3rd Exercise.ipynb

{
 "metadata": {
  "name": ""
 },
 "nbformat": 3,
 "nbformat_minor": 0,
 "worksheets": [
  {
   "cells": [
    {
     "cell_type": "heading",
     "level": 1,
     "metadata": {},
     "source": [
      "Data Analysis"
     ]
    },
    {
     "cell_type": "heading",
     "level": 2,
     "metadata": {},
     "source": [
      "3rd exercise"
     ]
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "Pandas and Numpy"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "#pandas\n",
      "import numpy as np\n",
      "import pandas as pd\n",
      "from pandas import Series, DataFrame"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 82
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "Geographic data"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "#geographic data\n",
      "from GeoBases import GeoBase\n",
      "geo_a = GeoBase(data='airports', verbose=False)\n",
      "#other things that might be useful\n",
      "geo_o = GeoBase(data='ori_por', verbose=False)\n",
      "#geo_t = GeoBase(data='stations', verbose=False)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 39
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "Get the airport codes for the airports in Malaga Madrid and Barcelona"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "print(geo_a.fuzzyFind('Madrid', 'name'))\n",
      "print(geo_a.fuzzyFind('Barcelona', 'name'))\n",
      "print(geo_a.fuzzyFind('Malaga', 'name'))"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "[(0.9, 'MAD'), (0.7692307692307693, 'IXM')]\n",
        "[(0.9, 'BCN'), (0.7777777777777778, 'QAK')]"
       ]
      },
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "\n",
        "[(0.9, 'AGP'), (0.7692307692307693, 'PLQ'), (0.7692307692307693, 'MAK')]"
       ]
      },
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "\n"
       ]
      }
     ],
     "prompt_number": 40
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "Verify airport names, and see which ones are the airports belonging to Madrid, Barcelona and Malaga"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "print(\"MAD: \", geo_o.get('MAD', 'name'))\n",
      "print(\"---------------\")\n",
      "print(\"IXM: \",geo_o.get('IXM', 'name')) #NO\n",
      "print(\"---------------\")\n",
      "print(\"BCN: \",geo_o.get('BCN', 'name'))\n",
      "print(\"---------------\")\n",
      "print(\"WAK: \",geo_o.get('WAK', 'name')) #NO\n",
      "print(\"---------------\")\n",
      "print(\"AGP: \",geo_o.get('AGP', 'name'))\n",
      "print(\"---------------\")\n",
      "print(\"PLQ: \",geo_o.get('PLQ', 'name')) #NO\n",
      "print(\"---------------\")\n",
      "print(\"MAK: \",geo_o.get('MAK', 'name')) #NO"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "('MAD: ', 'Madrid / Barajas')\n",
        "---------------\n",
        "('IXM: ', 'Madurai Airport')\n",
        "---------------\n",
        "('BCN: ', 'Barcelona\\xe2\\x80\\x93El Prat Airport')\n",
        "---------------\n",
        "('WAK: ', 'Ankazoabo')\n",
        "---------------\n",
        "('AGP: ', 'M\\xc3\\xa1laga Airport')\n",
        "---------------\n",
        "('PLQ: ', 'Palanga International Airport')\n",
        "---------------\n",
        "('MAK: ', 'Malakal Airport')\n"
       ]
      }
     ],
     "prompt_number": 41
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "Converter helper functions for transform data on load"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "from datetime import date\n",
      "\n",
      "def strip_field(data):\n",
      "    \"\"\"\n",
      "    strip white characters from input data if is string\n",
      "    \"\"\"\n",
      "    if type(data) == str:\n",
      "        return data.strip()\n",
      "    return data\n",
      "\n",
      "def to_date(data):\n",
      "    \"\"\"\n",
      "    converts input data in yyyy-mm-dd format to Pandas Timestamp object.\n",
      "    If it fails returns original object\n",
      "    \"\"\"\n",
      "    try:\n",
      "        return pd.Timestamp(data)\n",
      "    except:\n",
      "        return data\n",
      "    "
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 42
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "To make a memory usage estimation, first I do:\n",
      "\n",
      "    head searches.csv > headsearch.csv\n",
      "\n",
      "then I start checking memory usage and estimate for the whole dataset"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "%time srch_test = pd.read_table('headsearch.csv',sep='^', usecols=['Date','Destination'], converters={'Date':to_date, 'Destination': strip_field})"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "CPU times: user 1.71 ms, sys: 239 \u00b5s, total: 1.95 ms\n",
        "Wall time: 1.96 ms\n"
       ]
      }
     ],
     "prompt_number": 43
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "srch_test.dtypes"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 44,
       "text": [
        "Date           datetime64[ns]\n",
        "Destination            object\n",
        "dtype: object"
       ]
      }
     ],
     "prompt_number": 44
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "srch_test[:1].Date.nbytes"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 45,
       "text": [
        "8"
       ]
      }
     ],
     "prompt_number": 45
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "srch_test[:1].Destination.nbytes"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 46,
       "text": [
        "8"
       ]
      }
     ],
     "prompt_number": 46
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "srch_test.memory_usage(index=True)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 47,
       "text": [
        "Index          72\n",
        "Date           72\n",
        "Destination    72\n",
        "dtype: int64"
       ]
      }
     ],
     "prompt_number": 47
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "####Memory estimation\n",
      "\n",
      "There are ~ 20M registers (1st exercise) \n",
      "    \n",
      "    index: int64 (8 bytes), Date: 8bytes, Destination: 8bytes\n",
      "    20M* (8*3) bytes"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "20 * 8 * 3"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 48,
       "text": [
        "480"
       ]
      }
     ],
     "prompt_number": 48
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "Aproximately 480MB for the whole data structure in memory\n",
      "\n",
      "I should be able to load everything in RAM"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "#cleanup test\n",
      "del(srch_test)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 49
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "####Loading data"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "#anyway, as data will be processed and new data generated I want to be sure that there is a cap in memory usage\n",
      "#loading with iterator and filtering in place for the destinations"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 50
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "%time srch = pd.read_table('searches.csv',sep='^', usecols=['Date','Destination'], converters={'Date':to_date, 'Destination': strip_field})"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "CPU times: user 1min 1s, sys: 5.26 s, total: 1min 6s\n",
        "Wall time: 1min 20s\n"
       ]
      }
     ],
     "prompt_number": 51
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "####Filtering data\n",
      "\n",
      "Preselect only the airports that are needed, time for reference"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "%time s_ports = srch[srch.Destination.isin([\"MAD\", \"BCN\",\"AGP\"])]"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "CPU times: user 1.1 s, sys: 136 ms, total: 1.23 s\n",
        "Wall time: 1.23 s\n"
       ]
      }
     ],
     "prompt_number": 53
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "####Visual Check"
     ]
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "Memory check"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "dfs = {\"srch\": srch,\n",
      "       \"s_ports\": s_ports,\n",
      "      }\n",
      "\n",
      "for k,v in dfs.iteritems():\n",
      "    print (k+\" mem: %f MB\" % (v.memory_usage(index=True).sum()/1024000.0))\n"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "s_ports mem: 15.852703 MB\n",
        "srch mem: 477.895266 MB\n"
       ]
      }
     ],
     "prompt_number": 54
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "Content check"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "s_ports.head()"
     ],
     "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>Date</th>\n",
        "      <th>Destination</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>4  </th>\n",
        "      <td> 2013-01-01 00:00:00</td>\n",
        "      <td> MAD</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>93 </th>\n",
        "      <td> 2013-01-01 00:00:00</td>\n",
        "      <td> AGP</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>113</th>\n",
        "      <td> 2013-01-01 00:00:00</td>\n",
        "      <td> BCN</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>147</th>\n",
        "      <td> 2013-01-01 00:00:00</td>\n",
        "      <td> AGP</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>151</th>\n",
        "      <td> 2013-01-01 00:00:00</td>\n",
        "      <td> MAD</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 55,
       "text": [
        "                    Date Destination\n",
        "4    2013-01-01 00:00:00         MAD\n",
        "93   2013-01-01 00:00:00         AGP\n",
        "113  2013-01-01 00:00:00         BCN\n",
        "147  2013-01-01 00:00:00         AGP\n",
        "151  2013-01-01 00:00:00         MAD"
       ]
      }
     ],
     "prompt_number": 55
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "Adding a column to be able to sum (warning happens also with loc method)"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "%time s_ports['count'] = Series(1, index=s_ports.index)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "CPU times: user 1.89 s, sys: 747 \u00b5s, total: 1.89 s\n",
        "Wall time: 1.88 s\n"
       ]
      },
      {
       "output_type": "stream",
       "stream": "stderr",
       "text": [
        "-c:1: SettingWithCopyWarning: \n",
        "A value is trying to be set on a copy of a slice from a DataFrame.\n",
        "Try using .loc[row_indexer,col_indexer] = value instead\n",
        "\n",
        "See the the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy\n"
       ]
      }
     ],
     "prompt_number": 83
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "Grouping, counting and changing the arrivals groups to columns. also selecting only data from 2013"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "%time sgroup = s_ports.groupby(['Date','Destination']).count().unstack()['2013']"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "CPU times: user 159 ms, sys: 3.46 ms, total: 162 ms\n",
        "Wall time: 162 ms\n"
       ]
      }
     ],
     "prompt_number": 105
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "sgroup.head()"
     ],
     "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>\n",
        "      <th></th>\n",
        "      <th colspan=\"3\" halign=\"left\">count</th>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>Destination</th>\n",
        "      <th>AGP</th>\n",
        "      <th>BCN</th>\n",
        "      <th>MAD</th>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>Date</th>\n",
        "      <th></th>\n",
        "      <th></th>\n",
        "      <th></th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>2013-01-01</th>\n",
        "      <td> 399</td>\n",
        "      <td> 1482</td>\n",
        "      <td> 660</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2013-01-02</th>\n",
        "      <td> 228</td>\n",
        "      <td>  513</td>\n",
        "      <td> 627</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2013-01-03</th>\n",
        "      <td> 285</td>\n",
        "      <td>  741</td>\n",
        "      <td> 285</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2013-01-04</th>\n",
        "      <td> 285</td>\n",
        "      <td> 1026</td>\n",
        "      <td> 798</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2013-01-05</th>\n",
        "      <td> 228</td>\n",
        "      <td>  741</td>\n",
        "      <td> 912</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 87,
       "text": [
        "            count           \n",
        "Destination   AGP   BCN  MAD\n",
        "Date                        \n",
        "2013-01-01    399  1482  660\n",
        "2013-01-02    228   513  627\n",
        "2013-01-03    285   741  285\n",
        "2013-01-04    285  1026  798\n",
        "2013-01-05    228   741  912"
       ]
      }
     ],
     "prompt_number": 87
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "sgroup.describe()"
     ],
     "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>\n",
        "      <th></th>\n",
        "      <th colspan=\"3\" halign=\"left\">count</th>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th></th>\n",
        "      <th>AGP</th>\n",
        "      <th>BCN</th>\n",
        "      <th>MAD</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>count</th>\n",
        "      <td> 357.000000</td>\n",
        "      <td>  359.000000</td>\n",
        "      <td>  359.000000</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>mean</th>\n",
        "      <td> 272.204482</td>\n",
        "      <td>  863.682451</td>\n",
        "      <td>  749.701950</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>std</th>\n",
        "      <td> 134.856146</td>\n",
        "      <td>  264.651514</td>\n",
        "      <td>  224.964722</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>min</th>\n",
        "      <td>  56.000000</td>\n",
        "      <td>  228.000000</td>\n",
        "      <td>  168.000000</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>25%</th>\n",
        "      <td> 171.000000</td>\n",
        "      <td>  684.000000</td>\n",
        "      <td>  570.000000</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>50%</th>\n",
        "      <td> 280.000000</td>\n",
        "      <td>  855.000000</td>\n",
        "      <td>  741.000000</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>75%</th>\n",
        "      <td> 342.000000</td>\n",
        "      <td> 1026.000000</td>\n",
        "      <td>  855.000000</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>max</th>\n",
        "      <td> 741.000000</td>\n",
        "      <td> 1539.000000</td>\n",
        "      <td> 1425.000000</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 88,
       "text": [
        "            count                          \n",
        "              AGP          BCN          MAD\n",
        "count  357.000000   359.000000   359.000000\n",
        "mean   272.204482   863.682451   749.701950\n",
        "std    134.856146   264.651514   224.964722\n",
        "min     56.000000   228.000000   168.000000\n",
        "25%    171.000000   684.000000   570.000000\n",
        "50%    280.000000   855.000000   741.000000\n",
        "75%    342.000000  1026.000000   855.000000\n",
        "max    741.000000  1539.000000  1425.000000"
       ]
      }
     ],
     "prompt_number": 88
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "Plot containing all the daily data from 2013"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "#dropping values that will not be able to be printed\n",
      "%time sgroup.dropna(inplace=True)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "CPU times: user 0 ns, sys: 0 ns, total: 0 ns\n",
        "Wall time: 1.15 ms\n"
       ]
      }
     ],
     "prompt_number": 102
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "sgroup.plot()"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 91,
       "text": [
        "<matplotlib.axes.AxesSubplot at 0x7f9f1e76ed50>"
       ]
      },
      {
       "metadata": {},
       "output_type": "display_data",
       "png": "iVBORw0KGgoAAAANSUhEUgAAAYUAAAEMCAYAAAArnKpYAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n",
       "text": [
        "<matplotlib.figure.Figure at 0x7f9f1e6248d0>"
       ]
      }
     ],
     "prompt_number": 91
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "It is not really clear, so I'll be grouping by month"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "#grouped time period by month summing the results for each\n",
      "%time gpdt = sgroup.resample('M', how='sum', kind='period')"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "CPU times: user 3.44 ms, sys: 0 ns, total: 3.44 ms\n",
        "Wall time: 2.89 ms\n"
       ]
      }
     ],
     "prompt_number": 103
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "gpdt"
     ],
     "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>\n",
        "      <th></th>\n",
        "      <th colspan=\"3\" halign=\"left\">count</th>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>Destination</th>\n",
        "      <th>AGP</th>\n",
        "      <th>BCN</th>\n",
        "      <th>MAD</th>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>Date</th>\n",
        "      <th></th>\n",
        "      <th></th>\n",
        "      <th></th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>2013-01</th>\n",
        "      <td>  9633</td>\n",
        "      <td> 29469</td>\n",
        "      <td> 24258</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2013-02</th>\n",
        "      <td>  8379</td>\n",
        "      <td> 28329</td>\n",
        "      <td> 22800</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2013-03</th>\n",
        "      <td> 10659</td>\n",
        "      <td> 30552</td>\n",
        "      <td> 24681</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2013-04</th>\n",
        "      <td>  8265</td>\n",
        "      <td> 31236</td>\n",
        "      <td> 25251</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2013-05</th>\n",
        "      <td> 10830</td>\n",
        "      <td> 28728</td>\n",
        "      <td> 26334</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2013-06</th>\n",
        "      <td>  7923</td>\n",
        "      <td> 26505</td>\n",
        "      <td> 22800</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2013-07</th>\n",
        "      <td>  8892</td>\n",
        "      <td> 29241</td>\n",
        "      <td> 22971</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2013-08</th>\n",
        "      <td>  7866</td>\n",
        "      <td> 27075</td>\n",
        "      <td> 21831</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2013-09</th>\n",
        "      <td>  8151</td>\n",
        "      <td> 23427</td>\n",
        "      <td> 21147</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2013-10</th>\n",
        "      <td>  6499</td>\n",
        "      <td> 20276</td>\n",
        "      <td> 22294</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2013-11</th>\n",
        "      <td>  6384</td>\n",
        "      <td> 19824</td>\n",
        "      <td> 20272</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2013-12</th>\n",
        "      <td>  3696</td>\n",
        "      <td> 14392</td>\n",
        "      <td> 13776</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 93,
       "text": [
        "             count              \n",
        "Destination    AGP    BCN    MAD\n",
        "Date                            \n",
        "2013-01       9633  29469  24258\n",
        "2013-02       8379  28329  22800\n",
        "2013-03      10659  30552  24681\n",
        "2013-04       8265  31236  25251\n",
        "2013-05      10830  28728  26334\n",
        "2013-06       7923  26505  22800\n",
        "2013-07       8892  29241  22971\n",
        "2013-08       7866  27075  21831\n",
        "2013-09       8151  23427  21147\n",
        "2013-10       6499  20276  22294\n",
        "2013-11       6384  19824  20272\n",
        "2013-12       3696  14392  13776"
       ]
      }
     ],
     "prompt_number": 93
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "#plotting\n",
      "#reset index because there is a problem when plotting with the period index ... (could't yet found why)\n",
      "ax = gpdt.reset_index()['count'].plot()\n",
      "\n",
      "#Setting labels - capturing the results in vars so it doesn't pollute the output\n",
      "yl = ax.set_ylabel(\"Arrivals\")\n",
      "xl = ax.set_xlabel(\"Date\")\n",
      "xticks = ax.set_xticks(range(gpdt.index.size))\n",
      "xlabs = ax.set_xticklabels(gpdt.index, rotation=50)\n"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "display_data",
       "png": "iVBORw0KGgoAAAANSUhEUgAAAZkAAAElCAYAAAA2rZ/AAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nhmGEwU2GYRiGEQY3GYZhGEYY/wtFUgsxP27JiQAAAABJRU5ErkJggg==\n",
       "text": [
        "<matplotlib.figure.Figure at 0x7f9f1e4b7b50>"
       ]
      }
     ],
     "prompt_number": 104
    },
    {
     "cell_type": "heading",
     "level": 3,
     "metadata": {},
     "source": [
      "Pure Python"
     ]
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "cleanup everything (memory)"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "%reset\n",
      "import gc\n",
      "gc.collect()"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "name": "stdout",
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "Once deleted, variables cannot be recovered. Proceed (y/[n])? y\n"
       ]
      },
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 36,
       "text": [
        "0"
       ]
      }
     ],
     "prompt_number": 36
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "import datetime"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 6
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "get header, headsearch.csv is the result of:\n",
      "\n",
      "    head searches.csv > headsearch.csv"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "headers = None\n",
      "with open('headsearch.csv', 'r') as f:\n",
      "    for l in f:\n",
      "        fields = [i.strip() for i in l.split('^')]\n",
      "        if headers is None:\n",
      "            headers = fields\n",
      "            break\n",
      "\n",
      "#get IATA code index\n",
      "dest_idx = headers.index('Destination')\n",
      "#get timestamp index\n",
      "date_idx = headers.index('Date')\n"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 7
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "print (\"idx destination = %d, idx date = %d\" % (dest_idx,date_idx))"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "idx destination = 6, idx date = 0\n"
       ]
      }
     ],
     "prompt_number": 8
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "visual check"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "!head -n 2 headsearch.csv"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "Date^Time^TxnCode^OfficeID^Country^Origin^Destination^RoundTrip^NbSegments^Seg1Departure^Seg1Arrival^Seg1Date^Seg1Carrier^Seg1BookingCode^Seg2Departure^Seg2Arrival^Seg2Date^Seg2Carrier^Seg2BookingCode^Seg3Departure^Seg3Arrival^Seg3Date^Seg3Carrier^Seg3BookingCode^Seg4Departure^Seg4Arrival^Seg4Date^Seg4Carrier^Seg4BookingCode^Seg5Departure^Seg5Arrival^Seg5Date^Seg5Carrier^Seg5BookingCode^Seg6Departure^Seg6Arrival^Seg6Date^Seg6Carrier^Seg6BookingCode^From^IsPublishedForNeg^IsFromInternet^IsFromVista^TerminalID^InternetOffice\r\n",
        "2013-01-01^20:25:57^MPT^624d8c3ac0b3a7ca03e3c167e0f48327^DE^TXL^AUH^1^2^TXL^AUH^2013-01-26^D2^^AUH^TXL^2013-02-02^D2^^^^^^^^^^^^^^^^^^^^^^1ASIWS^0^0^0^d41d8cd98f00b204e9800998ecf8427e^FRA\r\n"
       ]
      }
     ],
     "prompt_number": 9
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "Ports and dates where we want to measure arrivals"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "PORTS = [\"MAD\", \"BCN\",\"AGP\"]\n",
      "YEARS = [2013]"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 10
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "#define function that makes the processing\n",
      "def group_by_port_and_month(fname):\n",
      "    \"\"\"\n",
      "    Opens the file, parses it and makes the sum of passengers by month in each arrival port\n",
      "    fname: name of the file containing the searches data\n",
      "    \"\"\"\n",
      "    arr_dict = {}\n",
      "    with open(fname, 'r') as f:\n",
      "        for l in f:\n",
      "            fields = [i.strip() for i in l.split('^')]\n",
      "            #be careful with empty fields \n",
      "            try:\n",
      "                #get destination IATA code\n",
      "                dst = fields[dest_idx]\n",
      "                #avoid innecessary processing\n",
      "                if dst in PORTS:\n",
      "                    #get timestamp\n",
      "                    ts = datetime.datetime.strptime(fields[date_idx], \"%Y-%m-%d\")\n",
      "                    #check is in YEARS\n",
      "                    if ts.year in YEARS:\n",
      "                        #sum\n",
      "                        if dst not in arr_dict:\n",
      "                            arr_dict[dst] = [0 for i in range(12)]\n",
      "                        #count\n",
      "                        arr_dict[dst][ts.month -1] +=1\n",
      "            except Exception as e:\n",
      "                print (\"ERROR: %s | Reading: %s \" %(e,l))\n",
      "                pass\n",
      "    return arr_dict\n"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 11
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "make the dictionary that contains the sums"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "%time counts = group_by_port_and_month('searches.csv')"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "ERROR: list index out of range | Reading: 2013-01-01,10:15:33,MPT,b0af35b31588dc4ab06d5cf2986e8e02,MD,ATH,MIL,0,1,ATH,MIL,2013-01-04,,,,,,,,,,,,,,,,,,,,,,,,,,,,1ASIWS,0,0,0,d41d8cd98f00b204e9800998ecf8427e,KIV\n",
        " \n",
        "ERROR: list index out of range | Reading: 2013-01-01,10:15:33,MPT,b0af35b31588dc4ab06d5cf2986e8e02,MD,ATH,MIL,0,1,ATH,MIL,2013-01-04,,,,,,,,,,,,,,,,,,,,,,,,,,,,1ASIWS,0,0,0,d41d8cd98f00b204e9800998ecf8427e,KIV\n",
        " "
       ]
      },
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "\n",
        "ERROR: list index out of range | Reading: 2013-01-01,10:15:33,MPT,b0af35b31588dc4ab06d5cf2986e8e02,MD,ATH,MIL,0,1,ATH,MIL,2013-01-04,,,,,,,,,,,,,,,,,,,,,,,,,,,,1ASIWS,0,0,0,d41d8cd98f00b204e9800998ecf8427e,KIV\n",
        " \n",
        "ERROR: list index out of range | Reading: 2013-01-01,10:15:33,MPT,b0af35b31588dc4ab06d5cf2986e8e02,MD,ATH,MIL,0,1,ATH,MIL,2013-01-04,,,,,,,,,,,,,,,,,,,,,,,,,,,,1ASIWS,0,0,0,d41d8cd98f00b204e9800998ecf8427e,KIV\n",
        " "
       ]
      },
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "\n",
        "ERROR: list index out of range | Reading: 2013-01-01,10:15:33,MPT,b0af35b31588dc4ab06d5cf2986e8e02,MD,ATH,MIL,0,1,ATH,MIL,2013-01-04,,,,,,,,,,,,,,,,,,,,,,,,,,,,1ASIWS,0,0,0,d41d8cd98f00b204e9800998ecf8427e,KIV\n",
        " "
       ]
      },
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "\n",
        "ERROR: list index out of range | Reading: 2013-01-01,10:15:33,MPT,b0af35b31588dc4ab06d5cf2986e8e02,MD,ATH,MIL,0,1,ATH,MIL,2013-01-04,,,,,,,,,,,,,,,,,,,,,,,,,,,,1ASIWS,0,0,0,d41d8cd98f00b204e9800998ecf8427e,KIV\n",
        " \n",
        "ERROR: list index out of range | Reading: 2013-01-01,10:15:33,MPT,b0af35b31588dc4ab06d5cf2986e8e02,MD,ATH,MIL,0,1,ATH,MIL,2013-01-04,,,,,,,,,,,,,,,,,,,,,,,,,,,,1ASIWS,0,0,0,d41d8cd98f00b204e9800998ecf8427e,KIV\n",
        " "
       ]
      },
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "\n",
        "ERROR: list index out of range | Reading: 2013-01-01,10:15:33,MPT,b0af35b31588dc4ab06d5cf2986e8e02,MD,ATH,MIL,0,1,ATH,MIL,2013-01-04,,,,,,,,,,,,,,,,,,,,,,,,,,,,1ASIWS,0,0,0,d41d8cd98f00b204e9800998ecf8427e,KIV\n",
        " "
       ]
      },
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "\n",
        "ERROR: list index out of range | Reading: 2013-01-01,10:15:33,MPT,b0af35b31588dc4ab06d5cf2986e8e02,MD,ATH,MIL,0,1,ATH,MIL,2013-01-04,,,,,,,,,,,,,,,,,,,,,,,,,,,,1ASIWS,0,0,0,d41d8cd98f00b204e9800998ecf8427e,KIV\n",
        " \n",
        "ERROR: list index out of range | Reading: 2013-01-01,10:15:33,MPT,b0af35b31588dc4ab06d5cf2986e8e02,MD,ATH,MIL,0,1,ATH,MIL,2013-01-04,,,,,,,,,,,,,,,,,,,,,,,,,,,,1ASIWS,0,0,0,d41d8cd98f00b204e9800998ecf8427e,KIV\n",
        " "
       ]
      },
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "\n",
        "ERROR: list index out of range | Reading: 2013-01-01,10:15:33,MPT,b0af35b31588dc4ab06d5cf2986e8e02,MD,ATH,MIL,0,1,ATH,MIL,2013-01-04,,,,,,,,,,,,,,,,,,,,,,,,,,,,1ASIWS,0,0,0,d41d8cd98f00b204e9800998ecf8427e,KIV\n",
        " "
       ]
      },
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "\n",
        "ERROR: list index out of range | Reading: 2013-01-01,10:15:33,MPT,b0af35b31588dc4ab06d5cf2986e8e02,MD,ATH,MIL,0,1,ATH,MIL,2013-01-04,,,,,,,,,,,,,,,,,,,,,,,,,,,,1ASIWS,0,0,0,d41d8cd98f00b204e9800998ecf8427e,KIV\n",
        " \n",
        "ERROR: list index out of range | Reading: 2013-01-01,10:15:33,MPT,b0af35b31588dc4ab06d5cf2986e8e02,MD,ATH,MIL,0,1,ATH,MIL,2013-01-04,,,,,,,,,,,,,,,,,,,,,,,,,,,,1ASIWS,0,0,0,d41d8cd98f00b204e9800998ecf8427e,KIV\n",
        " "
       ]
      },
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "\n",
        "ERROR: list index out of range | Reading: 2013-01-01,10:15:33,MPT,b0af35b31588dc4ab06d5cf2986e8e02,MD,ATH,MIL,0,1,ATH,MIL,2013-01-04,,,,,,,,,,,,,,,,,,,,,,,,,,,,1ASIWS,0,0,0,d41d8cd98f00b204e9800998ecf8427e,KIV\n",
        " "
       ]
      },
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "\n",
        "ERROR: list index out of range | Reading: 2013-01-01,10:15:33,MPT,b0af35b31588dc4ab06d5cf2986e8e02,MD,ATH,MIL,0,1,ATH,MIL,2013-01-04,,,,,,,,,,,,,,,,,,,,,,,,,,,,1ASIWS,0,0,0,d41d8cd98f00b204e9800998ecf8427e,KIV\n",
        " \n",
        "ERROR: list index out of range | Reading: 2013-01-01,10:15:33,MPT,b0af35b31588dc4ab06d5cf2986e8e02,MD,ATH,MIL,0,1,ATH,MIL,2013-01-04,,,,,,,,,,,,,,,,,,,,,,,,,,,,1ASIWS,0,0,0,d41d8cd98f00b204e9800998ecf8427e,KIV\n",
        " "
       ]
      },
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "\n",
        "ERROR: list index out of range | Reading: 2013-01-01,10:15:33,MPT,b0af35b31588dc4ab06d5cf2986e8e02,MD,ATH,MIL,0,1,ATH,MIL,2013-01-04,,,,,,,,,,,,,,,,,,,,,,,,,,,,1ASIWS,0,0,0,d41d8cd98f00b204e9800998ecf8427e,KIV\n",
        " "
       ]
      },
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "\n",
        "ERROR: list index out of range | Reading: 2013-01-01,10:15:33,MPT,b0af35b31588dc4ab06d5cf2986e8e02,MD,ATH,MIL,0,1,ATH,MIL,2013-01-04,,,,,,,,,,,,,,,,,,,,,,,,,,,,1ASIWS,0,0,0,d41d8cd98f00b204e9800998ecf8427e,KIV\n",
        " \n",
        "ERROR: list index out of range | Reading: 2013-01-01,10:15:33,MPT,b0af35b31588dc4ab06d5cf2986e8e02,MD,ATH,MIL,0,1,ATH,MIL,2013-01-04,,,,,,,,,,,,,,,,,,,,,,,,,,,,1ASIWS,0,0,0,d41d8cd98f00b204e9800998ecf8427e,KIV\n",
        " "
       ]
      },
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "\n",
        "ERROR: list index out of range | Reading: 2013-01-01,10:15:33,MPT,b0af35b31588dc4ab06d5cf2986e8e02,MD,ATH,MIL,0,1,ATH,MIL,2013-01-04,,,,,,,,,,,,,,,,,,,,,,,,,,,,1ASIWS,0,0,0,d41d8cd98f00b204e9800998ecf8427e,KIV\n",
        " "
       ]
      },
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "\n",
        "ERROR: list index out of range | Reading: 2013-01-01,10:15:33,MPT,b0af35b31588dc4ab06d5cf2986e8e02,MD,ATH,MIL,0,1,ATH,MIL,2013-01-04,,,,,,,,,,,,,,,,,,,,,,,,,,,,1ASIWS,0,0,0,d41d8cd98f00b204e9800998ecf8427e,KIV\n",
        " \n",
        "ERROR: list index out of range | Reading: 2013-01-01,10:15:33,MPT,b0af35b31588dc4ab06d5cf2986e8e02,MD,ATH,MIL,0,1,ATH,MIL,2013-01-04,,,,,,,,,,,,,,,,,,,,,,,,,,,,1ASIWS,0,0,0,d41d8cd98f00b204e9800998ecf8427e,KIV\n",
        " "
       ]
      },
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "\n",
        "ERROR: list index out of range | Reading: 2013-01-01,10:15:33,MPT,b0af35b31588dc4ab06d5cf2986e8e02,MD,ATH,MIL,0,1,ATH,MIL,2013-01-04,,,,,,,,,,,,,,,,,,,,,,,,,,,,1ASIWS,0,0,0,d41d8cd98f00b204e9800998ecf8427e,KIV\n",
        " "
       ]
      },
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "\n",
        "ERROR: list index out of range | Reading: 2013-01-01,10:15:33,MPT,b0af35b31588dc4ab06d5cf2986e8e02,MD,ATH,MIL,0,1,ATH,MIL,2013-01-04,,,,,,,,,,,,,,,,,,,,,,,,,,,,1ASIWS,0,0,0,d41d8cd98f00b204e9800998ecf8427e,KIV\n",
        " \n",
        "ERROR: list index out of range | Reading: 2013-01-01,10:15:33,MPT,b0af35b31588dc4ab06d5cf2986e8e02,MD,ATH,MIL,0,1,ATH,MIL,2013-01-04,,,,,,,,,,,,,,,,,,,,,,,,,,,,1ASIWS,0,0,0,d41d8cd98f00b204e9800998ecf8427e,KIV\n",
        " "
       ]
      },
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "\n",
        "ERROR: list index out of range | Reading: 2013-01-01,10:15:33,MPT,b0af35b31588dc4ab06d5cf2986e8e02,MD,ATH,MIL,0,1,ATH,MIL,2013-01-04,,,,,,,,,,,,,,,,,,,,,,,,,,,,1ASIWS,0,0,0,d41d8cd98f00b204e9800998ecf8427e,KIV\n",
        " "
       ]
      },
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "\n",
        "ERROR: list index out of range | Reading: 2013-01-01,10:15:33,MPT,b0af35b31588dc4ab06d5cf2986e8e02,MD,ATH,MIL,0,1,ATH,MIL,2013-01-04,,,,,,,,,,,,,,,,,,,,,,,,,,,,1ASIWS,0,0,0,d41d8cd98f00b204e9800998ecf8427e,KIV\n",
        " \n",
        "ERROR: list index out of range | Reading: 2013-01-01,10:15:33,MPT,b0af35b31588dc4ab06d5cf2986e8e02,MD,ATH,MIL,0,1,ATH,MIL,2013-01-04,,,,,,,,,,,,,,,,,,,,,,,,,,,,1ASIWS,0,0,0,d41d8cd98f00b204e9800998ecf8427e,KIV\n",
        " "
       ]
      },
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "\n",
        "ERROR: list index out of range | Reading: 2013-01-01,10:15:33,MPT,b0af35b31588dc4ab06d5cf2986e8e02,MD,ATH,MIL,0,1,ATH,MIL,2013-01-04,,,,,,,,,,,,,,,,,,,,,,,,,,,,1ASIWS,0,0,0,d41d8cd98f00b204e9800998ecf8427e,KIV\n",
        " "
       ]
      },
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "\n",
        "ERROR: list index out of range | Reading: 2013-01-01,10:15:33,MPT,b0af35b31588dc4ab06d5cf2986e8e02,MD,ATH,MIL,0,1,ATH,MIL,2013-01-04,,,,,,,,,,,,,,,,,,,,,,,,,,,,1ASIWS,0,0,0,d41d8cd98f00b204e9800998ecf8427e,KIV\n",
        " \n",
        "ERROR: list index out of range | Reading: 2013-01-01,10:15:33,MPT,b0af35b31588dc4ab06d5cf2986e8e02,MD,ATH,MIL,0,1,ATH,MIL,2013-01-04,,,,,,,,,,,,,,,,,,,,,,,,,,,,1ASIWS,0,0,0,d41d8cd98f00b204e9800998ecf8427e,KIV\n",
        " "
       ]
      },
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "\n",
        "ERROR: list index out of range | Reading: 2013-01-01,10:15:33,MPT,b0af35b31588dc4ab06d5cf2986e8e02,MD,ATH,MIL,0,1,ATH,MIL,2013-01-04,,,,,,,,,,,,,,,,,,,,,,,,,,,,1ASIWS,0,0,0,d41d8cd98f00b204e9800998ecf8427e,KIV\n",
        " "
       ]
      },
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "\n",
        "ERROR: list index out of range | Reading: 2013-01-01,10:15:33,MPT,b0af35b31588dc4ab06d5cf2986e8e02,MD,ATH,MIL,0,1,ATH,MIL,2013-01-04,,,,,,,,,,,,,,,,,,,,,,,,,,,,1ASIWS,0,0,0,d41d8cd98f00b204e9800998ecf8427e,KIV\n",
        " \n",
        "CPU times: user 2min 1s, sys: 3.67 s, total: 2min 5s"
       ]
      },
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "\n",
        "Wall time: 2min 7s\n"
       ]
      }
     ],
     "prompt_number": 12
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "We can observe that the separator **^** is not applied thorugh all the file\n",
      "\n",
      "For this particular case it is not problematic as the airport (MPT) is not in our use cases"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "#visual check\n",
      "counts"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 13,
       "text": [
        "{'AGP': [9633,\n",
        "  8379,\n",
        "  10659,\n",
        "  8265,\n",
        "  10830,\n",
        "  7923,\n",
        "  8892,\n",
        "  7866,\n",
        "  8151,\n",
        "  6499,\n",
        "  6384,\n",
        "  3696],\n",
        " 'BCN': [29469,\n",
        "  28329,\n",
        "  30552,\n",
        "  31236,\n",
        "  28728,\n",
        "  26505,\n",
        "  29241,\n",
        "  27075,\n",
        "  23427,\n",
        "  20276,\n",
        "  19824,\n",
        "  15400],\n",
        " 'MAD': [24258,\n",
        "  22800,\n",
        "  24681,\n",
        "  25251,\n",
        "  26334,\n",
        "  22800,\n",
        "  22971,\n",
        "  21831,\n",
        "  21147,\n",
        "  22294,\n",
        "  20272,\n",
        "  14504]}"
       ]
      }
     ],
     "prompt_number": 13
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "Plotting"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "%matplotlib inline\n",
      "import matplotlib.pyplot as plt"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 17
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "xticks = [s+' 2013' for s in['Jan','Feb','Mar','Apr','May','Jun','Jul','Aug','Sep','Oct','Nov','Dec']]\n",
      "fig, ax = plt.subplots()\n",
      "ax.plot(counts['MAD'], marker='o', label='MAD')\n",
      "ax.plot(counts['BCN'], marker='d', label='BCN')\n",
      "ax.plot(counts['AGP'], marker='v', label='AGP')\n",
      "ax.set_ylabel(\"Arrivals\")\n",
      "ax.set_xlabel(\"Date\")\n",
      "ax.set_xticks(range(len(xticks)))\n",
      "ax.set_xticklabels(xticks, rotation=50)\n",
      "plt.legend()\n",
      "plt.title('Monthly arrivals in 2013');\n"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "display_data",
       "png": "iVBORw0KGgoAAAANSUhEUgAAAYoAAAEzCAYAAAAvu0StAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n",
       "text": [
        "<matplotlib.figure.Figure at 0x7f9f340ad310>"
       ]
      }
     ],
     "prompt_number": 34
    },
    {
     "cell_type": "heading",
     "level": 2,
     "metadata": {},
     "source": [
      "Conclussions"
     ]
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "Working with pandas was really instructive, once that I started understanding the idea everything became easier and faster.\n",
      "\n",
      "Memory usage with pandas is much higher than reading and adding line by line, and is much higher than the estimations because behind the scenes pandas needs more memory for data and also because ipython notebook keeps the history\n",
      "\n",
      "Working with incomplete data can be tricky but pandas makes it easier\n",
      "\n",
      "Processing with Pandas 3 times faster than pure python. most of the time is spent reading from disk, but later filtering and data handling operations are faster\n"
     ]
    }
   ],
   "metadata": {}
  }
 ]
}