{
 "metadata": {
  "name": "Pandas experiments"
 },
 "nbformat": 3,
 "nbformat_minor": 0,
 "worksheets": [
  {
   "cells": [
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "import pandas as pd\n",
      "import numpy\n",
      "\n",
      "N = 100\n",
      "data = pd.DataFrame({\n",
      "    'A': numpy.random.randint(0, 5, N),\n",
      "    'B': numpy.random.randint(0, 3, N),\n",
      "    'X': numpy.random.rand(N),\n",
      "    'Y': numpy.random.rand(N),\n",
      "})"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 1
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "data.groupby(['A', 'B']).agg({'X': ['sum', 'count'], 'Y': ['sum', 'count']})"
     ],
     "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></th>\n",
        "      <th colspan=\"2\" halign=\"left\">Y</th>\n",
        "      <th colspan=\"2\" halign=\"left\">X</th>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th></th>\n",
        "      <th></th>\n",
        "      <th>sum</th>\n",
        "      <th>count</th>\n",
        "      <th>sum</th>\n",
        "      <th>count</th>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>A</th>\n",
        "      <th>B</th>\n",
        "      <th></th>\n",
        "      <th></th>\n",
        "      <th></th>\n",
        "      <th></th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th rowspan=\"3\" valign=\"top\">0</th>\n",
        "      <th>0</th>\n",
        "      <td> 1.049082</td>\n",
        "      <td>  3</td>\n",
        "      <td> 1.670366</td>\n",
        "      <td>  3</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>1</th>\n",
        "      <td> 5.578948</td>\n",
        "      <td> 11</td>\n",
        "      <td> 6.407933</td>\n",
        "      <td> 11</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2</th>\n",
        "      <td> 1.228797</td>\n",
        "      <td>  3</td>\n",
        "      <td> 1.674203</td>\n",
        "      <td>  3</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th rowspan=\"3\" valign=\"top\">1</th>\n",
        "      <th>0</th>\n",
        "      <td> 0.970503</td>\n",
        "      <td>  2</td>\n",
        "      <td> 1.152771</td>\n",
        "      <td>  2</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>1</th>\n",
        "      <td> 2.410762</td>\n",
        "      <td>  5</td>\n",
        "      <td> 2.727062</td>\n",
        "      <td>  5</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2</th>\n",
        "      <td> 5.685782</td>\n",
        "      <td> 12</td>\n",
        "      <td> 6.092611</td>\n",
        "      <td> 12</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th rowspan=\"3\" valign=\"top\">2</th>\n",
        "      <th>0</th>\n",
        "      <td> 1.065329</td>\n",
        "      <td>  4</td>\n",
        "      <td> 1.488982</td>\n",
        "      <td>  4</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>1</th>\n",
        "      <td> 4.147895</td>\n",
        "      <td> 11</td>\n",
        "      <td> 5.999030</td>\n",
        "      <td> 11</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2</th>\n",
        "      <td> 4.694436</td>\n",
        "      <td>  9</td>\n",
        "      <td> 4.075007</td>\n",
        "      <td>  9</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th rowspan=\"3\" valign=\"top\">3</th>\n",
        "      <th>0</th>\n",
        "      <td> 4.446768</td>\n",
        "      <td>  8</td>\n",
        "      <td> 2.976906</td>\n",
        "      <td>  8</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>1</th>\n",
        "      <td> 1.600019</td>\n",
        "      <td>  3</td>\n",
        "      <td> 1.204319</td>\n",
        "      <td>  3</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2</th>\n",
        "      <td> 5.457779</td>\n",
        "      <td> 10</td>\n",
        "      <td> 4.391731</td>\n",
        "      <td> 10</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th rowspan=\"3\" valign=\"top\">4</th>\n",
        "      <th>0</th>\n",
        "      <td> 2.109207</td>\n",
        "      <td>  6</td>\n",
        "      <td> 1.780748</td>\n",
        "      <td>  6</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>1</th>\n",
        "      <td> 3.242274</td>\n",
        "      <td>  6</td>\n",
        "      <td> 3.170702</td>\n",
        "      <td>  6</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2</th>\n",
        "      <td> 2.669061</td>\n",
        "      <td>  7</td>\n",
        "      <td> 3.298991</td>\n",
        "      <td>  7</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "output_type": "pyout",
       "prompt_number": 15,
       "text": [
        "            Y                X       \n",
        "          sum  count       sum  count\n",
        "A B                                  \n",
        "0 0  1.049082      3  1.670366      3\n",
        "  1  5.578948     11  6.407933     11\n",
        "  2  1.228797      3  1.674203      3\n",
        "1 0  0.970503      2  1.152771      2\n",
        "  1  2.410762      5  2.727062      5\n",
        "  2  5.685782     12  6.092611     12\n",
        "2 0  1.065329      4  1.488982      4\n",
        "  1  4.147895     11  5.999030     11\n",
        "  2  4.694436      9  4.075007      9\n",
        "3 0  4.446768      8  2.976906      8\n",
        "  1  1.600019      3  1.204319      3\n",
        "  2  5.457779     10  4.391731     10\n",
        "4 0  2.109207      6  1.780748      6\n",
        "  1  3.242274      6  3.170702      6\n",
        "  2  2.669061      7  3.298991      7"
       ]
      }
     ],
     "prompt_number": 15
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "import datetime\n",
      "x = pd.Series(['1', '2', '3', numpy.nan])\n",
      "y = pd.Series(['1/1/2012', '1/1/2013'])\n",
      "y2 = y.apply(lambda v: pd.datetools.parse(v, dayfirst=True))"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 39
    }
   ],
   "metadata": {}
  }
 ]
}