{ "cells": [ { "cell_type": "markdown", "metadata": {}, "source": [ "# Iterators" ] }, { "cell_type": "code", "execution_count": 8, "metadata": { "collapsed": true }, "outputs": [], "source": [ "df = DataFrame({'A' : np.random.randn(10), 'B' : 'foo'})\n", "df.to_csv('data/test_iterator.csv',mode='w')\n", "df.to_hdf('data/test_iterator.h5','df',mode='w',format='table',data_columns=True)" ] }, { "cell_type": "code", "execution_count": 9, "metadata": { "collapsed": false }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ " A B\n", "0 0.548203 foo\n", "1 0.513688 foo\n", "2 0.260623 foo\n", " A B\n", "3 -1.474517 foo\n", "4 -2.653109 foo\n", "5 -0.201879 foo\n", " A B\n", "6 0.850183 foo\n", "7 -0.796159 foo\n", "8 -0.874545 foo\n", " A B\n", "9 -0.272888 foo\n" ] } ], "source": [ "for df in pd.read_csv('data/test_iterator.csv',chunksize=3,index_col=0):\n", " print df" ] }, { "cell_type": "code", "execution_count": 10, "metadata": { "collapsed": false }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ " A B\n", "0 0.548203 foo\n", "1 0.513688 foo\n", "2 0.260623 foo\n", " A B\n", "3 -1.474517 foo\n", "4 -2.653109 foo\n", "5 -0.201879 foo\n", " A B\n", "6 0.850183 foo\n", "7 -0.796159 foo\n", "8 -0.874545 foo\n", " A B\n", "9 -0.272888 foo\n" ] } ], "source": [ "for df in pd.read_hdf('data/test_iterator.h5','df',chunksize=3):\n", " print df" ] }, { "cell_type": "markdown", "metadata": { "collapsed": true }, "source": [ "# usecols" ] }, { "cell_type": "code", "execution_count": 11, "metadata": { "collapsed": false }, "outputs": [ { "data": { "text/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", "
B
0foo
1foo
2foo
3foo
4foo
5foo
6foo
7foo
8foo
9foo
\n", "
" ], "text/plain": [ " B\n", "0 foo\n", "1 foo\n", "2 foo\n", "3 foo\n", "4 foo\n", "5 foo\n", "6 foo\n", "7 foo\n", "8 foo\n", "9 foo" ] }, "execution_count": 11, "metadata": {}, "output_type": "execute_result" } ], "source": [ "pd.read_csv('data/test_iterator.csv',usecols=[0,'B'],index_col=0)" ] }, { "cell_type": "code", "execution_count": 12, "metadata": { "collapsed": false }, "outputs": [ { "data": { "text/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", "
B
0foo
1foo
2foo
3foo
4foo
5foo
6foo
7foo
8foo
9foo
\n", "
" ], "text/plain": [ " B\n", "0 foo\n", "1 foo\n", "2 foo\n", "3 foo\n", "4 foo\n", "5 foo\n", "6 foo\n", "7 foo\n", "8 foo\n", "9 foo" ] }, "execution_count": 12, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# this is actually a reindex\n", "pd.read_hdf('data/test_iterator.h5','df',columns=['B'])" ] }, { "cell_type": "code", "execution_count": 20, "metadata": { "collapsed": false }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "0 foo\n", "1 foo\n", "2 foo\n", "3 foo\n", "4 foo\n", "5 foo\n", "6 foo\n", "7 foo\n", "8 foo\n", "9 foo\n", "dtype: object\n" ] } ], "source": [ "with pd.HDFStore('data/test_iterator.h5') as store:\n", " print store.select_column('df','B')" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "collapsed": true }, "outputs": [], "source": [] } ], "metadata": { "kernelspec": { "display_name": "Python 2", "language": "python", "name": "python2" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 2 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython2", "version": "2.7.10" } }, "nbformat": 4, "nbformat_minor": 0 }