def main(ci,gamma,wi,data_dir,p):
emotions = [x[1] for x in os.walk(data_dir)][0]
c = [30,30,0.1,0.01,10]
count=0
for emo in emotions:
print 80*"*"
print "Emotion is", emo
dir = data_dir+emo
trainfile = dir+"/train.scale"
CVtestfile = dir+"/test.scale.cv"
testfile = dir+"/test.scale"
predfile = dir+"/pred"
truefile = dir+'/y_test'
cv_trfile = dir+'/cv/train.cv'
cv_tfile = dir+'/cv/test.cv'
cv_pfile = dir+'/cv/predresults.cv'
cv_truey = dir+'/cv/y_test.cv'
ci = c[count]
count+=1
if 'scale' in p:
print "---Feature scaling"
scaling(dir,emo)
else:
pass
if 'tune' in p:
print "---Parameter tuning"
tunec=tuneC(trainfile,CVtestfile,cv_trfile,cv_tfile,cv_pfile,cv_truey)
bestc=tunec[0][0]
bestgamma=tunec[0][1]
bestwi=tunec[0][3]
bestCV=tunec[0][-1]
# for i in tunec:
# print "CV: Learning LibSVM with kernel=rbf and C=%f and gamma=(1/num_feature), its F1 is %f"%(i[0],i[-1])
print "Tuning: Five-fold CV on %s, the best F1 is %f at c=%f, gamma=%f and wi=%s"%(trainfile,bestCV,bestc,bestgamma,str(bestwi))
if ('tune' in p) and ('pred' in p):
print "---Model fitting and prediction"
predict(str(bestc),str(bestgamma),str(tunec[0][2]),str(bestwi),trainfile, testfile, predfile, emo)
if ('tune' not in p) and ('pred' in p):
print "---Model fitting and prediction"
print 'C=%s, gamma=%s and wi=%s'%(str(ci), str(gamma), str(wi))
predict(str(ci), str(gamma), str(2), str(wi), trainfile, testfile, predfile, emo)
if 'evaluation' in p:
print "---Evaluation"
y_test, y_predicted = feval(truefile, predfile)
print 'Precision score: ', metrics.precision_score(y_test, y_predicted, average='binary')
print 'Recall score: ', metrics.recall_score(y_test, y_predicted, average='binary')
print 'F1 score: ', metrics.f1_score(y_test, y_predicted, average='binary')
print 80*"*"
def main(data_dir):
emotions = [x[1] for x in os.walk(data_dir)][0]
data_split = "/30-30/" # define the test data split ratio here and make sure you have the sub folders
for emo in emotions:
print 80 * "*"
print "Emotion is", emo
dir = data_dir + emo
datafile = dir + "/test.scale"
# predfile = dir+"/pred"
# truefile = dir+'/y_test'
trainfile = dir + data_split + emo + ".train"
valfile = dir + data_split + emo + ".val"
valpredfile = dir + data_split + emo + ".val.pred"
valtruefile = dir + data_split + emo + ".val.true"
testfile = dir + data_split + emo + ".test"
predfile = dir + data_split + emo + ".test.pred"
truefile = dir + data_split + emo + ".test.true"
cv_trfile = dir + '/cv/train.cv'
cv_tfile = dir + '/cv/test.cv'
cv_pfile = dir + '/cv/predresults.cv'
cv_truey = dir + '/cv/y_test.cv'
print "---Parameter tuning"
tune_ = tune(emo, trainfile, valfile, valpredfile, valtruefile,
cv_trfile, cv_tfile, cv_pfile, cv_truey)
bestc = tune_[0][0]
bestw = tune_[0][1]
bests1 = tune_[0][2]
bests2 = tune_[0][3]
bests3 = tune_[0][4]
bestr = tune_[0][-3]
bestp = tune_[0][-2]
bestf1 = tune_[0][-1]
print "Tuning aSVM on %s, the best F1 is %f at c=%s, wi=%s and (s1=%s ; s2=%s ; s3=%s)" % (
valfile, bestf1, str(bestc), str(bestw), str(bests1), str(bests2),
str(bests3))
print "---Model fitting and prediction"
adapt(str(bestc), str(bestw), str(bests1), str(bests2), str(bests3),
trainfile, testfile, predfile, emo)
print "---Evaluation"
y_test, y_predicted = feval(truefile, predfile)
print 'Precision score: ', metrics.precision_score(y_test,
y_predicted,
average='binary')
print 'Recall score: ', metrics.recall_score(y_test,
y_predicted,
average='binary')
print 'F1 score: ', metrics.f1_score(y_test,
y_predicted,
average='binary')
print 80 * "*"
def main(ci, gamma, wi, data_dir, p):
emotions = [x[1] for x in os.walk(data_dir)][0]
for emo in emotions:
print 80*"*"
print "Emotion is", emo
dir = data_dir+emo
trainfile = dir+"/train.scale"
testfile = dir+"/test.scale"
predfile = dir+"/test.pred"
truefile = dir+'/y_test'
cv_trfile = dir+'/cv/train.cv'
cv_tfile = dir+'/cv/test.cv'
cv_pfile = dir+'/cv/predresults.cv'
cv_truey = dir+'/cv/y_test.cv'
if 'scale' in p:
print "---Feature scaling"
scaling(dir, emo)
else:
pass
if 'tune' in p:
print '---Parameter tuning'
tune_ = tune(trainfile, cv_trfile, cv_tfile, cv_pfile, cv_truey)
bestc = tune_[0][0]
bestgamma = tune_[0][1]
bestwi = tune_[0][2]
bestF = tune_[0][-1]
bestP = tune_[0][-2]
bestR = tune_[0][-3]
print "Five-fold CV on %s, best Precision is %f"%(trainfile, bestP)
print "Five-fold CV on %s, best Recall is %f"%(trainfile, bestR)
print "Five-fold CV on %s, best F1 is %f at c=%s, gamma=%s and wi=%s"%(trainfile, bestF, str(bestc), str(bestgamma), str(bestwi))
if ('tune' in p) and ('pred' in p):
print "---Model fitting and prediction"
predict(str(bestc), str(bestgamma), str(2), str(bestwi), trainfile, testfile, predfile, dir, emo)
if ('tune' not in p) and ('pred' in p):
print "---Model fitting and prediction"
# print 'C=%s, gamma=%s and wi=%s'%(str(ci), str(gamma), str(wi))
predict2(testfile, predfile, dir, emo)
if 'evaluation' in p:
print "---Evaluation"
y_test, y_predicted = feval(truefile, predfile)
print 'Precision score: ', metrics.precision_score(y_test, y_predicted, average='binary')
print 'Recall score: ', metrics.recall_score(y_test, y_predicted, average='binary')
print 'F1 score: ', metrics.f1_score(y_test, y_predicted, average='binary')
print 80*"*"
def CV(ci, gamma, kernel, wi, trfile, tfile, CV_trfile, CV_tfile, CV_pfile,
CV_truey):
trfeat = readfeats(trfile)
tfeat = readfeats(tfile)
cv = ShuffleSplit(n=len(tfeat), n_iter=5, test_size=0.2, random_state=0)
f1_list = []
p_list = []
r_list = []
count = 0
for train_index, test_index in cv:
count += 1
cv_tfile = CV_tfile + str(count)
cv_pfile = CV_pfile + str(count)
cv_truey = CV_truey + str(count)
X_train = trfeat
X_test = tfeat[test_index]
y_test = getlabels(X_test)
writingfile(cv_tfile, X_test)
writingfile(cv_truey, y_test)
# traincmd=["svm-train", "-c", "0.001", "-t", "2", "-g", "1", "-q", trfile]
traincmd = [
"svm-train", "-c", "0.001", "-t", "2", "-g", "1", "-w1", "1",
"-w0", "1", "-q", trfile
]
traincmd[2] = ci
traincmd[4] = kernel
traincmd[6] = gamma
traincmd[10] = wi
subprocess.call(traincmd)
model = trfile.split('/')[-1] + '.model'
predcmd = ["svm-predict", cv_tfile, model, cv_pfile]
p = subprocess.Popen(predcmd, stdout=subprocess.PIPE)
output, err = p.communicate()
y_test, y_predicted = feval(cv_truey, cv_pfile)
p_list.append(
metrics.precision_score(y_test, y_predicted, average='binary'))
r_list.append(
metrics.recall_score(y_test, y_predicted, average='binary'))
f1_list.append(metrics.f1_score(y_test, y_predicted, average='binary'))
recall = np.mean(np.asarray(r_list))
precision = np.mean(np.asarray(p_list))
f1 = np.mean(np.asarray(f1_list))
print "C=%s, gamma=%s and wi=%s, its F1 is %f" % (ci, gamma, wi, f1)
return [recall, precision, f1]
def CV(ci,gamma,kernel,wi,trfile,tfile,CV_trfile,CV_tfile,CV_pfile,CV_truey):
trfeat = readfeats(trfile)
tfeat = readfeats(tfile)
cv = ShuffleSplit(n=len(tfeat), n_iter=5, test_size=0.2, random_state=0)
f1_list = []
p_list = []
r_list = []
count = 0
for train_index, test_index in cv:
count+=1
cv_tfile = CV_tfile+str(count)
cv_pfile = CV_pfile+str(count)
cv_truey = CV_truey+str(count)
X_train=trfeat
X_test=tfeat[test_index]
y_test = getlabels(X_test)
writingfile(cv_tfile, X_test)
writingfile(cv_truey, y_test)
# traincmd=["svm-train", "-c", "0.001", "-t", "2", "-g", "1", "-q", trfile]
traincmd=["svm-train", "-c", "0.001", "-t", "2", "-g", "1", "-w1", "1", "-w0", "1", "-q", trfile]
traincmd[2]=ci
traincmd[4]=kernel
traincmd[6]=gamma
traincmd[10]=wi
subprocess.call(traincmd)
model=trfile.split('/')[-1]+'.model'
predcmd=["svm-predict", cv_tfile, model, cv_pfile]
p = subprocess.Popen(predcmd, stdout=subprocess.PIPE)
output, err = p.communicate()
y_test, y_predicted = feval(cv_truey, cv_pfile)
p_list.append(metrics.precision_score(y_test, y_predicted, average='binary'))
r_list.append(metrics.recall_score(y_test, y_predicted, average='binary'))
f1_list.append(metrics.f1_score(y_test, y_predicted, average='binary'))
recall = np.mean(np.asarray(r_list))
precision = np.mean(np.asarray(p_list))
f1 = np.mean(np.asarray(f1_list))
print "C=%s, gamma=%s and wi=%s, its F1 is %f"%(ci,gamma,wi,f1)
return [recall, precision, f1]
def CV(ci, wi, s1, s2, s3, trfile, CV_trfile, CV_tfile, CV_pfile, CV_truey,
emo):
feats = readfeats(trfile)
cv = StratifiedShuffleSplit(y=getlabels(feats),
n_iter=5,
test_size=0.2,
random_state=0)
f1_list = []
p_list = []
r_list = []
count = 0
for train_index, test_index in cv:
count += 1
cv_trfile = CV_trfile + str(count)
cv_tfile = CV_tfile + str(count)
cv_pfile = CV_pfile + str(count)
cv_truey = CV_truey + str(count)
X_train = feats[train_index]
X_test = feats[test_index]
y_test = getlabels(X_test)
writingfile(cv_trfile, X_train)
writingfile(cv_tfile, X_test)
writingfile(cv_truey, y_test)
adapt(str(ci), str(wi), str(s1), str(s2), str(s3), cv_trfile, cv_tfile,
cv_pfile, emo)
y_test, y_predicted = feval(cv_truey, cv_pfile)
p_list.append(
metrics.precision_score(y_test, y_predicted, average='binary'))
r_list.append(
metrics.recall_score(y_test, y_predicted, average='binary'))
f1_list.append(metrics.f1_score(y_test, y_predicted, average='binary'))
recall = np.mean(np.asarray(r_list))
precision = np.mean(np.asarray(p_list))
f1 = np.mean(np.asarray(f1_list))
print "C=%s, wi=%s and (s1=%s ; s2=%s ; s3=%s), its F1 is %f" % (
ci, wi, s1, s2, s3, f1)
return recall, precision, f1
def main(ci, gamma, wi, data_dir, p):
emotions = [x[1] for x in os.walk(data_dir)][0]
c = [30, 30, 0.1, 0.01, 10]
count = 0
for emo in emotions:
print 80 * "*"
print "Emotion is", emo
dir = data_dir + emo
trainfile = dir + "/train.scale"
CVtestfile = dir + "/test.scale.cv"
testfile = dir + "/test.scale"
predfile = dir + "/pred"
truefile = dir + '/y_test'
cv_trfile = dir + '/cv/train.cv'
cv_tfile = dir + '/cv/test.cv'
cv_pfile = dir + '/cv/predresults.cv'
cv_truey = dir + '/cv/y_test.cv'
ci = c[count]
count += 1
if 'scale' in p:
print "---Feature scaling"
scaling(dir, emo)
else:
pass
if 'tune' in p:
print "---Parameter tuning"
tunec = tuneC(trainfile, CVtestfile, cv_trfile, cv_tfile, cv_pfile,
cv_truey)
bestc = tunec[0][0]
bestgamma = tunec[0][1]
bestwi = tunec[0][3]
bestCV = tunec[0][-1]
# for i in tunec:
# print "CV: Learning LibSVM with kernel=rbf and C=%f and gamma=(1/num_feature), its F1 is %f"%(i[0],i[-1])
print "Tuning: Five-fold CV on %s, the best F1 is %f at c=%f, gamma=%f and wi=%s" % (
trainfile, bestCV, bestc, bestgamma, str(bestwi))
if ('tune' in p) and ('pred' in p):
print "---Model fitting and prediction"
predict(str(bestc), str(bestgamma), str(tunec[0][2]), str(bestwi),
trainfile, testfile, predfile, emo)
if ('tune' not in p) and ('pred' in p):
print "---Model fitting and prediction"
print 'C=%s, gamma=%s and wi=%s' % (str(ci), str(gamma), str(wi))
predict(str(ci), str(gamma), str(2), str(wi), trainfile, testfile,
predfile, emo)
if 'evaluation' in p:
print "---Evaluation"
y_test, y_predicted = feval(truefile, predfile)
print 'Precision score: ', metrics.precision_score(
y_test, y_predicted, average='binary')
print 'Recall score: ', metrics.recall_score(y_test,
y_predicted,
average='binary')
print 'F1 score: ', metrics.f1_score(y_test,
y_predicted,
average='binary')
print 80 * "*"
