{
 "metadata": {
  "name": "",
  "signature": "sha256:ebbbd1a5dfe53666784a8a535b0c80474c3776c6d3382adde75214c32e804978"
 },
 "nbformat": 3,
 "nbformat_minor": 0,
 "worksheets": [
  {
   "cells": [
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "from __future__ import print_function, division\n",
      "import numpy as np\n",
      "%matplotlib inline\n",
      "import matplotlib.pyplot as plt\n",
      "import vcfnp\n",
      "vcfnp.__version__"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 1,
       "text": [
        "'2.0.0'"
       ]
      }
     ],
     "prompt_number": 1
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "# VCF file name\n",
      "filename = 'fixture/sample.vcf'"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 2
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "# load data from fixed fields (including INFO)\n",
      "v = vcfnp.variants(filename, cache=True).view(np.recarray)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stderr",
       "text": [
        "[vcfnp] 2015-01-23 11:22:59.232507 :: caching is enabled\n"
       ]
      },
      {
       "output_type": "stream",
       "stream": "stderr",
       "text": [
        "[vcfnp] 2015-01-23 11:22:59.232909 :: cache file available\n"
       ]
      },
      {
       "output_type": "stream",
       "stream": "stderr",
       "text": [
        "[vcfnp] 2015-01-23 11:22:59.233095 :: loading from cache file fixture/sample.vcf.vcfnp_cache/variants.npy\n"
       ]
      }
     ],
     "prompt_number": 3
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "v.dtype"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 4,
       "text": [
        "dtype([('CHROM', 'S12'), ('POS', '<i4'), ('ID', 'S12'), ('REF', 'S12'), ('ALT', 'S12'), ('QUAL', '<f4'), ('FILTER_q10', '?'), ('FILTER_s50', '?'), ('FILTER_PASS', '?'), ('num_alleles', 'u1'), ('is_snp', '?'), ('svlen', '<i4'), ('AA', 'S12'), ('AC', '<u2'), ('AF', '<f2'), ('AN', '<u2'), ('DB', '?'), ('DP', '<i4'), ('H2', '?'), ('NS', '<i4')])"
       ]
      }
     ],
     "prompt_number": 4
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "v.CHROM"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 5,
       "text": [
        "chararray([b'19', b'19', b'20', b'20', b'20', b'20', b'20', b'20', b'X'], \n",
        "      dtype='|S12')"
       ]
      }
     ],
     "prompt_number": 5
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "v.POS"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 6,
       "text": [
        "array([    111,     112,   14370,   17330, 1110696, 1230237, 1234567,\n",
        "       1235237,      10], dtype=int32)"
       ]
      }
     ],
     "prompt_number": 6
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "v.DP"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 7,
       "text": [
        "array([ 0,  0, 14, 11, 10, 13,  9,  0,  0], dtype=int32)"
       ]
      }
     ],
     "prompt_number": 7
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "# print some simple variant metrics\n",
      "print('found %s variants (%s SNPs)' % (v.size, np.count_nonzero(v.is_snp)))\n",
      "print('QUAL mean (std): %s (%s)' % (np.mean(v.QUAL), np.std(v.QUAL)))"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "found 9 variants (5 SNPs)\n",
        "QUAL mean (std): 25.0667 (22.816)\n"
       ]
      }
     ],
     "prompt_number": 8
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "# plot a histogram of variant depth\n",
      "fig = plt.figure(1)\n",
      "ax = fig.add_subplot(111)\n",
      "ax.hist(v.DP)\n",
      "ax.set_title('DP histogram')\n",
      "ax.set_xlabel('DP');"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "display_data",
       "png": "iVBORw0KGgoAAAANSUhEUgAAAXUAAAEZCAYAAABoy7XpAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n86KKzRhE9m8AAAAASUVORK5CYII=\n",
       "text": [
        "<matplotlib.figure.Figure at 0x7f527a064908>"
       ]
      }
     ],
     "prompt_number": 9
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "# load data from sample columns\n",
      "c = vcfnp.calldata_2d(filename, cache=True).view(np.recarray)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stderr",
       "text": [
        "[vcfnp] 2015-01-23 11:22:59.494181 :: caching is enabled\n"
       ]
      },
      {
       "output_type": "stream",
       "stream": "stderr",
       "text": [
        "[vcfnp] 2015-01-23 11:22:59.494571 :: cache file available\n"
       ]
      },
      {
       "output_type": "stream",
       "stream": "stderr",
       "text": [
        "[vcfnp] 2015-01-23 11:22:59.494840 :: loading from cache file fixture/sample.vcf.vcfnp_cache/calldata_2d.npy\n"
       ]
      }
     ],
     "prompt_number": 10
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "c.dtype"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 11,
       "text": [
        "dtype([('is_called', '?'), ('is_phased', '?'), ('genotype', 'i1', (2,)), ('DP', '<u2'), ('GQ', 'u1'), ('GT', 'S3'), ('HQ', '<i4', (2,))])"
       ]
      }
     ],
     "prompt_number": 11
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "c.genotype"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 12,
       "text": [
        "array([[[ 0,  0],\n",
        "        [ 0,  0],\n",
        "        [ 0,  1]],\n",
        "\n",
        "       [[ 0,  0],\n",
        "        [ 0,  0],\n",
        "        [ 0,  1]],\n",
        "\n",
        "       [[ 0,  0],\n",
        "        [ 1,  0],\n",
        "        [ 1,  1]],\n",
        "\n",
        "       [[ 0,  0],\n",
        "        [ 0,  1],\n",
        "        [ 0,  0]],\n",
        "\n",
        "       [[ 1,  2],\n",
        "        [ 2,  1],\n",
        "        [ 2,  2]],\n",
        "\n",
        "       [[ 0,  0],\n",
        "        [ 0,  0],\n",
        "        [ 0,  0]],\n",
        "\n",
        "       [[ 0,  1],\n",
        "        [ 0,  2],\n",
        "        [-1, -1]],\n",
        "\n",
        "       [[ 0,  0],\n",
        "        [ 0,  0],\n",
        "        [-1, -1]],\n",
        "\n",
        "       [[ 0, -1],\n",
        "        [ 0,  1],\n",
        "        [ 0,  2]]], dtype=int8)"
       ]
      }
     ],
     "prompt_number": 12
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "# print some simple genotype metrics\n",
      "count_phased = np.count_nonzero(c.is_phased)\n",
      "count_variant = np.count_nonzero(np.any(c.genotype > 0, axis=2))\n",
      "count_missing = np.count_nonzero(~c.is_called)\n",
      "print('calls (phased, variant, missing): %s (%s, %s, %s)'\n",
      "    % (c.flatten().size, count_phased, count_variant, count_missing))"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "calls (phased, variant, missing): 27 (14, 12, 2)\n"
       ]
      }
     ],
     "prompt_number": 13
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "# plot a histogram of genotype quality\n",
      "fig = plt.figure(2)\n",
      "ax = fig.add_subplot(111)\n",
      "ax.hist(c.GQ.flatten())\n",
      "ax.set_title('GQ histogram')\n",
      "ax.set_xlabel('GQ');"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "display_data",
       "png": "iVBORw0KGgoAAAANSUhEUgAAAXEAAAEZCAYAAABhIBWTAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n",
       "text": [
        "<matplotlib.figure.Figure at 0x7f527a064518>"
       ]
      }
     ],
     "prompt_number": 14
    }
   ],
   "metadata": {}
  }
 ]
}