{
 "metadata": {
  "name": "",
  "signature": "sha256:afa3b01761ac7585c8180b98261e155f847792c2936a1243eea85e47e90b64ab"
 },
 "nbformat": 3,
 "nbformat_minor": 0,
 "worksheets": [
  {
   "cells": [
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "Next to do:\n",
      "====\n",
      "Using species - unit to get distance, may be better??? "
     ]
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "Pipeline of running IGS analysis to GPGC data (an example for large datasets)\n",
      "=========\n",
      "\n",
      "Raw reads: downloaded from JGI\n",
      "\n",
      "HPC: /mnt/scratch/tg/qingpeng/2014JGI_Data/ \n",
      "\n",
      "Step 1: quality trimming, adaptor removing, convert .fq to .fa\n",
      "--------\n",
      "\n",
      "HPC: /mnt/scratch/tg/qingpeng/2014JGI_Data_Work/\n",
      "\n",
      "quality_trimming.qsub\n",
      "\n",
      "*.qsub\n",
      "\n",
      "Output: *.trimmed.fasta.gz\n",
      "\n",
      "    [qingpeng@dev-intel14 2014JGI_Data_Work]$ ls -lh *.fasta.gz\n",
      "    -rw-r--r-- 1 qingpeng tg  46G Apr 29  2014 iowa_corn.trimmed.fasta.gz\n",
      "    -rw-r--r-- 1 qingpeng tg  74G Apr 29  2014 iowa_prairie.trimmed.fasta.gz\n",
      "    -rw-r--r-- 1 qingpeng tg  66G Apr 29  2014 kansas_corn.trimmed.fasta.gz\n",
      "    -rw-r--r-- 1 qingpeng tg 145G Apr 30  2014 kansas_prairie.trimmed.fasta.gz\n",
      "    -rw-r--r-- 1 qingpeng tg  51G Apr 29  2014 wisconsin_corn.trimmed.fasta.gz\n",
      "    -rw-r--r-- 1 qingpeng tg  53G Apr 29  2014 wisconsin_prairie.trimmed.fasta.gz\n",
      "    -rw-r--r-- 1 qingpeng tg  11G Apr 29  2014 wisconsin_restored.trimmed.fasta.gz\n",
      "    -rw-r--r-- 1 qingpeng tg  13G Apr 29  2014 wisconsin_switchgrass.trimmed.fasta.gz\n",
      "\n",
      "\n",
      "Step 2: Load into hash table. with variable hash size\n",
      "----------\n",
      "/mnt/scratch/tg/qingpeng/2014JGI_Data_Work/run/\n",
      "\n",
      "    [qingpeng@dev-intel14 run]$ ls load*.qsub\n",
      "    load_iowa_corn.qsub     load_kansas_corn.qsub     load_wisconsin_corn.qsub     load_wisconsin_restored.qsub\n",
      "    load_iowa_prairie.qsub  load_kansas_prairie.qsub  load_wisconsin_prairie.qsub  load_wisconsin_switchgrass.qsub\n",
      "\n",
      "Output: \n",
      "\n",
      "    [qingpeng@dev-intel14 run]$ ls -lh *.ht\n",
      "    -rw-r--r-- 1 qingpeng tg 131G May  3  2014 iowa_corn.trimmed.fasta.gz.ht\n",
      "    -rw-r--r-- 1 qingpeng tg 213G May  3  2014 iowa_prairie.trimmed.fasta.gz.ht\n",
      "    -rw-r--r-- 1 qingpeng tg 191G May  3  2014 kansas_corn.trimmed.fasta.gz.ht\n",
      "    -rw-r--r-- 1 qingpeng tg 418G May  4  2014 kansas_prairie.trimmed.fasta.gz.ht\n",
      "    -rw-r--r-- 1 qingpeng tg 146G May  3  2014 wisconsin_corn.trimmed.fasta.gz.ht\n",
      "    -rw-r--r-- 1 qingpeng tg 153G May  3  2014 wisconsin_prairie.trimmed.fasta.gz.ht\n",
      "    -rw-r--r-- 1 qingpeng tg 131G May  3  2014 wisconsin_restored.trimmed.fasta.gz.ht\n",
      "    -rw-r--r-- 1 qingpeng tg 131G May  3  2014 wisconsin_switchgrass.trimmed.fasta.gz.ht\n",
      "\n",
      "Step 3: Get the coverage of each read in sample A in another sample B\n",
      "-------------\n",
      "/mnt/scratch/tg/qingpeng/2014JGI_Data_Work/run/Count_Pair\n",
      "\n",
      "\n",
      "    wisconsin_restored-in-wisconsin_restored.qsub\n",
      "    wisconsin_restored-in-wisconsin_switchgrass.qsub\n",
      "    wisconsin_switchgrass-in-iowa_corn.qsub\n",
      "    wisconsin_switchgrass-in-iowa_prairie.qsub\n",
      "    wisconsin_switchgrass-in-kansas_corn.qsub\n",
      "    wisconsin_switchgrass-in-kansas_prairie.qsub\n",
      "    wisconsin_switchgrass-in-wisconsin_corn.qsub\n",
      "    wisconsin_switchgrass-in-wisconsin_prairie.qsub\n",
      "    wisconsin_switchgrass-in-wisconsin_restored.qsub\n",
      "\n",
      "Output: \n",
      "    [qingpeng@dev-intel14 Count_Pair]$ ls *.out\n",
      "    iowa_corn-in-iowa_corn.out                   wisconsin_corn-in-iowa_corn.out\n",
      "    iowa_corn-in-iowa_prairie.out                wisconsin_corn-in-iowa_prairie.out\n",
      "    iowa_corn-in-kansas_corn.out                 wisconsin_corn-in-kansas_corn.out\n",
      "    iowa_corn-in-kansas_prairie.out              wisconsin_corn-in-kansas_prairie.out\n",
      "    iowa_corn-in-wisconsin_corn.out              wisconsin_corn-in-wisconsin_corn.out\n",
      "    iowa_corn-in-wisconsin_prairie.out           wisconsin_corn-in-wisconsin_prairie.out\n",
      "    iowa_corn-in-wisconsin_restored.out          wisconsin_corn-in-wisconsin_restored.out\n",
      "    iowa_corn-in-wisconsin_switchgrass.out       wisconsin_corn-in-wisconsin_switchgrass.out\n",
      "    iowa_prairie-in-iowa_corn.out                wisconsin_prairie-in-iowa_corn.out\n",
      "\n",
      "Step 3.plus: to get the reads coverage between samples. like compareads methods. \"previous results\" as blow\n",
      "-----------\n",
      "\n",
      "    [qingpeng@dev-intel14 Count_Pair]$ ls *.out.qsub\n",
      "    iowa_prairie-in-wisconsin_corn.out.qsub         kansas_prairie-in-kansas_corn.out.qsub\n",
      "    iowa_prairie-in-wisconsin_restored.out.qsub     kansas_prairie-in-wisconsin_corn.out.qsub\n",
      "\n",
      "\n",
      "Output:\n",
      "\n",
      "GPGC_distance.txt\n",
      "\n",
      "\n",
      "    \n",
      "Step 4: Rebuild .comb files. \n",
      "---------\n",
      "/mnt/scratch/tg/qingpeng/2014JGI_Data_Work/run/Count_Pair/Get_Table\n",
      "\n",
      "\n",
      "rebuild_freq_table_stream.qsub\n",
      "\n",
      "rebuild_freq_table_stream.py\n",
      "\n",
      "Output:\n",
      "    [qingpeng@dev-intel14 Get_Table]$ ls *.freq_table\n",
      "    iowa_corn-in.list.freq_table     kansas_prairie-in.list.freq_table     wisconsin_restored-in.list.freq_table\n",
      "    iowa_prairie-in.list.freq_table  wisconsin_corn-in.list.freq_table     wisconsin_switchgrass-in.list.freq_table\n",
      "    kansas_corn-in.list.freq_table   wisconsin_prairie-in.list.freq_table\n",
      "\n",
      "Step 5: Actual IGS analysis from .comb files (.freq_table files)\n",
      "----------\n",
      "\n",
      "\n",
      "    [qingpeng@dev-intel14 Table]$ ls spectrum.out*\n",
      "    spectrum.out  spectrum.out.IGS  spectrum.out.IGS_abund\n",
      "\n",
      "\n",
      "\n",
      "\n",
      "Get the IGS\n",
      "\n",
      "count_spectrum.qsub\n",
      "\n",
      "\n",
      "generate MAP.txt file\n",
      "qsub seperate_IGS.py.qsub \n",
      "\n",
      "get_dm.qsub\n",
      "\n",
      "\n",
      "matrix.out  ( **new results** as below)\n",
      "\n",
      "\n"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [],
     "language": "python",
     "metadata": {},
     "outputs": []
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "\n"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "import pandas as pd\n",
      "import pandas as pd\n",
      "import numpy as np\n",
      "import scipy\n",
      "from IPython.display import HTML\n",
      "from scipy.cluster.hierarchy import linkage, dendrogram\n",
      "from scipy.spatial.distance import pdist, squareform\n",
      "from IPython.display import Image\n",
      "from pandas import *"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 2
    },
    {
     "cell_type": "heading",
     "level": 2,
     "metadata": {},
     "source": [
      "New result: Using full IGS table with abundance information, Bray\u2013Curtis dissimilarity measurement"
     ]
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "Typical IGS pipeline."
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "GOS=pd.read_csv('../data/matrix_GPGC_IGS.out',delimiter=' ',header=None)\n",
      "#label=pd.read_csv('../data/config-GOS.txt',delimiter='  ',header=None)\n",
      "label = GOS[0]\n",
      "label_list = []\n",
      "for i in GOS[0]:\n",
      "    label = i.split('.')[0]\n",
      "    label_list.append(label)\n",
      "len(label_list)\n",
      "GOS=GOS.ix[:,1:46]\n",
      "GOS.columns=label_list\n",
      "GOS.index=label_list\n",
      "GOS.to_csv(\"../data/dm_GPGC_IGS.txt\",sep=\"\\t\")\n",
      "GOS"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "html": [
        "<div style=\"max-height:1000px;max-width:1500px;overflow:auto;\">\n",
        "<table border=\"1\" class=\"dataframe\">\n",
        "  <thead>\n",
        "    <tr style=\"text-align: right;\">\n",
        "      <th></th>\n",
        "      <th>iowa_corn-in</th>\n",
        "      <th>iowa_prairie-in</th>\n",
        "      <th>kansas_corn-in</th>\n",
        "      <th>kansas_prairie-in</th>\n",
        "      <th>wisconsin_corn-in</th>\n",
        "      <th>wisconsin_prairie-in</th>\n",
        "      <th>wisconsin_restored-in</th>\n",
        "      <th>wisconsin_switchgrass-in</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>iowa_corn-in</th>\n",
        "      <td> 0.000000</td>\n",
        "      <td> 0.810425</td>\n",
        "      <td> 1.000000</td>\n",
        "      <td> 0.682664</td>\n",
        "      <td> 0.802263</td>\n",
        "      <td> 1.000000</td>\n",
        "      <td> 0.998201</td>\n",
        "      <td> 0.538422</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>iowa_prairie-in</th>\n",
        "      <td> 0.810425</td>\n",
        "      <td> 0.000000</td>\n",
        "      <td> 1.000000</td>\n",
        "      <td> 0.904476</td>\n",
        "      <td> 0.855969</td>\n",
        "      <td> 1.000000</td>\n",
        "      <td> 0.999224</td>\n",
        "      <td> 0.864518</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>kansas_corn-in</th>\n",
        "      <td> 1.000000</td>\n",
        "      <td> 1.000000</td>\n",
        "      <td> 0.000000</td>\n",
        "      <td> 1.000000</td>\n",
        "      <td> 1.000000</td>\n",
        "      <td> 0.952156</td>\n",
        "      <td> 1.000000</td>\n",
        "      <td> 1.000000</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>kansas_prairie-in</th>\n",
        "      <td> 0.682664</td>\n",
        "      <td> 0.904476</td>\n",
        "      <td> 1.000000</td>\n",
        "      <td> 0.000000</td>\n",
        "      <td> 0.934775</td>\n",
        "      <td> 1.000000</td>\n",
        "      <td> 0.990498</td>\n",
        "      <td> 0.841433</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>wisconsin_corn-in</th>\n",
        "      <td> 0.802263</td>\n",
        "      <td> 0.855969</td>\n",
        "      <td> 1.000000</td>\n",
        "      <td> 0.934775</td>\n",
        "      <td> 0.000000</td>\n",
        "      <td> 1.000000</td>\n",
        "      <td> 0.999173</td>\n",
        "      <td> 0.809836</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>wisconsin_prairie-in</th>\n",
        "      <td> 1.000000</td>\n",
        "      <td> 1.000000</td>\n",
        "      <td> 0.952156</td>\n",
        "      <td> 1.000000</td>\n",
        "      <td> 1.000000</td>\n",
        "      <td> 0.000000</td>\n",
        "      <td> 1.000000</td>\n",
        "      <td> 1.000000</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>wisconsin_restored-in</th>\n",
        "      <td> 0.998201</td>\n",
        "      <td> 0.999224</td>\n",
        "      <td> 1.000000</td>\n",
        "      <td> 0.990498</td>\n",
        "      <td> 0.999173</td>\n",
        "      <td> 1.000000</td>\n",
        "      <td> 0.000000</td>\n",
        "      <td> 1.000000</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>wisconsin_switchgrass-in</th>\n",
        "      <td> 0.538422</td>\n",
        "      <td> 0.864518</td>\n",
        "      <td> 1.000000</td>\n",
        "      <td> 0.841433</td>\n",
        "      <td> 0.809836</td>\n",
        "      <td> 1.000000</td>\n",
        "      <td> 1.000000</td>\n",
        "      <td> 0.000000</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 5,
       "text": [
        "                          iowa_corn-in  iowa_prairie-in  kansas_corn-in  \\\n",
        "iowa_corn-in                  0.000000         0.810425        1.000000   \n",
        "iowa_prairie-in               0.810425         0.000000        1.000000   \n",
        "kansas_corn-in                1.000000         1.000000        0.000000   \n",
        "kansas_prairie-in             0.682664         0.904476        1.000000   \n",
        "wisconsin_corn-in             0.802263         0.855969        1.000000   \n",
        "wisconsin_prairie-in          1.000000         1.000000        0.952156   \n",
        "wisconsin_restored-in         0.998201         0.999224        1.000000   \n",
        "wisconsin_switchgrass-in      0.538422         0.864518        1.000000   \n",
        "\n",
        "                          kansas_prairie-in  wisconsin_corn-in  \\\n",
        "iowa_corn-in                       0.682664           0.802263   \n",
        "iowa_prairie-in                    0.904476           0.855969   \n",
        "kansas_corn-in                     1.000000           1.000000   \n",
        "kansas_prairie-in                  0.000000           0.934775   \n",
        "wisconsin_corn-in                  0.934775           0.000000   \n",
        "wisconsin_prairie-in               1.000000           1.000000   \n",
        "wisconsin_restored-in              0.990498           0.999173   \n",
        "wisconsin_switchgrass-in           0.841433           0.809836   \n",
        "\n",
        "                          wisconsin_prairie-in  wisconsin_restored-in  \\\n",
        "iowa_corn-in                          1.000000               0.998201   \n",
        "iowa_prairie-in                       1.000000               0.999224   \n",
        "kansas_corn-in                        0.952156               1.000000   \n",
        "kansas_prairie-in                     1.000000               0.990498   \n",
        "wisconsin_corn-in                     1.000000               0.999173   \n",
        "wisconsin_prairie-in                  0.000000               1.000000   \n",
        "wisconsin_restored-in                 1.000000               0.000000   \n",
        "wisconsin_switchgrass-in              1.000000               1.000000   \n",
        "\n",
        "                          wisconsin_switchgrass-in  \n",
        "iowa_corn-in                              0.538422  \n",
        "iowa_prairie-in                           0.864518  \n",
        "kansas_corn-in                            1.000000  \n",
        "kansas_prairie-in                         0.841433  \n",
        "wisconsin_corn-in                         0.809836  \n",
        "wisconsin_prairie-in                      1.000000  \n",
        "wisconsin_restored-in                     1.000000  \n",
        "wisconsin_switchgrass-in                  0.000000  "
       ]
      }
     ],
     "prompt_number": 5
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "\n",
      "figure(num=None, figsize=(12, 12))\n",
      "R = dendrogram(linkage(GOS, method='average'),labels=label_list, leaf_font_size=20,orientation='left')\n",
      "\n",
      "ylabel('points')\n",
      "xlabel('Height')\n",
      "xlim(1,1.6)\n",
      "suptitle('GOS: average', fontweight='bold', fontsize=20)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 4,
       "text": [
        "<matplotlib.text.Text at 0x10efefa50>"
       ]
      },
      {
       "metadata": {},
       "output_type": "display_data",
       "png": "iVBORw0KGgoAAAANSUhEUgAAA74AAAMOCAYAAAA5tNp0AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\niTszCgAAAABJRU5ErkJggg==\n",
       "text": [
        "<matplotlib.figure.Figure at 0x10ee6cdd0>"
       ]
      }
     ],
     "prompt_number": 4
    },
    {
     "cell_type": "heading",
     "level": 2,
     "metadata": {},
     "source": [
      "Previous result: Reads-overlap based method"
     ]
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "dissimilarity = 1 - (number-of-reads-in-A-covered-by-B + number-of-reads-in-B-covered-by-A)/total-number-of-reads"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "GOS=pd.read_csv('../data/GPGC_matrix.txt',delimiter=',',header=None)\n",
      "#label=pd.read_csv('../data/config-GOS.txt',delimiter='  ',header=None)\n",
      "#print GOS\n",
      "label = GOS[0]\n",
      "#print label\n",
      "label_list = []\n",
      "for i in GOS[0]:\n",
      "    label = i.split(',')[0]\n",
      " #   print label\n",
      "    label_list.append(label)\n",
      "#print len(label_list)\n",
      "GOS=GOS.ix[:,1:9]\n",
      "GOS.columns=label_list\n",
      "GOS.index=label_list\n",
      "\n",
      "GOS =1-GOS\n",
      "GOS"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "html": [
        "<div style=\"max-height:1000px;max-width:1500px;overflow:auto;\">\n",
        "<table border=\"1\" class=\"dataframe\">\n",
        "  <thead>\n",
        "    <tr style=\"text-align: right;\">\n",
        "      <th></th>\n",
        "      <th>iowa_corn</th>\n",
        "      <th>iowa_prairie</th>\n",
        "      <th>kansas_corn</th>\n",
        "      <th>kansas_prairie</th>\n",
        "      <th>wisconsin_corn</th>\n",
        "      <th>wisconsin_prairie</th>\n",
        "      <th>wisconsin_restored</th>\n",
        "      <th>wisconsin_switchgrass</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>iowa_corn</th>\n",
        "      <td> 0.000000</td>\n",
        "      <td> 0.551921</td>\n",
        "      <td> 0.677156</td>\n",
        "      <td> 0.719225</td>\n",
        "      <td> 0.734101</td>\n",
        "      <td> 0.615157</td>\n",
        "      <td> 0.429304</td>\n",
        "      <td> 0.499282</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>iowa_prairie</th>\n",
        "      <td> 0.551921</td>\n",
        "      <td> 0.000000</td>\n",
        "      <td> 0.583938</td>\n",
        "      <td> 0.646602</td>\n",
        "      <td> 0.585341</td>\n",
        "      <td> 0.438256</td>\n",
        "      <td> 0.328167</td>\n",
        "      <td> 0.373863</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>kansas_corn</th>\n",
        "      <td> 0.677156</td>\n",
        "      <td> 0.583938</td>\n",
        "      <td> 0.000000</td>\n",
        "      <td> 0.789139</td>\n",
        "      <td> 0.767876</td>\n",
        "      <td> 0.623198</td>\n",
        "      <td> 0.377628</td>\n",
        "      <td> 0.461251</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>kansas_prairie</th>\n",
        "      <td> 0.719225</td>\n",
        "      <td> 0.646602</td>\n",
        "      <td> 0.789139</td>\n",
        "      <td> 0.000000</td>\n",
        "      <td> 0.798620</td>\n",
        "      <td> 0.708182</td>\n",
        "      <td> 0.410425</td>\n",
        "      <td> 0.462230</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>wisconsin_corn</th>\n",
        "      <td> 0.734101</td>\n",
        "      <td> 0.585341</td>\n",
        "      <td> 0.767876</td>\n",
        "      <td> 0.798620</td>\n",
        "      <td> 0.000000</td>\n",
        "      <td> 0.683612</td>\n",
        "      <td> 0.578405</td>\n",
        "      <td> 0.661665</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>wisconsin_prairie</th>\n",
        "      <td> 0.615157</td>\n",
        "      <td> 0.438256</td>\n",
        "      <td> 0.623198</td>\n",
        "      <td> 0.708182</td>\n",
        "      <td> 0.683612</td>\n",
        "      <td> 0.000000</td>\n",
        "      <td> 0.386761</td>\n",
        "      <td> 0.420220</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>wisconsin_restored</th>\n",
        "      <td> 0.429304</td>\n",
        "      <td> 0.328167</td>\n",
        "      <td> 0.377628</td>\n",
        "      <td> 0.410425</td>\n",
        "      <td> 0.578405</td>\n",
        "      <td> 0.386761</td>\n",
        "      <td> 0.000000</td>\n",
        "      <td> 0.574357</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>wisconsin_switchgrass</th>\n",
        "      <td> 0.499282</td>\n",
        "      <td> 0.373863</td>\n",
        "      <td> 0.461251</td>\n",
        "      <td> 0.462230</td>\n",
        "      <td> 0.661665</td>\n",
        "      <td> 0.420220</td>\n",
        "      <td> 0.574357</td>\n",
        "      <td> 0.000000</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 9,
       "text": [
        "                       iowa_corn  iowa_prairie  kansas_corn  kansas_prairie  \\\n",
        "iowa_corn               0.000000      0.551921     0.677156        0.719225   \n",
        "iowa_prairie            0.551921      0.000000     0.583938        0.646602   \n",
        "kansas_corn             0.677156      0.583938     0.000000        0.789139   \n",
        "kansas_prairie          0.719225      0.646602     0.789139        0.000000   \n",
        "wisconsin_corn          0.734101      0.585341     0.767876        0.798620   \n",
        "wisconsin_prairie       0.615157      0.438256     0.623198        0.708182   \n",
        "wisconsin_restored      0.429304      0.328167     0.377628        0.410425   \n",
        "wisconsin_switchgrass   0.499282      0.373863     0.461251        0.462230   \n",
        "\n",
        "                       wisconsin_corn  wisconsin_prairie  wisconsin_restored  \\\n",
        "iowa_corn                    0.734101           0.615157            0.429304   \n",
        "iowa_prairie                 0.585341           0.438256            0.328167   \n",
        "kansas_corn                  0.767876           0.623198            0.377628   \n",
        "kansas_prairie               0.798620           0.708182            0.410425   \n",
        "wisconsin_corn               0.000000           0.683612            0.578405   \n",
        "wisconsin_prairie            0.683612           0.000000            0.386761   \n",
        "wisconsin_restored           0.578405           0.386761            0.000000   \n",
        "wisconsin_switchgrass        0.661665           0.420220            0.574357   \n",
        "\n",
        "                       wisconsin_switchgrass  \n",
        "iowa_corn                           0.499282  \n",
        "iowa_prairie                        0.373863  \n",
        "kansas_corn                         0.461251  \n",
        "kansas_prairie                      0.462230  \n",
        "wisconsin_corn                      0.661665  \n",
        "wisconsin_prairie                   0.420220  \n",
        "wisconsin_restored                  0.574357  \n",
        "wisconsin_switchgrass               0.000000  "
       ]
      }
     ],
     "prompt_number": 9
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "\n",
      "figure(num=None, figsize=(12, 12))\n",
      "R = dendrogram(linkage(GOS, method='average'),labels=label_list, leaf_font_size=20,orientation='left')\n",
      "\n",
      "ylabel('points')\n",
      "xlabel('Height')\n",
      "#xlim(1,1.6)\n",
      "suptitle('GPGC: average', fontweight='bold', fontsize=20)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 8,
       "text": [
        "<matplotlib.text.Text at 0x10ee6cf50>"
       ]
      },
      {
       "metadata": {},
       "output_type": "display_data",
       "png": "iVBORw0KGgoAAAANSUhEUgAAA54AAAMOCAYAAAB26dmkAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nALAVwRMAAAAAYKv/A/9/nTLl/+KzAAAAAElFTkSuQmCC\n",
       "text": [
        "<matplotlib.figure.Figure at 0x10bdb4590>"
       ]
      }
     ],
     "prompt_number": 8
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [],
     "language": "python",
     "metadata": {},
     "outputs": []
    }
   ],
   "metadata": {}
  }
 ]
}