h5py_indices.ipynb

{
 "metadata": {
  "name": "",
  "signature": "sha256:b57688628ab9dced9a7a1cd4ca63a4ecbbb88f993ce65bc2e0a4f5cf9fe4e278"
 },
 "nbformat": 3,
 "nbformat_minor": 0,
 "worksheets": [
  {
   "cells": [
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "# Slicing huge arrays in h5py"
     ]
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "Let's import h5py and NumPy."
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "import h5py\n",
      "import numpy as np\n",
      "import os"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 1
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "## Chunked array"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "n, k = 1000000, 500"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 11
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "if not os.path.exists('test_ind'):\n",
      "    # We create the file.\n",
      "    with h5py.File(\"test_ind\", \"w\") as f:\n",
      "        a = f.create_dataset('/test', shape=(n, k),\n",
      "                             chunks=(100, k))\n",
      "        # We fill the array progressively.\n",
      "        for i in range(10):\n",
      "            print i,\n",
      "            a[i*(n//10):(i+1)*(n//10),...] = np.random.rand((n//10), k)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "0 "
       ]
      },
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "1 "
       ]
      },
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "2 "
       ]
      },
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "3 "
       ]
      },
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "4 "
       ]
      },
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "5 "
       ]
      },
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "6 "
       ]
      },
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "7 "
       ]
      },
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "8 "
       ]
      },
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "9\n"
       ]
      }
     ],
     "prompt_number": 12
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "Now, let's do some benchmarks."
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "ind = np.random.randint(size=1000, low=0, high=n)\n",
      "ind = np.sort(ind)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 15
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "with h5py.File(\"test_ind\", \"r\") as f:\n",
      "    a = f['/test']\n",
      "    \n",
      "    %timeit -r1 -n1 [a[i,...] for i in ind]\n",
      "    %timeit [a[i,...] for i in ind]\n",
      "    %timeit -r1 -n1 [a[i:i+1,...] for i in ind]\n",
      "    %timeit [a[i:i+1,...] for i in ind]\n",
      "    #%timeit -r1 -n1 a[:,...]\n",
      "    #%timeit -r1 -n1 a[:,...][ind,...]"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "1 loops, best of 1: 198 ms per loop\n",
        "10 loops, best of 3: 180 ms per loop"
       ]
      },
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "\n",
        "1 loops, best of 1: 177 ms per loop"
       ]
      },
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "\n",
        "10 loops, best of 3: 177 ms per loop"
       ]
      },
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "\n"
       ]
      }
     ],
     "prompt_number": 16
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "## Contiguous array"
     ]
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "Let's try with a contiguous array."
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "if not os.path.exists('test_ind_contiguous'):\n",
      "    # We create the file.\n",
      "    with h5py.File(\"test_ind_contiguous\", \"w\") as f:\n",
      "        a = f.create_dataset('/test', shape=(n, k),)\n",
      "        # We fill the array progressively.\n",
      "        for i in range(10):\n",
      "            print i,\n",
      "            a[i*(n//10):(i+1)*(n//10),...] = np.random.rand((n//10), k)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 6
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "with h5py.File(\"test_ind_contiguous\", \"r\") as f:\n",
      "    a = f['/test']\n",
      "    \n",
      "    %timeit -r1 -n1 [a[i,...] for i in ind]\n",
      "    %timeit [a[i,...] for i in ind]\n",
      "    %timeit -r1 -n1 [a[i:i+1,...] for i in ind]\n",
      "    %timeit [a[i:i+1,...] for i in ind]\n",
      "    #%timeit -r1 -n1 a[:,...]\n",
      "    #%timeit -r1 -n1 a[:,...][ind,...]"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "1 loops, best of 1: 159 ms per loop\n",
        "10 loops, best of 3: 149 ms per loop"
       ]
      },
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "\n",
        "1 loops, best of 1: 147 ms per loop"
       ]
      },
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "\n",
        "10 loops, best of 3: 141 ms per loop"
       ]
      },
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "\n"
       ]
      }
     ],
     "prompt_number": 9
    }
   ],
   "metadata": {}
  }
 ]
}

h5py_slice.ipynb

pytables_slice.ipynb