def plot_best_worst():
"""
Plots the pdfs of the training set for the best and worst draws
and compare with the whole training set.
"""
from options import MultiOptions, read_binary_file
opt = MultiOptions()
feat_list = [('AsDec',0,1),('Bandwidth',5,0),('CentralF',1,0),('Centroid_time',4,0),('Dur',4,1),('Ene0-5',1,4),('Ene5-10',0,4),('Ene',0,3),('F_low',4,2),('F_up',0,7),('IFslope',7,8),('Kurto',2,0),('MeanPredF',1,4),('PredF',1,4),('RappMaxMean',0,1),('RappMaxMeanTF',4,0),('Skewness',2,5),('TimeMaxSpec',4,0),('Rectilinearity',8,3),('Planarity',1,2)]
opt.opdict['feat_list'] = opt.opdict['feat_all']
opt.opdict['feat_log'] = ['AsDec','Ene','Kurto','RappMaxMean']
opt.opdict['feat_filename'] = '../results/Piton/features/Piton_trainset.csv'
opt.opdict['label_filename'] = '../lib/Piton/class_train_set.csv'
x_all, y_all = opt.features_onesta('BOR','Z')
list_files = glob.glob(os.path.join('../lib/Piton','learning*'))
list_files.sort()
m = len(y_all)
mtraining = int(0.6*m)
mcv = int(0.2*m)
mtest = int(0.2*m)
for feat,best,worst in feat_list:
print feat, best, worst
fig = plt.figure()
fig.set_facecolor('white')
# ALL
opt.x = x_all.reindex(columns=[feat])
opt.y = y_all.reindex(index=opt.x.index)
opt.opdict['feat_list'] = [feat]
opt.compute_pdfs()
g = opt.gaussians
plt.plot(g[feat]['vec'],g[feat]['VT'],'k',lw=2.,label='VT')
plt.plot(g[feat]['vec'],g[feat]['EB'],'k--',lw=2.,label='EB')
labels = ['best','worst']
colors = ['r','g']
b_file = list_files[best]
w_file = list_files[worst]
for ifile,file in enumerate([b_file,w_file]):
dic = read_binary_file(file)
# TRAINING SET
opt.x = x_all.reindex(columns=[feat],index=dic[:mtraining])
opt.y = y_all.reindex(index=dic[:mtraining])
opt.compute_pdfs()
g_train = opt.gaussians
plt.plot(g_train[feat]['vec'],g_train[feat]['VT'],'-',c=colors[ifile],label=labels[ifile])
plt.plot(g_train[feat]['vec'],g_train[feat]['EB'],'--',c=colors[ifile])
plt.legend()
plt.title(feat)
plt.savefig('%s/best_worst_%s.png'%(opt.opdict['fig_path'],feat))
plt.show()
def compare_pdfs_train():
"""
Affiche et compare les pdfs des différents training sets.
"""
from options import MultiOptions
opt = MultiOptions()
opt.opdict['stations'] = ['IJEN']
opt.opdict['channels'] = ['Z']
opt.opdict['Types'] = ['Tremor', 'VulkanikB', '?']
opt.opdict['train_file'] = '%s/train_10' % (opt.opdict['libdir'])
opt.opdict[
'label_filename'] = '%s/Ijen_reclass_all.csv' % opt.opdict['libdir']
train = read_binary_file(opt.opdict['train_file'])
nb_tir = len(train)
for sta in opt.opdict['stations']:
for comp in opt.opdict['channels']:
opt.x, opt.y = opt.features_onesta(sta, comp)
X = opt.x
Y = opt.y
c = ['r', 'b', 'g']
lines = ['-', '--', '-.', ':', '-', '--', '-.', ':', '*', 'v']
features = opt.opdict['feat_list']
for feat in features:
print feat
opt.opdict['feat_list'] = [feat]
fig = plt.figure()
fig.set_facecolor('white')
for tir in range(nb_tir):
tr = map(int, train[tir])
opt.x = X.reindex(index=tr, columns=[feat])
opt.y = Y.reindex(index=tr)
opt.classname2number()
opt.compute_pdfs()
g = opt.gaussians
for it, t in enumerate(opt.types):
plt.plot(g[feat]['vec'],
g[feat][t],
ls=lines[tir],
color=c[it])
plt.title(feat)
plt.legend(opt.types)
plt.show()
def compare_pdfs_train():
"""
Affiche et compare les pdfs des différents training sets.
"""
from options import MultiOptions
opt = MultiOptions()
opt.opdict['stations'] = ['IJEN']
opt.opdict['channels'] = ['Z']
opt.opdict['Types'] = ['Tremor','VulkanikB','?']
opt.opdict['train_file'] = '%s/train_10'%(opt.opdict['libdir'])
opt.opdict['label_filename'] = '%s/Ijen_reclass_all.csv'%opt.opdict['libdir']
train = opt.read_binary_file(opt.opdict['train_file'])
nb_tir = len(train)
for sta in opt.opdict['stations']:
for comp in opt.opdict['channels']:
opt.x, opt.y = opt.features_onesta(sta,comp)
X = opt.x
Y = opt.y
c = ['r','b','g']
lines = ['-','--','-.',':','-','--','-.',':','*','v']
features = opt.opdict['feat_list']
for feat in features:
print feat
opt.opdict['feat_list'] = [feat]
fig = plt.figure()
fig.set_facecolor('white')
for tir in range(nb_tir):
tr = map(int,train[tir])
opt.x = X.reindex(index=tr,columns=[feat])
opt.y = Y.reindex(index=tr)
opt.classname2number()
opt.compute_pdfs()
g = opt.gaussians
for it,t in enumerate(opt.types):
plt.plot(g[feat]['vec'],g[feat][t],ls=lines[tir],color=c[it])
plt.title(feat)
plt.legend(opt.types)
plt.show()
def plot_pdf_subsets():
"""
Plots the pdfs of the training set, CV set and test set on the same
figure. One subfigure for each event type.
"""
from options import MultiOptions, read_binary_file
opt = MultiOptions()
feat_list = [('AsDec',0,1),('Bandwidth',5,0),('CentralF',1,0),('Centroid_time',4,0),('Dur',4,1),('Ene0-5',1,4),('Ene5-10',0,4),('Ene',0,3),('F_low',4,2),('F_up',0,7),('IFslope',7,8),('Kurto',2,0),('MeanPredF',1,4),('PredF',1,4),('RappMaxMean',0,1),('RappMaxMeanTF',4,0),('Skewness',2,5),('TimeMaxSpec',4,0),('Rectilinearity',8,3),('Planarity',1,2)]
opt.opdict['feat_list'] = opt.opdict['feat_all']
opt.opdict['feat_filename'] = '../results/Piton/features/Piton_trainset.csv'
opt.opdict['label_filename'] = '../lib/Piton/class_train_set.csv'
x_all, y_all = opt.features_onesta('BOR','Z')
print len(y_all)
list_files = glob.glob(os.path.join('../lib/Piton','learning*'))
list_files.sort()
m = len(y_all)
mtraining = int(0.6*m)
mcv = int(0.2*m)
mtest = int(0.2*m)
for feat,best,worst in feat_list:
print feat, best, worst
fig = plt.figure(figsize=(10,4))
fig.set_facecolor('white')
ax1 = fig.add_subplot(121)
ax2 = fig.add_subplot(122)
# ALL
opt.x = x_all.reindex(columns=[feat])
opt.y = y_all.reindex(index=opt.x.index)
opt.opdict['feat_list'] = [feat]
opt.compute_pdfs()
g = opt.gaussians
ax1.plot(g[feat]['vec'],g[feat]['VT'],'k',lw=2.)
ax2.plot(g[feat]['vec'],g[feat]['EB'],'k',lw=2.)
labels = ['best','worst']
colors = ['r','g']
b_file = list_files[best]
w_file = list_files[worst]
for ifile,file in enumerate([b_file,w_file]):
dic = read_binary_file(file)
# TRAINING SET
opt.x = x_all.reindex(columns=[feat],index=dic[:mtraining])
opt.y = y_all.reindex(index=dic[:mtraining])
opt.compute_pdfs()
g_train = opt.gaussians
ax1.plot(g_train[feat]['vec'],g_train[feat]['VT'],'-',c=colors[ifile],label=labels[ifile])
ax2.plot(g_train[feat]['vec'],g_train[feat]['EB'],'-',c=colors[ifile],label=labels[ifile])
# CV SET
opt.x = x_all.reindex(columns=[feat],index=dic[mtraining:mtraining+mcv])
opt.y = y_all.reindex(index=dic[mtraining:mtraining+mcv])
opt.compute_pdfs()
g_cv = opt.gaussians
ax1.plot(g_cv[feat]['vec'],g_cv[feat]['VT'],'--',c=colors[ifile])
ax2.plot(g_cv[feat]['vec'],g_cv[feat]['EB'],'--',c=colors[ifile])
# TEST SET
opt.x = x_all.reindex(columns=[feat],index=dic[mtraining+mcv:])
opt.y = y_all.reindex(index=dic[mtraining+mcv:])
opt.compute_pdfs()
g_test = opt.gaussians
ax1.plot(g_test[feat]['vec'],g_test[feat]['VT'],':',c=colors[ifile])
ax2.plot(g_test[feat]['vec'],g_test[feat]['EB'],':',c=colors[ifile])
ax1.set_title('VT')
ax2.set_title('EB')
ax1.legend()
ax2.legend()
plt.suptitle(feat)
plt.savefig('%s/subsets_%s.png'%(opt.opdict['fig_path'],feat))
plt.show()
def plot_best_worst():
"""
Plots the pdfs of the training set for the best and worst draws
and compare with the whole training set.
"""
from options import MultiOptions, read_binary_file
opt = MultiOptions()
feat_list = [('AsDec', 0, 1), ('Bandwidth', 5, 0), ('CentralF', 1, 0),
('Centroid_time', 4, 0), ('Dur', 4, 1), ('Ene0-5', 1, 4),
('Ene5-10', 0, 4), ('Ene', 0, 3), ('F_low', 4, 2),
('F_up', 0, 7), ('IFslope', 7, 8), ('Kurto', 2, 0),
('MeanPredF', 1, 4), ('PredF', 1, 4), ('RappMaxMean', 0, 1),
('RappMaxMeanTF', 4, 0), ('Skewness', 2, 5),
('TimeMaxSpec', 4, 0), ('Rectilinearity', 8, 3),
('Planarity', 1, 2)]
opt.opdict['feat_list'] = opt.opdict['feat_all']
opt.opdict['feat_log'] = ['AsDec', 'Ene', 'Kurto', 'RappMaxMean']
opt.opdict[
'feat_filename'] = '../results/Piton/features/Piton_trainset.csv'
opt.opdict['label_filename'] = '../lib/Piton/class_train_set.csv'
x_all, y_all = opt.features_onesta('BOR', 'Z')
list_files = glob.glob(os.path.join('../lib/Piton', 'learning*'))
list_files.sort()
m = len(y_all)
mtraining = int(0.6 * m)
mcv = int(0.2 * m)
mtest = int(0.2 * m)
for feat, best, worst in feat_list:
print feat, best, worst
fig = plt.figure()
fig.set_facecolor('white')
# ALL
opt.x = x_all.reindex(columns=[feat])
opt.y = y_all.reindex(index=opt.x.index)
opt.opdict['feat_list'] = [feat]
opt.compute_pdfs()
g = opt.gaussians
plt.plot(g[feat]['vec'], g[feat]['VT'], 'k', lw=2., label='VT')
plt.plot(g[feat]['vec'], g[feat]['EB'], 'k--', lw=2., label='EB')
labels = ['best', 'worst']
colors = ['r', 'g']
b_file = list_files[best]
w_file = list_files[worst]
for ifile, file in enumerate([b_file, w_file]):
dic = read_binary_file(file)
# TRAINING SET
opt.x = x_all.reindex(columns=[feat], index=dic[:mtraining])
opt.y = y_all.reindex(index=dic[:mtraining])
opt.compute_pdfs()
g_train = opt.gaussians
plt.plot(g_train[feat]['vec'],
g_train[feat]['VT'],
'-',
c=colors[ifile],
label=labels[ifile])
plt.plot(g_train[feat]['vec'],
g_train[feat]['EB'],
'--',
c=colors[ifile])
plt.legend()
plt.title(feat)
plt.savefig('%s/best_worst_%s.png' % (opt.opdict['fig_path'], feat))
plt.show()
def plot_pdf_subsets():
"""
Plots the pdfs of the training set, CV set and test set on the same
figure. One subfigure for each event type.
"""
from options import MultiOptions, read_binary_file
opt = MultiOptions()
feat_list = [('AsDec', 0, 1), ('Bandwidth', 5, 0), ('CentralF', 1, 0),
('Centroid_time', 4, 0), ('Dur', 4, 1), ('Ene0-5', 1, 4),
('Ene5-10', 0, 4), ('Ene', 0, 3), ('F_low', 4, 2),
('F_up', 0, 7), ('IFslope', 7, 8), ('Kurto', 2, 0),
('MeanPredF', 1, 4), ('PredF', 1, 4), ('RappMaxMean', 0, 1),
('RappMaxMeanTF', 4, 0), ('Skewness', 2, 5),
('TimeMaxSpec', 4, 0), ('Rectilinearity', 8, 3),
('Planarity', 1, 2)]
opt.opdict['feat_list'] = opt.opdict['feat_all']
opt.opdict[
'feat_filename'] = '../results/Piton/features/Piton_trainset.csv'
opt.opdict['label_filename'] = '../lib/Piton/class_train_set.csv'
x_all, y_all = opt.features_onesta('BOR', 'Z')
print len(y_all)
list_files = glob.glob(os.path.join('../lib/Piton', 'learning*'))
list_files.sort()
m = len(y_all)
mtraining = int(0.6 * m)
mcv = int(0.2 * m)
mtest = int(0.2 * m)
for feat, best, worst in feat_list:
print feat, best, worst
fig = plt.figure(figsize=(10, 4))
fig.set_facecolor('white')
ax1 = fig.add_subplot(121)
ax2 = fig.add_subplot(122)
# ALL
opt.x = x_all.reindex(columns=[feat])
opt.y = y_all.reindex(index=opt.x.index)
opt.opdict['feat_list'] = [feat]
opt.compute_pdfs()
g = opt.gaussians
ax1.plot(g[feat]['vec'], g[feat]['VT'], 'k', lw=2.)
ax2.plot(g[feat]['vec'], g[feat]['EB'], 'k', lw=2.)
labels = ['best', 'worst']
colors = ['r', 'g']
b_file = list_files[best]
w_file = list_files[worst]
for ifile, file in enumerate([b_file, w_file]):
dic = read_binary_file(file)
# TRAINING SET
opt.x = x_all.reindex(columns=[feat], index=dic[:mtraining])
opt.y = y_all.reindex(index=dic[:mtraining])
opt.compute_pdfs()
g_train = opt.gaussians
ax1.plot(g_train[feat]['vec'],
g_train[feat]['VT'],
'-',
c=colors[ifile],
label=labels[ifile])
ax2.plot(g_train[feat]['vec'],
g_train[feat]['EB'],
'-',
c=colors[ifile],
label=labels[ifile])
# CV SET
opt.x = x_all.reindex(columns=[feat],
index=dic[mtraining:mtraining + mcv])
opt.y = y_all.reindex(index=dic[mtraining:mtraining + mcv])
opt.compute_pdfs()
g_cv = opt.gaussians
ax1.plot(g_cv[feat]['vec'],
g_cv[feat]['VT'],
'--',
c=colors[ifile])
ax2.plot(g_cv[feat]['vec'],
g_cv[feat]['EB'],
'--',
c=colors[ifile])
# TEST SET
opt.x = x_all.reindex(columns=[feat], index=dic[mtraining + mcv:])
opt.y = y_all.reindex(index=dic[mtraining + mcv:])
opt.compute_pdfs()
g_test = opt.gaussians
ax1.plot(g_test[feat]['vec'],
g_test[feat]['VT'],
':',
c=colors[ifile])
ax2.plot(g_test[feat]['vec'],
g_test[feat]['EB'],
':',
c=colors[ifile])
ax1.set_title('VT')
ax2.set_title('EB')
ax1.legend()
ax2.legend()
plt.suptitle(feat)
plt.savefig('%s/subsets_%s.png' % (opt.opdict['fig_path'], feat))
plt.show()
