data-science-ipython-notebooks/pandas/pandas_clean.ipynb

{
 "metadata": {
  "name": "",
  "signature": "sha256:3d55aefd3368aca223546c0d26816eb99aed51fe2f81f1f2f68d7bdbcc73651d"
 },
 "nbformat": 3,
 "nbformat_minor": 0,
 "worksheets": [
  {
   "cells": [
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "# Pandas Cleaning\n",
      "* Clean\n",
      "* Transform\n",
      "* Merge\n",
      "* Reshape"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "from pandas import Series, DataFrame\n",
      "import pandas as pd"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 1
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "data_1 = {'state' : ['VA', 'VA', 'VA', 'MD', 'MD'],\n",
      "          'year' : [2012, 2013, 2014, 2014, 2015],\n",
      "          'pop' : [5.0, 5.1, 5.2, 4.0, 4.1]}\n",
      "df_1 = DataFrame(data_1)\n",
      "df_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>pop</th>\n",
        "      <th>state</th>\n",
        "      <th>year</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>0</th>\n",
        "      <td> 5.0</td>\n",
        "      <td> VA</td>\n",
        "      <td> 2012</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>1</th>\n",
        "      <td> 5.1</td>\n",
        "      <td> VA</td>\n",
        "      <td> 2013</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2</th>\n",
        "      <td> 5.2</td>\n",
        "      <td> VA</td>\n",
        "      <td> 2014</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>3</th>\n",
        "      <td> 4.0</td>\n",
        "      <td> MD</td>\n",
        "      <td> 2014</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>4</th>\n",
        "      <td> 4.1</td>\n",
        "      <td> MD</td>\n",
        "      <td> 2015</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 2,
       "text": [
        "   pop state  year\n",
        "0  5.0    VA  2012\n",
        "1  5.1    VA  2013\n",
        "2  5.2    VA  2014\n",
        "3  4.0    MD  2014\n",
        "4  4.1    MD  2015"
       ]
      }
     ],
     "prompt_number": 2
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "df_1.replace('VA', 'VIRGINIA', inplace=True)\n",
      "df_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>pop</th>\n",
        "      <th>state</th>\n",
        "      <th>year</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>0</th>\n",
        "      <td> 5.0</td>\n",
        "      <td> VIRGINIA</td>\n",
        "      <td> 2012</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>1</th>\n",
        "      <td> 5.1</td>\n",
        "      <td> VIRGINIA</td>\n",
        "      <td> 2013</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2</th>\n",
        "      <td> 5.2</td>\n",
        "      <td> VIRGINIA</td>\n",
        "      <td> 2014</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>3</th>\n",
        "      <td> 4.0</td>\n",
        "      <td>       MD</td>\n",
        "      <td> 2014</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>4</th>\n",
        "      <td> 4.1</td>\n",
        "      <td>       MD</td>\n",
        "      <td> 2015</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 3,
       "text": [
        "   pop     state  year\n",
        "0  5.0  VIRGINIA  2012\n",
        "1  5.1  VIRGINIA  2013\n",
        "2  5.2  VIRGINIA  2014\n",
        "3  4.0        MD  2014\n",
        "4  4.1        MD  2015"
       ]
      }
     ],
     "prompt_number": 3
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "df_1.replace({'state' : { 'MD' : 'MARYLAND' }})"
     ],
     "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>pop</th>\n",
        "      <th>state</th>\n",
        "      <th>year</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>0</th>\n",
        "      <td> 5.0</td>\n",
        "      <td> VIRGINIA</td>\n",
        "      <td> 2012</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>1</th>\n",
        "      <td> 5.1</td>\n",
        "      <td> VIRGINIA</td>\n",
        "      <td> 2013</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2</th>\n",
        "      <td> 5.2</td>\n",
        "      <td> VIRGINIA</td>\n",
        "      <td> 2014</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>3</th>\n",
        "      <td> 4.0</td>\n",
        "      <td> MARYLAND</td>\n",
        "      <td> 2014</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>4</th>\n",
        "      <td> 4.1</td>\n",
        "      <td> MARYLAND</td>\n",
        "      <td> 2015</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 6,
       "text": [
        "   pop     state  year\n",
        "0  5.0  VIRGINIA  2012\n",
        "1  5.1  VIRGINIA  2013\n",
        "2  5.2  VIRGINIA  2014\n",
        "3  4.0  MARYLAND  2014\n",
        "4  4.1  MARYLAND  2015"
       ]
      }
     ],
     "prompt_number": 6
    }
   ],
   "metadata": {}
  }
 ]
}