{
 "metadata": {
  "kernelspec": {
   "display_name": "Python 2",
   "language": "python",
   "name": "python2"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 2
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython2",
   "version": "2.7.9"
  },
  "name": "",
  "signature": "sha256:d40fe77e36a680d91ba0199e8063f19d2b66fc340741a96d4e12a670f915dbee"
 },
 "nbformat": 3,
 "nbformat_minor": 0,
 "worksheets": [
  {
   "cells": [
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "import os, sys\n",
      "import networkx as nx\n",
      "import numpy as np\n",
      "import pickle\n",
      "import pandas as pd\n",
      "sys.path.append('../');\n",
      "import Holes as ho\n",
      "import matplotlib.pyplot as plt"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 1
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "%matplotlib inline"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 2
    },
    {
     "cell_type": "heading",
     "level": 3,
     "metadata": {},
     "source": [
      "Maximal homology dimension $k$ to calculate"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "max_dimensions=1;"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 3
    },
    {
     "cell_type": "heading",
     "level": 3,
     "metadata": {},
     "source": [
      "Load generators dictionaries"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "import scipy.io\n",
      "data_dir='../stores/phom/country_high_act_low_entropy_matrices/'\n",
      "ld = os.listdir(data_dir);\n",
      "threshold_factor=0.1;\n",
      "thr=2.7\n",
      "call_thresholds=[thr] \n",
      "nsigma_round = [-3.4, -3.0, -2.7, -2.3, -1.9, -1.6, -1.2, -0.9, -0.5, -0.1]\n",
      "\n",
      "countries_to_cells={}\n",
      "    \n",
      "weighted_gen_dict={}\n",
      "for country in ld:\n",
      "    if country == '.gitignore':\n",
      "            continue\n",
      "    country = country.split('.')[0]\n",
      "    weighted_gen_dict[country]={}\n",
      "    for call_thr in call_thresholds:\n",
      "        try:\n",
      "            filename=open('../stores/phom/output/gen/weighted_generators_'+country+'_.pck');\n",
      "            weighted_gen_dict[country][call_thr]=pickle.load(filename);\n",
      "            filename.close()\n",
      "        except:\n",
      "            print 'didnt work with', country, call_thr"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "didnt work with 14413 2.7\n",
        "didnt work with 14415 2.7\n",
        "didnt work with 14417 2.7\n",
        "didnt work with 88213 2.7\n",
        "didnt work with 88233 2.7\n",
        "didnt work with 88235 2.7\n",
        "didnt work with 88239 2.7\n",
        "didnt work with 246 2.7\n",
        "didnt work with 247 2.7\n",
        "didnt work with 18686 2.7\n",
        "didnt work with 258 2.7\n",
        "didnt work with 262 2.7\n",
        "didnt work with 263 2.7\n",
        "didnt work with 264 2.7\n",
        "didnt work with 265 2.7\n",
        "didnt work with 267 2.7\n",
        "didnt work with 290 2.7\n",
        "didnt work with 297 2.7\n",
        "didnt work with 298 2.7\n",
        "didnt work with 299 2.7\n",
        "didnt work with 18696 2.7\n",
        "didnt work with 18765 2.7\n",
        "didnt work with 18767 2.7\n",
        "didnt work with 18768 2.7\n",
        "didnt work with 18769 2.7\n",
        "didnt work with"
       ]
      },
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        " 379 2.7\n",
        "didnt work with 12684 2.7\n",
        "didnt work with 1784 2.7\n",
        "didnt work with 12843 2.7\n",
        "didnt work with 12844 2.7\n",
        "didnt work with 12845 2.7\n",
        "didnt work with 8816 2.7\n",
        "didnt work with 8818 2.7\n",
        "didnt work with 8819 2.7\n",
        "didnt work with 674 2.7\n",
        "didnt work with 680 2.7\n",
        "didnt work with 681 2.7\n",
        "didnt work with 682 2.7\n",
        "didnt work with 683 2.7\n",
        "didnt work with 685 2.7\n",
        "didnt work with 687 2.7\n",
        "didnt work with 689 2.7\n",
        "didnt work with 691 2.7\n",
        "didnt work with 881 2.7\n",
        "didnt work with 97222 2.7\n",
        "didnt work with 68572 2.7\n",
        "didnt work with 68577 2.7\n",
        "didnt work with 97256 2.7\n",
        "didnt work with 29773 2.7\n",
        "didnt work with 29774 2.7\n",
        "didnt work with 1129 2.7\n",
        "didnt work with 1139 2.7\n",
        "didnt work with 1226 2.7\n",
        "didnt work with 1235 2.7\n",
        "didnt work with 1242 2.7\n",
        "didnt work with 1246 2.7\n",
        "didnt work with 1249 2.7\n",
        "didnt work with 1264 2.7\n",
        "didnt work with 1579 2.7\n",
        "didnt work with 1284 2.7\n",
        "didnt work with 17676 2.7\n",
        "didnt work with 1581 2.7\n",
        "didnt work with 1340 2.7\n",
        "didnt work with 1365 2.7\n",
        "didnt work with 1441 2.7\n",
        "didnt work with 1450 2.7\n",
        "didnt work with 1506 2.7\n",
        "didnt work with 18683 2.7\n",
        "didnt work with 18684 2.7\n",
        "didnt work with 7711 2.7\n",
        "didnt work with 7713 2.7\n",
        "didnt work with 7714 2.7\n",
        "didnt work with 7715 2.7\n",
        "didnt work with 7716 2.7\n",
        "didnt work with 7717 2.7\n",
        "didnt work with 7718 2.7\n",
        "didnt work with 7721 2.7\n",
        "didnt work with 7722 2.7\n",
        "didnt work with 7723 2.7\n",
        "didnt work with 7725 2.7\n",
        "didnt work with 7726 2.7\n",
        "didnt work with 7760 2.7\n",
        "didnt work with 7761 2.7\n",
        "didnt work with 7762 2.7\n",
        "didnt work with 7775 2.7\n",
        "didnt work with 7776 2.7\n",
        "didnt work with 1641 2.7\n",
        "didnt work with 1645 2.7\n",
        "didnt work with 1649 2.7\n",
        "didnt work with 1664 2.7\n",
        "didnt work with 1671 2.7\n",
        "didnt work with 1684 2.7\n",
        "didnt work with"
       ]
      },
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        " 1709 2.7\n",
        "didnt work with 1758 2.7\n",
        "didnt work with 50931 2.7\n",
        "didnt work with 50936 2.7\n",
        "didnt work with 50938 2.7\n",
        "didnt work with 50947 2.7\n",
        "didnt work with 50948 2.7\n",
        "didnt work with 1819 2.7\n",
        "didnt work with 1867 2.7\n",
        "didnt work with 1902 2.7\n",
        "didnt work with 1907 2.7\n",
        "didnt work with 1924 2.7\n",
        "didnt work with 1927 2.7\n",
        "didnt work with 1929 2.7\n",
        "didnt work with 1930 2.7\n",
        "didnt work with 1938 2.7\n",
        "didnt work with 1939 2.7\n"
       ]
      }
     ],
     "prompt_number": 4
    },
    {
     "cell_type": "heading",
     "level": 3,
     "metadata": {},
     "source": [
      "Construct spatial coherency and cyclity from generators"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "wmax_H_1_persistent = {}\n",
      "\n",
      "for c in weighted_gen_dict:\n",
      "    wmax_H_1_persistent[c] = {}\n",
      "    for call_thr in weighted_gen_dict[c]:\n",
      "        if len(weighted_gen_dict[c][call_thr][1])>0:\n",
      "            wmax_H_1_persistent[c][call_thr] = np.max(map(lambda x:  x.persistence_interval(), weighted_gen_dict[c][call_thr][1]))\n",
      "        else:\n",
      "            wmax_H_1_persistent[c][call_thr]=0;"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 5
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "wH_0_persistent = {}\n",
      "wH_0_persistent_mod = {}\n",
      "for c in weighted_gen_dict:\n",
      "    wH_0_persistent[c] = {}\n",
      "    wH_0_persistent_mod[c] = {}\n",
      "    for call_thr in weighted_gen_dict[c]:\n",
      "        if len(weighted_gen_dict[c][call_thr][0])>1:\n",
      "            wH_0_persistent[c][call_thr] = (sorted(map(lambda x:  x.persistence_interval(), weighted_gen_dict[c][call_thr][0])))\n",
      "            wH_0_persistent_mod[c][call_thr] = (wH_0_persistent[c][call_thr][-1]-wH_0_persistent[c][call_thr][-2])/float(wH_0_persistent[c][call_thr][-1])\n",
      "        else:\n",
      "            wH_0_persistent[c][call_thr]=[1];\n",
      "            wH_0_persistent_mod[c][call_thr]=[1];"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 6
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "coords_matrix={}\n",
      "country_order = {}\n",
      "for i,call_thr in enumerate(sorted(call_thresholds)):\n",
      "    coords_matrix[call_thr]=[]\n",
      "    country_order [call_thr] = []\n",
      "    for c in wH_0_persistent_mod.keys():\n",
      "        if call_thr in wH_0_persistent_mod[c]:\n",
      "            coords_matrix[call_thr].append([ wH_0_persistent_mod[c][call_thr], wmax_H_1_persistent[c][call_thr]/float(max(wH_0_persistent[c][call_thr]))]); \n",
      "            country_order[call_thr].append(c);"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 7
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "X={}\n",
      "for thr in sorted(coords_matrix.keys()):\n",
      "    X[thr]=np.zeros((int(len(coords_matrix[thr])),2));\n",
      "    print X[thr].shape\n",
      "    for i, pair in enumerate(coords_matrix[thr]):\n",
      "        if plt.is_numlike(pair[0]):\n",
      "            pair = [pair[0], pair[1]]\n",
      "            X[thr][i]=pair[0];\n",
      "            X[thr][i][1]=pair[1];\n",
      "        else:\n",
      "            pair = [pair[0][0], pair[1]]\n",
      "            X[thr][i][0]=pair[0];\n",
      "            X[thr][i][1]=pair[1];"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "(247, 2)\n"
       ]
      }
     ],
     "prompt_number": 8
    },
    {
     "cell_type": "heading",
     "level": 3,
     "metadata": {},
     "source": [
      "K-means"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "import time as time\n",
      "import numpy as np\n",
      "import pylab as pl\n",
      "import mpl_toolkits.mplot3d.axes3d as p3\n",
      "from sklearn import cluster, datasets\n",
      "\n",
      "k_means = cluster.KMeans(n_clusters=2, n_init=1)\n",
      "k_means.fit(X[2.7]) \n",
      "\n",
      "values = k_means.cluster_centers_.squeeze()\n",
      "labels = k_means.labels_\n",
      "fig = plt.figure()\n",
      "ax = fig.add_subplot(111)\n",
      "for l in np.unique(labels):\n",
      "    ax.plot(X[2.7][labels == l, 0], X[2.7][labels == l, 1],\n",
      "              'o', color=pl.cm.jet(np.float(l) / np.max(labels + 1)))\n",
      "plt.title('Without connectivity constraints')"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 9,
       "text": [
        "<matplotlib.text.Text at 0x7f6a7cacb810>"
       ]
      },
      {
       "metadata": {},
       "output_type": "display_data",
       "png": "iVBORw0KGgoAAAANSUhEUgAAAX0AAAEKCAYAAAD+XoUoAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n",
       "text": [
        "<matplotlib.figure.Figure at 0x7f6a846ce290>"
       ]
      }
     ],
     "prompt_number": 9
    },
    {
     "cell_type": "heading",
     "level": 3,
     "metadata": {},
     "source": [
      "Import population data"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "import pandas as pd\n",
      "remitt=pd.read_csv('../data/phom/population_data.csv');"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 10
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "short_country_order = {}\n",
      "for thr in country_order:\n",
      "    short_country_order[thr]=[]\n",
      "    for c in country_order[thr]:\n",
      "        try:\n",
      "            short_country_order[thr].append(remitt[remitt['prefix']==int(c)]['country_cca'].values[0])\n",
      "        except:\n",
      "            pass"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 11
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "X_filter = pd.Series(short_country_order[thr]).str.match('[A-Z]+').values"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 12
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "country_cluster_assignment={}\n",
      "k_means = cluster.KMeans(n_clusters=2, n_init=1)\n",
      "k_means.fit(X[thr][X_filter]);\n",
      "labels = k_means.labels_;\n",
      "country_cluster_assignment[thr] = zip(short_country_order[thr], labels)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 13
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "fig = plt.figure(figsize=(21,7))\n",
      "ax1 = plt.subplot2grid((1,9), (0,0), colspan=4)\n",
      "\n",
      "thr=2.7\n",
      "\n",
      "from sklearn import cluster, datasets\n",
      "k_means = cluster.KMeans(n_clusters=2, n_init=1)\n",
      "k_means.fit(X[thr][X_filter]) \n",
      "values = k_means.cluster_centers_.squeeze()\n",
      "labels = k_means.labels_\n",
      "\n",
      "col = ['r','k']\n",
      "\n",
      "for l in np.unique(labels):\n",
      "#    ax1.plot(X[thr][labels == l, 0], X[thr][labels == l, 1],\n",
      " #             'o', color=pl.cm.jet(np.float(l) / np.max(labels + 1)),markersize=10)\n",
      "    ax1.plot(X[thr][X_filter][labels == l, 0], X[thr][X_filter][labels == l, 1],\n",
      "              '.', color=col[l],markersize=13)\n",
      "for i, c in enumerate(X[thr][X_filter]):\n",
      "    plt.text(c[0], c[1], short_country_order[thr][i], fontsize=14)\n",
      "\n",
      "xtickNames = plt.setp(ax1, xticklabels=np.linspace(0,1,6))\n",
      "plt.setp(xtickNames, fontsize=23)\n",
      "ytickNames = plt.setp(ax1, yticklabels=np.linspace(-0.05,.2,6))\n",
      "plt.setp(ytickNames, fontsize=23)\n",
      "ax1.set_ylabel(r'$r_1$',fontsize=28)\n",
      "ax1.set_xlabel(r'$r_0$',fontsize=28)\n",
      "plt.text(0.02,0.186,'(a)',fontsize=23)\n",
      "plt.ylim(-0.02,0.2)\n",
      "plt.xlim(0,1.05)\n",
      "\n",
      "#plt.tight_layout()\n",
      "    \n",
      "ax2 = plt.subplot2grid((1,9), (0,4), colspan=2)\n",
      "\n",
      "group1=[]\n",
      "group2=[]\n",
      "for c_tuple in country_cluster_assignment[thr]:\n",
      "    if c_tuple[1]==0:\n",
      "        group1.append(c_tuple[0]);\n",
      "    else:\n",
      "        group2.append(c_tuple[0]);\n",
      "\n",
      "GDP_group1=[]\n",
      "GDP_group2=[]\n",
      "for c in group1:\n",
      "    try:\n",
      "        GDP_group1.append(remitt['GDPpercapita'][remitt['country_cca']==c].values[0])\n",
      "    except:\n",
      "        print 'Country not in dataset :', c\n",
      "for c in group2:\n",
      "    try:\n",
      "        GDP_group2.append(remitt['GDPpercapita'][remitt['country_cca']==c].values[0])\n",
      "    except:\n",
      "        print 'Country not in dataset :', c\n",
      "\n",
      "data = [(GDP_group1), (GDP_group2)]\n",
      "numDists=2\n",
      "#plt.subplots_adjust(left=0.095, right=0.95, top=0.9, bottom=0.25)\n",
      "bp = plt.boxplot(data, notch=0, sym='+', vert=1, whis=1.5)\n",
      "plt.setp(bp['boxes'], color='black')\n",
      "plt.setp(bp['whiskers'], color='black')\n",
      "plt.setp(bp['fliers'], color='red', marker='+')\n",
      "\n",
      "# Add a horizontal grid to the plot, but make it very light in color\n",
      "# so we can use it for reading data values but not be distracting\n",
      "ax2.yaxis.grid(True, linestyle='-', which='major', color='lightgrey',\n",
      "              alpha=0.5)\n",
      "\n",
      "# Hide these grid behind plot objects\n",
      "ax2.set_axisbelow(True)\n",
      "#ax1.set_title('Comparison of IID Bootstrap Resampling Across Five Distributions')\n",
      "ax2.set_ylabel(r'Avg GDP per capita ($10^3$USD)',fontsize=23)\n",
      "\n",
      "# Now fill the boxes with desired colors\n",
      "boxColors = ['red','black']\n",
      "numBoxes = numDists\n",
      "medians = range(numBoxes)\n",
      "for i in range(numBoxes):\n",
      "  box = bp['boxes'][i]\n",
      "  boxX = []\n",
      "  boxY = []\n",
      "  for j in range(5):\n",
      "      boxX.append(box.get_xdata()[j])\n",
      "      boxY.append(box.get_ydata()[j])\n",
      "  boxCoords = zip(boxX,boxY)\n",
      "  # Alternate between Dark Khaki and Royal Blue\n",
      "  k = i % 2\n",
      "  boxPolygon = plt.Polygon(boxCoords, facecolor=boxColors[k], alpha=0.7)\n",
      "  ax2.add_patch(boxPolygon)\n",
      "  # Now draw the median lines back over what we just filled in\n",
      "  med = bp['medians'][i]\n",
      "  medianX = []\n",
      "  medianY = []\n",
      "  for j in range(2):\n",
      "      medianX.append(med.get_xdata()[j])\n",
      "      medianY.append(med.get_ydata()[j])\n",
      "      plt.plot(medianX, medianY, 'k')\n",
      "      medians[i] = medianY[0]\n",
      "  # Finally, overplot the sample averages, with horizontal alignment\n",
      "  # in the center of each box\n",
      "  plt.plot([np.average(med.get_xdata())], [np.average(data[i])],\n",
      "           color='w', marker='*', markeredgecolor='k')\n",
      "\n",
      "# Set the axes ranges and axes labels\n",
      "ax2.set_xlim(0.5, numBoxes+0.5)\n",
      "xtickNames = plt.setp(ax2, xticklabels=['Cluster 1','Cluster 2'])\n",
      "plt.setp(xtickNames, fontsize=23)\n",
      "ytickNames = plt.setp(ax2, yticklabels=range(0,100,10))\n",
      "plt.setp(ytickNames, fontsize=23)\n",
      "plt.text(0.6,75000,'(b)',fontsize=23)\n",
      "\n",
      "ax3 = plt.subplot2grid((1,9), (0,6), colspan=2)\n",
      "GDP_group1=[]\n",
      "GDP_group2=[]\n",
      "for c in group1:\n",
      "    try:\n",
      "        GDP_group1.append(remitt['AvgMIRemittance'][remitt['country_cca']==c].values[0])\n",
      "    except:\n",
      "        print 'Country not in dataset :', c\n",
      "for c in group2:\n",
      "    try:\n",
      "        GDP_group2.append(remitt['AvgMIRemittance'][remitt['country_cca']==c].values[0])\n",
      "    except:\n",
      "        print 'Country not in dataset :', c\n",
      "\n",
      "data = [GDP_group1, (GDP_group2)]\n",
      "numDists=2\n",
      "#plt.subplots_adjust(left=0.095, right=0.95, top=0.9, bottom=0.25)\n",
      "bp = plt.boxplot(data, notch=0, sym='+', vert=1, whis=1.5)\n",
      "plt.setp(bp['boxes'], color='black')\n",
      "plt.setp(bp['whiskers'], color='black')\n",
      "plt.setp(bp['fliers'], color='red', marker='+')\n",
      "\n",
      "# Add a horizontal grid to the plot, but make it very light in color\n",
      "# so we can use it for reading data values but not be distracting\n",
      "ax3.yaxis.grid(True, linestyle='-', which='major', color='lightgrey',\n",
      "              alpha=0.5)\n",
      "# Hide these grid behind plot objects\n",
      "ax3.set_axisbelow(True)\n",
      "#ax1.set_title('Comparison of IID Bootstrap Resampling Across Five Distributions')\n",
      "ax3.set_ylabel('Avg remittance fraction per capita (%)',fontsize=23)\n",
      "\n",
      "# Now fill the boxes with desired colors\n",
      "boxColors = ['red','black']\n",
      "numBoxes = numDists\n",
      "medians = range(numBoxes)\n",
      "for i in range(numBoxes):\n",
      "  box = bp['boxes'][i]\n",
      "  boxX = []\n",
      "  boxY = []\n",
      "  for j in range(5):\n",
      "      boxX.append(box.get_xdata()[j])\n",
      "      boxY.append(box.get_ydata()[j])\n",
      "  boxCoords = zip(boxX,boxY)\n",
      "  # Alternate between Dark Khaki and Royal Blue\n",
      "  k = i % 2\n",
      "  boxPolygon = plt.Polygon(boxCoords, facecolor=boxColors[k], alpha=0.7)\n",
      "  ax3.add_patch(boxPolygon)\n",
      "  # Now draw the median lines back over what we just filled in\n",
      "  med = bp['medians'][i]\n",
      "  medianX = []\n",
      "  medianY = []\n",
      "  for j in range(2):\n",
      "      medianX.append(med.get_xdata()[j])\n",
      "      medianY.append(med.get_ydata()[j])\n",
      "      ax3.plot(medianX, medianY, 'k')\n",
      "      medians[i] = medianY[0]\n",
      "  # Finally, overplot the sample averages, with horizontal alignment\n",
      "  # in the center of each box\n",
      "  plt.plot([np.average(med.get_xdata())], [np.average(data[i])],\n",
      "           color='w', marker='*', markeredgecolor='k')\n",
      "\n",
      "# Set the axes ranges and axes labels\n",
      "ax3.set_xlim(0.5, numBoxes+0.5)\n",
      "top = 100\n",
      "bottom = -5\n",
      "ax3.set_ylim(0,50)\n",
      "xtickNames = plt.setp(ax3, xticklabels=['Cluster 1','Cluster 2'])\n",
      "plt.setp(xtickNames, fontsize=23)\n",
      "ytickNames = plt.setp(ax3, yticklabels=range(0,60,10))\n",
      "plt.setp(ytickNames, fontsize=23)\n",
      "\n",
      "plt.text(0.6,47,'(c)',fontsize=23)\n",
      "plt.tight_layout()\n",
      "plt.show()"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "display_data",
       "png": "iVBORw0KGgoAAAANSUhEUgAABT0AAANqCAYAAABPVu95AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nD7TX0aiWIpquAAAAAElFTkSuQmCC\n",
       "text": [
        "<matplotlib.figure.Figure at 0x7f6a7c6d7690>"
       ]
      }
     ],
     "prompt_number": 14
    }
   ],
   "metadata": {}
  }
 ]
}