possible_bug.ipynb

{
 "metadata": {
  "name": "",
  "signature": "sha256:a35ba5cf62583326081251bbb8c13dc76d747fa7fc2c8bee3616faae26381d95"
 },
 "nbformat": 3,
 "nbformat_minor": 0,
 "worksheets": [
  {
   "cells": [
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "!pwd"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "/Users/mcdonadt/rs/qiime/qiime_test_data/parallel_beta_diversity\r\n"
       ]
      }
     ],
     "prompt_number": 1
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "# using cogent as that's what backs fast unifrac but same issue exists if done with skbio\n",
      "base_tree = 'rep_set.tre'\n",
      "changed_tree = 'rep_set_int_changed.tre'\n",
      "from cogent.parse.tree import DndParser"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 9
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "unchanged = DndParser(open(base_tree))\n",
      "altered_internal_labels = DndParser(open(base_tree))"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 4
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "# change the internal labels on the tree\n",
      "for idx, node in enumerate(altered_internal_labels.nontips()):\n",
      "    node.Name = idx\n",
      "\n",
      "with open(changed_tree, 'w') as fp:\n",
      "    fp.write(altered_internal_labels.getNewick(with_distances=True))"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 28
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "# verify tip names are unchanged\n",
      "[n.Name for n in unchanged.tips()] == [n.Name for n in altered_internal_labels.tips()]"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 29,
       "text": [
        "True"
       ]
      }
     ],
     "prompt_number": 29
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "# verify branch lengths in the tree haven't changed\n",
      "[n.Length for n in unchanged.traverse()] == [n.Length for n in altered_internal_labels.traverse()]"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 30,
       "text": [
        "True"
       ]
      }
     ],
     "prompt_number": 30
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "# verify the topologies are the same\n",
      "print unchanged.compareBySubsets(altered_internal_labels)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "0.0\n"
       ]
      }
     ],
     "prompt_number": 8
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "!beta_diversity.py -i otu_table.biom -o unchanged_test -t $base_tree -m unweighted_unifrac,weighted_unifrac  -r PC.636,PC.481,PC.354,PC.635,PC.593,PC.356,PC.355,PC.607,PC.634"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "/Users/mcdonadt/.virtualenvs/python27/lib/python2.7/site-packages/numpy/core/fromnumeric.py:2507: VisibleDeprecationWarning: `rank` is deprecated; use the `ndim` attribute or function instead. To find the rank of a matrix see `numpy.linalg.matrix_rank`.\r\n",
        "  VisibleDeprecationWarning)\r\n"
       ]
      },
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "/Users/mcdonadt/.virtualenvs/python27/lib/python2.7/site-packages/pytz/__init__.py:29: UserWarning: Module argparse was already imported from /System/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/argparse.pyc, but /Users/mcdonadt/.virtualenvs/python27/lib/python2.7/site-packages is being added to sys.path\r\n",
        "  from pkg_resources import resource_stream\r\n"
       ]
      }
     ],
     "prompt_number": 18
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "!beta_diversity.py -i otu_table.biom -o changed_test -t $changed_tree -m unweighted_unifrac,weighted_unifrac  -r PC.636,PC.481,PC.354,PC.635,PC.593,PC.356,PC.355,PC.607,PC.634"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "/Users/mcdonadt/.virtualenvs/python27/lib/python2.7/site-packages/numpy/core/fromnumeric.py:2507: VisibleDeprecationWarning: `rank` is deprecated; use the `ndim` attribute or function instead. To find the rank of a matrix see `numpy.linalg.matrix_rank`.\r\n",
        "  VisibleDeprecationWarning)\r\n"
       ]
      },
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "/Users/mcdonadt/.virtualenvs/python27/lib/python2.7/site-packages/pytz/__init__.py:29: UserWarning: Module argparse was already imported from /System/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/argparse.pyc, but /Users/mcdonadt/.virtualenvs/python27/lib/python2.7/site-packages is being added to sys.path\r\n",
        "  from pkg_resources import resource_stream\r\n"
       ]
      }
     ],
     "prompt_number": 19
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "from skbio import DistanceMatrix, read"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stderr",
       "text": [
        "/Users/mcdonadt/.virtualenvs/python27/lib/python2.7/site-packages/pytz/__init__.py:29: UserWarning: Module argparse was already imported from /System/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/argparse.pyc, but /Users/mcdonadt/.virtualenvs/python27/lib/python2.7/site-packages is being added to sys.path\n",
        "  from pkg_resources import resource_stream\n"
       ]
      }
     ],
     "prompt_number": 20
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "# load the distance matrics\n",
      "unchanged_uw_dm = read('unchanged_test/unweighted_unifrac_otu_table.txt', into=DistanceMatrix)\n",
      "changed_uw_dm = read('changed_test/unweighted_unifrac_otu_table.txt', into=DistanceMatrix)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 23
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "# check if they're the same\n",
      "unchanged_uw_dm == changed_uw_dm"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 24,
       "text": [
        "False"
       ]
      }
     ],
     "prompt_number": 24
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "# verify the IDs are in the same order\n",
      "unchanged_uw_dm.ids == changed_uw_dm.ids"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 25,
       "text": [
        "True"
       ]
      }
     ],
     "prompt_number": 25
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "# show an example of the changed data\n",
      "print unchanged_uw_dm.data[0, :]\n",
      "print changed_uw_dm.data[0, :]"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "[ 0.          0.60645837  0.6563796   0.5760386   0.65509986  0.62061374\n",
        "  0.57519786  0.65976109  0.56825433]\n",
        "[ 0.          0.61048819  0.69541332  0.62852528  0.64096947  0.68815016\n",
        "  0.64415814  0.61814587  0.49493281]\n"
       ]
      }
     ],
     "prompt_number": 31
    }
   ],
   "metadata": {}
  }
 ]
}