table_row_timing.py

{
 "metadata": {
  "name": "",
  "signature": "sha256:4a49c6d0edca23508b557df3528e49f4d68874bce29b47251e2bfe77b10e39f2"
 },
 "nbformat": 3,
 "nbformat_minor": 0,
 "worksheets": [
  {
   "cells": [
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "from astropy.table import Table\n",
      "import numpy as np"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 3
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "### Experiment with a table having 1000 rows and 100 columns"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "t = Table(np.arange(100000).reshape(1000, 100))"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 5
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "#### Iterate with current Rows and access one of the table columns in each row"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "def access1(t):\n",
      "    for row in t:\n",
      "        col25 = row['col25'] + 1"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 6
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "timeit access1(t)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "100 loops, best of 3: 8.42 ms per loop\n"
       ]
      }
     ],
     "prompt_number": 7
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "#### Iterate with something like proposed Row and access one table column in each row"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "def access2(t):\n",
      "    cols = t.columns.values()\n",
      "    for i in xrange(len(t)):\n",
      "        rowvals = [col[i] for col in cols]\n",
      "        col25 = rowvals[25] + 1"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 8
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "timeit access2(t)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "10 loops, best of 3: 27.3 ms per loop\n"
       ]
      }
     ],
     "prompt_number": 9
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "#### Iterate with current Row but do someting with every table column"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "def access3(t):\n",
      "    colnames = t.colnames\n",
      "    for row in t:\n",
      "        for icol in xrange(len(colnames)):\n",
      "            col = row[icol] + 1"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 15
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "timeit access3(t)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "1 loops, best of 3: 373 ms per loop\n"
       ]
      }
     ],
     "prompt_number": 16
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "#### Iterate with proposed Row and do something with every table column"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "def access4(t):\n",
      "    cols = t.columns.values()\n",
      "    for i in xrange(len(t)):\n",
      "        for col in cols:\n",
      "            colval = col[i] + 1"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 17
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "timeit access4(t)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "10 loops, best of 3: 130 ms per loop\n"
       ]
      }
     ],
     "prompt_number": 18
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [],
     "language": "python",
     "metadata": {},
     "outputs": []
    }
   ],
   "metadata": {}
  }
 ]
}