cuartiles.ipynb

{
 "metadata": {
  "name": "Cuartiles-resumen"
 },
 "nbformat": 3,
 "nbformat_minor": 0,
 "worksheets": [
  {
   "cells": [
    {
     "cell_type": "heading",
     "level": 1,
     "metadata": {},
     "source": "Cuartiles Grupos A, Instituto de F\u00edsica UdeA"
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": "Fuentes: S\u00e1lida en excel de las categor\u00edas de [SJR](http://www.scimagojr.com/journalrank.php), con algunas entradas manuales de: [ISI-Thompson](http://aplicacionesbiblioteca.udea.edu.co:2253/JCR/JCR) (accesible desde la UdeA): [Cuartiles](https://docs.google.com/spreadsheet/ccc?key=0AuLa_xuSIEvxdHk4Tk9GczNxdFRTYkd5YlhHVFFQZkE&usp=sharing)."
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": "cd gssis/utilities/",
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": "/home/ipython/gssis/utilities\n"
      }
     ],
     "prompt_number": 1
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": "Instale el programa `gssis`, y en particular el m\u00f3dulo `cvsreader` de m\u00e1s abajo, desde: https://github.com/rescolo/gssis "
    },
    {
     "cell_type": "heading",
     "level": 2,
     "metadata": {},
     "source": "Cargue datos"
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": "from cvsreader import *\ndef loaddf(google_gss_key,google_gss_sheet=0):\n    return read_google_cvs(gss_key=google_gss_key,gss_sheet=google_gss_sheet,gss_query='select *')\n\nIndicadores={'Art\u00edculos':'0AjqGPI5Q_Ez6dDA3ajhtYVVDOWdBckVhWm1MSFRET1E'} \nIndicadores['Cuartiles']=\"0AuLa_xuSIEvxdHk4Tk9GczNxdFRTYkd5YlhHVFFQZkE\"\n\narticulos=loaddf(Indicadores['Art\u00edculos'])\npublicadas=articulos[articulos['ISSN']!='0000-0000'].reset_index(drop=True)\n\ncuartiles=loaddf(Indicadores['Cuartiles'])\n#fix missing leading 0's in ISSN\ncuartiles['ISSN']=[re.sub('^([0-9]{4})$','0000\\\\1',i) for i in cuartiles['ISSN']]\ncuartiles['ISSN']=[re.sub('^([0-9]{5})$','000\\\\1',i) for i in cuartiles['ISSN']]\ncuartiles['ISSN']=[re.sub('^([0-9]{6})$','00\\\\1',i) for i in cuartiles['ISSN']]\ncuartiles['ISSN']=[re.sub('^([0-9]{7})$','0\\\\1',i) for i in cuartiles['ISSN']]\n#fix ISSN hypenathion\ncuartiles['ISSN']=[re.sub('^([0-9]{4})','\\\\1-',i) for i in cuartiles['ISSN']]\n",
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 2
    },
    {
     "cell_type": "heading",
     "level": 2,
     "metadata": {},
     "source": "Adicione cuartiles a la tabla de art\u00edculos"
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": "Escoja el cuart\u00edl m\u00e1s alto entre ISI y Scopus"
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": "publicadas['Cuartiles']=''\npublicadas['Categorias']=''\nfor i in range(len(publicadas)):\n    journal=cuartiles[cuartiles['ISSN']==publicadas['ISSN'][i]].sort('Quartile').reset_index(drop=True)\n    if journal:\n        publicadas['Cuartiles'][i]=journal['Quartile'][0]\n        publicadas['Categorias'][i]=journal['Categories'][0]\n        ",
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 3
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": "Defina Grupos y a\u00f1os de publicaci\u00f3n"
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": "grupos={'GFIF':'Grupo de Fenomenolog\u00eda de Interacciones Fundamentales',\n        'GFAM':'Grupo de F\u00edsica At\u00f3mica y Molecular',\n        'GMC':'Grupo de Materia Condensada',\n        'GOF':'Grupo de \u00d3ptica y Fot\u00f3nica',\n        'GES':'Grupo de Estado S\u00f3lido','MS':'Magnetismo y Simulaci\u00f3n'}\nyears=[2012,2013]\ndf=pd.DataFrame(data=None,columns=['Grupo','Q1(2012)','Q2(2012)','Q3(2012)','Q4(2012)','Total(2012)',\n                                   'Q1(2013)','Q2(2013)','Q3(2013)','Q4(2013)','Total(2013)',])\nfor grupo in grupos.keys():\n    pb=publicadas[publicadas['Grupo'].str.contains(grupo)].reset_index(drop=True)\n    entry={'Grupo':grupos[grupo]}\n    for year in years:\n        crtls=pb[pb['A\u00f1o']==year]['Cuartiles'].value_counts()\n        crtlsd=crtls.to_dict()\n        total=0\n        for i in range(1,5):\n            if crtlsd.has_key('Q%d' %i):\n                entry['Q%d(%d)' %(i,year)]=crtls['Q%d' %i]\n                total=total+crtls['Q%d' %i]\n            else:\n                entry['Q%d(%d)' %(i,year)]=0\n            \n        \n        entry['Total(%d)' %year]=total\n        \n    df=df.append(entry,ignore_index=True)    ",
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 4
    },
    {
     "cell_type": "heading",
     "level": 2,
     "metadata": {},
     "source": "Resultados:"
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": "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>Grupo</th>\n      <th>Q1(2012)</th>\n      <th>Q2(2012)</th>\n      <th>Q3(2012)</th>\n      <th>Q4(2012)</th>\n      <th>Total(2012)</th>\n      <th>Q1(2013)</th>\n      <th>Q2(2013)</th>\n      <th>Q3(2013)</th>\n      <th>Q4(2013)</th>\n      <th>Total(2013)</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>                            Grupo de Estado S\u00f3lido</td>\n      <td>  5</td>\n      <td>  2</td>\n      <td> 0</td>\n      <td> 0</td>\n      <td>  7</td>\n      <td>  3</td>\n      <td> 5</td>\n      <td> 4</td>\n      <td> 2</td>\n      <td> 14</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>               Grupo de F\u00edsica At\u00f3mica y Molecular</td>\n      <td>  3</td>\n      <td>  0</td>\n      <td> 0</td>\n      <td> 4</td>\n      <td>  7</td>\n      <td>  4</td>\n      <td> 1</td>\n      <td> 0</td>\n      <td> 0</td>\n      <td>  5</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>                       Grupo de Materia Condensada</td>\n      <td> 11</td>\n      <td> 17</td>\n      <td> 0</td>\n      <td> 1</td>\n      <td> 29</td>\n      <td>  3</td>\n      <td> 8</td>\n      <td> 0</td>\n      <td> 0</td>\n      <td> 11</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>                        Grupo de \u00d3ptica y Fot\u00f3nica</td>\n      <td>  4</td>\n      <td>  1</td>\n      <td> 0</td>\n      <td> 0</td>\n      <td>  5</td>\n      <td>  4</td>\n      <td> 0</td>\n      <td> 0</td>\n      <td> 0</td>\n      <td>  4</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td> Grupo de Fenomenolog\u00eda de Interacciones Fundam...</td>\n      <td>  6</td>\n      <td>  0</td>\n      <td> 1</td>\n      <td> 0</td>\n      <td>  7</td>\n      <td> 10</td>\n      <td> 0</td>\n      <td> 0</td>\n      <td> 0</td>\n      <td> 10</td>\n    </tr>\n    <tr>\n      <th>5</th>\n      <td>                           Magnetismo y Simulaci\u00f3n</td>\n      <td>  1</td>\n      <td>  0</td>\n      <td> 3</td>\n      <td> 0</td>\n      <td>  4</td>\n      <td>  0</td>\n      <td> 0</td>\n      <td> 0</td>\n      <td> 0</td>\n      <td>  0</td>\n    </tr>\n  </tbody>\n</table>\n</div>",
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 5,
       "text": "                                               Grupo Q1(2012) Q2(2012)  \\\n0                             Grupo de Estado S\u00f3lido        5        2   \n1                Grupo de F\u00edsica At\u00f3mica y Molecular        3        0   \n2                        Grupo de Materia Condensada       11       17   \n3                         Grupo de \u00d3ptica y Fot\u00f3nica        4        1   \n4  Grupo de Fenomenolog\u00eda de Interacciones Fundam...        6        0   \n5                            Magnetismo y Simulaci\u00f3n        1        0   \n\n  Q3(2012) Q4(2012) Total(2012) Q1(2013) Q2(2013) Q3(2013) Q4(2013)  \\\n0        0        0           7        3        5        4        2   \n1        0        4           7        4        1        0        0   \n2        0        1          29        3        8        0        0   \n3        0        0           5        4        0        0        0   \n4        1        0           7       10        0        0        0   \n5        3        0           4        0        0        0        0   \n\n  Total(2013)  \n0          14  \n1           5  \n2          11  \n3           4  \n4          10  \n5           0  "
      }
     ],
     "prompt_number": 5
    },
    {
     "cell_type": "heading",
     "level": 2,
     "metadata": {},
     "source": "Conclusiones"
    },
    {
     "cell_type": "heading",
     "level": 4,
     "metadata": {},
     "source": "Porcentaje de art\u00edculo ISI o Scopus en Q1:"
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": "#for year in years\nyear=2012\nfor year in years:\n    print '%d: %g' %(year,(df['Q1(%d)' %year].values.sum()/float(df['Total(%d)' %year].values.sum())*100))+'%'",
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": "2012: 50.8475%\n2013: 54.5455%\n"
      }
     ],
     "prompt_number": 6
    }
   ],
   "metadata": {}
  }
 ]
}