{
 "metadata": {
  "name": "",
  "signature": "sha256:afa3fa52acc2e4f4c7f68fdccddfd7dbe5a9beed2b1e103a25095d2865b3519b"
 },
 "nbformat": 3,
 "nbformat_minor": 0,
 "worksheets": [
  {
   "cells": [
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "%pylab inline\n",
      "\n",
      "import pandas as pd"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "Populating the interactive namespace from numpy and matplotlib\n"
       ]
      },
      {
       "output_type": "stream",
       "stream": "stderr",
       "text": [
        "/home/walrus/.virtualenvs/py/local/lib/python2.7/site-packages/pandas/io/excel.py:626: UserWarning: Installed openpyxl is not supported at this time. Use >=1.6.1 and <2.0.0.\n",
        "  .format(openpyxl_compat.start_ver, openpyxl_compat.stop_ver))\n"
       ]
      }
     ],
     "prompt_number": 1
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "data = pd.read_excel('../Orcamento/2015/Proposta/PLOA467BaseDadosQuadroDetalhadoDaAcao.xls')"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 3
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "def get_data_info(data):\n",
      "    data_info = {}\n",
      "    \n",
      "    for c in data.columns:\n",
      "        if data[c].dtype in [np.dtype('int64'), np.dtype('float64')]:\n",
      "            data_info[c] = {}\n",
      "            data_info[c]['distinct_values'] = len(data[c].value_counts())\n",
      "            data_info[c]['range'] = (data[c].min(), data[c].max())\n",
      "            \n",
      "    return data_info"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 61
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "data_info = get_data_info(data)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 64
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "data_info"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 65,
       "text": [
        "{u'ANO_EX': {'distinct_values': 1, 'range': (2015, 2015)},\n",
        " u'COD_DA': {'distinct_values': 73, 'range': (1, 100)},\n",
        " u'COD_DISTRITO': {'distinct_values': 68, 'range': (0, 99)},\n",
        " u'COD_EMP': {'distinct_values': 14, 'range': (1, 91)},\n",
        " u'COD_META': {'distinct_values': 321, 'range': (1, 999)},\n",
        " u'COD_REGIAO': {'distinct_values': 7, 'range': (0, 9)},\n",
        " u'COD_SUBPREFEITURA': {'distinct_values': 34, 'range': (0, 99)},\n",
        " u'ORGAO': {'distinct_values': 86, 'range': (1, 99)},\n",
        " u'PA': {'distinct_values': 313, 'range': (4, 9133)},\n",
        " u'UNIDADE': {'distinct_values': 24, 'range': (10, 70)},\n",
        " u'VALOR_DA': {'distinct_values': 1071, 'range': (1000.0, 5488238392.0)}}"
       ]
      }
     ],
     "prompt_number": 65
    }
   ],
   "metadata": {}
  }
 ]
}