pandas-0.13-bug

pandas-0.13-bug.ipynb

{
 "metadata": {
  "name": "pandas 0.13 bug"
 },
 "nbformat": 3,
 "nbformat_minor": 0,
 "worksheets": [
  {
   "cells": [
    {
     "cell_type": "code",
     "collapsed": false,
     "input": "import pandas as pd\nimport datetime",
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 3
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": "# First frame\ndf1 = pd.DataFrame(dict(a=list(range(1,4)), b=list(range(1,4))))\ndf1.columns = pd.MultiIndex.from_product([['frame1'], df1.columns])",
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 7
    },
    {
     "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>\n      <th></th>\n      <th colspan=\"2\" halign=\"left\">frame1</th>\n    </tr>\n    <tr>\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> 1</td>\n      <td> 1</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td> 2</td>\n      <td> 2</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td> 3</td>\n      <td> 3</td>\n    </tr>\n  </tbody>\n</table>\n<p>3 rows \u00d7 2 columns</p>\n</div>",
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 8,
       "text": "   frame1   \n        a  b\n0       1  1\n1       2  2\n2       3  3\n\n[3 rows x 2 columns]"
      }
     ],
     "prompt_number": 8
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": "# Second frame with a datetime in first column\n\ndf2 = pd.DataFrame(dict(c=[datetime.datetime.now()]*3, d=[1,2,3]))\ndf2.columns = pd.MultiIndex.from_product([['frame2'], df2.columns])\n",
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 15
    },
    {
     "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>\n      <th></th>\n      <th colspan=\"2\" halign=\"left\">frame2</th>\n    </tr>\n    <tr>\n      <th></th>\n      <th>c</th>\n      <th>d</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>2015-10-08 21:47:01.106762</td>\n      <td> 1</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>2015-10-08 21:47:01.106762</td>\n      <td> 2</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>2015-10-08 21:47:01.106762</td>\n      <td> 3</td>\n    </tr>\n  </tbody>\n</table>\n<p>3 rows \u00d7 2 columns</p>\n</div>",
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 16,
       "text": "                      frame2  frame2\n                           c       d\n0 2015-10-08 21:47:01.106762       1\n1 2015-10-08 21:47:01.106762       2\n2 2015-10-08 21:47:01.106762       3\n\n[3 rows x 2 columns]"
      }
     ],
     "prompt_number": 16
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": "",
     "language": "python",
     "metadata": {},
     "outputs": []
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": "# now create an empty dataframe using df2\ndf3=df2.loc[[]]\ndf3",
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "html": "<div style=\"max-height:1000px;max-width:1500px;overflow:auto;\">\n<table border=\"1\" class=\"dataframe\">\n  <tbody>\n    <tr>\n      <td>Index([], dtype='object')</td>\n      <td>Empty DataFrame</td>\n    </tr>\n  </tbody>\n</table>\n<p>0 rows \u00d7 2 columns</p>\n</div>",
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 17,
       "text": "Empty DataFrame\nColumns: [(frame2, c), (frame2, d)]\nIndex: []\n\n[0 rows x 2 columns]"
      }
     ],
     "prompt_number": 17
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": "df3.columns",
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 18,
       "text": "MultiIndex(levels=[['frame2'], ['c', 'd']],\n           labels=[[0, 0], [0, 1]])"
      }
     ],
     "prompt_number": 18
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": "# now merge df1 with df3\n\nmerged_df = pd.merge(df1, df3, how='left' , left_index=True, right_index=True)",
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 22
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": "merged_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>\n      <th></th>\n      <th colspan=\"2\" halign=\"left\">frame1</th>\n      <th colspan=\"2\" halign=\"left\">frame2</th>\n    </tr>\n    <tr>\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> 1</td>\n      <td> 1</td>\n      <td>NaT</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td> 2</td>\n      <td> 2</td>\n      <td>NaT</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td> 3</td>\n      <td> 3</td>\n      <td>NaT</td>\n      <td>NaN</td>\n    </tr>\n  </tbody>\n</table>\n<p>3 rows \u00d7 4 columns</p>\n</div>",
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 23,
       "text": "   frame1    frame2  frame2\n        a  b      c       d\n0       1  1    NaT     NaN\n1       2  2    NaT     NaN\n2       3  3    NaT     NaN\n\n[3 rows x 4 columns]"
      }
     ],
     "prompt_number": 23
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": "# Now, here is the climax, observe how the values change based on how they are indexed into\nmerged_df['frame2'].loc[1, 'd'], merged_df['frame2'].at[1, 'd'], merged_df.loc[1, ('frame2', 'd')]",
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 24,
       "text": "(NaT, nan, nan)"
      }
     ],
     "prompt_number": 24
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": "",
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": "*"
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": "",
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": "*"
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": "",
     "language": "python",
     "metadata": {},
     "outputs": []
    }
   ],
   "metadata": {}
  }
 ]
}