{
 "metadata": {
  "name": "",
  "signature": "sha256:69af2654f6b68061f8ee043a4413fbed27c3d5d890eaf654610db2faf95faab8"
 },
 "nbformat": 3,
 "nbformat_minor": 0,
 "worksheets": [
  {
   "cells": [
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "# Dropping Rows And Columns In pandas Dataframe\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": 1
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "### Create a 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",
        "<p>5 rows \u00d7 3 columns</p>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 4,
       "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\n",
        "\n",
        "[5 rows x 3 columns]"
       ]
      }
     ],
     "prompt_number": 4
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "### Drop an observation (row)"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "df.drop(['Cochice', 'Pima'])"
     ],
     "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>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",
        "<p>3 rows \u00d7 3 columns</p>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 5,
       "text": [
        "            name  reports  year\n",
        "Santa Cruz  Tina       31  2013\n",
        "Maricopa    Jake        2  2014\n",
        "Yuma         Amy        3  2014\n",
        "\n",
        "[3 rows x 3 columns]"
       ]
      }
     ],
     "prompt_number": 5
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "### Drop a variable (column)\n",
      "\n",
      "Note: axis=1 denotes that we are referring to a column, not a row"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "df.drop('reports', axis=1)"
     ],
     "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>year</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>Cochice</th>\n",
        "      <td> Jason</td>\n",
        "      <td> 2012</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>Pima</th>\n",
        "      <td> Molly</td>\n",
        "      <td> 2012</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>Santa Cruz</th>\n",
        "      <td>  Tina</td>\n",
        "      <td> 2013</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>Maricopa</th>\n",
        "      <td>  Jake</td>\n",
        "      <td> 2014</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>Yuma</th>\n",
        "      <td>   Amy</td>\n",
        "      <td> 2014</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "<p>5 rows \u00d7 2 columns</p>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 8,
       "text": [
        "             name  year\n",
        "Cochice     Jason  2012\n",
        "Pima        Molly  2012\n",
        "Santa Cruz   Tina  2013\n",
        "Maricopa     Jake  2014\n",
        "Yuma          Amy  2014\n",
        "\n",
        "[5 rows x 2 columns]"
       ]
      }
     ],
     "prompt_number": 8
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "### Drop a row if it contains a certain value (in this case, \"Tina\")\n",
      "\n",
      "Specifically: Create a new dataframe called df that includes all rows where the value of a cell in the name column does not equal \"Tina\""
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "df = df[df.name != 'Tina']\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>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",
        "<p>4 rows \u00d7 3 columns</p>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 10,
       "text": [
        "           name  reports  year\n",
        "Cochice   Jason        4  2012\n",
        "Pima      Molly       24  2012\n",
        "Maricopa   Jake        2  2014\n",
        "Yuma        Amy        3  2014\n",
        "\n",
        "[4 rows x 3 columns]"
       ]
      }
     ],
     "prompt_number": 10
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [],
     "language": "python",
     "metadata": {},
     "outputs": []
    }
   ],
   "metadata": {}
  }
 ]
}