\n",
        "      <td> female</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>4</th>\n",
        "      <td>   Amy</td>\n",
        "      <td>    Cooze</td>\n",
        "      <td> female</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "<p>5 rows \u00d7 3 columns</p>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 15,
       "text": [
        "  first_name last_name     sex\n",
        "0      Jason    Miller    male\n",
        "1      Molly  Jacobson  female\n",
        "2       Tina       Ali    male\n",
        "3       Jake    Milner  female\n",
        "4        Amy     Cooze  female\n",
        "\n",
        "[5 rows x 3 columns]"
       ]
      }
     ],
     "prompt_number": 15
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "### Create a set of dummy variables from the sex variable"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "df_sex = pd.get_dummies(df['sex'])"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 16
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "### Join the dummy variables to the main dataframe"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "df_new = pd.concat([df, df_sex], axis=1)\n",
      "df_new"
     ],
     "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>first_name</th>\n",
        "      <th>last_name</th>\n",
        "      <th>sex</th>\n",
        "      <th>female</th>\n",
        "      <th>male</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>0</th>\n",
        "      <td> Jason</td>\n",
        "      <td>   Miller</td>\n",
        "      <td>   male</td>\n",
        "      <td> 0</td>\n",
        "      <td> 1</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>1</th>\n",
        "      <td> Molly</td>\n",
        "      <td> Jacobson</td>\n",
        "      <td> female</td>\n",
        "      <td> 1</td>\n",
        "      <td> 0</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2</th>\n",
        "      <td>  Tina</td>\n",
        "      <td>      Ali</td>\n",
        "      <td>   male</td>\n",
        "      <td> 0</td>\n",
        "      <td> 1</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>3</th>\n",
        "      <td>  Jake</td>\n",
        "      <td>   Milner</td>\n",
        "      <td> female</td>\n",
        "      <td> 1</td>\n",
        "      <td> 0</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>4</th>\n",
        "      <td>   Amy</td>\n",
        "      <td>    Cooze</td>\n",
        "      <td> female</td>\n",
        "      <td> 1</td>\n",
        "      <td> 0</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "<p>5 rows \u00d7 5 columns</p>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 17,
       "text": [
        "  first_name last_name     sex  female  male\n",
        "0      Jason    Miller    male       0     1\n",
        "1      Molly  Jacobson  female       1     0\n",
        "2       Tina       Ali    male       0     1\n",
        "3       Jake    Milner  female       1     0\n",
        "4        Amy     Cooze  female       1     0\n",
        "\n",
        "[5 rows x 5 columns]"
       ]
      }
     ],
     "prompt_number": 17
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "### Alterative for joining the new columns"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "df_new = df.join(df_sex)\n",
      "df_new"
     ],
     "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>first_name</th>\n",
        "      <th>last_name</th>\n",
        "      <th>sex</th>\n",
        "      <th>female</th>\n",
        "      <th>male</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>0</th>\n",
        "      <td> Jason</td>\n",
        "      <td>   Miller</td>\n",
        "      <td>   male</td>\n",
        "      <td> 0</td>\n",
        "      <td> 1</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>1</th>\n",
        "      <td> Molly</td>\n",
        "      <td> Jacobson</td>\n",
        "      <td> female</td>\n",
        "      <td> 1</td>\n",
        "      <td> 0</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2</th>\n",
        "      <td>  Tina</td>\n",
        "      <td>      Ali</td>\n",
        "      <td>   male</td>\n",
        "      <td> 0</td>\n",
        "      <td> 1</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>3</th>\n",
        "      <td>  Jake</td>\n",
        "      <td>   Milner</td>\n",
        "      <td> female</td>\n",
        "      <td> 1</td>\n",
        "      <td> 0</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>4</th>\n",
        "      <td>   Amy</td>\n",
        "      <td>    Cooze</td>\n",
        "      <td> female</td>\n",
        "      <td> 1</td>\n",
        "      <td> 0</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "<p>5 rows \u00d7 5 columns</p>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 19,
       "text": [
        "  first_name last_name     sex  female  male\n",
        "0      Jason    Miller    male       0     1\n",
        "1      Molly  Jacobson  female       1     0\n",
        "2       Tina       Ali    male       0     1\n",
        "3       Jake    Milner  female       1     0\n",
        "4        Amy     Cooze  female       1     0\n",
        "\n",
        "[5 rows x 5 columns]"
       ]
      }
     ],
     "prompt_number": 19
    }
   ],
   "metadata": {}
  }
 ]
}