From c7bc8e386f6ea8f6189986fae90c91dbfdaefcdc Mon Sep 17 00:00:00 2001 From: Donne Martin Date: Fri, 13 Feb 2015 15:53:15 -0500 Subject: [PATCH] Added snippet to concatenate two DataFrames. --- pandas/pandas_clean.ipynb | 208 +++++++++++++++++++++++++++++++++++++- 1 file changed, 203 insertions(+), 5 deletions(-) diff --git a/pandas/pandas_clean.ipynb b/pandas/pandas_clean.ipynb index 69d8c37..8523bc3 100644 --- a/pandas/pandas_clean.ipynb +++ b/pandas/pandas_clean.ipynb @@ -1,7 +1,7 @@ { "metadata": { "name": "", - "signature": "sha256:82be3772f18b2c96a1486b76adf812e774890e366b350dfd5b1257ab4b086b8e" + "signature": "sha256:f776a525b9cd73f2f19e9e51e3318238aa9c122bb94228ae307286d483a6c2f1" }, "nbformat": 3, "nbformat_minor": 0, @@ -301,13 +301,13 @@ " \n", " 3\n", " 4.0\n", - " MARYLAND\n", + " MD\n", " 2014\n", " \n", " \n", " 4\n", " 4.1\n", - " MARYLAND\n", + " MD\n", " 2015\n", " \n", " \n", @@ -322,12 +322,210 @@ "0 5.0 VIRGINIA 2012\n", "1 5.1 VIRGINIA 2013\n", "2 5.2 VIRGINIA 2014\n", - "3 4.0 MARYLAND 2014\n", - "4 4.1 MARYLAND 2015" + "3 4.0 MD 2014\n", + "4 4.1 MD 2015" ] } ], "prompt_number": 5 + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "Concatenate two DataFrames:" + ] + }, + { + "cell_type": "code", + "collapsed": false, + "input": [ + "data_2 = {'state' : ['NY', 'NY', 'NY', 'FL', 'FL'],\n", + " 'year' : [2012, 2013, 2014, 2014, 2015],\n", + " 'pop' : [6.0, 6.1, 6.2, 3.0, 3.1]}\n", + "df_2 = DataFrame(data_2)\n", + "df_2" + ], + "language": "python", + "metadata": {}, + "outputs": [ + { + "html": [ + "
\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
popstateyear
0 6.0 NY 2012
1 6.1 NY 2013
2 6.2 NY 2014
3 3.0 FL 2014
4 3.1 FL 2015
\n", + "
" + ], + "metadata": {}, + "output_type": "pyout", + "prompt_number": 6, + "text": [ + " pop state year\n", + "0 6.0 NY 2012\n", + "1 6.1 NY 2013\n", + "2 6.2 NY 2014\n", + "3 3.0 FL 2014\n", + "4 3.1 FL 2015" + ] + } + ], + "prompt_number": 6 + }, + { + "cell_type": "code", + "collapsed": false, + "input": [ + "df_3 = pd.concat([df_1, df_2])\n", + "df_3" + ], + "language": "python", + "metadata": {}, + "outputs": [ + { + "html": [ + "
\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
popstateyear
0 5.0 VIRGINIA 2012
1 5.1 VIRGINIA 2013
2 5.2 VIRGINIA 2014
3 4.0 MD 2014
4 4.1 MD 2015
0 6.0 NY 2012
1 6.1 NY 2013
2 6.2 NY 2014
3 3.0 FL 2014
4 3.1 FL 2015
\n", + "
" + ], + "metadata": {}, + "output_type": "pyout", + "prompt_number": 7, + "text": [ + " pop state year\n", + "0 5.0 VIRGINIA 2012\n", + "1 5.1 VIRGINIA 2013\n", + "2 5.2 VIRGINIA 2014\n", + "3 4.0 MD 2014\n", + "4 4.1 MD 2015\n", + "0 6.0 NY 2012\n", + "1 6.1 NY 2013\n", + "2 6.2 NY 2014\n", + "3 3.0 FL 2014\n", + "4 3.1 FL 2015" + ] + } + ], + "prompt_number": 7 + }, + { + "cell_type": "code", + "collapsed": false, + "input": [], + "language": "python", + "metadata": {}, + "outputs": [], + "prompt_number": 7 } ], "metadata": {}