Mercurial > hg > chourdakisreiss2016

annotate experiment-reverb/code/plots.py @ 2:c87a9505f294 tip

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Added LICENSE for code, removed .wav files
author Emmanouil Theofanis Chourdakis <e.t.chourdakis@qmul.ac.uk>
date Sat, 30 Sep 2017 13:25:50 +0100
parents 246d5546657c
children
rev   line source
e@0 1 # -*- coding: utf-8 -*-
e@0 2 """
e@0 3 Created on Mon Jul 13 06:45:38 2015
e@0 4
e@0 5 @author: Emmanouil Theofanis Chourdakis
e@0 6 """
e@0 7
e@0 8
e@0 9 # Plots for our paper
e@0 10
e@0 11 from numpy import *
e@0 12 import matplotlib.pyplot as plt
e@0 13 from matplotlib import rc
e@0 14 #from matplotlib2tikz import save as tikz_save
e@0 15 rc('font',**{'family':'serif','serif':['Palatino']})
e@0 16 rc('text', usetex=True)
e@0 17 rc('pgf', texsystem='pdflatex')
e@0 18
e@0 19 sucrats1 = (0.716, 0.793, 0.703, 0.696, 0.820)
e@0 20 sucrats2 = (0.789, 0.789, 0.729, 0.525, 0.793)
e@0 21 sucrats3 = (0.769, 0.736, 0.760, 0.537, 0.709)
e@0 22 sucrats4 = (0.689, 0.689, 0.552, 0.562, 0.673)
e@0 23 sucrats5 = (0.80508403361344549, 0.77222689075630258, 0.76915966386554613, 0.5345168067226892, 0.7770588235294118)
e@0 24 sucrats6 = (0.796, 0.898, 0.798, 0.563, 0.875)
e@0 25
e@0 26 example = {'SIM/C1':(0.5,0.7,0.6,0.8), 'FUL/C1':(0.6,0.7,0.9,0.8), 'SIM/C2': (0.4,0.3,0.5,0.6)}
e@0 27
e@0 28 FONTSIZE=20
e@0 29
e@0 30 GNBCR = []
e@0 31 SVMR = []
e@0 32 HMMCR = []
e@0 33 HMMSVMR = []
e@0 34 SINKHOLE = []
e@0 35
e@0 36
e@0 37
e@0 38
e@0 39 labels = ['Set 1', 'Set 2', 'Set 3', 'Set 4', 'Set 5', 'Set 6']
e@0 40
e@0 41 results = [sucrats1, sucrats2, sucrats3, sucrats4]
e@0 42
e@0 43 for i in range(0, len(results)):
e@0 44 GNBCR.append(results[i][0])
e@0 45 SVMR.append(results[i][1])
e@0 46 HMMCR.append(results[i][2])
e@0 47 HMMSVMR.append(results[i][3])
e@0 48 SINKHOLE.append(results[i][4])
e@0 49
e@0 50
e@0 51 pos = list(range(len(SVMR)))
e@0 52 width = 0.15
e@0 53
e@0 54 fig,ax=plt.subplots(figsize=(10,10))
e@0 55
e@0 56 bar1=plt.bar(pos, GNBCR, width,
e@0 57 alpha=0.5,
e@0 58 color='r',
e@0 59 hatch='x', # this one defines the fill pattern
e@0 60 label=labels[0])
e@0 61
e@0 62 plt.bar([p + width for p in pos], SVMR, width,
e@0 63 alpha=0.5,
e@0 64 color='g',
e@0 65 hatch='-',
e@0 66 label=labels[1])
e@0 67
e@0 68 plt.bar([p + width*2 for p in pos], HMMCR, width,
e@0 69 alpha=0.5,
e@0 70 color='b',
e@0 71 hatch='',
e@0 72 label=labels[2])
e@0 73
e@0 74 plt.bar([p + width*3 for p in pos], HMMSVMR, width,
e@0 75 alpha=0.5,
e@0 76 color='c',hatch='/',
e@0 77 label=labels[3])
e@0 78
e@0 79 plt.bar([p + width*4 for p in pos], SINKHOLE, width,
e@0 80 alpha=0.5,
e@0 81 color='m',hatch='\\',
e@0 82 label=labels[3])
e@0 83
e@0 84
e@0 85
e@0 86 # Setting axis labels and ticks
e@0 87 ax.set_ylabel('Success Ratio', fontsize=FONTSIZE)
e@0 88 ax.set_xlabel('Data set', fontsize=FONTSIZE)
e@0 89 ax.set_title('Classifier Success Ratio', fontsize=FONTSIZE)
e@0 90 ax.set_xticks([p + 2 * width for p in pos])
e@0 91 ax.set_yticks([0, 0.2, 0.6, 0.8, 1.0])
e@0 92 ax.set_xticklabels(labels, fontsize=FONTSIZE)
e@0 93 ax.set_yticklabels([0, 0.2, 0.6, 0.8, 1.0], fontsize=FONTSIZE)
e@0 94
e@0 95 # Setting the x-axis and y-axis limits
e@0 96 plt.xlim(min(pos)-width, max(pos)+width*6)
e@0 97 plt.ylim([0,1.2])
e@0 98
e@0 99 # Adding the legend and showing the plot
e@0 100 leg = plt.legend(['GNB', 'SVM', 'HMM', 'HMM/SVM', 'SINK-HOLE'], loc='upper right', fontsize=FONTSIZE, fancybox=True)
e@0 101
e@0 102 # leg.get_frame().set_alpha(0.5)
e@0 103 plt.grid()
e@0 104 #plt.show()
e@0 105
e@0 106 #tikz_save('plot.tkz', figureheight='4cm', figurewidth='6cm')
e@0 107 fig.tight_layout()
e@0 108 fig.savefig('./plot.pgf', dpi=500)
e@0 109
e@0 110 from sklearn import metrics
e@0 111 def plot_confusion_matrix(y_pred, y):
e@0 112 plt.imshow(metrics.confusion_matrix(y, y_pred),
e@0 113 cmap=plt.cm.binary, interpolation='nearest')
e@0 114 plt.colorbar()
e@0 115 plt.xlabel('true value')
e@0 116 plt.ylabel('predicted value')
e@0 117
e@0 118 #plt.figure()
e@0 119 #plot_confusion_matrix(predhmmc3, parameters_state)
e@0 120
e@0 121
e@0 122 msecrats1 = (0.015, 0.013, 0.019, 0.012, 0.007)
e@0 123 msecrats2 = (0.005, 0.006, 0.009, 0.007, 0.004)
e@0 124 msecrats3 = (0.018, 0.020, 0.014, 0.019, 0.019)
e@0 125 msecrats4 = (0.010, 0.010, 0.018, 0.010, 0.010)
e@0 126 msecrats5 = (0.097, 0.014, 0.013, 0.017, 0.010)
e@0 127 msecrats6 = (0.006, 0.003, 0.012, 0.013, 0.003)
e@0 128
e@0 129
e@0 130 results = [msecrats1, msecrats2, msecrats3, msecrats4, msecrats5, msecrats6]
e@0 131
e@0 132 GNBCR = []
e@0 133 SVMR = []
e@0 134 HMMCR = []
e@0 135 HMMSVMR = []
e@0 136 SINKHOLE = []
e@0 137 for i in range(0, len(results)):
e@0 138 GNBCR.append(results[i][0])
e@0 139 SVMR.append(results[i][1])
e@0 140 HMMCR.append(results[i][2])
e@0 141 HMMSVMR.append(results[i][3])
e@0 142 SINKHOLE.append(results[i][4])
e@0 143
e@0 144 pos = list(range(len(SVMR)))
e@0 145
e@0 146 plt.close('all')
e@0 147 #plt.figure()
e@0 148 fig,ax=plt.subplots(figsize=(10,10))
e@0 149
e@0 150
e@0 151
e@0 152 bar1=plt.barh(pos, GNBCR, width,
e@0 153 alpha=0.5,
e@0 154 color='r',
e@0 155 hatch='x', # this one defines the fill pattern
e@0 156 label=labels[0])
e@0 157
e@0 158 plt.barh([p + width for p in pos], SVMR, width,
e@0 159 alpha=0.5,
e@0 160 color='g',
e@0 161 hatch='-',
e@0 162 label=labels[1])
e@0 163
e@0 164 plt.barh([p + width*2 for p in pos], HMMCR, width,
e@0 165 alpha=0.5,
e@0 166 color='b',
e@0 167 hatch='',
e@0 168 label=labels[2])
e@0 169
e@0 170 plt.barh([p + width*3 for p in pos], HMMSVMR, width,
e@0 171 alpha=0.5,
e@0 172 color='c',hatch='/',
e@0 173 label=labels[3])
e@0 174
e@0 175 plt.barh([p + width*4 for p in pos], SINKHOLE, width,
e@0 176 alpha=0.5,
e@0 177 color='m',hatch='\\',
e@0 178 label=labels[3])
e@0 179
e@0 180
e@0 181 # Setting axis labels and ticks
e@0 182 ax.set_ylabel('Data set', fontsize=FONTSIZE)
e@0 183 ax.set_xlabel('Mean Squared Error', fontsize=FONTSIZE)
e@0 184 ax.set_title('Mean Squared Errors', fontsize=FONTSIZE)
e@0 185 ax.set_yticks([p + 2 * width for p in pos])
e@0 186 ax.set_xticks([0, 0.02])
e@0 187 ax.set_yticklabels(labels, fontsize=FONTSIZE)
e@0 188 ax.set_xticklabels([0, 0.02], fontsize=FONTSIZE)
e@0 189
e@0 190 # Setting the x-axis and y-axis limits
e@0 191 plt.ylim(min(pos)-width, max(pos)+width*6)
e@0 192 plt.xlim([0,0.03])
e@0 193
e@0 194 # Adding the legend and showing the plot
e@0 195 leg = plt.legend(['GNB', 'SVM', 'HMM', 'HMM/SVM', 'SINK-HOLE'], loc='upper right', fontsize=FONTSIZE, fancybox=True)
e@0 196
e@0 197 # leg.get_frame().set_alpha(0.5)
e@0 198 plt.grid()
e@0 199
e@0 200
e@0 201 #tikz_save('plot.tkz', figureheight='4cm', figurewidth='6cm')
e@0 202 fig.tight_layout()
e@0 203 fig.savefig('./plotmses.pgf', dpi=500)
e@0 204
e@0 205 from sklearn import metrics
e@0 206 def plot_confusion_matrix(y_pred, y):
e@0 207 plt.imshow(metrics.confusion_matrix(y, y_pred),
e@0 208 cmap=plt.cm.binary, interpolation='nearest')
e@0 209 plt.colorbar()
e@0 210 plt.xlabel('true value')
e@0 211 plt.ylabel('predicted value')
e@0 212 #plt.show()