{
 "metadata": {
  "name": "",
  "signature": "sha256:46cdb303e7e791d8c7056413f93df8cd9403aea2aae02bf3546fa083d0d4fcf9"
 },
 "nbformat": 3,
 "nbformat_minor": 0,
 "worksheets": [
  {
   "cells": [
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "%pylab inline"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "Populating the interactive namespace from numpy and matplotlib\n"
       ]
      }
     ],
     "prompt_number": 1
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "from pandas import Series, DataFrame"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 3
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "import pandas as pd"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 2
    },
    {
     "cell_type": "heading",
     "level": 1,
     "metadata": {},
     "source": [
      "Introduction to pandas Data Structures"
     ]
    },
    {
     "cell_type": "heading",
     "level": 2,
     "metadata": {},
     "source": [
      "Series"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "obj = Series([4, 7, -5, 3])"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 4
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "obj"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 5,
       "text": [
        "0    4\n",
        "1    7\n",
        "2   -5\n",
        "3    3\n",
        "dtype: int64"
       ]
      }
     ],
     "prompt_number": 5
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "obj.values"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 7,
       "text": [
        "array([ 4,  7, -5,  3])"
       ]
      }
     ],
     "prompt_number": 7
    },
    {
     "cell_type": "code",
     "collapsed": true,
     "input": [
      "obj.index"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 8,
       "text": [
        "Int64Index([0, 1, 2, 3], dtype='int64')"
       ]
      }
     ],
     "prompt_number": 8
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "obj2 = Series([4,7,-5,3], index = ['d','b','a','c'])"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 9
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "obj2"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 10,
       "text": [
        "d    4\n",
        "b    7\n",
        "a   -5\n",
        "c    3\n",
        "dtype: int64"
       ]
      }
     ],
     "prompt_number": 10
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "obj2.values"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 11,
       "text": [
        "array([ 4,  7, -5,  3])"
       ]
      }
     ],
     "prompt_number": 11
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "obj2.index"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 12,
       "text": [
        "Index([u'd', u'b', u'a', u'c'], dtype='object')"
       ]
      }
     ],
     "prompt_number": 12
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "obj2['a']"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 13,
       "text": [
        "-5"
       ]
      }
     ],
     "prompt_number": 13
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "obj2[['c','a','d']]"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 14,
       "text": [
        "c    3\n",
        "a   -5\n",
        "d    4\n",
        "dtype: int64"
       ]
      }
     ],
     "prompt_number": 14
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "obj2[obj2>0]"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 15,
       "text": [
        "d    4\n",
        "b    7\n",
        "c    3\n",
        "dtype: int64"
       ]
      }
     ],
     "prompt_number": 15
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "obj2*2"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 16,
       "text": [
        "d     8\n",
        "b    14\n",
        "a   -10\n",
        "c     6\n",
        "dtype: int64"
       ]
      }
     ],
     "prompt_number": 16
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "np.exp(obj2)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 17,
       "text": [
        "d      54.598150\n",
        "b    1096.633158\n",
        "a       0.006738\n",
        "c      20.085537\n",
        "dtype: float64"
       ]
      }
     ],
     "prompt_number": 17
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "'b' in obj2"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 18,
       "text": [
        "True"
       ]
      }
     ],
     "prompt_number": 18
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "'e' in obj2"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 19,
       "text": [
        "False"
       ]
      }
     ],
     "prompt_number": 19
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "sdata = {'Ohio':3500,'Texas':71000,'Oregon':16000, 'Utah':5000}"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 20
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "obj3 = Series(sdata)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 21
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "obj3"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 22,
       "text": [
        "Ohio       3500\n",
        "Oregon    16000\n",
        "Texas     71000\n",
        "Utah       5000\n",
        "dtype: int64"
       ]
      }
     ],
     "prompt_number": 22
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "states = ['California','Ohio','Oregon','Texas']"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 23
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "obj4 = Series(sdata, index=states)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 24
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "obj4"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 25,
       "text": [
        "California      NaN\n",
        "Ohio           3500\n",
        "Oregon        16000\n",
        "Texas         71000\n",
        "dtype: float64"
       ]
      }
     ],
     "prompt_number": 25
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "pd.isnull(obj4)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 26,
       "text": [
        "California     True\n",
        "Ohio          False\n",
        "Oregon        False\n",
        "Texas         False\n",
        "dtype: bool"
       ]
      }
     ],
     "prompt_number": 26
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "pd.notnull(obj4)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 27,
       "text": [
        "California    False\n",
        "Ohio           True\n",
        "Oregon         True\n",
        "Texas          True\n",
        "dtype: bool"
       ]
      }
     ],
     "prompt_number": 27
    },
    {
     "cell_type": "heading",
     "level": 5,
     "metadata": {},
     "source": [
      "Series also has instance methods."
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "obj4.isnull()"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 28,
       "text": [
        "California     True\n",
        "Ohio          False\n",
        "Oregon        False\n",
        "Texas         False\n",
        "dtype: bool"
       ]
      }
     ],
     "prompt_number": 28
    },
    {
     "cell_type": "heading",
     "level": 5,
     "metadata": {},
     "source": [
      "Automatically aligns differently indexed data in arithmetic operations."
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "obj3"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 29,
       "text": [
        "Ohio       3500\n",
        "Oregon    16000\n",
        "Texas     71000\n",
        "Utah       5000\n",
        "dtype: int64"
       ]
      }
     ],
     "prompt_number": 29
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "obj4"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 30,
       "text": [
        "California      NaN\n",
        "Ohio           3500\n",
        "Oregon        16000\n",
        "Texas         71000\n",
        "dtype: float64"
       ]
      }
     ],
     "prompt_number": 30
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "obj3 + obj4"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 31,
       "text": [
        "California       NaN\n",
        "Ohio            7000\n",
        "Oregon         32000\n",
        "Texas         142000\n",
        "Utah             NaN\n",
        "dtype: float64"
       ]
      }
     ],
     "prompt_number": 31
    },
    {
     "cell_type": "heading",
     "level": 5,
     "metadata": {},
     "source": [
      "name attribute"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "obj4.name = 'population'"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 32
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "obj4.index.name='state'"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 33
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "obj4"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 34,
       "text": [
        "state\n",
        "California      NaN\n",
        "Ohio           3500\n",
        "Oregon        16000\n",
        "Texas         71000\n",
        "Name: population, dtype: float64"
       ]
      }
     ],
     "prompt_number": 34
    },
    {
     "cell_type": "heading",
     "level": 5,
     "metadata": {},
     "source": [
      "index altered in place"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "obj.index = ['Bob','Steve','Jeff','Ryan']"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 35
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "obj"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 36,
       "text": [
        "Bob      4\n",
        "Steve    7\n",
        "Jeff    -5\n",
        "Ryan     3\n",
        "dtype: int64"
       ]
      }
     ],
     "prompt_number": 36
    },
    {
     "cell_type": "heading",
     "level": 2,
     "metadata": {},
     "source": [
      "DataFrame"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "data = {'state':['Ohio', 'Ohio', 'Ohio', 'Nevada', 'Nevada'],\n",
      "        'year':[2000, 2001, 2002, 2001, 2002],\n",
      "        'pop':[1.5, 1.7, 3.6, 2.4, 2.9]}\n",
      "frame = DataFrame(data)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 37
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "frame"
     ],
     "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>pop</th>\n",
        "      <th>state</th>\n",
        "      <th>year</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>0</th>\n",
        "      <td> 1.5</td>\n",
        "      <td>   Ohio</td>\n",
        "      <td> 2000</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>1</th>\n",
        "      <td> 1.7</td>\n",
        "      <td>   Ohio</td>\n",
        "      <td> 2001</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2</th>\n",
        "      <td> 3.6</td>\n",
        "      <td>   Ohio</td>\n",
        "      <td> 2002</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>3</th>\n",
        "      <td> 2.4</td>\n",
        "      <td> Nevada</td>\n",
        "      <td> 2001</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>4</th>\n",
        "      <td> 2.9</td>\n",
        "      <td> Nevada</td>\n",
        "      <td> 2002</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 38,
       "text": [
        "   pop   state  year\n",
        "0  1.5    Ohio  2000\n",
        "1  1.7    Ohio  2001\n",
        "2  3.6    Ohio  2002\n",
        "3  2.4  Nevada  2001\n",
        "4  2.9  Nevada  2002"
       ]
      }
     ],
     "prompt_number": 38
    },
    {
     "cell_type": "heading",
     "level": 5,
     "metadata": {},
     "source": [
      "column that is not contained in the data"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "frame2 = DataFrame(data, columns = ['year','state','pop','debt'],\n",
      "                   index=['one','two','three','four','five'])"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 39
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "frame2"
     ],
     "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>year</th>\n",
        "      <th>state</th>\n",
        "      <th>pop</th>\n",
        "      <th>debt</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>one</th>\n",
        "      <td> 2000</td>\n",
        "      <td>   Ohio</td>\n",
        "      <td> 1.5</td>\n",
        "      <td> NaN</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>two</th>\n",
        "      <td> 2001</td>\n",
        "      <td>   Ohio</td>\n",
        "      <td> 1.7</td>\n",
        "      <td> NaN</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>three</th>\n",
        "      <td> 2002</td>\n",
        "      <td>   Ohio</td>\n",
        "      <td> 3.6</td>\n",
        "      <td> NaN</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>four</th>\n",
        "      <td> 2001</td>\n",
        "      <td> Nevada</td>\n",
        "      <td> 2.4</td>\n",
        "      <td> NaN</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>five</th>\n",
        "      <td> 2002</td>\n",
        "      <td> Nevada</td>\n",
        "      <td> 2.9</td>\n",
        "      <td> NaN</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 40,
       "text": [
        "       year   state  pop debt\n",
        "one    2000    Ohio  1.5  NaN\n",
        "two    2001    Ohio  1.7  NaN\n",
        "three  2002    Ohio  3.6  NaN\n",
        "four   2001  Nevada  2.4  NaN\n",
        "five   2002  Nevada  2.9  NaN"
       ]
      }
     ],
     "prompt_number": 40
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "frame2.columns"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 41,
       "text": [
        "Index([u'year', u'state', u'pop', u'debt'], dtype='object')"
       ]
      }
     ],
     "prompt_number": 41
    },
    {
     "cell_type": "heading",
     "level": 5,
     "metadata": {},
     "source": [
      "column retrieved"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "frame2['state']"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 42,
       "text": [
        "one        Ohio\n",
        "two        Ohio\n",
        "three      Ohio\n",
        "four     Nevada\n",
        "five     Nevada\n",
        "Name: state, dtype: object"
       ]
      }
     ],
     "prompt_number": 42
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "frame2.year"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 44,
       "text": [
        "one      2000\n",
        "two      2001\n",
        "three    2002\n",
        "four     2001\n",
        "five     2002\n",
        "Name: year, dtype: int64"
       ]
      }
     ],
     "prompt_number": 44
    },
    {
     "cell_type": "heading",
     "level": 5,
     "metadata": {},
     "source": [
      "rows retrieved"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "frame2.ix['three']"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 45,
       "text": [
        "year     2002\n",
        "state    Ohio\n",
        "pop       3.6\n",
        "debt      NaN\n",
        "Name: three, dtype: object"
       ]
      }
     ],
     "prompt_number": 45
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "frame2.ix[2]"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 47,
       "text": [
        "year     2002\n",
        "state    Ohio\n",
        "pop       3.6\n",
        "debt      NaN\n",
        "Name: three, dtype: object"
       ]
      }
     ],
     "prompt_number": 47
    },
    {
     "cell_type": "heading",
     "level": 5,
     "metadata": {},
     "source": [
      "columns modified by assignment"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "frame2['debt']=16.5"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 48
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "frame2"
     ],
     "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>year</th>\n",
        "      <th>state</th>\n",
        "      <th>pop</th>\n",
        "      <th>debt</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>one</th>\n",
        "      <td> 2000</td>\n",
        "      <td>   Ohio</td>\n",
        "      <td> 1.5</td>\n",
        "      <td> 16.5</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>two</th>\n",
        "      <td> 2001</td>\n",
        "      <td>   Ohio</td>\n",
        "      <td> 1.7</td>\n",
        "      <td> 16.5</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>three</th>\n",
        "      <td> 2002</td>\n",
        "      <td>   Ohio</td>\n",
        "      <td> 3.6</td>\n",
        "      <td> 16.5</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>four</th>\n",
        "      <td> 2001</td>\n",
        "      <td> Nevada</td>\n",
        "      <td> 2.4</td>\n",
        "      <td> 16.5</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>five</th>\n",
        "      <td> 2002</td>\n",
        "      <td> Nevada</td>\n",
        "      <td> 2.9</td>\n",
        "      <td> 16.5</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 49,
       "text": [
        "       year   state  pop  debt\n",
        "one    2000    Ohio  1.5  16.5\n",
        "two    2001    Ohio  1.7  16.5\n",
        "three  2002    Ohio  3.6  16.5\n",
        "four   2001  Nevada  2.4  16.5\n",
        "five   2002  Nevada  2.9  16.5"
       ]
      }
     ],
     "prompt_number": 49
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "frame2['debt']=np.arange(5.)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 50
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "frame2"
     ],
     "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>year</th>\n",
        "      <th>state</th>\n",
        "      <th>pop</th>\n",
        "      <th>debt</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>one</th>\n",
        "      <td> 2000</td>\n",
        "      <td>   Ohio</td>\n",
        "      <td> 1.5</td>\n",
        "      <td> 0</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>two</th>\n",
        "      <td> 2001</td>\n",
        "      <td>   Ohio</td>\n",
        "      <td> 1.7</td>\n",
        "      <td> 1</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>three</th>\n",
        "      <td> 2002</td>\n",
        "      <td>   Ohio</td>\n",
        "      <td> 3.6</td>\n",
        "      <td> 2</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>four</th>\n",
        "      <td> 2001</td>\n",
        "      <td> Nevada</td>\n",
        "      <td> 2.4</td>\n",
        "      <td> 3</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>five</th>\n",
        "      <td> 2002</td>\n",
        "      <td> Nevada</td>\n",
        "      <td> 2.9</td>\n",
        "      <td> 4</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 51,
       "text": [
        "       year   state  pop  debt\n",
        "one    2000    Ohio  1.5     0\n",
        "two    2001    Ohio  1.7     1\n",
        "three  2002    Ohio  3.6     2\n",
        "four   2001  Nevada  2.4     3\n",
        "five   2002  Nevada  2.9     4"
       ]
      }
     ],
     "prompt_number": 51
    },
    {
     "cell_type": "heading",
     "level": 5,
     "metadata": {},
     "source": [
      "assign series to a column"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "val = Series([1.2, 1.5, -1.7], index = ['two', 'four','five'])"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 52
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "frame2['debt']=val"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 53
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "frame2"
     ],
     "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>year</th>\n",
        "      <th>state</th>\n",
        "      <th>pop</th>\n",
        "      <th>debt</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>one</th>\n",
        "      <td> 2000</td>\n",
        "      <td>   Ohio</td>\n",
        "      <td> 1.5</td>\n",
        "      <td> NaN</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>two</th>\n",
        "      <td> 2001</td>\n",
        "      <td>   Ohio</td>\n",
        "      <td> 1.7</td>\n",
        "      <td> 1.2</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>three</th>\n",
        "      <td> 2002</td>\n",
        "      <td>   Ohio</td>\n",
        "      <td> 3.6</td>\n",
        "      <td> NaN</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>four</th>\n",
        "      <td> 2001</td>\n",
        "      <td> Nevada</td>\n",
        "      <td> 2.4</td>\n",
        "      <td> 1.5</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>five</th>\n",
        "      <td> 2002</td>\n",
        "      <td> Nevada</td>\n",
        "      <td> 2.9</td>\n",
        "      <td>-1.7</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 54,
       "text": [
        "       year   state  pop  debt\n",
        "one    2000    Ohio  1.5   NaN\n",
        "two    2001    Ohio  1.7   1.2\n",
        "three  2002    Ohio  3.6   NaN\n",
        "four   2001  Nevada  2.4   1.5\n",
        "five   2002  Nevada  2.9  -1.7"
       ]
      }
     ],
     "prompt_number": 54
    },
    {
     "cell_type": "heading",
     "level": 5,
     "metadata": {},
     "source": [
      "assigning a column that does not exist"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "frame2['eastern'] = frame2.state=='Ohio'"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 55
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "frame2"
     ],
     "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>year</th>\n",
        "      <th>state</th>\n",
        "      <th>pop</th>\n",
        "      <th>debt</th>\n",
        "      <th>eastern</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>one</th>\n",
        "      <td> 2000</td>\n",
        "      <td>   Ohio</td>\n",
        "      <td> 1.5</td>\n",
        "      <td> NaN</td>\n",
        "      <td>  True</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>two</th>\n",
        "      <td> 2001</td>\n",
        "      <td>   Ohio</td>\n",
        "      <td> 1.7</td>\n",
        "      <td> 1.2</td>\n",
        "      <td>  True</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>three</th>\n",
        "      <td> 2002</td>\n",
        "      <td>   Ohio</td>\n",
        "      <td> 3.6</td>\n",
        "      <td> NaN</td>\n",
        "      <td>  True</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>four</th>\n",
        "      <td> 2001</td>\n",
        "      <td> Nevada</td>\n",
        "      <td> 2.4</td>\n",
        "      <td> 1.5</td>\n",
        "      <td> False</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>five</th>\n",
        "      <td> 2002</td>\n",
        "      <td> Nevada</td>\n",
        "      <td> 2.9</td>\n",
        "      <td>-1.7</td>\n",
        "      <td> False</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 56,
       "text": [
        "       year   state  pop  debt eastern\n",
        "one    2000    Ohio  1.5   NaN    True\n",
        "two    2001    Ohio  1.7   1.2    True\n",
        "three  2002    Ohio  3.6   NaN    True\n",
        "four   2001  Nevada  2.4   1.5   False\n",
        "five   2002  Nevada  2.9  -1.7   False"
       ]
      }
     ],
     "prompt_number": 56
    },
    {
     "cell_type": "heading",
     "level": 5,
     "metadata": {},
     "source": [
      "delete columns"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "del frame2['eastern']"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 57
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "frame2.columns"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 58,
       "text": [
        "Index([u'year', u'state', u'pop', u'debt'], dtype='object')"
       ]
      }
     ],
     "prompt_number": 58
    },
    {
     "cell_type": "heading",
     "level": 5,
     "metadata": {},
     "source": [
      "nested dict of dicts"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "pop={'Nevada':{2001:2.4, 2002:2.9},\n",
      "     'Ohio': {2000:1.5, 2001:1.7,2002:3.6} }"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 59
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "frame3 = DataFrame(pop)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 60
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "frame3"
     ],
     "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>Nevada</th>\n",
        "      <th>Ohio</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>2000</th>\n",
        "      <td> NaN</td>\n",
        "      <td> 1.5</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2001</th>\n",
        "      <td> 2.4</td>\n",
        "      <td> 1.7</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2002</th>\n",
        "      <td> 2.9</td>\n",
        "      <td> 3.6</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 61,
       "text": [
        "      Nevada  Ohio\n",
        "2000     NaN   1.5\n",
        "2001     2.4   1.7\n",
        "2002     2.9   3.6"
       ]
      }
     ],
     "prompt_number": 61
    },
    {
     "cell_type": "heading",
     "level": 5,
     "metadata": {},
     "source": [
      "transpose"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "frame3.T"
     ],
     "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>2000</th>\n",
        "      <th>2001</th>\n",
        "      <th>2002</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>Nevada</th>\n",
        "      <td> NaN</td>\n",
        "      <td> 2.4</td>\n",
        "      <td> 2.9</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>Ohio</th>\n",
        "      <td> 1.5</td>\n",
        "      <td> 1.7</td>\n",
        "      <td> 3.6</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 62,
       "text": [
        "        2000  2001  2002\n",
        "Nevada   NaN   2.4   2.9\n",
        "Ohio     1.5   1.7   3.6"
       ]
      }
     ],
     "prompt_number": 62
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "Note that the keys in the inner dicts are unioned and sorted to form the index in the resul. This is not true if an explicit index is specified."
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "DataFrame(pop, index=[2001, 2002, 2003])"
     ],
     "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>Nevada</th>\n",
        "      <th>Ohio</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>2001</th>\n",
        "      <td> 2.4</td>\n",
        "      <td> 1.7</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2002</th>\n",
        "      <td> 2.9</td>\n",
        "      <td> 3.6</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2003</th>\n",
        "      <td> NaN</td>\n",
        "      <td> NaN</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 63,
       "text": [
        "      Nevada  Ohio\n",
        "2001     2.4   1.7\n",
        "2002     2.9   3.6\n",
        "2003     NaN   NaN"
       ]
      }
     ],
     "prompt_number": 63
    },
    {
     "cell_type": "heading",
     "level": 5,
     "metadata": {},
     "source": [
      "Dicts of series"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "pdata = {'Ohio':frame3['Ohio'][:-1],\n",
      "         'Nevada':frame3['Nevada'][:2]}"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 64
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "DataFrame(pdata)"
     ],
     "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>Nevada</th>\n",
        "      <th>Ohio</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>2000</th>\n",
        "      <td> NaN</td>\n",
        "      <td> 1.5</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2001</th>\n",
        "      <td> 2.4</td>\n",
        "      <td> 1.7</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 65,
       "text": [
        "      Nevada  Ohio\n",
        "2000     NaN   1.5\n",
        "2001     2.4   1.7"
       ]
      }
     ],
     "prompt_number": 65
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "frame3.index.name='year'"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 66
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "frame3.columns.name = 'state'"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 67
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "frame3"
     ],
     "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>state</th>\n",
        "      <th>Nevada</th>\n",
        "      <th>Ohio</th>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>year</th>\n",
        "      <th></th>\n",
        "      <th></th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>2000</th>\n",
        "      <td> NaN</td>\n",
        "      <td> 1.5</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2001</th>\n",
        "      <td> 2.4</td>\n",
        "      <td> 1.7</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2002</th>\n",
        "      <td> 2.9</td>\n",
        "      <td> 3.6</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 68,
       "text": [
        "state  Nevada  Ohio\n",
        "year               \n",
        "2000      NaN   1.5\n",
        "2001      2.4   1.7\n",
        "2002      2.9   3.6"
       ]
      }
     ],
     "prompt_number": 68
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "frame3.values"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 69,
       "text": [
        "array([[ nan,  1.5],\n",
        "       [ 2.4,  1.7],\n",
        "       [ 2.9,  3.6]])"
       ]
      }
     ],
     "prompt_number": 69
    },
    {
     "cell_type": "heading",
     "level": 5,
     "metadata": {},
     "source": [
      "different types of columns"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "frame2.values"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 70,
       "text": [
        "array([[2000, 'Ohio', 1.5, nan],\n",
        "       [2001, 'Ohio', 1.7, 1.2],\n",
        "       [2002, 'Ohio', 3.6, nan],\n",
        "       [2001, 'Nevada', 2.4, 1.5],\n",
        "       [2002, 'Nevada', 2.9, -1.7]], dtype=object)"
       ]
      }
     ],
     "prompt_number": 70
    },
    {
     "cell_type": "heading",
     "level": 2,
     "metadata": {},
     "source": [
      "Index Objects"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "obj = Series(range(3), index=['a','b','c'])"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 71
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "index = obj.index"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 73
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "index[1:]"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 74,
       "text": [
        "Index([u'b', u'c'], dtype='object')"
       ]
      }
     ],
     "prompt_number": 74
    },
    {
     "cell_type": "heading",
     "level": 5,
     "metadata": {},
     "source": [
      "immutable"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "index[1]='d'"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "ename": "TypeError",
       "evalue": "'<class 'pandas.core.index.Index'>' does not support mutable operations.",
       "output_type": "pyerr",
       "traceback": [
        "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m\n\u001b[0;31mTypeError\u001b[0m                                 Traceback (most recent call last)",
        "\u001b[0;32m<ipython-input-75-d3f90986bdb1>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m()\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0mindex\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;36m1\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m'd'\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
        "\u001b[0;32m/Users/sergulaydore/anaconda/lib/python2.7/site-packages/pandas/core/base.pyc\u001b[0m in \u001b[0;36m_disabled\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m    180\u001b[0m         \u001b[0;34m\"\"\"This method will not function because object is immutable.\"\"\"\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    181\u001b[0m         raise TypeError(\"'%s' does not support mutable operations.\" %\n\u001b[0;32m--> 182\u001b[0;31m                         self.__class__)\n\u001b[0m\u001b[1;32m    183\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    184\u001b[0m     \u001b[0m__setitem__\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0m__setslice__\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0m__delitem__\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0m__delslice__\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0m_disabled\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
        "\u001b[0;31mTypeError\u001b[0m: '<class 'pandas.core.index.Index'>' does not support mutable operations."
       ]
      }
     ],
     "prompt_number": 75
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "index = pd.Index(np.arange(3))"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 76
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "obj2 = Series([1.5,-2.5,0], index=index)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 77
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "obj2.index is index"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 78,
       "text": [
        "True"
       ]
      }
     ],
     "prompt_number": 78
    },
    {
     "cell_type": "heading",
     "level": 5,
     "metadata": {},
     "source": [
      "Index objects are sets"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "frame3"
     ],
     "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>state</th>\n",
        "      <th>Nevada</th>\n",
        "      <th>Ohio</th>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>year</th>\n",
        "      <th></th>\n",
        "      <th></th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>2000</th>\n",
        "      <td> NaN</td>\n",
        "      <td> 1.5</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2001</th>\n",
        "      <td> 2.4</td>\n",
        "      <td> 1.7</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2002</th>\n",
        "      <td> 2.9</td>\n",
        "      <td> 3.6</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 79,
       "text": [
        "state  Nevada  Ohio\n",
        "year               \n",
        "2000      NaN   1.5\n",
        "2001      2.4   1.7\n",
        "2002      2.9   3.6"
       ]
      }
     ],
     "prompt_number": 79
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "'Ohio' in frame3"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 80,
       "text": [
        "True"
       ]
      }
     ],
     "prompt_number": 80
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "2003 in frame3.index"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 81,
       "text": [
        "False"
       ]
      }
     ],
     "prompt_number": 81
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "frame3.index-frame2.index"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 82,
       "text": [
        "Int64Index([2000, 2001, 2002], dtype='int64')"
       ]
      }
     ],
     "prompt_number": 82
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "frame3.index.diff(frame2.index)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 85,
       "text": [
        "Int64Index([2000, 2001, 2002], dtype='int64')"
       ]
      }
     ],
     "prompt_number": 85
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "Index methods: append, diff, intersection, union, isin, delete, drop, insert, is_monotonic, is_unique, uniuq"
     ]
    },
    {
     "cell_type": "heading",
     "level": 2,
     "metadata": {},
     "source": [
      "Essential Functionality"
     ]
    },
    {
     "cell_type": "heading",
     "level": 2,
     "metadata": {},
     "source": [
      "Reindexing"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "obj = Series([4.5,7.2,-5.3,3.6], index=['d','b','a','c'])"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 86
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "obj"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 87,
       "text": [
        "d    4.5\n",
        "b    7.2\n",
        "a   -5.3\n",
        "c    3.6\n",
        "dtype: float64"
       ]
      }
     ],
     "prompt_number": 87
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "obj2 = obj.reindex(['a','b','c','d','e'])"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 88
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "obj2"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 89,
       "text": [
        "a   -5.3\n",
        "b    7.2\n",
        "c    3.6\n",
        "d    4.5\n",
        "e    NaN\n",
        "dtype: float64"
       ]
      }
     ],
     "prompt_number": 89
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "obj.reindex(['a','b','c','d','e'], fill_value=0)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 90,
       "text": [
        "a   -5.3\n",
        "b    7.2\n",
        "c    3.6\n",
        "d    4.5\n",
        "e    0.0\n",
        "dtype: float64"
       ]
      }
     ],
     "prompt_number": 90
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "obj"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 91,
       "text": [
        "d    4.5\n",
        "b    7.2\n",
        "a   -5.3\n",
        "c    3.6\n",
        "dtype: float64"
       ]
      }
     ],
     "prompt_number": 91
    },
    {
     "cell_type": "heading",
     "level": 5,
     "metadata": {},
     "source": [
      "filling of values"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "obj3 = Series(['blue','purple','yellow'], index=[0,2,4])"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 92
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "obj3.reindex(range(6))"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 93,
       "text": [
        "0      blue\n",
        "1       NaN\n",
        "2    purple\n",
        "3       NaN\n",
        "4    yellow\n",
        "5       NaN\n",
        "dtype: object"
       ]
      }
     ],
     "prompt_number": 93
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "obj3.reindex(range(6),method='ffill') # forward fills the values"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 95,
       "text": [
        "0      blue\n",
        "1      blue\n",
        "2    purple\n",
        "3    purple\n",
        "4    yellow\n",
        "5    yellow\n",
        "dtype: object"
       ]
      }
     ],
     "prompt_number": 95
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "available method options: ffill or pad, bfill or backfill"
     ]
    },
    {
     "cell_type": "heading",
     "level": 5,
     "metadata": {},
     "source": [
      "reindexing columns"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "frame = DataFrame(np.arange(9).reshape(3,3), index = ['a','c','d'],\n",
      "                  columns=['Ohio','Texas','California'])"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 96
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "frame"
     ],
     "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>Ohio</th>\n",
        "      <th>Texas</th>\n",
        "      <th>California</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>a</th>\n",
        "      <td> 0</td>\n",
        "      <td> 1</td>\n",
        "      <td> 2</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>c</th>\n",
        "      <td> 3</td>\n",
        "      <td> 4</td>\n",
        "      <td> 5</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>d</th>\n",
        "      <td> 6</td>\n",
        "      <td> 7</td>\n",
        "      <td> 8</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 97,
       "text": [
        "   Ohio  Texas  California\n",
        "a     0      1           2\n",
        "c     3      4           5\n",
        "d     6      7           8"
       ]
      }
     ],
     "prompt_number": 97
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "frame2 = frame.reindex(['a','b','c','d'])"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 98
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "frame2"
     ],
     "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>Ohio</th>\n",
        "      <th>Texas</th>\n",
        "      <th>California</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>a</th>\n",
        "      <td>  0</td>\n",
        "      <td>  1</td>\n",
        "      <td>  2</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>b</th>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>c</th>\n",
        "      <td>  3</td>\n",
        "      <td>  4</td>\n",
        "      <td>  5</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>d</th>\n",
        "      <td>  6</td>\n",
        "      <td>  7</td>\n",
        "      <td>  8</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 99,
       "text": [
        "   Ohio  Texas  California\n",
        "a     0      1           2\n",
        "b   NaN    NaN         NaN\n",
        "c     3      4           5\n",
        "d     6      7           8"
       ]
      }
     ],
     "prompt_number": 99
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "states = ['Texas','Utah','California']"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 100
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "frame.reindex(columns=states)"
     ],
     "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>Texas</th>\n",
        "      <th>Utah</th>\n",
        "      <th>California</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>a</th>\n",
        "      <td> 1</td>\n",
        "      <td>NaN</td>\n",
        "      <td> 2</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>c</th>\n",
        "      <td> 4</td>\n",
        "      <td>NaN</td>\n",
        "      <td> 5</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>d</th>\n",
        "      <td> 7</td>\n",
        "      <td>NaN</td>\n",
        "      <td> 8</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 101,
       "text": [
        "   Texas  Utah  California\n",
        "a      1   NaN           2\n",
        "c      4   NaN           5\n",
        "d      7   NaN           8"
       ]
      }
     ],
     "prompt_number": 101
    },
    {
     "cell_type": "heading",
     "level": 5,
     "metadata": {},
     "source": [
      "Both columns and rows can be reindexed"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "frame.reindex(index=['a','b','c','d'], method='ffill',\n",
      "              columns=states)"
     ],
     "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>Texas</th>\n",
        "      <th>Utah</th>\n",
        "      <th>California</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>a</th>\n",
        "      <td> 1</td>\n",
        "      <td>NaN</td>\n",
        "      <td> 2</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>b</th>\n",
        "      <td> 1</td>\n",
        "      <td>NaN</td>\n",
        "      <td> 2</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>c</th>\n",
        "      <td> 4</td>\n",
        "      <td>NaN</td>\n",
        "      <td> 5</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>d</th>\n",
        "      <td> 7</td>\n",
        "      <td>NaN</td>\n",
        "      <td> 8</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 102,
       "text": [
        "   Texas  Utah  California\n",
        "a      1   NaN           2\n",
        "b      1   NaN           2\n",
        "c      4   NaN           5\n",
        "d      7   NaN           8"
       ]
      }
     ],
     "prompt_number": 102
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "frame"
     ],
     "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>Ohio</th>\n",
        "      <th>Texas</th>\n",
        "      <th>California</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>a</th>\n",
        "      <td> 0</td>\n",
        "      <td> 1</td>\n",
        "      <td> 2</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>c</th>\n",
        "      <td> 3</td>\n",
        "      <td> 4</td>\n",
        "      <td> 5</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>d</th>\n",
        "      <td> 6</td>\n",
        "      <td> 7</td>\n",
        "      <td> 8</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 103,
       "text": [
        "   Ohio  Texas  California\n",
        "a     0      1           2\n",
        "c     3      4           5\n",
        "d     6      7           8"
       ]
      }
     ],
     "prompt_number": 103
    },
    {
     "cell_type": "heading",
     "level": 5,
     "metadata": {},
     "source": [
      "reindexing with ix"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "frame.ix[['a','b','c','d'], states]"
     ],
     "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>Texas</th>\n",
        "      <th>Utah</th>\n",
        "      <th>California</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>a</th>\n",
        "      <td>  1</td>\n",
        "      <td>NaN</td>\n",
        "      <td>  2</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>b</th>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>c</th>\n",
        "      <td>  4</td>\n",
        "      <td>NaN</td>\n",
        "      <td>  5</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>d</th>\n",
        "      <td>  7</td>\n",
        "      <td>NaN</td>\n",
        "      <td>  8</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 105,
       "text": [
        "   Texas  Utah  California\n",
        "a      1   NaN           2\n",
        "b    NaN   NaN         NaN\n",
        "c      4   NaN           5\n",
        "d      7   NaN           8"
       ]
      }
     ],
     "prompt_number": 105
    },
    {
     "cell_type": "heading",
     "level": 5,
     "metadata": {},
     "source": [
      "Dropping entries from an axis"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "obj = Series(np.arange(5.), index = ['a','b','c','d','e'])"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 106
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "obj"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 107,
       "text": [
        "a    0\n",
        "b    1\n",
        "c    2\n",
        "d    3\n",
        "e    4\n",
        "dtype: float64"
       ]
      }
     ],
     "prompt_number": 107
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "new_obj = obj.drop('c')"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 109
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "new_obj"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 110,
       "text": [
        "a    0\n",
        "b    1\n",
        "d    3\n",
        "e    4\n",
        "dtype: float64"
       ]
      }
     ],
     "prompt_number": 110
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "obj.drop(['d','c'])"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 111,
       "text": [
        "a    0\n",
        "b    1\n",
        "e    4\n",
        "dtype: float64"
       ]
      }
     ],
     "prompt_number": 111
    },
    {
     "cell_type": "heading",
     "level": 5,
     "metadata": {},
     "source": [
      "Index values can be deleted from either axis"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "data = DataFrame(np.arange(16).reshape((4,4)),\n",
      "                 index = ['Ohio','Colorado','Utah','New York'],\n",
      "                 columns = ['one','two','three','four'])"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 112
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "data"
     ],
     "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>one</th>\n",
        "      <th>two</th>\n",
        "      <th>three</th>\n",
        "      <th>four</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>Ohio</th>\n",
        "      <td>  0</td>\n",
        "      <td>  1</td>\n",
        "      <td>  2</td>\n",
        "      <td>  3</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>Colorado</th>\n",
        "      <td>  4</td>\n",
        "      <td>  5</td>\n",
        "      <td>  6</td>\n",
        "      <td>  7</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>Utah</th>\n",
        "      <td>  8</td>\n",
        "      <td>  9</td>\n",
        "      <td> 10</td>\n",
        "      <td> 11</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>New York</th>\n",
        "      <td> 12</td>\n",
        "      <td> 13</td>\n",
        "      <td> 14</td>\n",
        "      <td> 15</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 113,
       "text": [
        "          one  two  three  four\n",
        "Ohio        0    1      2     3\n",
        "Colorado    4    5      6     7\n",
        "Utah        8    9     10    11\n",
        "New York   12   13     14    15"
       ]
      }
     ],
     "prompt_number": 113
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "data.drop(['Colorado','Ohio'])"
     ],
     "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>one</th>\n",
        "      <th>two</th>\n",
        "      <th>three</th>\n",
        "      <th>four</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>Utah</th>\n",
        "      <td>  8</td>\n",
        "      <td>  9</td>\n",
        "      <td> 10</td>\n",
        "      <td> 11</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>New York</th>\n",
        "      <td> 12</td>\n",
        "      <td> 13</td>\n",
        "      <td> 14</td>\n",
        "      <td> 15</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 114,
       "text": [
        "          one  two  three  four\n",
        "Utah        8    9     10    11\n",
        "New York   12   13     14    15"
       ]
      }
     ],
     "prompt_number": 114
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "data.drop('two', axis=1)"
     ],
     "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>one</th>\n",
        "      <th>three</th>\n",
        "      <th>four</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>Ohio</th>\n",
        "      <td>  0</td>\n",
        "      <td>  2</td>\n",
        "      <td>  3</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>Colorado</th>\n",
        "      <td>  4</td>\n",
        "      <td>  6</td>\n",
        "      <td>  7</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>Utah</th>\n",
        "      <td>  8</td>\n",
        "      <td> 10</td>\n",
        "      <td> 11</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>New York</th>\n",
        "      <td> 12</td>\n",
        "      <td> 14</td>\n",
        "      <td> 15</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 115,
       "text": [
        "          one  three  four\n",
        "Ohio        0      2     3\n",
        "Colorado    4      6     7\n",
        "Utah        8     10    11\n",
        "New York   12     14    15"
       ]
      }
     ],
     "prompt_number": 115
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "data.drop(['two','four'], axis=1)"
     ],
     "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>one</th>\n",
        "      <th>three</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>Ohio</th>\n",
        "      <td>  0</td>\n",
        "      <td>  2</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>Colorado</th>\n",
        "      <td>  4</td>\n",
        "      <td>  6</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>Utah</th>\n",
        "      <td>  8</td>\n",
        "      <td> 10</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>New York</th>\n",
        "      <td> 12</td>\n",
        "      <td> 14</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 116,
       "text": [
        "          one  three\n",
        "Ohio        0      2\n",
        "Colorado    4      6\n",
        "Utah        8     10\n",
        "New York   12     14"
       ]
      }
     ],
     "prompt_number": 116
    },
    {
     "cell_type": "heading",
     "level": 2,
     "metadata": {},
     "source": [
      "Indexing, selection and filtering"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "obj = Series(np.arange(4.), index=['a','b','c','d'])"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 117
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "obj['b']"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 118,
       "text": [
        "1.0"
       ]
      }
     ],
     "prompt_number": 118
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "obj[2:4]"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 119,
       "text": [
        "c    2\n",
        "d    3\n",
        "dtype: float64"
       ]
      }
     ],
     "prompt_number": 119
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "obj[['b','a','d']]"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 120,
       "text": [
        "b    1\n",
        "a    0\n",
        "d    3\n",
        "dtype: float64"
       ]
      }
     ],
     "prompt_number": 120
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "obj[[1,3]]"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 121,
       "text": [
        "b    1\n",
        "d    3\n",
        "dtype: float64"
       ]
      }
     ],
     "prompt_number": 121
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "obj[obj<2]"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 122,
       "text": [
        "a    0\n",
        "b    1\n",
        "dtype: float64"
       ]
      }
     ],
     "prompt_number": 122
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "obj['b':'c']"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 123,
       "text": [
        "b    1\n",
        "c    2\n",
        "dtype: float64"
       ]
      }
     ],
     "prompt_number": 123
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "obj['b':'c']=5"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 124
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "obj"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 125,
       "text": [
        "a    0\n",
        "b    5\n",
        "c    5\n",
        "d    3\n",
        "dtype: float64"
       ]
      }
     ],
     "prompt_number": 125
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "data=DataFrame(np.arange(16).reshape((4,4)),\n",
      "               index=['Ohio','Colorado','Utah','New York'],\n",
      "               columns=['one','two','three','four'])"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 126
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "data"
     ],
     "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>one</th>\n",
        "      <th>two</th>\n",
        "      <th>three</th>\n",
        "      <th>four</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>Ohio</th>\n",
        "      <td>  0</td>\n",
        "      <td>  1</td>\n",
        "      <td>  2</td>\n",
        "      <td>  3</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>Colorado</th>\n",
        "      <td>  4</td>\n",
        "      <td>  5</td>\n",
        "      <td>  6</td>\n",
        "      <td>  7</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>Utah</th>\n",
        "      <td>  8</td>\n",
        "      <td>  9</td>\n",
        "      <td> 10</td>\n",
        "      <td> 11</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>New York</th>\n",
        "      <td> 12</td>\n",
        "      <td> 13</td>\n",
        "      <td> 14</td>\n",
        "      <td> 15</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 127,
       "text": [
        "          one  two  three  four\n",
        "Ohio        0    1      2     3\n",
        "Colorado    4    5      6     7\n",
        "Utah        8    9     10    11\n",
        "New York   12   13     14    15"
       ]
      }
     ],
     "prompt_number": 127
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "data['two']"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 128,
       "text": [
        "Ohio         1\n",
        "Colorado     5\n",
        "Utah         9\n",
        "New York    13\n",
        "Name: two, dtype: int64"
       ]
      }
     ],
     "prompt_number": 128
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "data[['three','one']]"
     ],
     "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>three</th>\n",
        "      <th>one</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>Ohio</th>\n",
        "      <td>  2</td>\n",
        "      <td>  0</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>Colorado</th>\n",
        "      <td>  6</td>\n",
        "      <td>  4</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>Utah</th>\n",
        "      <td> 10</td>\n",
        "      <td>  8</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>New York</th>\n",
        "      <td> 14</td>\n",
        "      <td> 12</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 129,
       "text": [
        "          three  one\n",
        "Ohio          2    0\n",
        "Colorado      6    4\n",
        "Utah         10    8\n",
        "New York     14   12"
       ]
      }
     ],
     "prompt_number": 129
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "data[:2]"
     ],
     "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>one</th>\n",
        "      <th>two</th>\n",
        "      <th>three</th>\n",
        "      <th>four</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>Ohio</th>\n",
        "      <td> 0</td>\n",
        "      <td> 1</td>\n",
        "      <td> 2</td>\n",
        "      <td> 3</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>Colorado</th>\n",
        "      <td> 4</td>\n",
        "      <td> 5</td>\n",
        "      <td> 6</td>\n",
        "      <td> 7</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 130,
       "text": [
        "          one  two  three  four\n",
        "Ohio        0    1      2     3\n",
        "Colorado    4    5      6     7"
       ]
      }
     ],
     "prompt_number": 130
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "data[data['three']>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>one</th>\n",
        "      <th>two</th>\n",
        "      <th>three</th>\n",
        "      <th>four</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>Colorado</th>\n",
        "      <td>  4</td>\n",
        "      <td>  5</td>\n",
        "      <td>  6</td>\n",
        "      <td>  7</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>Utah</th>\n",
        "      <td>  8</td>\n",
        "      <td>  9</td>\n",
        "      <td> 10</td>\n",
        "      <td> 11</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>New York</th>\n",
        "      <td> 12</td>\n",
        "      <td> 13</td>\n",
        "      <td> 14</td>\n",
        "      <td> 15</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 131,
       "text": [
        "          one  two  three  four\n",
        "Colorado    4    5      6     7\n",
        "Utah        8    9     10    11\n",
        "New York   12   13     14    15"
       ]
      }
     ],
     "prompt_number": 131
    },
    {
     "cell_type": "heading",
     "level": 5,
     "metadata": {},
     "source": [
      "indexing with boolean DataFrame"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "data<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>one</th>\n",
        "      <th>two</th>\n",
        "      <th>three</th>\n",
        "      <th>four</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>Ohio</th>\n",
        "      <td>  True</td>\n",
        "      <td>  True</td>\n",
        "      <td>  True</td>\n",
        "      <td>  True</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>Colorado</th>\n",
        "      <td>  True</td>\n",
        "      <td> False</td>\n",
        "      <td> False</td>\n",
        "      <td> False</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>Utah</th>\n",
        "      <td> False</td>\n",
        "      <td> False</td>\n",
        "      <td> False</td>\n",
        "      <td> False</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>New York</th>\n",
        "      <td> False</td>\n",
        "      <td> False</td>\n",
        "      <td> False</td>\n",
        "      <td> False</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 132,
       "text": [
        "            one    two  three   four\n",
        "Ohio       True   True   True   True\n",
        "Colorado   True  False  False  False\n",
        "Utah      False  False  False  False\n",
        "New York  False  False  False  False"
       ]
      }
     ],
     "prompt_number": 132
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "data[data<5]=0"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 133
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "data"
     ],
     "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>one</th>\n",
        "      <th>two</th>\n",
        "      <th>three</th>\n",
        "      <th>four</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>Ohio</th>\n",
        "      <td>  0</td>\n",
        "      <td>  0</td>\n",
        "      <td>  0</td>\n",
        "      <td>  0</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>Colorado</th>\n",
        "      <td>  0</td>\n",
        "      <td>  5</td>\n",
        "      <td>  6</td>\n",
        "      <td>  7</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>Utah</th>\n",
        "      <td>  8</td>\n",
        "      <td>  9</td>\n",
        "      <td> 10</td>\n",
        "      <td> 11</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>New York</th>\n",
        "      <td> 12</td>\n",
        "      <td> 13</td>\n",
        "      <td> 14</td>\n",
        "      <td> 15</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 134,
       "text": [
        "          one  two  three  four\n",
        "Ohio        0    0      0     0\n",
        "Colorado    0    5      6     7\n",
        "Utah        8    9     10    11\n",
        "New York   12   13     14    15"
       ]
      }
     ],
     "prompt_number": 134
    },
    {
     "cell_type": "heading",
     "level": 5,
     "metadata": {},
     "source": [
      "label-indexing on the rows (this is a less verbose way to do reindexing)"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "data.ix['Colorado',['two','three']]"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 135,
       "text": [
        "two      5\n",
        "three    6\n",
        "Name: Colorado, dtype: int64"
       ]
      }
     ],
     "prompt_number": 135
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "data.ix[['Colorado','Utah'],[3,0,1]]"
     ],
     "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>four</th>\n",
        "      <th>one</th>\n",
        "      <th>two</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>Colorado</th>\n",
        "      <td>  7</td>\n",
        "      <td> 0</td>\n",
        "      <td> 5</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>Utah</th>\n",
        "      <td> 11</td>\n",
        "      <td> 8</td>\n",
        "      <td> 9</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 136,
       "text": [
        "          four  one  two\n",
        "Colorado     7    0    5\n",
        "Utah        11    8    9"
       ]
      }
     ],
     "prompt_number": 136
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "data.ix[2]"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 137,
       "text": [
        "one       8\n",
        "two       9\n",
        "three    10\n",
        "four     11\n",
        "Name: Utah, dtype: int64"
       ]
      }
     ],
     "prompt_number": 137
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "data.ix[:'Utah','two']"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 138,
       "text": [
        "Ohio        0\n",
        "Colorado    5\n",
        "Utah        9\n",
        "Name: two, dtype: int64"
       ]
      }
     ],
     "prompt_number": 138
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "data.ix[data.three>5,:3]"
     ],
     "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>one</th>\n",
        "      <th>two</th>\n",
        "      <th>three</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>Colorado</th>\n",
        "      <td>  0</td>\n",
        "      <td>  5</td>\n",
        "      <td>  6</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>Utah</th>\n",
        "      <td>  8</td>\n",
        "      <td>  9</td>\n",
        "      <td> 10</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>New York</th>\n",
        "      <td> 12</td>\n",
        "      <td> 13</td>\n",
        "      <td> 14</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 140,
       "text": [
        "          one  two  three\n",
        "Colorado    0    5      6\n",
        "Utah        8    9     10\n",
        "New York   12   13     14"
       ]
      }
     ],
     "prompt_number": 140
    },
    {
     "cell_type": "heading",
     "level": 2,
     "metadata": {},
     "source": [
      "Arithmetic and data alignment"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "s1 = Series([7.3,-2.5,3.4,1.5], index=['a','c','d','e'])"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 141
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "s2 = Series([-2.1,3.6,-1.5,4,3.1], index=['a','c','e','f','g'])"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 142
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "s1"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 143,
       "text": [
        "a    7.3\n",
        "c   -2.5\n",
        "d    3.4\n",
        "e    1.5\n",
        "dtype: float64"
       ]
      }
     ],
     "prompt_number": 143
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "s2"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 144,
       "text": [
        "a   -2.1\n",
        "c    3.6\n",
        "e   -1.5\n",
        "f    4.0\n",
        "g    3.1\n",
        "dtype: float64"
       ]
      }
     ],
     "prompt_number": 144
    },
    {
     "cell_type": "heading",
     "level": 5,
     "metadata": {},
     "source": [
      "adding these together yields"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "s1+s2"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 145,
       "text": [
        "a    5.2\n",
        "c    1.1\n",
        "d    NaN\n",
        "e    0.0\n",
        "f    NaN\n",
        "g    NaN\n",
        "dtype: float64"
       ]
      }
     ],
     "prompt_number": 145
    },
    {
     "cell_type": "heading",
     "level": 5,
     "metadata": {},
     "source": [
      "aligment is performed on both the rows and the columns"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "df1 = DataFrame(np.arange(9.).reshape((3,3)),\n",
      "                columns = list('bcd'),\n",
      "                index=['Ohio','Texas','Colorado'])"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 146
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "df2 = DataFrame(np.arange(12.).reshape((4,3)),\n",
      "               columns = list('bde'),\n",
      "               index=['Utah','Ohio','Texas','Oregon'])"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 150
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "df1"
     ],
     "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>b</th>\n",
        "      <th>c</th>\n",
        "      <th>d</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>Ohio</th>\n",
        "      <td> 0</td>\n",
        "      <td> 1</td>\n",
        "      <td> 2</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>Texas</th>\n",
        "      <td> 3</td>\n",
        "      <td> 4</td>\n",
        "      <td> 5</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>Colorado</th>\n",
        "      <td> 6</td>\n",
        "      <td> 7</td>\n",
        "      <td> 8</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 148,
       "text": [
        "          b  c  d\n",
        "Ohio      0  1  2\n",
        "Texas     3  4  5\n",
        "Colorado  6  7  8"
       ]
      }
     ],
     "prompt_number": 148
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "df2"
     ],
     "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>b</th>\n",
        "      <th>d</th>\n",
        "      <th>e</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>Utah</th>\n",
        "      <td> 0</td>\n",
        "      <td>  1</td>\n",
        "      <td>  2</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>Ohio</th>\n",
        "      <td> 3</td>\n",
        "      <td>  4</td>\n",
        "      <td>  5</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>Texas</th>\n",
        "      <td> 6</td>\n",
        "      <td>  7</td>\n",
        "      <td>  8</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>Oregon</th>\n",
        "      <td> 9</td>\n",
        "      <td> 10</td>\n",
        "      <td> 11</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 151,
       "text": [
        "        b   d   e\n",
        "Utah    0   1   2\n",
        "Ohio    3   4   5\n",
        "Texas   6   7   8\n",
        "Oregon  9  10  11"
       ]
      }
     ],
     "prompt_number": 151
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "df1 + df2"
     ],
     "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>b</th>\n",
        "      <th>c</th>\n",
        "      <th>d</th>\n",
        "      <th>e</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>Colorado</th>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>Ohio</th>\n",
        "      <td>  3</td>\n",
        "      <td>NaN</td>\n",
        "      <td>  6</td>\n",
        "      <td>NaN</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>Oregon</th>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>Texas</th>\n",
        "      <td>  9</td>\n",
        "      <td>NaN</td>\n",
        "      <td> 12</td>\n",
        "      <td>NaN</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>Utah</th>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 152,
       "text": [
        "           b   c   d   e\n",
        "Colorado NaN NaN NaN NaN\n",
        "Ohio       3 NaN   6 NaN\n",
        "Oregon   NaN NaN NaN NaN\n",
        "Texas      9 NaN  12 NaN\n",
        "Utah     NaN NaN NaN NaN"
       ]
      }
     ],
     "prompt_number": 152
    },
    {
     "cell_type": "heading",
     "level": 5,
     "metadata": {},
     "source": [
      "Arithmetci operations with fill values"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "df1 = DataFrame(np.arange(12.).reshape((3,4)), columns = list('abcd'))"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 153
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "df2 = DataFrame(np.arange(20.).reshape((4,5)), columns = list('abcde'))"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 154
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "df1"
     ],
     "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>a</th>\n",
        "      <th>b</th>\n",
        "      <th>c</th>\n",
        "      <th>d</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>0</th>\n",
        "      <td> 0</td>\n",
        "      <td> 1</td>\n",
        "      <td>  2</td>\n",
        "      <td>  3</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>1</th>\n",
        "      <td> 4</td>\n",
        "      <td> 5</td>\n",
        "      <td>  6</td>\n",
        "      <td>  7</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2</th>\n",
        "      <td> 8</td>\n",
        "      <td> 9</td>\n",
        "      <td> 10</td>\n",
        "      <td> 11</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 155,
       "text": [
        "   a  b   c   d\n",
        "0  0  1   2   3\n",
        "1  4  5   6   7\n",
        "2  8  9  10  11"
       ]
      }
     ],
     "prompt_number": 155
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "df2"
     ],
     "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>a</th>\n",
        "      <th>b</th>\n",
        "      <th>c</th>\n",
        "      <th>d</th>\n",
        "      <th>e</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>0</th>\n",
        "      <td>  0</td>\n",
        "      <td>  1</td>\n",
        "      <td>  2</td>\n",
        "      <td>  3</td>\n",
        "      <td>  4</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>1</th>\n",
        "      <td>  5</td>\n",
        "      <td>  6</td>\n",
        "      <td>  7</td>\n",
        "      <td>  8</td>\n",
        "      <td>  9</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2</th>\n",
        "      <td> 10</td>\n",
        "      <td> 11</td>\n",
        "      <td> 12</td>\n",
        "      <td> 13</td>\n",
        "      <td> 14</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>3</th>\n",
        "      <td> 15</td>\n",
        "      <td> 16</td>\n",
        "      <td> 17</td>\n",
        "      <td> 18</td>\n",
        "      <td> 19</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 156,
       "text": [
        "    a   b   c   d   e\n",
        "0   0   1   2   3   4\n",
        "1   5   6   7   8   9\n",
        "2  10  11  12  13  14\n",
        "3  15  16  17  18  19"
       ]
      }
     ],
     "prompt_number": 156
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "df1 + df2"
     ],
     "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>a</th>\n",
        "      <th>b</th>\n",
        "      <th>c</th>\n",
        "      <th>d</th>\n",
        "      <th>e</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>0</th>\n",
        "      <td>  0</td>\n",
        "      <td>  2</td>\n",
        "      <td>  4</td>\n",
        "      <td>  6</td>\n",
        "      <td>NaN</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>1</th>\n",
        "      <td>  9</td>\n",
        "      <td> 11</td>\n",
        "      <td> 13</td>\n",
        "      <td> 15</td>\n",
        "      <td>NaN</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2</th>\n",
        "      <td> 18</td>\n",
        "      <td> 20</td>\n",
        "      <td> 22</td>\n",
        "      <td> 24</td>\n",
        "      <td>NaN</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>3</th>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 157,
       "text": [
        "    a   b   c   d   e\n",
        "0   0   2   4   6 NaN\n",
        "1   9  11  13  15 NaN\n",
        "2  18  20  22  24 NaN\n",
        "3 NaN NaN NaN NaN NaN"
       ]
      }
     ],
     "prompt_number": 157
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "df1.add(df2, fill_value=0)"
     ],
     "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>a</th>\n",
        "      <th>b</th>\n",
        "      <th>c</th>\n",
        "      <th>d</th>\n",
        "      <th>e</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>0</th>\n",
        "      <td>  0</td>\n",
        "      <td>  2</td>\n",
        "      <td>  4</td>\n",
        "      <td>  6</td>\n",
        "      <td>  4</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>1</th>\n",
        "      <td>  9</td>\n",
        "      <td> 11</td>\n",
        "      <td> 13</td>\n",
        "      <td> 15</td>\n",
        "      <td>  9</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2</th>\n",
        "      <td> 18</td>\n",
        "      <td> 20</td>\n",
        "      <td> 22</td>\n",
        "      <td> 24</td>\n",
        "      <td> 14</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>3</th>\n",
        "      <td> 15</td>\n",
        "      <td> 16</td>\n",
        "      <td> 17</td>\n",
        "      <td> 18</td>\n",
        "      <td> 19</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 158,
       "text": [
        "    a   b   c   d   e\n",
        "0   0   2   4   6   4\n",
        "1   9  11  13  15   9\n",
        "2  18  20  22  24  14\n",
        "3  15  16  17  18  19"
       ]
      }
     ],
     "prompt_number": 158
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "df1.reindex(columns=df2.columns, fill_value=0)"
     ],
     "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>a</th>\n",
        "      <th>b</th>\n",
        "      <th>c</th>\n",
        "      <th>d</th>\n",
        "      <th>e</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>0</th>\n",
        "      <td> 0</td>\n",
        "      <td> 1</td>\n",
        "      <td>  2</td>\n",
        "      <td>  3</td>\n",
        "      <td> 0</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>1</th>\n",
        "      <td> 4</td>\n",
        "      <td> 5</td>\n",
        "      <td>  6</td>\n",
        "      <td>  7</td>\n",
        "      <td> 0</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2</th>\n",
        "      <td> 8</td>\n",
        "      <td> 9</td>\n",
        "      <td> 10</td>\n",
        "      <td> 11</td>\n",
        "      <td> 0</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 159,
       "text": [
        "   a  b   c   d  e\n",
        "0  0  1   2   3  0\n",
        "1  4  5   6   7  0\n",
        "2  8  9  10  11  0"
       ]
      }
     ],
     "prompt_number": 159
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "aritmetic methods: add, sub, div, mul"
     ]
    },
    {
     "cell_type": "heading",
     "level": 5,
     "metadata": {},
     "source": [
      "Operations between DataFrame and Series"
     ]
    },
    {
     "cell_type": "heading",
     "level": 5,
     "metadata": {},
     "source": [
      "broadcasting"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "arr = np.arange(12.).reshape((3,4))"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 160
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "arr"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 161,
       "text": [
        "array([[  0.,   1.,   2.,   3.],\n",
        "       [  4.,   5.,   6.,   7.],\n",
        "       [  8.,   9.,  10.,  11.]])"
       ]
      }
     ],
     "prompt_number": 161
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "arr[0]"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 162,
       "text": [
        "array([ 0.,  1.,  2.,  3.])"
       ]
      }
     ],
     "prompt_number": 162
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "arr-arr[0]"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 163,
       "text": [
        "array([[ 0.,  0.,  0.,  0.],\n",
        "       [ 4.,  4.,  4.,  4.],\n",
        "       [ 8.,  8.,  8.,  8.]])"
       ]
      }
     ],
     "prompt_number": 163
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "frame = DataFrame(np.arange(12.).reshape((4,3)), columns=list('bde'),\n",
      "                  index=['Utah','Ohio','Texas','Oregon'])"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 164
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "frame"
     ],
     "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>b</th>\n",
        "      <th>d</th>\n",
        "      <th>e</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>Utah</th>\n",
        "      <td> 0</td>\n",
        "      <td>  1</td>\n",
        "      <td>  2</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>Ohio</th>\n",
        "      <td> 3</td>\n",
        "      <td>  4</td>\n",
        "      <td>  5</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>Texas</th>\n",
        "      <td> 6</td>\n",
        "      <td>  7</td>\n",
        "      <td>  8</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>Oregon</th>\n",
        "      <td> 9</td>\n",
        "      <td> 10</td>\n",
        "      <td> 11</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 165,
       "text": [
        "        b   d   e\n",
        "Utah    0   1   2\n",
        "Ohio    3   4   5\n",
        "Texas   6   7   8\n",
        "Oregon  9  10  11"
       ]
      }
     ],
     "prompt_number": 165
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "series =frame.ix[0]"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 166
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "series"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 167,
       "text": [
        "b    0\n",
        "d    1\n",
        "e    2\n",
        "Name: Utah, dtype: float64"
       ]
      }
     ],
     "prompt_number": 167
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "frame-series"
     ],
     "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>b</th>\n",
        "      <th>d</th>\n",
        "      <th>e</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>Utah</th>\n",
        "      <td> 0</td>\n",
        "      <td> 0</td>\n",
        "      <td> 0</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>Ohio</th>\n",
        "      <td> 3</td>\n",
        "      <td> 3</td>\n",
        "      <td> 3</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>Texas</th>\n",
        "      <td> 6</td>\n",
        "      <td> 6</td>\n",
        "      <td> 6</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>Oregon</th>\n",
        "      <td> 9</td>\n",
        "      <td> 9</td>\n",
        "      <td> 9</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 168,
       "text": [
        "        b  d  e\n",
        "Utah    0  0  0\n",
        "Ohio    3  3  3\n",
        "Texas   6  6  6\n",
        "Oregon  9  9  9"
       ]
      }
     ],
     "prompt_number": 168
    },
    {
     "cell_type": "heading",
     "level": 5,
     "metadata": {},
     "source": [
      "if an index value is not found"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "series2 = Series(range(3), index=['b','e','f'])"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 169
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "series2"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 170,
       "text": [
        "b    0\n",
        "e    1\n",
        "f    2\n",
        "dtype: int64"
       ]
      }
     ],
     "prompt_number": 170
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "frame + series2"
     ],
     "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>b</th>\n",
        "      <th>d</th>\n",
        "      <th>e</th>\n",
        "      <th>f</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>Utah</th>\n",
        "      <td> 0</td>\n",
        "      <td>NaN</td>\n",
        "      <td>  3</td>\n",
        "      <td>NaN</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>Ohio</th>\n",
        "      <td> 3</td>\n",
        "      <td>NaN</td>\n",
        "      <td>  6</td>\n",
        "      <td>NaN</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>Texas</th>\n",
        "      <td> 6</td>\n",
        "      <td>NaN</td>\n",
        "      <td>  9</td>\n",
        "      <td>NaN</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>Oregon</th>\n",
        "      <td> 9</td>\n",
        "      <td>NaN</td>\n",
        "      <td> 12</td>\n",
        "      <td>NaN</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 172,
       "text": [
        "        b   d   e   f\n",
        "Utah    0 NaN   3 NaN\n",
        "Ohio    3 NaN   6 NaN\n",
        "Texas   6 NaN   9 NaN\n",
        "Oregon  9 NaN  12 NaN"
       ]
      }
     ],
     "prompt_number": 172
    },
    {
     "cell_type": "heading",
     "level": 5,
     "metadata": {},
     "source": [
      "broadcast over the columns"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "series3 = frame['d']"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 174
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "frame"
     ],
     "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>b</th>\n",
        "      <th>d</th>\n",
        "      <th>e</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>Utah</th>\n",
        "      <td> 0</td>\n",
        "      <td>  1</td>\n",
        "      <td>  2</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>Ohio</th>\n",
        "      <td> 3</td>\n",
        "      <td>  4</td>\n",
        "      <td>  5</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>Texas</th>\n",
        "      <td> 6</td>\n",
        "      <td>  7</td>\n",
        "      <td>  8</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>Oregon</th>\n",
        "      <td> 9</td>\n",
        "      <td> 10</td>\n",
        "      <td> 11</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 175,
       "text": [
        "        b   d   e\n",
        "Utah    0   1   2\n",
        "Ohio    3   4   5\n",
        "Texas   6   7   8\n",
        "Oregon  9  10  11"
       ]
      }
     ],
     "prompt_number": 175
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "series3"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 176,
       "text": [
        "Utah       1\n",
        "Ohio       4\n",
        "Texas      7\n",
        "Oregon    10\n",
        "Name: d, dtype: float64"
       ]
      }
     ],
     "prompt_number": 176
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "frame.sub(series3, axis=0)"
     ],
     "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>b</th>\n",
        "      <th>d</th>\n",
        "      <th>e</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>Utah</th>\n",
        "      <td>-1</td>\n",
        "      <td> 0</td>\n",
        "      <td> 1</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>Ohio</th>\n",
        "      <td>-1</td>\n",
        "      <td> 0</td>\n",
        "      <td> 1</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>Texas</th>\n",
        "      <td>-1</td>\n",
        "      <td> 0</td>\n",
        "      <td> 1</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>Oregon</th>\n",
        "      <td>-1</td>\n",
        "      <td> 0</td>\n",
        "      <td> 1</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 179,
       "text": [
        "        b  d  e\n",
        "Utah   -1  0  1\n",
        "Ohio   -1  0  1\n",
        "Texas  -1  0  1\n",
        "Oregon -1  0  1"
       ]
      }
     ],
     "prompt_number": 179
    },
    {
     "cell_type": "heading",
     "level": 2,
     "metadata": {},
     "source": [
      "Function Application and Mapping"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "import numpy as np"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 5
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "frame = DataFrame(np.random.randn(4,3), columns=list('bde'),\n",
      "                  index=['Utah','Ohio','Texas','Oregon'])"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 6
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "frame"
     ],
     "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>b</th>\n",
        "      <th>d</th>\n",
        "      <th>e</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>Utah</th>\n",
        "      <td>-0.267451</td>\n",
        "      <td>-1.829889</td>\n",
        "      <td> 2.544224</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>Ohio</th>\n",
        "      <td> 1.116375</td>\n",
        "      <td>-0.270886</td>\n",
        "      <td> 1.086111</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>Texas</th>\n",
        "      <td> 0.390590</td>\n",
        "      <td>-0.339125</td>\n",
        "      <td> 0.341343</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>Oregon</th>\n",
        "      <td> 1.145794</td>\n",
        "      <td>-1.268138</td>\n",
        "      <td>-0.925395</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 7,
       "text": [
        "               b         d         e\n",
        "Utah   -0.267451 -1.829889  2.544224\n",
        "Ohio    1.116375 -0.270886  1.086111\n",
        "Texas   0.390590 -0.339125  0.341343\n",
        "Oregon  1.145794 -1.268138 -0.925395"
       ]
      }
     ],
     "prompt_number": 7
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "np.abs(frame)"
     ],
     "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>b</th>\n",
        "      <th>d</th>\n",
        "      <th>e</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>Utah</th>\n",
        "      <td> 0.267451</td>\n",
        "      <td> 1.829889</td>\n",
        "      <td> 2.544224</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>Ohio</th>\n",
        "      <td> 1.116375</td>\n",
        "      <td> 0.270886</td>\n",
        "      <td> 1.086111</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>Texas</th>\n",
        "      <td> 0.390590</td>\n",
        "      <td> 0.339125</td>\n",
        "      <td> 0.341343</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>Oregon</th>\n",
        "      <td> 1.145794</td>\n",
        "      <td> 1.268138</td>\n",
        "      <td> 0.925395</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 8,
       "text": [
        "               b         d         e\n",
        "Utah    0.267451  1.829889  2.544224\n",
        "Ohio    1.116375  0.270886  1.086111\n",
        "Texas   0.390590  0.339125  0.341343\n",
        "Oregon  1.145794  1.268138  0.925395"
       ]
      }
     ],
     "prompt_number": 8
    },
    {
     "cell_type": "heading",
     "level": 5,
     "metadata": {},
     "source": [
      "apply method"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "f = lambda x: x.max()-x.min()"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 10
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "frame.apply(f,axis=1)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 13,
       "text": [
        "Utah      4.374113\n",
        "Ohio      1.387261\n",
        "Texas     0.729715\n",
        "Oregon    2.413932\n",
        "dtype: float64"
       ]
      }
     ],
     "prompt_number": 13
    },
    {
     "cell_type": "heading",
     "level": 5,
     "metadata": {},
     "source": [
      "function return a series with multiple values"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "def f(x):\n",
      "    return Series([x.min(),x.max()], index=['min','max'])"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 14
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "frame.apply(f, axis=0)"
     ],
     "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>b</th>\n",
        "      <th>d</th>\n",
        "      <th>e</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>min</th>\n",
        "      <td>-0.267451</td>\n",
        "      <td>-1.829889</td>\n",
        "      <td>-0.925395</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>max</th>\n",
        "      <td> 1.145794</td>\n",
        "      <td>-0.270886</td>\n",
        "      <td> 2.544224</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 17,
       "text": [
        "            b         d         e\n",
        "min -0.267451 -1.829889 -0.925395\n",
        "max  1.145794 -0.270886  2.544224"
       ]
      }
     ],
     "prompt_number": 17
    },
    {
     "cell_type": "heading",
     "level": 5,
     "metadata": {},
     "source": [
      "element-wise python functions"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "format = lambda x: '%.2f' %x"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 18
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "frame.applymap(format)"
     ],
     "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>b</th>\n",
        "      <th>d</th>\n",
        "      <th>e</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>Utah</th>\n",
        "      <td> -0.27</td>\n",
        "      <td> -1.83</td>\n",
        "      <td>  2.54</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>Ohio</th>\n",
        "      <td>  1.12</td>\n",
        "      <td> -0.27</td>\n",
        "      <td>  1.09</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>Texas</th>\n",
        "      <td>  0.39</td>\n",
        "      <td> -0.34</td>\n",
        "      <td>  0.34</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>Oregon</th>\n",
        "      <td>  1.15</td>\n",
        "      <td> -1.27</td>\n",
        "      <td> -0.93</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 19,
       "text": [
        "            b      d      e\n",
        "Utah    -0.27  -1.83   2.54\n",
        "Ohio     1.12  -0.27   1.09\n",
        "Texas    0.39  -0.34   0.34\n",
        "Oregon   1.15  -1.27  -0.93"
       ]
      }
     ],
     "prompt_number": 19
    },
    {
     "cell_type": "heading",
     "level": 5,
     "metadata": {},
     "source": [
      "map method"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "frame['e'].map(format)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 20,
       "text": [
        "Utah       2.54\n",
        "Ohio       1.09\n",
        "Texas      0.34\n",
        "Oregon    -0.93\n",
        "Name: e, dtype: object"
       ]
      }
     ],
     "prompt_number": 20
    },
    {
     "cell_type": "heading",
     "level": 2,
     "metadata": {},
     "source": [
      "Sorting and ranking"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "obj = Series(range(4), index=['d','a','b','c'])"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 21
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "obj.sort_index()"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 22,
       "text": [
        "a    1\n",
        "b    2\n",
        "c    3\n",
        "d    0\n",
        "dtype: int64"
       ]
      }
     ],
     "prompt_number": 22
    },
    {
     "cell_type": "heading",
     "level": 5,
     "metadata": {},
     "source": [
      "sort by index on either axis"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "frame = DataFrame(np.arange(8).reshape((2,4)), index = ['three','one'],\n",
      "                  columns = ['d','a','b','c'])"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 23
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "frame.sort_index()"
     ],
     "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>d</th>\n",
        "      <th>a</th>\n",
        "      <th>b</th>\n",
        "      <th>c</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>one</th>\n",
        "      <td> 4</td>\n",
        "      <td> 5</td>\n",
        "      <td> 6</td>\n",
        "      <td> 7</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>three</th>\n",
        "      <td> 0</td>\n",
        "      <td> 1</td>\n",
        "      <td> 2</td>\n",
        "      <td> 3</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 24,
       "text": [
        "       d  a  b  c\n",
        "one    4  5  6  7\n",
        "three  0  1  2  3"
       ]
      }
     ],
     "prompt_number": 24
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "frame.sort_index(axis=1)"
     ],
     "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>a</th>\n",
        "      <th>b</th>\n",
        "      <th>c</th>\n",
        "      <th>d</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>three</th>\n",
        "      <td> 1</td>\n",
        "      <td> 2</td>\n",
        "      <td> 3</td>\n",
        "      <td> 0</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>one</th>\n",
        "      <td> 5</td>\n",
        "      <td> 6</td>\n",
        "      <td> 7</td>\n",
        "      <td> 4</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 25,
       "text": [
        "       a  b  c  d\n",
        "three  1  2  3  0\n",
        "one    5  6  7  4"
       ]
      }
     ],
     "prompt_number": 25
    },
    {
     "cell_type": "heading",
     "level": 5,
     "metadata": {},
     "source": [
      "descending order"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "frame.sort_index(axis=1, ascending = False)"
     ],
     "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>d</th>\n",
        "      <th>c</th>\n",
        "      <th>b</th>\n",
        "      <th>a</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>three</th>\n",
        "      <td> 0</td>\n",
        "      <td> 3</td>\n",
        "      <td> 2</td>\n",
        "      <td> 1</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>one</th>\n",
        "      <td> 4</td>\n",
        "      <td> 7</td>\n",
        "      <td> 6</td>\n",
        "      <td> 5</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 26,
       "text": [
        "       d  c  b  a\n",
        "three  0  3  2  1\n",
        "one    4  7  6  5"
       ]
      }
     ],
     "prompt_number": 26
    },
    {
     "cell_type": "heading",
     "level": 5,
     "metadata": {},
     "source": [
      "sort a series by values"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "obj = Series([4,7,-3,2])"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 27
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "obj.order()"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 28,
       "text": [
        "2   -3\n",
        "3    2\n",
        "0    4\n",
        "1    7\n",
        "dtype: int64"
       ]
      }
     ],
     "prompt_number": 28
    },
    {
     "cell_type": "heading",
     "level": 5,
     "metadata": {},
     "source": [
      "missing values"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "obj = Series([4,np.nan,7,np.nan,-3,2])"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 29
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "obj.order()"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 30,
       "text": [
        "4    -3\n",
        "5     2\n",
        "0     4\n",
        "2     7\n",
        "1   NaN\n",
        "3   NaN\n",
        "dtype: float64"
       ]
      }
     ],
     "prompt_number": 30
    },
    {
     "cell_type": "heading",
     "level": 5,
     "metadata": {},
     "source": [
      "sort values in one or more columns in data frame"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "frame = DataFrame({'b':[4,7,-3,2],'a':[0,1,0,1]})"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 31
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "frame"
     ],
     "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>a</th>\n",
        "      <th>b</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>0</th>\n",
        "      <td> 0</td>\n",
        "      <td> 4</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>1</th>\n",
        "      <td> 1</td>\n",
        "      <td> 7</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2</th>\n",
        "      <td> 0</td>\n",
        "      <td>-3</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>3</th>\n",
        "      <td> 1</td>\n",
        "      <td> 2</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 32,
       "text": [
        "   a  b\n",
        "0  0  4\n",
        "1  1  7\n",
        "2  0 -3\n",
        "3  1  2"
       ]
      }
     ],
     "prompt_number": 32
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "frame.sort_index(by='b')"
     ],
     "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>a</th>\n",
        "      <th>b</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>2</th>\n",
        "      <td> 0</td>\n",
        "      <td>-3</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>3</th>\n",
        "      <td> 1</td>\n",
        "      <td> 2</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>0</th>\n",
        "      <td> 0</td>\n",
        "      <td> 4</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>1</th>\n",
        "      <td> 1</td>\n",
        "      <td> 7</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 33,
       "text": [
        "   a  b\n",
        "2  0 -3\n",
        "3  1  2\n",
        "0  0  4\n",
        "1  1  7"
       ]
      }
     ],
     "prompt_number": 33
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "frame.sort_index(by = ['a','b'])"
     ],
     "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>a</th>\n",
        "      <th>b</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>2</th>\n",
        "      <td> 0</td>\n",
        "      <td>-3</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>0</th>\n",
        "      <td> 0</td>\n",
        "      <td> 4</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>3</th>\n",
        "      <td> 1</td>\n",
        "      <td> 2</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>1</th>\n",
        "      <td> 1</td>\n",
        "      <td> 7</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 34,
       "text": [
        "   a  b\n",
        "2  0 -3\n",
        "0  0  4\n",
        "3  1  2\n",
        "1  1  7"
       ]
      }
     ],
     "prompt_number": 34
    },
    {
     "cell_type": "heading",
     "level": 5,
     "metadata": {},
     "source": [
      "Ranking"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "obj = Series([7, -5, 7, 4, 2, 0, 4])"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 35
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "obj.rank()"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 36,
       "text": [
        "0    6.5\n",
        "1    1.0\n",
        "2    6.5\n",
        "3    4.5\n",
        "4    3.0\n",
        "5    2.0\n",
        "6    4.5\n",
        "dtype: float64"
       ]
      }
     ],
     "prompt_number": 36
    },
    {
     "cell_type": "heading",
     "level": 5,
     "metadata": {},
     "source": [
      "ranking according to the order they're observed in the data"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "obj.rank(method='first')"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 37,
       "text": [
        "0    6\n",
        "1    1\n",
        "2    7\n",
        "3    4\n",
        "4    3\n",
        "5    2\n",
        "6    5\n",
        "dtype: float64"
       ]
      }
     ],
     "prompt_number": 37
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "obj.rank(ascending=False, method='max')"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 38,
       "text": [
        "0    2\n",
        "1    7\n",
        "2    2\n",
        "3    4\n",
        "4    5\n",
        "5    6\n",
        "6    4\n",
        "dtype: float64"
       ]
      }
     ],
     "prompt_number": 38
    },
    {
     "cell_type": "heading",
     "level": 5,
     "metadata": {},
     "source": [
      "ranks over the rows or columns"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "frame = DataFrame({'b':[4.3,7,-3,2], 'a':[0,1,0,1],\n",
      "                   'c':[-2,5,8,-2.5]})"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 39
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "frame"
     ],
     "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>a</th>\n",
        "      <th>b</th>\n",
        "      <th>c</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>0</th>\n",
        "      <td> 0</td>\n",
        "      <td> 4.3</td>\n",
        "      <td>-2.0</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>1</th>\n",
        "      <td> 1</td>\n",
        "      <td> 7.0</td>\n",
        "      <td> 5.0</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2</th>\n",
        "      <td> 0</td>\n",
        "      <td>-3.0</td>\n",
        "      <td> 8.0</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>3</th>\n",
        "      <td> 1</td>\n",
        "      <td> 2.0</td>\n",
        "      <td>-2.5</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 40,
       "text": [
        "   a    b    c\n",
        "0  0  4.3 -2.0\n",
        "1  1  7.0  5.0\n",
        "2  0 -3.0  8.0\n",
        "3  1  2.0 -2.5"
       ]
      }
     ],
     "prompt_number": 40
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "frame.rank(axis=1)"
     ],
     "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>a</th>\n",
        "      <th>b</th>\n",
        "      <th>c</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>0</th>\n",
        "      <td> 2</td>\n",
        "      <td> 3</td>\n",
        "      <td> 1</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>1</th>\n",
        "      <td> 1</td>\n",
        "      <td> 3</td>\n",
        "      <td> 2</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2</th>\n",
        "      <td> 2</td>\n",
        "      <td> 1</td>\n",
        "      <td> 3</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>3</th>\n",
        "      <td> 2</td>\n",
        "      <td> 3</td>\n",
        "      <td> 1</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 41,
       "text": [
        "   a  b  c\n",
        "0  2  3  1\n",
        "1  1  3  2\n",
        "2  2  1  3\n",
        "3  2  3  1"
       ]
      }
     ],
     "prompt_number": 41
    },
    {
     "cell_type": "heading",
     "level": 5,
     "metadata": {},
     "source": [
      "Tie-breaking methods with rank"
     ]
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "average (default), min, max, first"
     ]
    },
    {
     "cell_type": "heading",
     "level": 2,
     "metadata": {},
     "source": [
      "Axis indexes with duplicate values"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "obj = Series(range(5),index=['a','a','b','b','c'])"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 42
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "obj"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 43,
       "text": [
        "a    0\n",
        "a    1\n",
        "b    2\n",
        "b    3\n",
        "c    4\n",
        "dtype: int64"
       ]
      }
     ],
     "prompt_number": 43
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "obj.index.is_unique"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 44,
       "text": [
        "False"
       ]
      }
     ],
     "prompt_number": 44
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "obj['a']"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 45,
       "text": [
        "a    0\n",
        "a    1\n",
        "dtype: int64"
       ]
      }
     ],
     "prompt_number": 45
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "obj['c']"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 46,
       "text": [
        "4"
       ]
      }
     ],
     "prompt_number": 46
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "df = DataFrame(np.random.randn(4,3), index=['a','a','b','b'])"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 47
    },
    {
     "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>0</th>\n",
        "      <th>1</th>\n",
        "      <th>2</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>a</th>\n",
        "      <td> 0.654546</td>\n",
        "      <td>-0.963798</td>\n",
        "      <td> 0.228551</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>a</th>\n",
        "      <td>-1.451196</td>\n",
        "      <td>-1.528684</td>\n",
        "      <td> 1.567436</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>b</th>\n",
        "      <td>-1.213714</td>\n",
        "      <td>-1.556472</td>\n",
        "      <td>-0.573577</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>b</th>\n",
        "      <td>-1.838320</td>\n",
        "      <td>-2.250823</td>\n",
        "      <td> 0.440242</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 48,
       "text": [
        "          0         1         2\n",
        "a  0.654546 -0.963798  0.228551\n",
        "a -1.451196 -1.528684  1.567436\n",
        "b -1.213714 -1.556472 -0.573577\n",
        "b -1.838320 -2.250823  0.440242"
       ]
      }
     ],
     "prompt_number": 48
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "df.ix['b']"
     ],
     "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>0</th>\n",
        "      <th>1</th>\n",
        "      <th>2</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>b</th>\n",
        "      <td>-1.213714</td>\n",
        "      <td>-1.556472</td>\n",
        "      <td>-0.573577</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>b</th>\n",
        "      <td>-1.838320</td>\n",
        "      <td>-2.250823</td>\n",
        "      <td> 0.440242</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 49,
       "text": [
        "          0         1         2\n",
        "b -1.213714 -1.556472 -0.573577\n",
        "b -1.838320 -2.250823  0.440242"
       ]
      }
     ],
     "prompt_number": 49
    },
    {
     "cell_type": "heading",
     "level": 2,
     "metadata": {},
     "source": [
      "Summarizing and Computing Descriptive Statistics"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "df = DataFrame([[1.4, np.nan], [7.1,-4.5],\n",
      "                [np.nan, np.nan],[0.75,-1.3]],\n",
      "               index=['a','b','c','d'],\n",
      "               columns=['one','two'])"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 50
    },
    {
     "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>one</th>\n",
        "      <th>two</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>a</th>\n",
        "      <td> 1.40</td>\n",
        "      <td> NaN</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>b</th>\n",
        "      <td> 7.10</td>\n",
        "      <td>-4.5</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>c</th>\n",
        "      <td>  NaN</td>\n",
        "      <td> NaN</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>d</th>\n",
        "      <td> 0.75</td>\n",
        "      <td>-1.3</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 51,
       "text": [
        "    one  two\n",
        "a  1.40  NaN\n",
        "b  7.10 -4.5\n",
        "c   NaN  NaN\n",
        "d  0.75 -1.3"
       ]
      }
     ],
     "prompt_number": 51
    },
    {
     "cell_type": "heading",
     "level": 5,
     "metadata": {},
     "source": [
      "column sums"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "df.sum()"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 52,
       "text": [
        "one    9.25\n",
        "two   -5.80\n",
        "dtype: float64"
       ]
      }
     ],
     "prompt_number": 52
    },
    {
     "cell_type": "heading",
     "level": 5,
     "metadata": {},
     "source": [
      "row sums"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "df.sum(axis=1) "
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 53,
       "text": [
        "a    1.40\n",
        "b    2.60\n",
        "c     NaN\n",
        "d   -0.55\n",
        "dtype: float64"
       ]
      }
     ],
     "prompt_number": 53
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "NA values are excluded unless the entire slice is NA. This can be disables using skipna."
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "df.mean(axis=1, skipna=False)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 54,
       "text": [
        "a      NaN\n",
        "b    1.300\n",
        "c      NaN\n",
        "d   -0.275\n",
        "dtype: float64"
       ]
      }
     ],
     "prompt_number": 54
    },
    {
     "cell_type": "heading",
     "level": 5,
     "metadata": {},
     "source": [
      "indirect statistics"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "df.idxmax()"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 55,
       "text": [
        "one    b\n",
        "two    d\n",
        "dtype: object"
       ]
      }
     ],
     "prompt_number": 55
    },
    {
     "cell_type": "heading",
     "level": 5,
     "metadata": {},
     "source": [
      "accumulations"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "df.cumsum()"
     ],
     "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>one</th>\n",
        "      <th>two</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>a</th>\n",
        "      <td> 1.40</td>\n",
        "      <td> NaN</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>b</th>\n",
        "      <td> 8.50</td>\n",
        "      <td>-4.5</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>c</th>\n",
        "      <td>  NaN</td>\n",
        "      <td> NaN</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>d</th>\n",
        "      <td> 9.25</td>\n",
        "      <td>-5.8</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 57,
       "text": [
        "    one  two\n",
        "a  1.40  NaN\n",
        "b  8.50 -4.5\n",
        "c   NaN  NaN\n",
        "d  9.25 -5.8"
       ]
      }
     ],
     "prompt_number": 57
    },
    {
     "cell_type": "heading",
     "level": 5,
     "metadata": {},
     "source": [
      "multiple summary statistics"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "df.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 style=\"text-align: right;\">\n",
        "      <th></th>\n",
        "      <th>one</th>\n",
        "      <th>two</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>count</th>\n",
        "      <td> 3.000000</td>\n",
        "      <td> 2.000000</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>mean</th>\n",
        "      <td> 3.083333</td>\n",
        "      <td>-2.900000</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>std</th>\n",
        "      <td> 3.493685</td>\n",
        "      <td> 2.262742</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>min</th>\n",
        "      <td> 0.750000</td>\n",
        "      <td>-4.500000</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>25%</th>\n",
        "      <td> 1.075000</td>\n",
        "      <td>-3.700000</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>50%</th>\n",
        "      <td> 1.400000</td>\n",
        "      <td>-2.900000</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>75%</th>\n",
        "      <td> 4.250000</td>\n",
        "      <td>-2.100000</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>max</th>\n",
        "      <td> 7.100000</td>\n",
        "      <td>-1.300000</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 59,
       "text": [
        "            one       two\n",
        "count  3.000000  2.000000\n",
        "mean   3.083333 -2.900000\n",
        "std    3.493685  2.262742\n",
        "min    0.750000 -4.500000\n",
        "25%    1.075000 -3.700000\n",
        "50%    1.400000 -2.900000\n",
        "75%    4.250000 -2.100000\n",
        "max    7.100000 -1.300000"
       ]
      }
     ],
     "prompt_number": 59
    },
    {
     "cell_type": "heading",
     "level": 5,
     "metadata": {},
     "source": [
      "non-numeric data"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "obj = Series(['a','a','b','c']*4)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 60
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "obj.describe()"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 61,
       "text": [
        "count     16\n",
        "unique     3\n",
        "top        a\n",
        "freq       8\n",
        "dtype: object"
       ]
      }
     ],
     "prompt_number": 61
    },
    {
     "cell_type": "heading",
     "level": 2,
     "metadata": {},
     "source": [
      "Correlation and Covariance"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "import pandas.io.data as web"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 62
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "all_data = {}"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 63
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "for ticker in ['AAPL','IBM','MSFT','GOOG']:\n",
      "    all_data[ticker] = web.get_data_yahoo(ticker,'04/11/2010','04/14/2014')"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 72
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "price =  DataFrame({tic: data['Adj Close']\n",
      "                    for tic, data in all_data.iteritems()})"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 73
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "volume = DataFrame({tic: data['Volume']\n",
      "                    for tic, data in all_data.iteritems()})"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 74
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "returns = price.pct_change()"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 75
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "returns.tail()"
     ],
     "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>AAPL</th>\n",
        "      <th>GOOG</th>\n",
        "      <th>IBM</th>\n",
        "      <th>MSFT</th>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>Date</th>\n",
        "      <th></th>\n",
        "      <th></th>\n",
        "      <th></th>\n",
        "      <th></th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>2014-04-08</th>\n",
        "      <td>-0.000136</td>\n",
        "      <td> 0.031125</td>\n",
        "      <td>-0.006328</td>\n",
        "      <td> 0.000516</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2014-04-09</th>\n",
        "      <td> 0.013219</td>\n",
        "      <td> 0.016652</td>\n",
        "      <td> 0.017355</td>\n",
        "      <td> 0.016508</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2014-04-10</th>\n",
        "      <td>-0.012912</td>\n",
        "      <td>-0.041107</td>\n",
        "      <td>-0.004904</td>\n",
        "      <td>-0.027404</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2014-04-11</th>\n",
        "      <td>-0.007358</td>\n",
        "      <td>-0.019133</td>\n",
        "      <td>-0.002516</td>\n",
        "      <td>-0.003913</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2014-04-14</th>\n",
        "      <td> 0.003981</td>\n",
        "      <td> 0.003619</td>\n",
        "      <td> 0.013244</td>\n",
        "      <td>-0.000786</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 77,
       "text": [
        "                AAPL      GOOG       IBM      MSFT\n",
        "Date                                              \n",
        "2014-04-08 -0.000136  0.031125 -0.006328  0.000516\n",
        "2014-04-09  0.013219  0.016652  0.017355  0.016508\n",
        "2014-04-10 -0.012912 -0.041107 -0.004904 -0.027404\n",
        "2014-04-11 -0.007358 -0.019133 -0.002516 -0.003913\n",
        "2014-04-14  0.003981  0.003619  0.013244 -0.000786"
       ]
      }
     ],
     "prompt_number": 77
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "returns.MSFT.corr(returns.IBM)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 78,
       "text": [
        "0.50623670894935635"
       ]
      }
     ],
     "prompt_number": 78
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "returns.MSFT.cov(returns.IBM)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 79,
       "text": [
        "8.8008494273331047e-05"
       ]
      }
     ],
     "prompt_number": 79
    },
    {
     "cell_type": "heading",
     "level": 5,
     "metadata": {},
     "source": [
      "full correlation or covariance"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "returns.corr()"
     ],
     "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>AAPL</th>\n",
        "      <th>GOOG</th>\n",
        "      <th>IBM</th>\n",
        "      <th>MSFT</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>AAPL</th>\n",
        "      <td> 1.000000</td>\n",
        "      <td> 0.737439</td>\n",
        "      <td> 0.384410</td>\n",
        "      <td> 0.336002</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>GOOG</th>\n",
        "      <td> 0.737439</td>\n",
        "      <td> 1.000000</td>\n",
        "      <td> 0.329676</td>\n",
        "      <td> 0.717087</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>IBM</th>\n",
        "      <td> 0.384410</td>\n",
        "      <td> 0.329676</td>\n",
        "      <td> 1.000000</td>\n",
        "      <td> 0.506237</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>MSFT</th>\n",
        "      <td> 0.336002</td>\n",
        "      <td> 0.717087</td>\n",
        "      <td> 0.506237</td>\n",
        "      <td> 1.000000</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 80,
       "text": [
        "          AAPL      GOOG       IBM      MSFT\n",
        "AAPL  1.000000  0.737439  0.384410  0.336002\n",
        "GOOG  0.737439  1.000000  0.329676  0.717087\n",
        "IBM   0.384410  0.329676  1.000000  0.506237\n",
        "MSFT  0.336002  0.717087  0.506237  1.000000"
       ]
      }
     ],
     "prompt_number": 80
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "returns.cov()"
     ],
     "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>AAPL</th>\n",
        "      <th>GOOG</th>\n",
        "      <th>IBM</th>\n",
        "      <th>MSFT</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>AAPL</th>\n",
        "      <td> 0.000301</td>\n",
        "      <td> 0.000152</td>\n",
        "      <td> 0.000080</td>\n",
        "      <td> 0.000085</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>GOOG</th>\n",
        "      <td> 0.000152</td>\n",
        "      <td> 0.000528</td>\n",
        "      <td> 0.000069</td>\n",
        "      <td> 0.000265</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>IBM</th>\n",
        "      <td> 0.000080</td>\n",
        "      <td> 0.000069</td>\n",
        "      <td> 0.000143</td>\n",
        "      <td> 0.000088</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>MSFT</th>\n",
        "      <td> 0.000085</td>\n",
        "      <td> 0.000265</td>\n",
        "      <td> 0.000088</td>\n",
        "      <td> 0.000211</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 81,
       "text": [
        "          AAPL      GOOG       IBM      MSFT\n",
        "AAPL  0.000301  0.000152  0.000080  0.000085\n",
        "GOOG  0.000152  0.000528  0.000069  0.000265\n",
        "IBM   0.000080  0.000069  0.000143  0.000088\n",
        "MSFT  0.000085  0.000265  0.000088  0.000211"
       ]
      }
     ],
     "prompt_number": 81
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "returns.corrwith(returns.IBM)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 82,
       "text": [
        "AAPL    0.384410\n",
        "GOOG    0.329676\n",
        "IBM     1.000000\n",
        "MSFT    0.506237\n",
        "dtype: float64"
       ]
      }
     ],
     "prompt_number": 82
    },
    {
     "cell_type": "heading",
     "level": 5,
     "metadata": {},
     "source": [
      "correlations of matching column names"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "returns.corrwith(volume)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 84,
       "text": [
        "AAPL   -0.128694\n",
        "GOOG   -0.478992\n",
        "IBM    -0.152372\n",
        "MSFT   -0.102546\n",
        "dtype: float64"
       ]
      }
     ],
     "prompt_number": 84
    },
    {
     "cell_type": "heading",
     "level": 2,
     "metadata": {},
     "source": [
      "Unique values, value count, and membership"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "obj = Series(['c','a','d','a','a','b','b','c','c'])"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 85
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "uniques = obj.unique()"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 86
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "uniques"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 87,
       "text": [
        "array(['c', 'a', 'd', 'b'], dtype=object)"
       ]
      }
     ],
     "prompt_number": 87
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "obj.value_counts()"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 89,
       "text": [
        "c    3\n",
        "a    3\n",
        "b    2\n",
        "d    1\n",
        "dtype: int64"
       ]
      }
     ],
     "prompt_number": 89
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "pd.value_counts(obj.values, sort=False)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 91,
       "text": [
        "a    3\n",
        "c    3\n",
        "b    2\n",
        "d    1\n",
        "dtype: int64"
       ]
      }
     ],
     "prompt_number": 91
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "mask = obj.isin(['b','c'])"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 93
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "mask"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 95,
       "text": [
        "0     True\n",
        "1    False\n",
        "2    False\n",
        "3    False\n",
        "4    False\n",
        "5     True\n",
        "6     True\n",
        "7     True\n",
        "8     True\n",
        "dtype: bool"
       ]
      }
     ],
     "prompt_number": 95
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "obj[mask]"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 96,
       "text": [
        "0    c\n",
        "5    b\n",
        "6    b\n",
        "7    c\n",
        "8    c\n",
        "dtype: object"
       ]
      }
     ],
     "prompt_number": 96
    },
    {
     "cell_type": "heading",
     "level": 5,
     "metadata": {},
     "source": [
      "compute a histogram"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "data = DataFrame({'Quo1':[1,3,4,3,4],\n",
      "                  'Quo2': [2,3,1,2,3],\n",
      "                  'Quo3':[1,5,2,4,4]})"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 97
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "data"
     ],
     "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>Quo1</th>\n",
        "      <th>Quo2</th>\n",
        "      <th>Quo3</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>0</th>\n",
        "      <td> 1</td>\n",
        "      <td> 2</td>\n",
        "      <td> 1</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>1</th>\n",
        "      <td> 3</td>\n",
        "      <td> 3</td>\n",
        "      <td> 5</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2</th>\n",
        "      <td> 4</td>\n",
        "      <td> 1</td>\n",
        "      <td> 2</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>3</th>\n",
        "      <td> 3</td>\n",
        "      <td> 2</td>\n",
        "      <td> 4</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>4</th>\n",
        "      <td> 4</td>\n",
        "      <td> 3</td>\n",
        "      <td> 4</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 98,
       "text": [
        "   Quo1  Quo2  Quo3\n",
        "0     1     2     1\n",
        "1     3     3     5\n",
        "2     4     1     2\n",
        "3     3     2     4\n",
        "4     4     3     4"
       ]
      }
     ],
     "prompt_number": 98
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "result = data.apply(pd.value_counts).fillna(0)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 100
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "result"
     ],
     "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>Quo1</th>\n",
        "      <th>Quo2</th>\n",
        "      <th>Quo3</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>1</th>\n",
        "      <td> 1</td>\n",
        "      <td> 1</td>\n",
        "      <td> 1</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2</th>\n",
        "      <td> 0</td>\n",
        "      <td> 2</td>\n",
        "      <td> 1</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>3</th>\n",
        "      <td> 2</td>\n",
        "      <td> 2</td>\n",
        "      <td> 0</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>4</th>\n",
        "      <td> 2</td>\n",
        "      <td> 0</td>\n",
        "      <td> 2</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>5</th>\n",
        "      <td> 0</td>\n",
        "      <td> 0</td>\n",
        "      <td> 1</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 101,
       "text": [
        "   Quo1  Quo2  Quo3\n",
        "1     1     1     1\n",
        "2     0     2     1\n",
        "3     2     2     0\n",
        "4     2     0     2\n",
        "5     0     0     1"
       ]
      }
     ],
     "prompt_number": 101
    },
    {
     "cell_type": "heading",
     "level": 2,
     "metadata": {},
     "source": [
      "Handling Missing Data"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "string_data = Series(['aardvark','artichoke',np.nan, 'avocado'])"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 103
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "string_data"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 104,
       "text": [
        "0     aardvark\n",
        "1    artichoke\n",
        "2          NaN\n",
        "3      avocado\n",
        "dtype: object"
       ]
      }
     ],
     "prompt_number": 104
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "string_data.isnull()"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 105,
       "text": [
        "0    False\n",
        "1    False\n",
        "2     True\n",
        "3    False\n",
        "dtype: bool"
       ]
      }
     ],
     "prompt_number": 105
    },
    {
     "cell_type": "heading",
     "level": 5,
     "metadata": {},
     "source": [
      "built-in Python's none"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "string_data[0] = None"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 106
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "string_data.isnull()"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 107,
       "text": [
        "0     True\n",
        "1    False\n",
        "2     True\n",
        "3    False\n",
        "dtype: bool"
       ]
      }
     ],
     "prompt_number": 107
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "NA handling methods: dropna, fillna, isnull, notnull"
     ]
    },
    {
     "cell_type": "heading",
     "level": 2,
     "metadata": {},
     "source": [
      "FIltering out missing data"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "from numpy import nan as NA"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 109
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "data = Series([1, NA, 3.5, NA, 7])"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 110
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "data.dropna()"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 111,
       "text": [
        "0    1.0\n",
        "2    3.5\n",
        "4    7.0\n",
        "dtype: float64"
       ]
      }
     ],
     "prompt_number": 111
    },
    {
     "cell_type": "heading",
     "level": 5,
     "metadata": {},
     "source": [
      "using boolean indexing"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "data[data.notnull()]"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 112,
       "text": [
        "0    1.0\n",
        "2    3.5\n",
        "4    7.0\n",
        "dtype: float64"
       ]
      }
     ],
     "prompt_number": 112
    },
    {
     "cell_type": "heading",
     "level": 5,
     "metadata": {},
     "source": [
      "dropna with dataframa"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "data = DataFrame([[1.,6.5,3.],[1.,NA,NA],\n",
      "                  [NA,NA,NA],[NA,6.5,3.]])"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 113
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "data"
     ],
     "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>0</th>\n",
        "      <th>1</th>\n",
        "      <th>2</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>0</th>\n",
        "      <td>  1</td>\n",
        "      <td> 6.5</td>\n",
        "      <td>  3</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>1</th>\n",
        "      <td>  1</td>\n",
        "      <td> NaN</td>\n",
        "      <td>NaN</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2</th>\n",
        "      <td>NaN</td>\n",
        "      <td> NaN</td>\n",
        "      <td>NaN</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>3</th>\n",
        "      <td>NaN</td>\n",
        "      <td> 6.5</td>\n",
        "      <td>  3</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 114,
       "text": [
        "    0    1   2\n",
        "0   1  6.5   3\n",
        "1   1  NaN NaN\n",
        "2 NaN  NaN NaN\n",
        "3 NaN  6.5   3"
       ]
      }
     ],
     "prompt_number": 114
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "cleaned = data.dropna()"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 115
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "cleaned"
     ],
     "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>0</th>\n",
        "      <th>1</th>\n",
        "      <th>2</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>0</th>\n",
        "      <td> 1</td>\n",
        "      <td> 6.5</td>\n",
        "      <td> 3</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 116,
       "text": [
        "   0    1  2\n",
        "0  1  6.5  3"
       ]
      }
     ],
     "prompt_number": 116
    },
    {
     "cell_type": "heading",
     "level": 5,
     "metadata": {},
     "source": [
      "drop rows that are all NA"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "data.dropna(how='all')"
     ],
     "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>0</th>\n",
        "      <th>1</th>\n",
        "      <th>2</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>0</th>\n",
        "      <td>  1</td>\n",
        "      <td> 6.5</td>\n",
        "      <td>  3</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>1</th>\n",
        "      <td>  1</td>\n",
        "      <td> NaN</td>\n",
        "      <td>NaN</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>3</th>\n",
        "      <td>NaN</td>\n",
        "      <td> 6.5</td>\n",
        "      <td>  3</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 117,
       "text": [
        "    0    1   2\n",
        "0   1  6.5   3\n",
        "1   1  NaN NaN\n",
        "3 NaN  6.5   3"
       ]
      }
     ],
     "prompt_number": 117
    },
    {
     "cell_type": "heading",
     "level": 5,
     "metadata": {},
     "source": [
      "drop columns that are all NA"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "data[4]=NA"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 118
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "data"
     ],
     "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>0</th>\n",
        "      <th>1</th>\n",
        "      <th>2</th>\n",
        "      <th>4</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>0</th>\n",
        "      <td>  1</td>\n",
        "      <td> 6.5</td>\n",
        "      <td>  3</td>\n",
        "      <td>NaN</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>1</th>\n",
        "      <td>  1</td>\n",
        "      <td> NaN</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2</th>\n",
        "      <td>NaN</td>\n",
        "      <td> NaN</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>3</th>\n",
        "      <td>NaN</td>\n",
        "      <td> 6.5</td>\n",
        "      <td>  3</td>\n",
        "      <td>NaN</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 119,
       "text": [
        "    0    1   2   4\n",
        "0   1  6.5   3 NaN\n",
        "1   1  NaN NaN NaN\n",
        "2 NaN  NaN NaN NaN\n",
        "3 NaN  6.5   3 NaN"
       ]
      }
     ],
     "prompt_number": 119
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "data.dropna(axis=1,how='all')"
     ],
     "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>0</th>\n",
        "      <th>1</th>\n",
        "      <th>2</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>0</th>\n",
        "      <td>  1</td>\n",
        "      <td> 6.5</td>\n",
        "      <td>  3</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>1</th>\n",
        "      <td>  1</td>\n",
        "      <td> NaN</td>\n",
        "      <td>NaN</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2</th>\n",
        "      <td>NaN</td>\n",
        "      <td> NaN</td>\n",
        "      <td>NaN</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>3</th>\n",
        "      <td>NaN</td>\n",
        "      <td> 6.5</td>\n",
        "      <td>  3</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 120,
       "text": [
        "    0    1   2\n",
        "0   1  6.5   3\n",
        "1   1  NaN NaN\n",
        "2 NaN  NaN NaN\n",
        "3 NaN  6.5   3"
       ]
      }
     ],
     "prompt_number": 120
    },
    {
     "cell_type": "heading",
     "level": 5,
     "metadata": {},
     "source": [
      "keep only rows contaiing a certain no of obs"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "df = DataFrame(np.random.randn(7,3))"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 121
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "df.ix[:4,1]=NA; df.ix[:2,2]=NA"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 122
    },
    {
     "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>0</th>\n",
        "      <th>1</th>\n",
        "      <th>2</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>0</th>\n",
        "      <td>-0.676323</td>\n",
        "      <td>      NaN</td>\n",
        "      <td>      NaN</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>1</th>\n",
        "      <td>-1.088497</td>\n",
        "      <td>      NaN</td>\n",
        "      <td>      NaN</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2</th>\n",
        "      <td> 0.122962</td>\n",
        "      <td>      NaN</td>\n",
        "      <td>      NaN</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>3</th>\n",
        "      <td> 2.087705</td>\n",
        "      <td>      NaN</td>\n",
        "      <td> 1.538338</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>4</th>\n",
        "      <td>-1.267822</td>\n",
        "      <td>      NaN</td>\n",
        "      <td>-0.924860</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>5</th>\n",
        "      <td>-1.596591</td>\n",
        "      <td>-1.001367</td>\n",
        "      <td>-0.705282</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>6</th>\n",
        "      <td>-0.026753</td>\n",
        "      <td>-0.694895</td>\n",
        "      <td>-0.386125</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 123,
       "text": [
        "          0         1         2\n",
        "0 -0.676323       NaN       NaN\n",
        "1 -1.088497       NaN       NaN\n",
        "2  0.122962       NaN       NaN\n",
        "3  2.087705       NaN  1.538338\n",
        "4 -1.267822       NaN -0.924860\n",
        "5 -1.596591 -1.001367 -0.705282\n",
        "6 -0.026753 -0.694895 -0.386125"
       ]
      }
     ],
     "prompt_number": 123
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "df.dropna(thresh=2)"
     ],
     "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>0</th>\n",
        "      <th>1</th>\n",
        "      <th>2</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>3</th>\n",
        "      <td> 2.087705</td>\n",
        "      <td>      NaN</td>\n",
        "      <td> 1.538338</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>4</th>\n",
        "      <td>-1.267822</td>\n",
        "      <td>      NaN</td>\n",
        "      <td>-0.924860</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>5</th>\n",
        "      <td>-1.596591</td>\n",
        "      <td>-1.001367</td>\n",
        "      <td>-0.705282</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>6</th>\n",
        "      <td>-0.026753</td>\n",
        "      <td>-0.694895</td>\n",
        "      <td>-0.386125</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 124,
       "text": [
        "          0         1         2\n",
        "3  2.087705       NaN  1.538338\n",
        "4 -1.267822       NaN -0.924860\n",
        "5 -1.596591 -1.001367 -0.705282\n",
        "6 -0.026753 -0.694895 -0.386125"
       ]
      }
     ],
     "prompt_number": 124
    },
    {
     "cell_type": "heading",
     "level": 2,
     "metadata": {},
     "source": [
      "Filling in Missing Data"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "df.fillna(0)"
     ],
     "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>0</th>\n",
        "      <th>1</th>\n",
        "      <th>2</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>0</th>\n",
        "      <td>-0.676323</td>\n",
        "      <td> 0.000000</td>\n",
        "      <td> 0.000000</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>1</th>\n",
        "      <td>-1.088497</td>\n",
        "      <td> 0.000000</td>\n",
        "      <td> 0.000000</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2</th>\n",
        "      <td> 0.122962</td>\n",
        "      <td> 0.000000</td>\n",
        "      <td> 0.000000</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>3</th>\n",
        "      <td> 2.087705</td>\n",
        "      <td> 0.000000</td>\n",
        "      <td> 1.538338</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>4</th>\n",
        "      <td>-1.267822</td>\n",
        "      <td> 0.000000</td>\n",
        "      <td>-0.924860</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>5</th>\n",
        "      <td>-1.596591</td>\n",
        "      <td>-1.001367</td>\n",
        "      <td>-0.705282</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>6</th>\n",
        "      <td>-0.026753</td>\n",
        "      <td>-0.694895</td>\n",
        "      <td>-0.386125</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 125,
       "text": [
        "          0         1         2\n",
        "0 -0.676323  0.000000  0.000000\n",
        "1 -1.088497  0.000000  0.000000\n",
        "2  0.122962  0.000000  0.000000\n",
        "3  2.087705  0.000000  1.538338\n",
        "4 -1.267822  0.000000 -0.924860\n",
        "5 -1.596591 -1.001367 -0.705282\n",
        "6 -0.026753 -0.694895 -0.386125"
       ]
      }
     ],
     "prompt_number": 125
    },
    {
     "cell_type": "heading",
     "level": 5,
     "metadata": {},
     "source": [
      "different fill value for each column"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "df.fillna({1:0.5,3:-1})"
     ],
     "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>0</th>\n",
        "      <th>1</th>\n",
        "      <th>2</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>0</th>\n",
        "      <td>-0.676323</td>\n",
        "      <td> 0.500000</td>\n",
        "      <td>      NaN</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>1</th>\n",
        "      <td>-1.088497</td>\n",
        "      <td> 0.500000</td>\n",
        "      <td>      NaN</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2</th>\n",
        "      <td> 0.122962</td>\n",
        "      <td> 0.500000</td>\n",
        "      <td>      NaN</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>3</th>\n",
        "      <td> 2.087705</td>\n",
        "      <td> 0.500000</td>\n",
        "      <td> 1.538338</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>4</th>\n",
        "      <td>-1.267822</td>\n",
        "      <td> 0.500000</td>\n",
        "      <td>-0.924860</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>5</th>\n",
        "      <td>-1.596591</td>\n",
        "      <td>-1.001367</td>\n",
        "      <td>-0.705282</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>6</th>\n",
        "      <td>-0.026753</td>\n",
        "      <td>-0.694895</td>\n",
        "      <td>-0.386125</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 126,
       "text": [
        "          0         1         2\n",
        "0 -0.676323  0.500000       NaN\n",
        "1 -1.088497  0.500000       NaN\n",
        "2  0.122962  0.500000       NaN\n",
        "3  2.087705  0.500000  1.538338\n",
        "4 -1.267822  0.500000 -0.924860\n",
        "5 -1.596591 -1.001367 -0.705282\n",
        "6 -0.026753 -0.694895 -0.386125"
       ]
      }
     ],
     "prompt_number": 126
    },
    {
     "cell_type": "heading",
     "level": 5,
     "metadata": {},
     "source": [
      "modify existing project in place"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "_ = df.fillna(0, inplace=True)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 127
    },
    {
     "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>0</th>\n",
        "      <th>1</th>\n",
        "      <th>2</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>0</th>\n",
        "      <td>-0.676323</td>\n",
        "      <td> 0.000000</td>\n",
        "      <td> 0.000000</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>1</th>\n",
        "      <td>-1.088497</td>\n",
        "      <td> 0.000000</td>\n",
        "      <td> 0.000000</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2</th>\n",
        "      <td> 0.122962</td>\n",
        "      <td> 0.000000</td>\n",
        "      <td> 0.000000</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>3</th>\n",
        "      <td> 2.087705</td>\n",
        "      <td> 0.000000</td>\n",
        "      <td> 1.538338</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>4</th>\n",
        "      <td>-1.267822</td>\n",
        "      <td> 0.000000</td>\n",
        "      <td>-0.924860</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>5</th>\n",
        "      <td>-1.596591</td>\n",
        "      <td>-1.001367</td>\n",
        "      <td>-0.705282</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>6</th>\n",
        "      <td>-0.026753</td>\n",
        "      <td>-0.694895</td>\n",
        "      <td>-0.386125</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 128,
       "text": [
        "          0         1         2\n",
        "0 -0.676323  0.000000  0.000000\n",
        "1 -1.088497  0.000000  0.000000\n",
        "2  0.122962  0.000000  0.000000\n",
        "3  2.087705  0.000000  1.538338\n",
        "4 -1.267822  0.000000 -0.924860\n",
        "5 -1.596591 -1.001367 -0.705282\n",
        "6 -0.026753 -0.694895 -0.386125"
       ]
      }
     ],
     "prompt_number": 128
    },
    {
     "cell_type": "heading",
     "level": 5,
     "metadata": {},
     "source": [
      "interpolation methods"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "df = DataFrame(np.random.randn(6,3))"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 129
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "df.ix[2:,1]=NA; df.ix[4:,2]=NA"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 130
    },
    {
     "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>0</th>\n",
        "      <th>1</th>\n",
        "      <th>2</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>0</th>\n",
        "      <td>-0.570090</td>\n",
        "      <td>-0.513487</td>\n",
        "      <td>-0.707382</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>1</th>\n",
        "      <td> 1.453435</td>\n",
        "      <td> 0.440059</td>\n",
        "      <td>-0.292707</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2</th>\n",
        "      <td>-0.045053</td>\n",
        "      <td>      NaN</td>\n",
        "      <td> 0.951857</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>3</th>\n",
        "      <td> 1.277519</td>\n",
        "      <td>      NaN</td>\n",
        "      <td>-0.463472</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>4</th>\n",
        "      <td>-2.012467</td>\n",
        "      <td>      NaN</td>\n",
        "      <td>      NaN</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>5</th>\n",
        "      <td>-0.854318</td>\n",
        "      <td>      NaN</td>\n",
        "      <td>      NaN</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 131,
       "text": [
        "          0         1         2\n",
        "0 -0.570090 -0.513487 -0.707382\n",
        "1  1.453435  0.440059 -0.292707\n",
        "2 -0.045053       NaN  0.951857\n",
        "3  1.277519       NaN -0.463472\n",
        "4 -2.012467       NaN       NaN\n",
        "5 -0.854318       NaN       NaN"
       ]
      }
     ],
     "prompt_number": 131
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "df.fillna(method = 'ffill')"
     ],
     "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>0</th>\n",
        "      <th>1</th>\n",
        "      <th>2</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>0</th>\n",
        "      <td>-0.570090</td>\n",
        "      <td>-0.513487</td>\n",
        "      <td>-0.707382</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>1</th>\n",
        "      <td> 1.453435</td>\n",
        "      <td> 0.440059</td>\n",
        "      <td>-0.292707</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2</th>\n",
        "      <td>-0.045053</td>\n",
        "      <td> 0.440059</td>\n",
        "      <td> 0.951857</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>3</th>\n",
        "      <td> 1.277519</td>\n",
        "      <td> 0.440059</td>\n",
        "      <td>-0.463472</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>4</th>\n",
        "      <td>-2.012467</td>\n",
        "      <td> 0.440059</td>\n",
        "      <td>-0.463472</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>5</th>\n",
        "      <td>-0.854318</td>\n",
        "      <td> 0.440059</td>\n",
        "      <td>-0.463472</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 132,
       "text": [
        "          0         1         2\n",
        "0 -0.570090 -0.513487 -0.707382\n",
        "1  1.453435  0.440059 -0.292707\n",
        "2 -0.045053  0.440059  0.951857\n",
        "3  1.277519  0.440059 -0.463472\n",
        "4 -2.012467  0.440059 -0.463472\n",
        "5 -0.854318  0.440059 -0.463472"
       ]
      }
     ],
     "prompt_number": 132
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "df.fillna(method='ffill',limit=2)"
     ],
     "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>0</th>\n",
        "      <th>1</th>\n",
        "      <th>2</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>0</th>\n",
        "      <td>-0.570090</td>\n",
        "      <td>-0.513487</td>\n",
        "      <td>-0.707382</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>1</th>\n",
        "      <td> 1.453435</td>\n",
        "      <td> 0.440059</td>\n",
        "      <td>-0.292707</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2</th>\n",
        "      <td>-0.045053</td>\n",
        "      <td> 0.440059</td>\n",
        "      <td> 0.951857</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>3</th>\n",
        "      <td> 1.277519</td>\n",
        "      <td> 0.440059</td>\n",
        "      <td>-0.463472</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>4</th>\n",
        "      <td>-2.012467</td>\n",
        "      <td>      NaN</td>\n",
        "      <td>-0.463472</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>5</th>\n",
        "      <td>-0.854318</td>\n",
        "      <td>      NaN</td>\n",
        "      <td>-0.463472</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 133,
       "text": [
        "          0         1         2\n",
        "0 -0.570090 -0.513487 -0.707382\n",
        "1  1.453435  0.440059 -0.292707\n",
        "2 -0.045053  0.440059  0.951857\n",
        "3  1.277519  0.440059 -0.463472\n",
        "4 -2.012467       NaN -0.463472\n",
        "5 -0.854318       NaN -0.463472"
       ]
      }
     ],
     "prompt_number": 133
    },
    {
     "cell_type": "heading",
     "level": 5,
     "metadata": {},
     "source": [
      "pass the mean or median value of a Series"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "data=Series([1.,NA,3.5,NA,7])"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 134
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "data.fillna(data.mean())"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 135,
       "text": [
        "0    1.000000\n",
        "1    3.833333\n",
        "2    3.500000\n",
        "3    3.833333\n",
        "4    7.000000\n",
        "dtype: float64"
       ]
      }
     ],
     "prompt_number": 135
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "fillna function arguments : value, method, axis, inplace, limit"
     ]
    },
    {
     "cell_type": "heading",
     "level": 2,
     "metadata": {},
     "source": [
      "Hierarchical Indexing"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "data = Series(np.random.randn(10),\n",
      "              index = [['a','a','a','b','b','b','c','c','d','d'],\n",
      "                       [1,2,3,1,2,3,1,2,2,3]])"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 136
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "data"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 137,
       "text": [
        "a  1   -0.734465\n",
        "   2   -0.775564\n",
        "   3   -2.134157\n",
        "b  1    1.169687\n",
        "   2    0.655510\n",
        "   3    0.229640\n",
        "c  1    0.607370\n",
        "   2   -0.227422\n",
        "d  2   -0.319022\n",
        "   3   -1.861461\n",
        "dtype: float64"
       ]
      }
     ],
     "prompt_number": 137
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "data.index"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 138,
       "text": [
        "MultiIndex(levels=[[u'a', u'b', u'c', u'd'], [1, 2, 3]],\n",
        "           labels=[[0, 0, 0, 1, 1, 1, 2, 2, 3, 3], [0, 1, 2, 0, 1, 2, 0, 1, 1, 2]])"
       ]
      }
     ],
     "prompt_number": 138
    },
    {
     "cell_type": "heading",
     "level": 5,
     "metadata": {},
     "source": [
      "partial indexing"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "data['b']"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 139,
       "text": [
        "1    1.169687\n",
        "2    0.655510\n",
        "3    0.229640\n",
        "dtype: float64"
       ]
      }
     ],
     "prompt_number": 139
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "data['b':'c']"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 140,
       "text": [
        "b  1    1.169687\n",
        "   2    0.655510\n",
        "   3    0.229640\n",
        "c  1    0.607370\n",
        "   2   -0.227422\n",
        "dtype: float64"
       ]
      }
     ],
     "prompt_number": 140
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "data.ix[['b','d']]"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 141,
       "text": [
        "b  1    1.169687\n",
        "   2    0.655510\n",
        "   3    0.229640\n",
        "d  2   -0.319022\n",
        "   3   -1.861461\n",
        "dtype: float64"
       ]
      }
     ],
     "prompt_number": 141
    },
    {
     "cell_type": "heading",
     "level": 5,
     "metadata": {},
     "source": [
      "selection from an inner level"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "data[:,2]"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 142,
       "text": [
        "a   -0.775564\n",
        "b    0.655510\n",
        "c   -0.227422\n",
        "d   -0.319022\n",
        "dtype: float64"
       ]
      }
     ],
     "prompt_number": 142
    },
    {
     "cell_type": "heading",
     "level": 5,
     "metadata": {},
     "source": [
      "rearranged into a DataFrame"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "data.unstack()"
     ],
     "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>1</th>\n",
        "      <th>2</th>\n",
        "      <th>3</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>a</th>\n",
        "      <td>-0.734465</td>\n",
        "      <td>-0.775564</td>\n",
        "      <td>-2.134157</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>b</th>\n",
        "      <td> 1.169687</td>\n",
        "      <td> 0.655510</td>\n",
        "      <td> 0.229640</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>c</th>\n",
        "      <td> 0.607370</td>\n",
        "      <td>-0.227422</td>\n",
        "      <td>      NaN</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>d</th>\n",
        "      <td>      NaN</td>\n",
        "      <td>-0.319022</td>\n",
        "      <td>-1.861461</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 143,
       "text": [
        "          1         2         3\n",
        "a -0.734465 -0.775564 -2.134157\n",
        "b  1.169687  0.655510  0.229640\n",
        "c  0.607370 -0.227422       NaN\n",
        "d       NaN -0.319022 -1.861461"
       ]
      }
     ],
     "prompt_number": 143
    },
    {
     "cell_type": "heading",
     "level": 5,
     "metadata": {},
     "source": [
      "inverse operation of unstack"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "data.unstack().stack()"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 144,
       "text": [
        "a  1   -0.734465\n",
        "   2   -0.775564\n",
        "   3   -2.134157\n",
        "b  1    1.169687\n",
        "   2    0.655510\n",
        "   3    0.229640\n",
        "c  1    0.607370\n",
        "   2   -0.227422\n",
        "d  2   -0.319022\n",
        "   3   -1.861461\n",
        "dtype: float64"
       ]
      }
     ],
     "prompt_number": 144
    },
    {
     "cell_type": "heading",
     "level": 5,
     "metadata": {},
     "source": [
      "either axis can have a hierarchical index:"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "frame = DataFrame(np.arange(12).reshape((4,3)),\n",
      "                  index = [['a','a','b','b'],[1,2,1,2]],\n",
      "                  columns = [['Ohio','Ohio','Colorado'],\n",
      "                             ['Green','Red','Green']])"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 145
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "frame"
     ],
     "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\">Ohio</th>\n",
        "      <th>Colorado</th>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th></th>\n",
        "      <th></th>\n",
        "      <th>Green</th>\n",
        "      <th>Red</th>\n",
        "      <th>Green</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th rowspan=\"2\" valign=\"top\">a</th>\n",
        "      <th>1</th>\n",
        "      <td> 0</td>\n",
        "      <td>  1</td>\n",
        "      <td>  2</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2</th>\n",
        "      <td> 3</td>\n",
        "      <td>  4</td>\n",
        "      <td>  5</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th rowspan=\"2\" valign=\"top\">b</th>\n",
        "      <th>1</th>\n",
        "      <td> 6</td>\n",
        "      <td>  7</td>\n",
        "      <td>  8</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2</th>\n",
        "      <td> 9</td>\n",
        "      <td> 10</td>\n",
        "      <td> 11</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 146,
       "text": [
        "      Ohio       Colorado\n",
        "     Green  Red     Green\n",
        "a 1      0    1         2\n",
        "  2      3    4         5\n",
        "b 1      6    7         8\n",
        "  2      9   10        11"
       ]
      }
     ],
     "prompt_number": 146
    },
    {
     "cell_type": "heading",
     "level": 5,
     "metadata": {},
     "source": [
      "hierarchical levels can have names"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "frame.index.names = ['key1', 'key2']"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 147
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "frame.columns.names = ['state', 'color']"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 149
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "frame"
     ],
     "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>state</th>\n",
        "      <th colspan=\"2\" halign=\"left\">Ohio</th>\n",
        "      <th>Colorado</th>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th></th>\n",
        "      <th>color</th>\n",
        "      <th>Green</th>\n",
        "      <th>Red</th>\n",
        "      <th>Green</th>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>key1</th>\n",
        "      <th>key2</th>\n",
        "      <th></th>\n",
        "      <th></th>\n",
        "      <th></th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th rowspan=\"2\" valign=\"top\">a</th>\n",
        "      <th>1</th>\n",
        "      <td> 0</td>\n",
        "      <td>  1</td>\n",
        "      <td>  2</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2</th>\n",
        "      <td> 3</td>\n",
        "      <td>  4</td>\n",
        "      <td>  5</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th rowspan=\"2\" valign=\"top\">b</th>\n",
        "      <th>1</th>\n",
        "      <td> 6</td>\n",
        "      <td>  7</td>\n",
        "      <td>  8</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2</th>\n",
        "      <td> 9</td>\n",
        "      <td> 10</td>\n",
        "      <td> 11</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 150,
       "text": [
        "state       Ohio       Colorado\n",
        "color      Green  Red     Green\n",
        "key1 key2                      \n",
        "a    1         0    1         2\n",
        "     2         3    4         5\n",
        "b    1         6    7         8\n",
        "     2         9   10        11"
       ]
      }
     ],
     "prompt_number": 150
    },
    {
     "cell_type": "heading",
     "level": 5,
     "metadata": {},
     "source": [
      "partial column indexing"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "frame['Ohio']"
     ],
     "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>color</th>\n",
        "      <th>Green</th>\n",
        "      <th>Red</th>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>key1</th>\n",
        "      <th>key2</th>\n",
        "      <th></th>\n",
        "      <th></th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th rowspan=\"2\" valign=\"top\">a</th>\n",
        "      <th>1</th>\n",
        "      <td> 0</td>\n",
        "      <td>  1</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2</th>\n",
        "      <td> 3</td>\n",
        "      <td>  4</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th rowspan=\"2\" valign=\"top\">b</th>\n",
        "      <th>1</th>\n",
        "      <td> 6</td>\n",
        "      <td>  7</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2</th>\n",
        "      <td> 9</td>\n",
        "      <td> 10</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 151,
       "text": [
        "color      Green  Red\n",
        "key1 key2            \n",
        "a    1         0    1\n",
        "     2         3    4\n",
        "b    1         6    7\n",
        "     2         9   10"
       ]
      }
     ],
     "prompt_number": 151
    },
    {
     "cell_type": "heading",
     "level": 2,
     "metadata": {},
     "source": [
      "Reordering and Sorting Levels"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "frame.swaplevel('key1','key2')"
     ],
     "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>state</th>\n",
        "      <th colspan=\"2\" halign=\"left\">Ohio</th>\n",
        "      <th>Colorado</th>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th></th>\n",
        "      <th>color</th>\n",
        "      <th>Green</th>\n",
        "      <th>Red</th>\n",
        "      <th>Green</th>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>key2</th>\n",
        "      <th>key1</th>\n",
        "      <th></th>\n",
        "      <th></th>\n",
        "      <th></th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>1</th>\n",
        "      <th>a</th>\n",
        "      <td> 0</td>\n",
        "      <td>  1</td>\n",
        "      <td>  2</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2</th>\n",
        "      <th>a</th>\n",
        "      <td> 3</td>\n",
        "      <td>  4</td>\n",
        "      <td>  5</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>1</th>\n",
        "      <th>b</th>\n",
        "      <td> 6</td>\n",
        "      <td>  7</td>\n",
        "      <td>  8</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2</th>\n",
        "      <th>b</th>\n",
        "      <td> 9</td>\n",
        "      <td> 10</td>\n",
        "      <td> 11</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 152,
       "text": [
        "state       Ohio       Colorado\n",
        "color      Green  Red     Green\n",
        "key2 key1                      \n",
        "1    a         0    1         2\n",
        "2    a         3    4         5\n",
        "1    b         6    7         8\n",
        "2    b         9   10        11"
       ]
      }
     ],
     "prompt_number": 152
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "frame.sortlevel(1)"
     ],
     "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>state</th>\n",
        "      <th colspan=\"2\" halign=\"left\">Ohio</th>\n",
        "      <th>Colorado</th>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th></th>\n",
        "      <th>color</th>\n",
        "      <th>Green</th>\n",
        "      <th>Red</th>\n",
        "      <th>Green</th>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>key1</th>\n",
        "      <th>key2</th>\n",
        "      <th></th>\n",
        "      <th></th>\n",
        "      <th></th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>a</th>\n",
        "      <th>1</th>\n",
        "      <td> 0</td>\n",
        "      <td>  1</td>\n",
        "      <td>  2</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>b</th>\n",
        "      <th>1</th>\n",
        "      <td> 6</td>\n",
        "      <td>  7</td>\n",
        "      <td>  8</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>a</th>\n",
        "      <th>2</th>\n",
        "      <td> 3</td>\n",
        "      <td>  4</td>\n",
        "      <td>  5</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>b</th>\n",
        "      <th>2</th>\n",
        "      <td> 9</td>\n",
        "      <td> 10</td>\n",
        "      <td> 11</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 153,
       "text": [
        "state       Ohio       Colorado\n",
        "color      Green  Red     Green\n",
        "key1 key2                      \n",
        "a    1         0    1         2\n",
        "b    1         6    7         8\n",
        "a    2         3    4         5\n",
        "b    2         9   10        11"
       ]
      }
     ],
     "prompt_number": 153
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "frame.sortlevel(0)"
     ],
     "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>state</th>\n",
        "      <th colspan=\"2\" halign=\"left\">Ohio</th>\n",
        "      <th>Colorado</th>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th></th>\n",
        "      <th>color</th>\n",
        "      <th>Green</th>\n",
        "      <th>Red</th>\n",
        "      <th>Green</th>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>key1</th>\n",
        "      <th>key2</th>\n",
        "      <th></th>\n",
        "      <th></th>\n",
        "      <th></th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th rowspan=\"2\" valign=\"top\">a</th>\n",
        "      <th>1</th>\n",
        "      <td> 0</td>\n",
        "      <td>  1</td>\n",
        "      <td>  2</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2</th>\n",
        "      <td> 3</td>\n",
        "      <td>  4</td>\n",
        "      <td>  5</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th rowspan=\"2\" valign=\"top\">b</th>\n",
        "      <th>1</th>\n",
        "      <td> 6</td>\n",
        "      <td>  7</td>\n",
        "      <td>  8</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2</th>\n",
        "      <td> 9</td>\n",
        "      <td> 10</td>\n",
        "      <td> 11</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 154,
       "text": [
        "state       Ohio       Colorado\n",
        "color      Green  Red     Green\n",
        "key1 key2                      \n",
        "a    1         0    1         2\n",
        "     2         3    4         5\n",
        "b    1         6    7         8\n",
        "     2         9   10        11"
       ]
      }
     ],
     "prompt_number": 154
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "frame.swaplevel(0,1).sortlevel(0)"
     ],
     "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>state</th>\n",
        "      <th colspan=\"2\" halign=\"left\">Ohio</th>\n",
        "      <th>Colorado</th>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th></th>\n",
        "      <th>color</th>\n",
        "      <th>Green</th>\n",
        "      <th>Red</th>\n",
        "      <th>Green</th>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>key2</th>\n",
        "      <th>key1</th>\n",
        "      <th></th>\n",
        "      <th></th>\n",
        "      <th></th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th rowspan=\"2\" valign=\"top\">1</th>\n",
        "      <th>a</th>\n",
        "      <td> 0</td>\n",
        "      <td>  1</td>\n",
        "      <td>  2</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>b</th>\n",
        "      <td> 6</td>\n",
        "      <td>  7</td>\n",
        "      <td>  8</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th rowspan=\"2\" valign=\"top\">2</th>\n",
        "      <th>a</th>\n",
        "      <td> 3</td>\n",
        "      <td>  4</td>\n",
        "      <td>  5</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>b</th>\n",
        "      <td> 9</td>\n",
        "      <td> 10</td>\n",
        "      <td> 11</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 155,
       "text": [
        "state       Ohio       Colorado\n",
        "color      Green  Red     Green\n",
        "key2 key1                      \n",
        "1    a         0    1         2\n",
        "     b         6    7         8\n",
        "2    a         3    4         5\n",
        "     b         9   10        11"
       ]
      }
     ],
     "prompt_number": 155
    },
    {
     "cell_type": "heading",
     "level": 2,
     "metadata": {},
     "source": [
      "Summary Statistics by level"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "frame"
     ],
     "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>state</th>\n",
        "      <th colspan=\"2\" halign=\"left\">Ohio</th>\n",
        "      <th>Colorado</th>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th></th>\n",
        "      <th>color</th>\n",
        "      <th>Green</th>\n",
        "      <th>Red</th>\n",
        "      <th>Green</th>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>key1</th>\n",
        "      <th>key2</th>\n",
        "      <th></th>\n",
        "      <th></th>\n",
        "      <th></th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th rowspan=\"2\" valign=\"top\">a</th>\n",
        "      <th>1</th>\n",
        "      <td> 0</td>\n",
        "      <td>  1</td>\n",
        "      <td>  2</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2</th>\n",
        "      <td> 3</td>\n",
        "      <td>  4</td>\n",
        "      <td>  5</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th rowspan=\"2\" valign=\"top\">b</th>\n",
        "      <th>1</th>\n",
        "      <td> 6</td>\n",
        "      <td>  7</td>\n",
        "      <td>  8</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2</th>\n",
        "      <td> 9</td>\n",
        "      <td> 10</td>\n",
        "      <td> 11</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 156,
       "text": [
        "state       Ohio       Colorado\n",
        "color      Green  Red     Green\n",
        "key1 key2                      \n",
        "a    1         0    1         2\n",
        "     2         3    4         5\n",
        "b    1         6    7         8\n",
        "     2         9   10        11"
       ]
      }
     ],
     "prompt_number": 156
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "frame.sum(level='key2')"
     ],
     "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>state</th>\n",
        "      <th colspan=\"2\" halign=\"left\">Ohio</th>\n",
        "      <th>Colorado</th>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>color</th>\n",
        "      <th>Green</th>\n",
        "      <th>Red</th>\n",
        "      <th>Green</th>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>key2</th>\n",
        "      <th></th>\n",
        "      <th></th>\n",
        "      <th></th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>1</th>\n",
        "      <td>  6</td>\n",
        "      <td>  8</td>\n",
        "      <td> 10</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2</th>\n",
        "      <td> 12</td>\n",
        "      <td> 14</td>\n",
        "      <td> 16</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 157,
       "text": [
        "state   Ohio       Colorado\n",
        "color  Green  Red     Green\n",
        "key2                       \n",
        "1          6    8        10\n",
        "2         12   14        16"
       ]
      }
     ],
     "prompt_number": 157
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "frame.sum(level='color',axis=1)"
     ],
     "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>color</th>\n",
        "      <th>Green</th>\n",
        "      <th>Red</th>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>key1</th>\n",
        "      <th>key2</th>\n",
        "      <th></th>\n",
        "      <th></th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th rowspan=\"2\" valign=\"top\">a</th>\n",
        "      <th>1</th>\n",
        "      <td>  2</td>\n",
        "      <td>  1</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2</th>\n",
        "      <td>  8</td>\n",
        "      <td>  4</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th rowspan=\"2\" valign=\"top\">b</th>\n",
        "      <th>1</th>\n",
        "      <td> 14</td>\n",
        "      <td>  7</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2</th>\n",
        "      <td> 20</td>\n",
        "      <td> 10</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 158,
       "text": [
        "color      Green  Red\n",
        "key1 key2            \n",
        "a    1         2    1\n",
        "     2         8    4\n",
        "b    1        14    7\n",
        "     2        20   10"
       ]
      }
     ],
     "prompt_number": 158
    },
    {
     "cell_type": "heading",
     "level": 2,
     "metadata": {},
     "source": [
      "Using DataFrame's COlumns"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "frame = DataFrame({'a':range(7), 'b':range(7,0,-1),\n",
      "          'c':['one','one','one','two','two','two','two'],\n",
      "          'd':[0,1,2,0,1,2,3]})"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 161
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "frame"
     ],
     "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>a</th>\n",
        "      <th>b</th>\n",
        "      <th>c</th>\n",
        "      <th>d</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>0</th>\n",
        "      <td> 0</td>\n",
        "      <td> 7</td>\n",
        "      <td> one</td>\n",
        "      <td> 0</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>1</th>\n",
        "      <td> 1</td>\n",
        "      <td> 6</td>\n",
        "      <td> one</td>\n",
        "      <td> 1</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2</th>\n",
        "      <td> 2</td>\n",
        "      <td> 5</td>\n",
        "      <td> one</td>\n",
        "      <td> 2</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>3</th>\n",
        "      <td> 3</td>\n",
        "      <td> 4</td>\n",
        "      <td> two</td>\n",
        "      <td> 0</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>4</th>\n",
        "      <td> 4</td>\n",
        "      <td> 3</td>\n",
        "      <td> two</td>\n",
        "      <td> 1</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>5</th>\n",
        "      <td> 5</td>\n",
        "      <td> 2</td>\n",
        "      <td> two</td>\n",
        "      <td> 2</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>6</th>\n",
        "      <td> 6</td>\n",
        "      <td> 1</td>\n",
        "      <td> two</td>\n",
        "      <td> 3</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 162,
       "text": [
        "   a  b    c  d\n",
        "0  0  7  one  0\n",
        "1  1  6  one  1\n",
        "2  2  5  one  2\n",
        "3  3  4  two  0\n",
        "4  4  3  two  1\n",
        "5  5  2  two  2\n",
        "6  6  1  two  3"
       ]
      }
     ],
     "prompt_number": 162
    },
    {
     "cell_type": "heading",
     "level": 5,
     "metadata": {},
     "source": [
      "new data frame"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "frame2 = frame.set_index(['c','d'])"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 163
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "frame2"
     ],
     "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></th>\n",
        "      <th>a</th>\n",
        "      <th>b</th>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>c</th>\n",
        "      <th>d</th>\n",
        "      <th></th>\n",
        "      <th></th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th rowspan=\"3\" valign=\"top\">one</th>\n",
        "      <th>0</th>\n",
        "      <td> 0</td>\n",
        "      <td> 7</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>1</th>\n",
        "      <td> 1</td>\n",
        "      <td> 6</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2</th>\n",
        "      <td> 2</td>\n",
        "      <td> 5</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th rowspan=\"4\" valign=\"top\">two</th>\n",
        "      <th>0</th>\n",
        "      <td> 3</td>\n",
        "      <td> 4</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>1</th>\n",
        "      <td> 4</td>\n",
        "      <td> 3</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2</th>\n",
        "      <td> 5</td>\n",
        "      <td> 2</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>3</th>\n",
        "      <td> 6</td>\n",
        "      <td> 1</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 164,
       "text": [
        "       a  b\n",
        "c   d      \n",
        "one 0  0  7\n",
        "    1  1  6\n",
        "    2  2  5\n",
        "two 0  3  4\n",
        "    1  4  3\n",
        "    2  5  2\n",
        "    3  6  1"
       ]
      }
     ],
     "prompt_number": 164
    },
    {
     "cell_type": "heading",
     "level": 5,
     "metadata": {},
     "source": [
      "you can leave the columns in"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "frame.set_index(['c','d'], drop=False)"
     ],
     "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></th>\n",
        "      <th>a</th>\n",
        "      <th>b</th>\n",
        "      <th>c</th>\n",
        "      <th>d</th>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>c</th>\n",
        "      <th>d</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\">one</th>\n",
        "      <th>0</th>\n",
        "      <td> 0</td>\n",
        "      <td> 7</td>\n",
        "      <td> one</td>\n",
        "      <td> 0</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>1</th>\n",
        "      <td> 1</td>\n",
        "      <td> 6</td>\n",
        "      <td> one</td>\n",
        "      <td> 1</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2</th>\n",
        "      <td> 2</td>\n",
        "      <td> 5</td>\n",
        "      <td> one</td>\n",
        "      <td> 2</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th rowspan=\"4\" valign=\"top\">two</th>\n",
        "      <th>0</th>\n",
        "      <td> 3</td>\n",
        "      <td> 4</td>\n",
        "      <td> two</td>\n",
        "      <td> 0</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>1</th>\n",
        "      <td> 4</td>\n",
        "      <td> 3</td>\n",
        "      <td> two</td>\n",
        "      <td> 1</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2</th>\n",
        "      <td> 5</td>\n",
        "      <td> 2</td>\n",
        "      <td> two</td>\n",
        "      <td> 2</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>3</th>\n",
        "      <td> 6</td>\n",
        "      <td> 1</td>\n",
        "      <td> two</td>\n",
        "      <td> 3</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 165,
       "text": [
        "       a  b    c  d\n",
        "c   d              \n",
        "one 0  0  7  one  0\n",
        "    1  1  6  one  1\n",
        "    2  2  5  one  2\n",
        "two 0  3  4  two  0\n",
        "    1  4  3  two  1\n",
        "    2  5  2  two  2\n",
        "    3  6  1  two  3"
       ]
      }
     ],
     "prompt_number": 165
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "frame2.reset_index()"
     ],
     "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>c</th>\n",
        "      <th>d</th>\n",
        "      <th>a</th>\n",
        "      <th>b</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>0</th>\n",
        "      <td> one</td>\n",
        "      <td> 0</td>\n",
        "      <td> 0</td>\n",
        "      <td> 7</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>1</th>\n",
        "      <td> one</td>\n",
        "      <td> 1</td>\n",
        "      <td> 1</td>\n",
        "      <td> 6</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2</th>\n",
        "      <td> one</td>\n",
        "      <td> 2</td>\n",
        "      <td> 2</td>\n",
        "      <td> 5</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>3</th>\n",
        "      <td> two</td>\n",
        "      <td> 0</td>\n",
        "      <td> 3</td>\n",
        "      <td> 4</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>4</th>\n",
        "      <td> two</td>\n",
        "      <td> 1</td>\n",
        "      <td> 4</td>\n",
        "      <td> 3</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>5</th>\n",
        "      <td> two</td>\n",
        "      <td> 2</td>\n",
        "      <td> 5</td>\n",
        "      <td> 2</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>6</th>\n",
        "      <td> two</td>\n",
        "      <td> 3</td>\n",
        "      <td> 6</td>\n",
        "      <td> 1</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 166,
       "text": [
        "     c  d  a  b\n",
        "0  one  0  0  7\n",
        "1  one  1  1  6\n",
        "2  one  2  2  5\n",
        "3  two  0  3  4\n",
        "4  two  1  4  3\n",
        "5  two  2  5  2\n",
        "6  two  3  6  1"
       ]
      }
     ],
     "prompt_number": 166
    },
    {
     "cell_type": "heading",
     "level": 2,
     "metadata": {},
     "source": [
      "Other Pandas Topics"
     ]
    },
    {
     "cell_type": "heading",
     "level": 4,
     "metadata": {},
     "source": [
      "Integer indexing "
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "ser = Series(np.arange(3.))"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 167
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "ser[-1]"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "ename": "KeyError",
       "evalue": "-1",
       "output_type": "pyerr",
       "traceback": [
        "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m\n\u001b[0;31mKeyError\u001b[0m                                  Traceback (most recent call last)",
        "\u001b[0;32m<ipython-input-168-3cbe0b873a9e>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m()\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0mser\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m-\u001b[0m\u001b[0;36m1\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
        "\u001b[0;32m/Users/sergulaydore/anaconda/lib/python2.7/site-packages/pandas/core/series.pyc\u001b[0m in \u001b[0;36m__getitem__\u001b[0;34m(self, key)\u001b[0m\n\u001b[1;32m    482\u001b[0m     \u001b[0;32mdef\u001b[0m \u001b[0m__getitem__\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mkey\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    483\u001b[0m         \u001b[0;32mtry\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 484\u001b[0;31m             \u001b[0mresult\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mindex\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mget_value\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mkey\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    485\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    486\u001b[0m             \u001b[0;32mif\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0mnp\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0misscalar\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mresult\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
        "\u001b[0;32m/Users/sergulaydore/anaconda/lib/python2.7/site-packages/pandas/core/index.pyc\u001b[0m in \u001b[0;36mget_value\u001b[0;34m(self, series, key)\u001b[0m\n\u001b[1;32m   1194\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1195\u001b[0m         \u001b[0;32mtry\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1196\u001b[0;31m             \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_engine\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mget_value\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0ms\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mk\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   1197\u001b[0m         \u001b[0;32mexcept\u001b[0m \u001b[0mKeyError\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0me1\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1198\u001b[0m             \u001b[0;32mif\u001b[0m \u001b[0mlen\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;34m>\u001b[0m \u001b[0;36m0\u001b[0m \u001b[0;32mand\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0minferred_type\u001b[0m \u001b[0;32min\u001b[0m \u001b[0;34m[\u001b[0m\u001b[0;34m'integer'\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m'boolean'\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
        "\u001b[0;32m/Users/sergulaydore/anaconda/lib/python2.7/site-packages/pandas/index.so\u001b[0m in \u001b[0;36mpandas.index.IndexEngine.get_value (pandas/index.c:2993)\u001b[0;34m()\u001b[0m\n",
        "\u001b[0;32m/Users/sergulaydore/anaconda/lib/python2.7/site-packages/pandas/index.so\u001b[0m in \u001b[0;36mpandas.index.IndexEngine.get_value (pandas/index.c:2808)\u001b[0;34m()\u001b[0m\n",
        "\u001b[0;32m/Users/sergulaydore/anaconda/lib/python2.7/site-packages/pandas/index.so\u001b[0m in \u001b[0;36mpandas.index.IndexEngine.get_loc (pandas/index.c:3534)\u001b[0;34m()\u001b[0m\n",
        "\u001b[0;32m/Users/sergulaydore/anaconda/lib/python2.7/site-packages/pandas/hashtable.so\u001b[0m in \u001b[0;36mpandas.hashtable.Int64HashTable.get_item (pandas/hashtable.c:7035)\u001b[0;34m()\u001b[0m\n",
        "\u001b[0;32m/Users/sergulaydore/anaconda/lib/python2.7/site-packages/pandas/hashtable.so\u001b[0m in \u001b[0;36mpandas.hashtable.Int64HashTable.get_item (pandas/hashtable.c:6976)\u001b[0;34m()\u001b[0m\n",
        "\u001b[0;31mKeyError\u001b[0m: -1"
       ]
      }
     ],
     "prompt_number": 168
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "ser"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 169,
       "text": [
        "0    0\n",
        "1    1\n",
        "2    2\n",
        "dtype: float64"
       ]
      }
     ],
     "prompt_number": 169
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "non-integer index works"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "ser2 = Series(np.arange(3.), index = ['a','b','c'])"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 170
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "ser2[-1]"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 171,
       "text": [
        "2.0"
       ]
      }
     ],
     "prompt_number": 171
    },
    {
     "cell_type": "heading",
     "level": 5,
     "metadata": {},
     "source": [
      "To keep things consistent, use .ix"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "ser.ix[:1]"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 172,
       "text": [
        "0    0\n",
        "1    1\n",
        "dtype: float64"
       ]
      }
     ],
     "prompt_number": 172
    },
    {
     "cell_type": "heading",
     "level": 5,
     "metadata": {},
     "source": [
      "reliable position indexing"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "ser3 = Series(range(3), index = [-5, 1,3])"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 173
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "ser3.iget_value(2)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 174,
       "text": [
        "2"
       ]
      }
     ],
     "prompt_number": 174
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "frame = DataFrame(np.arange(6).reshape(3,2), index=[2,0,1])"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 175
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "frame"
     ],
     "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>0</th>\n",
        "      <th>1</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>2</th>\n",
        "      <td> 0</td>\n",
        "      <td> 1</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>0</th>\n",
        "      <td> 2</td>\n",
        "      <td> 3</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>1</th>\n",
        "      <td> 4</td>\n",
        "      <td> 5</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 176,
       "text": [
        "   0  1\n",
        "2  0  1\n",
        "0  2  3\n",
        "1  4  5"
       ]
      }
     ],
     "prompt_number": 176
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "frame.irow(0)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 177,
       "text": [
        "0    0\n",
        "1    1\n",
        "Name: 2, dtype: int64"
       ]
      }
     ],
     "prompt_number": 177
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "frame.irow(2)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 179,
       "text": [
        "0    4\n",
        "1    5\n",
        "Name: 1, dtype: int64"
       ]
      }
     ],
     "prompt_number": 179
    }
   ],
   "metadata": {}
  }
 ]
}