{
 "metadata": {
  "name": "",
  "signature": "sha256:385948bcca06a9e75bbf9cbf0d8473fefdb64d718f38a1c81b21ffecf762fa33"
 },
 "nbformat": 3,
 "nbformat_minor": 0,
 "worksheets": [
  {
   "cells": [
    {
     "cell_type": "heading",
     "level": 1,
     "metadata": {},
     "source": [
      "[``anhima.util``](http://anhima.readthedocs.org/en/latest/util.html) - Miscellaneous utilities"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "from __future__ import print_function, division\n",
      "import sys\n",
      "import numpy as np\n",
      "import random\n",
      "# import anhima\n",
      "# dev imports\n",
      "sys.path.insert(0, '..')\n",
      "%reload_ext autoreload\n",
      "%autoreload 1\n",
      "%aimport anhima.util"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 1
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "n_variants = 100000\n",
      "n_samples = 1000\n",
      "genotypes = np.random.randint(0, 2, size=(n_variants, n_samples, 2)).astype('i1')\n",
      "genotypes.shape, genotypes.nbytes / 1e6"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "pyout",
       "prompt_number": 2,
       "text": [
        "((100000, 1000, 2), 200.0)"
       ]
      }
     ],
     "prompt_number": 2
    },
    {
     "cell_type": "heading",
     "level": 2,
     "metadata": {},
     "source": [
      "Block apply"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "gn = anhima.gt.as_n_alt(genotypes)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 3
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "gn2 = anhima.util.block_apply(anhima.gt.as_n_alt, genotypes, block_size=1000)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 4
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "assert np.array_equal(gn, gn2)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 5
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "ac = anhima.af.allele_counts(genotypes)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 6
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "ac2 = anhima.util.block_apply(anhima.af.allele_counts, genotypes, block_size=1000)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 7
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "assert np.array_equal(ac, ac2)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 8
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "packed = anhima.gt.pack_diploid(genotypes)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 9
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "packed2 = anhima.util.block_apply(anhima.gt.pack_diploid, genotypes, block_size=1000)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 10
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "assert np.array_equal(packed, packed2)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 11
    },
    {
     "cell_type": "heading",
     "level": 2,
     "metadata": {},
     "source": [
      "Block take2D"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "row_indices = sorted(random.sample(range(n_variants), n_variants//10))\n",
      "col_indices = sorted(random.sample(range(n_samples), n_samples//10))"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 12
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "g = genotypes.take(row_indices, axis=0).take(col_indices, axis=1)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 13
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "g2 = anhima.util.block_take2d(genotypes, row_indices, col_indices, block_size=1000)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 14
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "assert np.array_equal(g, g2)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 15
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 16
    }
   ],
   "metadata": {}
  }
 ]
}