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

{
 "metadata": {
  "name": "",
  "signature": "sha256:b619f1fd1f2d4495d6a2fe9d048c09b7319b119d4e10a5b2348f0ac6f380a27c"
 },
 "nbformat": 3,
 "nbformat_minor": 0,
 "worksheets": [
  {
   "cells": [
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "# Pandas Cleaning\n",
      "* Clean\n",
      "* Transform\n",
      "* Merge\n",
      "* Reshape\n",
      "* Concatenate"
     ]
    },
    {
     "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": "markdown",
     "metadata": {},
     "source": [
      "Check for matching values in a specific column for replacement:"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "data_1 = {'state' : ['VA', 'VA', 'VA', 'MD', 'MD'],\n",
      "          'year' : [2012, 2013, 2014, 2014, 2015],\n",
      "          'population' : [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>population</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": [
        "   population 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[df_1['state'] == 'VA']"
     ],
     "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>population</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",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 3,
       "text": [
        "   population state  year\n",
        "0         5.0    VA  2012\n",
        "1         5.1    VA  2013\n",
        "2         5.2    VA  2014"
       ]
      }
     ],
     "prompt_number": 3
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "Replace all occurrences of a string with another string, in place (no copy):"
     ]
    },
    {
     "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>population</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": 4,
       "text": [
        "   population     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": 4
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "In a specified column, replace all occurrences of a string with another string, in place (no copy):"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "df_1.replace({'state' : { 'MD' : 'MARYLAND' }}, 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>population</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": 5,
       "text": [
        "   population     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": 5
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "Drop the 'population' column and return a copy of the DataFrame:"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "df_2 = df_1.drop('population', axis=1)\n",
      "df_2"
     ],
     "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>state</th>\n",
        "      <th>year</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>0</th>\n",
        "      <td> VIRGINIA</td>\n",
        "      <td> 2012</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>1</th>\n",
        "      <td> VIRGINIA</td>\n",
        "      <td> 2013</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2</th>\n",
        "      <td> VIRGINIA</td>\n",
        "      <td> 2014</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>3</th>\n",
        "      <td> MARYLAND</td>\n",
        "      <td> 2014</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>4</th>\n",
        "      <td> MARYLAND</td>\n",
        "      <td> 2015</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 6,
       "text": [
        "      state  year\n",
        "0  VIRGINIA  2012\n",
        "1  VIRGINIA  2013\n",
        "2  VIRGINIA  2014\n",
        "3  MARYLAND  2014\n",
        "4  MARYLAND  2015"
       ]
      }
     ],
     "prompt_number": 6
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "Concatenate two DataFrames:"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "data_2 = {'state' : ['NY', 'NY', 'NY', 'FL', 'FL'],\n",
      "          'year' : [2012, 2013, 2014, 2014, 2015],\n",
      "          'population' : [6.0, 6.1, 6.2, 3.0, 3.1]}\n",
      "df_3 = DataFrame(data_2)\n",
      "df_3"
     ],
     "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>population</th>\n",
        "      <th>state</th>\n",
        "      <th>year</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>0</th>\n",
        "      <td> 6.0</td>\n",
        "      <td> NY</td>\n",
        "      <td> 2012</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>1</th>\n",
        "      <td> 6.1</td>\n",
        "      <td> NY</td>\n",
        "      <td> 2013</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2</th>\n",
        "      <td> 6.2</td>\n",
        "      <td> NY</td>\n",
        "      <td> 2014</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>3</th>\n",
        "      <td> 3.0</td>\n",
        "      <td> FL</td>\n",
        "      <td> 2014</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>4</th>\n",
        "      <td> 3.1</td>\n",
        "      <td> FL</td>\n",
        "      <td> 2015</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 7,
       "text": [
        "   population state  year\n",
        "0         6.0    NY  2012\n",
        "1         6.1    NY  2013\n",
        "2         6.2    NY  2014\n",
        "3         3.0    FL  2014\n",
        "4         3.1    FL  2015"
       ]
      }
     ],
     "prompt_number": 7
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "df_4 = pd.concat([df_1, df_3])\n",
      "df_4"
     ],
     "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>population</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",
        "    <tr>\n",
        "      <th>0</th>\n",
        "      <td> 6.0</td>\n",
        "      <td>       NY</td>\n",
        "      <td> 2012</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>1</th>\n",
        "      <td> 6.1</td>\n",
        "      <td>       NY</td>\n",
        "      <td> 2013</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2</th>\n",
        "      <td> 6.2</td>\n",
        "      <td>       NY</td>\n",
        "      <td> 2014</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>3</th>\n",
        "      <td> 3.0</td>\n",
        "      <td>       FL</td>\n",
        "      <td> 2014</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>4</th>\n",
        "      <td> 3.1</td>\n",
        "      <td>       FL</td>\n",
        "      <td> 2015</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 8,
       "text": [
        "   population     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\n",
        "0         6.0        NY  2012\n",
        "1         6.1        NY  2013\n",
        "2         6.2        NY  2014\n",
        "3         3.0        FL  2014\n",
        "4         3.1        FL  2015"
       ]
      }
     ],
     "prompt_number": 8
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 8
    }
   ],
   "metadata": {}
  }
 ]
}