Learning Pandas within iPython Notebook

Pandas CSV

{
 "metadata": {
  "name": "CSV read with Pandas"
 },
 "nbformat": 3,
 "nbformat_minor": 0,
 "worksheets": [
  {
   "cells": [
    {
     "cell_type": "code",
     "collapsed": false,
     "input": "import urllib2, zipfile\nurl = 'http://ipython.rossant.net/'\nfilename = 'cities.zip'\ndownloaded = urllib2.urlopen(url + filename)\nfolder = 'data'\n!mkdir $folder\nwith open(filename, \"wb\") as f:\n    f.write(downloaded.read())\nwith zipfile.ZipFile(filename) as zip:\n    zip.extractall(folder)",
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": "mkdir: data: File exists\r\n"
      }
     ],
     "prompt_number": 1
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": "import pandas as pd\nfilename = 'data/worldcitiespop.txt'\ndata = pd.read_csv(filename)",
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 2
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": "type(data)",
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "pyout",
       "prompt_number": 3,
       "text": "pandas.core.frame.DataFrame"
      }
     ],
     "prompt_number": 3
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": "data.shape, data.keys()",
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "pyout",
       "prompt_number": 9,
       "text": "((3173958, 7),\n Index([Country, City, AccentCity, Region, Population, Latitude, Longitude], dtype=object))"
      }
     ],
     "prompt_number": 9
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": "data.head(5)",
     "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>Country</th>\n      <th>City</th>\n      <th>AccentCity</th>\n      <th>Region</th>\n      <th>Population</th>\n      <th>Latitude</th>\n      <th>Longitude</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td> ad</td>\n      <td>      aixas</td>\n      <td>      Aix\ufffds</td>\n      <td> 6</td>\n      <td>NaN</td>\n      <td> 42.483333</td>\n      <td> 1.466667</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td> ad</td>\n      <td> aixirivali</td>\n      <td> Aixirivali</td>\n      <td> 6</td>\n      <td>NaN</td>\n      <td> 42.466667</td>\n      <td> 1.500000</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td> ad</td>\n      <td> aixirivall</td>\n      <td> Aixirivall</td>\n      <td> 6</td>\n      <td>NaN</td>\n      <td> 42.466667</td>\n      <td> 1.500000</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td> ad</td>\n      <td>  aixirvall</td>\n      <td>  Aixirvall</td>\n      <td> 6</td>\n      <td>NaN</td>\n      <td> 42.466667</td>\n      <td> 1.500000</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td> ad</td>\n      <td>   aixovall</td>\n      <td>   Aixovall</td>\n      <td> 6</td>\n      <td>NaN</td>\n      <td> 42.466667</td>\n      <td> 1.483333</td>\n    </tr>\n  </tbody>\n</table>\n</div>",
       "output_type": "pyout",
       "prompt_number": 4,
       "text": "  Country        City  AccentCity Region  Population   Latitude  Longitude\n0      ad       aixas       Aix\ufffds      6         NaN  42.483333   1.466667\n1      ad  aixirivali  Aixirivali      6         NaN  42.466667   1.500000\n2      ad  aixirivall  Aixirivall      6         NaN  42.466667   1.500000\n3      ad   aixirvall   Aixirvall      6         NaN  42.466667   1.500000\n4      ad    aixovall    Aixovall      6         NaN  42.466667   1.483333"
      }
     ],
     "prompt_number": 4
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": "data[0:4]",
     "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>Country</th>\n      <th>City</th>\n      <th>AccentCity</th>\n      <th>Region</th>\n      <th>Population</th>\n      <th>Latitude</th>\n      <th>Longitude</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td> ad</td>\n      <td>      aixas</td>\n      <td>      Aix\ufffds</td>\n      <td> 6</td>\n      <td>NaN</td>\n      <td> 42.483333</td>\n      <td> 1.466667</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td> ad</td>\n      <td> aixirivali</td>\n      <td> Aixirivali</td>\n      <td> 6</td>\n      <td>NaN</td>\n      <td> 42.466667</td>\n      <td> 1.500000</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td> ad</td>\n      <td> aixirivall</td>\n      <td> Aixirivall</td>\n      <td> 6</td>\n      <td>NaN</td>\n      <td> 42.466667</td>\n      <td> 1.500000</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td> ad</td>\n      <td>  aixirvall</td>\n      <td>  Aixirvall</td>\n      <td> 6</td>\n      <td>NaN</td>\n      <td> 42.466667</td>\n      <td> 1.500000</td>\n    </tr>\n  </tbody>\n</table>\n</div>",
       "output_type": "pyout",
       "prompt_number": 5,
       "text": "  Country        City  AccentCity Region  Population   Latitude  Longitude\n0      ad       aixas       Aix\ufffds      6         NaN  42.483333   1.466667\n1      ad  aixirivali  Aixirivali      6         NaN  42.466667   1.500000\n2      ad  aixirivall  Aixirivall      6         NaN  42.466667   1.500000\n3      ad   aixirvall   Aixirvall      6         NaN  42.466667   1.500000"
      }
     ],
     "prompt_number": 5
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": "data.City[24599]",
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "pyout",
       "prompt_number": 9,
       "text": "'garm ab'"
      }
     ],
     "prompt_number": 9
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": "data[data.AccentCity=='Stockholm']",
     "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>Country</th>\n      <th>City</th>\n      <th>AccentCity</th>\n      <th>Region</th>\n      <th>Population</th>\n      <th>Latitude</th>\n      <th>Longitude</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>2617638</th>\n      <td> se</td>\n      <td> stockholm</td>\n      <td> Stockholm</td>\n      <td> 07</td>\n      <td>     NaN</td>\n      <td> 61.883056</td>\n      <td> 13.750000</td>\n    </tr>\n    <tr>\n      <th>2617639</th>\n      <td> se</td>\n      <td> stockholm</td>\n      <td> Stockholm</td>\n      <td> 26</td>\n      <td> 1253309</td>\n      <td> 59.333333</td>\n      <td> 18.050000</td>\n    </tr>\n    <tr>\n      <th>2617640</th>\n      <td> se</td>\n      <td> stockholm</td>\n      <td> Stockholm</td>\n      <td> 27</td>\n      <td>     NaN</td>\n      <td> 56.133333</td>\n      <td> 13.416667</td>\n    </tr>\n    <tr>\n      <th>2957359</th>\n      <td> us</td>\n      <td> stockholm</td>\n      <td> Stockholm</td>\n      <td> ME</td>\n      <td>     NaN</td>\n      <td> 47.042222</td>\n      <td>-68.140000</td>\n    </tr>\n    <tr>\n      <th>2972262</th>\n      <td> us</td>\n      <td> stockholm</td>\n      <td> Stockholm</td>\n      <td> MN</td>\n      <td>     NaN</td>\n      <td> 45.036389</td>\n      <td>-94.220833</td>\n    </tr>\n    <tr>\n      <th>2985302</th>\n      <td> us</td>\n      <td> stockholm</td>\n      <td> Stockholm</td>\n      <td> NJ</td>\n      <td>     NaN</td>\n      <td> 41.089444</td>\n      <td>-74.517500</td>\n    </tr>\n    <tr>\n      <th>3020588</th>\n      <td> us</td>\n      <td> stockholm</td>\n      <td> Stockholm</td>\n      <td> SD</td>\n      <td>     NaN</td>\n      <td> 45.099722</td>\n      <td>-96.801667</td>\n    </tr>\n    <tr>\n      <th>3048843</th>\n      <td> us</td>\n      <td> stockholm</td>\n      <td> Stockholm</td>\n      <td> WI</td>\n      <td>     NaN</td>\n      <td> 44.483333</td>\n      <td>-92.261944</td>\n    </tr>\n  </tbody>\n</table>\n</div>",
       "output_type": "pyout",
       "prompt_number": 14,
       "text": "        Country       City AccentCity Region  Population   Latitude  Longitude\n2617638      se  stockholm  Stockholm     07         NaN  61.883056  13.750000\n2617639      se  stockholm  Stockholm     26     1253309  59.333333  18.050000\n2617640      se  stockholm  Stockholm     27         NaN  56.133333  13.416667\n2957359      us  stockholm  Stockholm     ME         NaN  47.042222 -68.140000\n2972262      us  stockholm  Stockholm     MN         NaN  45.036389 -94.220833\n2985302      us  stockholm  Stockholm     NJ         NaN  41.089444 -74.517500\n3020588      us  stockholm  Stockholm     SD         NaN  45.099722 -96.801667\n3048843      us  stockholm  Stockholm     WI         NaN  44.483333 -92.261944"
      }
     ],
     "prompt_number": 14
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": "sthlm = 2617639\ndata.ix[sthlm]",
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "pyout",
       "prompt_number": 15,
       "text": "Country              se\nCity          stockholm\nAccentCity    Stockholm\nRegion               26\nPopulation      1253309\nLatitude       59.33333\nLongitude         18.05\nName: 2617639, dtype: object"
      }
     ],
     "prompt_number": 15
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": "",
     "language": "python",
     "metadata": {},
     "outputs": []
    }
   ],
   "metadata": {}
  }
 ]
}