def svm_objective(hyperparams):
global eval_num
global best_loss
global best_hyperparams
eval_num += 1
(c, gamma) = hyperparams
print(hyperparams)
l = svmModel.main(FLAGS.hyper_svm_train_path, FLAGS.hyper_svm_eval_path,
accuracyOnt, test_size, remaining_size, c, gamma)
tf.reset_default_graph()
# Save training results to disks with unique filenames
print(eval_num, l, hyperparams)
if best_loss is None or -l < best_loss:
best_loss = -l
best_hyperparams = hyperparams
result = {
'loss': -l,
'status': STATUS_OK,
'space': hyperparams,
}
save_json_result(str(l), result)
return result
def main(_):
loadData = False
useOntology = False
runCABASC = False
runLCRROT = False
runLCRROTINVERSE = False
runLCRROTALT = False
runSVM = False
runLCRModelAlt_hierarchical_v4 = True
runAdversarial = True
#determine if backupmethod is used
if runCABASC or runLCRROT or runLCRROTALT or runLCRROTINVERSE or runSVM:
backup = True
else:
backup = False
BASE_train = FLAGS.hardcoded_path + "/data/programGeneratedData/crossValidation" + str(
FLAGS.year) + '/cross_train_'
BASE_val = FLAGS.hardcoded_path + "/data/programGeneratedData/crossValidation" + str(
FLAGS.year) + '/cross_val_'
BASE_svm_train = FLAGS.hardcoded_path + "/data/programGeneratedData/crossValidation" + str(
FLAGS.year) + '/svm/cross_train_svm_'
BASE_svm_val = FLAGS.hardcoded_path + "/data/programGeneratedData/crossValidation" + str(
FLAGS.year) + '/svm/cross_val_svm_'
REMAIN_val = FLAGS.hardcoded_path + "/data/programGeneratedData/crossValidation" + str(
FLAGS.year) + '/cross_val_remainder_'
REMAIN_svm_val = FLAGS.hardcoded_path + "/data/programGeneratedData/crossValidation" + str(
FLAGS.year) + '/svm/cross_val_remainder_'
# Number of k-fold cross validations
split_size = 10
# retrieve data and wordembeddings
train_size, test_size, train_polarity_vector, test_polarity_vector = loadCrossValidation(
FLAGS, split_size, loadData)
remaining_size = 248
accuracyOnt = 0.87
if useOntology == True:
print('Starting Ontology Reasoner')
acc = []
remaining_size_vec = []
#k-fold cross validation
for i in range(split_size):
Ontology = OntReasoner()
accuracyOnt, remaining_size = Ontology.run(
backup, BASE_val + str(i) + '.txt', runSVM, True, i)
acc.append(accuracyOnt)
remaining_size_vec.append(remaining_size)
with open(
FLAGS.hardcoded_path +
"/data/programGeneratedData/crossValidation" +
str(FLAGS.year) +
'/cross_results_"+str(FLAGS.year)+"/ONTOLOGY_"+str(FLAGS.year)'
+ '.txt', 'w') as result:
print(str(split_size) + '-fold cross validation results')
print('Accuracy: {}, St Dev:{}'.format(np.mean(np.asarray(acc)),
np.std(np.asarray(acc))))
print(acc)
result.write('size:' + str(test_size))
result.write('accuracy: ' + str(acc) + '\n')
result.write('remaining size: ' + str(remaining_size_vec) + '\n')
result.write('Accuracy: {}, St Dev:{} \n'.format(
np.mean(np.asarray(acc)), np.std(np.asarray(acc))))
if runSVM == True:
test = REMAIN_svm_val
else:
test = REMAIN_val
else:
if runSVM == True:
test = BASE_svm_val
else:
test = BASE_val
#test = REMAIN_val
if runLCRROT == True:
acc = []
#k-fold cross validation
for i in [8]:
acc1, _, _, _, _, _, _, _, _ = lcrModel.main(
BASE_train + str(i) + '.txt', test + str(i) + '.txt',
accuracyOnt, test_size[i], remaining_size)
acc.append(acc1)
tf.reset_default_graph()
print('iteration: ' + str(i))
with open(
"cross_results_" + str(FLAGS.year) + "/LCRROT_" +
str(FLAGS.year) + '.txt', 'w') as result:
result.write(str(acc) + '\n')
result.write('Accuracy: {}, St Dev:{} /n'.format(
np.mean(np.asarray(acc)), np.std(np.asarray(acc))))
print(str(split_size) + '-fold cross validation results')
print('Accuracy: {}, St Dev:{}'.format(np.mean(np.asarray(acc)),
np.std(np.asarray(acc))))
if runLCRROTINVERSE == True:
acc = []
#k-fold cross validation
for i in range(split_size):
acc1, _, _, _, _, _ = lcrModelInverse.main(
BASE_train + str(i) + '.txt', test + str(i) + '.txt',
accuracyOnt, test_size[i], remaining_size)
acc.append(acc1)
tf.reset_default_graph()
print('iteration: ' + str(i))
with open(
"cross_results_" + str(FLAGS.year) + "/LCRROT_INVERSE_" +
str(FLAGS.year) + '.txt', 'w') as result:
result.write(str(acc))
result.write('Accuracy: {}, St Dev:{} /n'.format(
np.mean(np.asarray(acc)), np.std(np.asarray(acc))))
print(str(split_size) + '-fold cross validation results')
print('Accuracy: {}, St Dev:{}'.format(np.mean(np.asarray(acc)),
np.std(np.asarray(acc))))
if runLCRROTALT == True:
acc = []
#k-fold cross validation
for i in range(split_size):
acc1, _, _, _, _, _ = lcrModelAlt_hierarchical_v3.main(
BASE_train + str(i) + '.txt', test + str(i) + '.txt',
accuracyOnt, test_size[i], remaining_size)
acc.append(acc1)
tf.reset_default_graph()
print('iteration: ' + str(i))
with open(
FLAGS.hardcoded_path +
"/data/programGeneratedData/crossValidation" +
str(FLAGS.year) +
'/cross_results_"+str(FLAGS.year)+"/LCRROT_ALT_"+str(FLAGS.year)'
+ '.txt', 'w') as result:
result.write(str(acc))
result.write('Accuracy: {}, St Dev:{} /n'.format(
np.mean(np.asarray(acc)), np.std(np.asarray(acc))))
print(str(split_size) + '-fold cross validation results')
print('Accuracy: {}, St Dev:{}'.format(np.mean(np.asarray(acc)),
np.std(np.asarray(acc))))
if runCABASC == True:
acc = []
#k-fold cross validation
for i in range(split_size):
acc1, _, _ = cabascModel.main(BASE_train + str(i) + '.txt',
REMAIN_val + str(i) + '.txt',
accuracyOnt, test_size[i],
remaining_size)
acc.append(acc1)
tf.reset_default_graph()
print('iteration: ' + str(i))
with open(
"cross_results_" + str(FLAGS.year) + "/CABASC_" +
str(FLAGS.year) + '.txt', 'w') as result:
result.write(str(acc))
result.write('Accuracy: {}, St Dev:{} /n'.format(
np.mean(np.asarray(acc)), np.std(np.asarray(acc))))
print(str(split_size) + '-fold cross validation results')
print('Accuracy: {}, St Dev:{}'.format(np.mean(np.asarray(acc)),
np.std(np.asarray(acc))))
if runSVM == True:
acc = []
#k-fold cross validation
for i in range(split_size):
acc1 = svmModel.main(BASE_svm_train + str(i) + '.txt',
test + str(i) + '.txt', accuracyOnt,
test_size[i], remaining_size)
acc.append(acc1)
tf.reset_default_graph()
with open(
"cross_results_" + str(FLAGS.year) + "/SVM_" +
str(FLAGS.year) + '.txt', 'w') as result:
print(str(split_size) + '-fold cross validation results')
print('Accuracy: {:.5f}, St Dev:{:.4f}'.format(
np.mean(np.asarray(acc)), np.std(np.asarray(acc))))
result.write(str(acc))
result.write('Accuracy: {:.5f}, St Dev:{:.4f} /n'.format(
np.mean(np.asarray(acc)), np.std(np.asarray(acc))))
print('Finished program succesfully')
if runLCRModelAlt_hierarchical_v4 == True:
print('Running CrossVal V4, year = ' + str(FLAGS.year))
acc = []
# k-fold cross validation
for i in range(split_size):
acc1 = lcrModelAlt_hierarchical_v4.main(
BASE_train + str(i) + '.txt', test + str(i) + '.txt',
accuracyOnt, test_size[i], remaining_size)
acc.append(acc1)
tf.reset_default_graph()
with open(
FLAGS.hardcoded_path +
"/data/programGeneratedData/crossValidation" +
str(FLAGS.year) + "cross_results_" + str(FLAGS.year) + "/v4_" +
str(FLAGS.year) + '.txt', 'w') as result:
print(str(split_size) + '-fold cross validation results')
print('Accuracy: {:.5f}, St Dev:{:.4f}'.format(
np.mean(np.asarray(acc)), np.std(np.asarray(acc))))
result.write(str(acc))
result.write('Accuracy: {:.5f}, St Dev:{:.4f} /n'.format(
np.mean(np.asarray(acc)), np.std(np.asarray(acc))))
print('Finished program succesfully')
if runAdversarial == True:
print('Running CrossVal adversarial, year = ' + str(FLAGS.year))
acc = []
# k-fold cross validation
for i in range(split_size):
if FLAGS.year == 2015:
acc1, pred2, fw2, bw2, tl2, tr2 = adversarial.main(
BASE_train + str(i) + '.txt',
test + str(i) + '.txt',
accuracyOnt,
test_size[i],
remaining_size,
learning_rate_dis=0.02,
learning_rate_gen=0.002,
keep_prob=0.3,
momentum_dis=0.9,
momentum_gen=0.36,
l2=0.00001,
k=3,
WriteFile=False)
else:
acc1, pred2, fw2, bw2, tl2, tr2 = adversarial.main(
BASE_train + str(i) + '.txt',
test + str(i) + '.txt',
accuracyOnt,
test_size[i],
remaining_size,
learning_rate_dis=0.03,
learning_rate_gen=0.0045,
keep_prob=0.3,
momentum_dis=0.7,
momentum_gen=0.42,
l2=0.00001,
k=3,
WriteFile=False)
acc.append(acc1)
tf.reset_default_graph()
with open(
FLAGS.hardcoded_path +
"/data/programGeneratedData/crossValidation" +
str(FLAGS.year) + "cross_results_" + str(FLAGS.year) +
"/Adv_" + str(FLAGS.year) + '.txt', 'w') as result:
print(str(split_size) + '-fold cross validation results')
print('Accuracy: {:.5f}, St Dev:{:.4f}'.format(
np.mean(np.asarray(acc)), np.std(np.asarray(acc))))
result.write(str(acc))
result.write('Accuracy: {:.5f}, St Dev:{:.4f} /n'.format(
np.mean(np.asarray(acc)), np.std(np.asarray(acc))))
print('Finished program succesfully')
def main(_):
loadData = False
# loadData = True
# useOntology = True
useOntology = False
runCABASC = False
runLCRROT = False
runLCRROTINVERSE = False
runLCRROTALT = True
runSVM = False
weightanalysis = False
#determine if backupmethod is used
if runCABASC or runLCRROT or runLCRROTALT or runLCRROTINVERSE or runSVM:
backup = True
else:
backup = False
# retrieve data and wordembeddings
train_size, test_size, train_polarity_vector, test_polarity_vector = loadDataAndEmbeddings(
FLAGS, loadData)
# print(test_size)
remaining_size = 250
accuracyOnt = 0.87
if useOntology == True:
print('Starting Ontology Reasoner')
Ontology = OntReasoner()
#out of sample accuracy
accuracyOnt, remaining_size = Ontology.run(backup, FLAGS.test_path,
runSVM)
#in sample accuracy
Ontology = OntReasoner()
accuracyInSampleOnt, remaining_size = Ontology.run(
backup, FLAGS.train_path, runSVM)
if runSVM == True:
test = FLAGS.remaining_svm_test_path
else:
test = FLAGS.remaining_test_path
print('train acc = {:.4f}, test acc={:.4f}, remaining size={}'.format(
accuracyOnt, accuracyOnt, remaining_size))
else:
if runSVM == True:
test = FLAGS.test_svm_path
else:
test = FLAGS.test_path
# LCR-Rot model
if runLCRROT == True:
_, pred1, fw1, bw1, tl1, tr1, sent, target, true = lcrModel.main(
FLAGS.train_path, test, accuracyOnt, test_size, remaining_size)
tf.reset_default_graph()
# LCR-Rot-inv model
if runLCRROTINVERSE == True:
lcrModelInverse.main(FLAGS.train_path, test, accuracyOnt, test_size,
remaining_size)
tf.reset_default_graph()
# LCR-Rot-hop model
if runLCRROTALT == True:
_, pred2, fw2, bw2, tl2, tr2 = lcrModelAlt.main(
FLAGS.train_path, test, accuracyOnt, test_size, remaining_size)
tf.reset_default_graph()
# CABASC model
if runCABASC == True:
_, pred3, weights = cabascModel.main(FLAGS.train_path, test,
accuracyOnt, test_size,
remaining_size)
if weightanalysis and runLCRROT and runLCRROTALT:
outF = open('sentence_analysis.txt', "w")
dif = np.subtract(pred3, pred1)
for i, value in enumerate(pred3):
if value == 1 and pred2[i] == 0:
sentleft, sentright = [], []
flag = True
for word in sent[i]:
if word == '$t$':
flag = False
continue
if flag:
sentleft.append(word)
else:
sentright.append(word)
print(i)
outF.write(str(i))
outF.write("\n")
outF.write(
'lcr pred: {}; CABASC pred: {}; lcralt pred: {}; true: {}'
.format(pred1[i], pred3[i], pred2[i], true[i]))
outF.write("\n")
outF.write(";".join(sentleft))
outF.write("\n")
outF.write(";".join(str(x) for x in fw1[i][0]))
outF.write("\n")
outF.write(";".join(sentright))
outF.write("\n")
outF.write(";".join(str(x) for x in bw1[i][0]))
outF.write("\n")
outF.write(";".join(target[i]))
outF.write("\n")
outF.write(";".join(str(x) for x in tl1[i][0]))
outF.write("\n")
outF.write(";".join(str(x) for x in tr1[i][0]))
outF.write("\n")
outF.write(";".join(sentleft))
outF.write("\n")
outF.write(";".join(str(x) for x in fw2[i][0]))
outF.write("\n")
outF.write(";".join(sentright))
outF.write("\n")
outF.write(";".join(str(x) for x in bw2[i][0]))
outF.write("\n")
outF.write(";".join(target[i]))
outF.write("\n")
outF.write(";".join(str(x) for x in tl2[i][0]))
outF.write("\n")
outF.write(";".join(str(x) for x in tr2[i][0]))
outF.write("\n")
outF.write(";".join(sent[i]))
outF.write("\n")
outF.write(";".join(str(x) for x in weights[i][0]))
outF.write("\n")
outF.close()
# BoW model
if runSVM == True:
svmModel.main(FLAGS.train_svm_path, test, accuracyOnt, test_size,
remaining_size)
print('Finished program succesfully')
def main(_):
loadData = False
useOntology = False
runCABASC = False
runLCRROT = False
runLCRROTINVERSE = False
runLCRROTALT = False
runSVM = False
runlcrDoubleRAA = True
runINVMULTIHOP1 = False
runlcrDoubleRAAtype2 = False
weightanalysis = False
#determine if backupmethod is used
if runCABASC or runLCRROT or runLCRROTALT or runLCRROTINVERSE or runSVM or runlcrDoubleRAA or runINVMULTIHOP1:
backup = True
else:
backup = False
# retrieve data and wordembeddings
train_size, test_size, train_polarity_vector, test_polarity_vector = loadDataAndEmbeddings(
FLAGS, loadData)
print(test_size)
remaining_size = 250
accuracyOnt = 0.87
if useOntology == True:
print('Starting Ontology Reasoner')
Ontology = OntReasoner()
#out of sample accuracy
accuracyOnt, remaining_size = Ontology.run(backup, FLAGS.test_path,
runSVM)
#in sample accuracy
Ontology = OntReasoner()
accuracyInSampleOnt, remaining_size = Ontology.run(
backup, FLAGS.train_path, runSVM)
if runSVM == True:
test = FLAGS.remaining_svm_test_path
else:
test = FLAGS.remaining_test_path
print('train acc = {:.4f}, test acc={:.4f}, remaining size={}'.format(
accuracyOnt, accuracyOnt, remaining_size))
else:
if runSVM == True:
test = FLAGS.test_svm_path
else:
test = FLAGS.test_path
# LCR-Rot model
if runLCRROT == True:
_, pred1, fw1, bw1, tl1, tr1, sent, target, true = lcrModel.main(
FLAGS.train_path, test, accuracyOnt, test_size, remaining_size)
tf.reset_default_graph()
# LCR-Rot-inv model
if runLCRROTINVERSE == True:
lcrModelInverse.main(FLAGS.train_path, test, accuracyOnt, test_size,
remaining_size)
tf.reset_default_graph()
# LCR-Rot-hop model
if runLCRROTALT == True:
_, pred2, fw2, bw2, tl2, tr2 = lcrModelAlt.main(
FLAGS.train_path, test, accuracyOnt, test_size, remaining_size)
tf.reset_default_graph()
if runlcrDoubleRAA == True:
_, pred2, fw2, bw2, tl2, tr2 = lcrDoubleRAA.main(
FLAGS.train_path, test, accuracyOnt, test_size, remaining_size)
tf.reset_default_graph()
if runINVMULTIHOP1 == True:
_, pred2, fw2, bw2, tl2, tr2 = lcrinvmodel2.main(
FLAGS.train_path, test, accuracyOnt, test_size, remaining_size)
tf.reset_default_graph()
if runlcrDoubleRAAtype2 == True:
_, pred2, fw2, bw2, tl2, tr2 = lcrDoubleRAAtype2.main(
FLAGS.train_path, test, accuracyOnt, test_size, remaining_size)
tf.reset_default_graph()
# BoW model
if runSVM == True:
svmModel.main(FLAGS.train_svm_path, test, accuracyOnt, test_size,
remaining_size)
print('Finished program succesfully')
def main(_):
loadData = False
useOntology = False
runCABASC = False
runLCRROT = False
runLCRROTINVERSE = False
runLCRROTALT = True
runSVM = False
#determine if backupmethod is used
if runCABASC or runLCRROT or runLCRROTALT or runLCRROTINVERSE or runSVM:
backup = True
else:
backup = False
BASE_train = "data/programGeneratedData/crossValidation" + str(
FLAGS.year) + '/cross_train_'
BASE_val = "data/programGeneratedData/crossValidation" + str(
FLAGS.year) + '/cross_val_'
BASE_svm_train = "data/programGeneratedData/crossValidation" + str(
FLAGS.year) + '/svm/cross_train_svm_'
BASE_svm_val = "data/programGeneratedData/crossValidation" + str(
FLAGS.year) + '/svm/cross_val_svm_'
REMAIN_val = "data/programGeneratedData/crossValidation" + str(
FLAGS.year) + '/cross_val_remainder_'
REMAIN_svm_val = "data/programGeneratedData/crossValidation" + str(
FLAGS.year) + '/svm/cross_val_remainder_'
# Number of k-fold cross validations
split_size = 10
# retrieve data and wordembeddings
train_size, test_size, train_polarity_vector, test_polarity_vector = loadCrossValidation(
FLAGS, split_size, loadData)
remaining_size = 248
accuracyOnt = 0.87
if useOntology == True:
print('Starting Ontology Reasoner')
acc = []
remaining_size_vec = []
#k-fold cross validation
for i in range(split_size):
Ontology = OntReasoner()
accuracyOnt, remaining_size = Ontology.run(
backup, BASE_val + str(i) + '.txt', runSVM, True, i)
acc.append(accuracyOnt)
remaining_size_vec.append(remaining_size)
with open(
"cross_results_" + str(FLAGS.year) + "/ONTOLOGY_" +
str(FLAGS.year) + '.txt', 'w') as result:
print(str(split_size) + '-fold cross validation results')
print('Accuracy: {}, St Dev:{}'.format(np.mean(np.asarray(acc)),
np.std(np.asarray(acc))))
print(acc)
result.write('size:' + str(test_size))
result.write('accuracy: ' + str(acc) + '\n')
result.write('remaining size: ' + str(remaining_size_vec) + '\n')
result.write('Accuracy: {}, St Dev:{} \n'.format(
np.mean(np.asarray(acc)), np.std(np.asarray(acc))))
if runSVM == True:
test = REMAIN_svm_val
else:
test = REMAIN_val
else:
if runSVM == True:
test = BASE_svm_val
else:
test = BASE_val
if runLCRROT == True:
acc = []
#k-fold cross validation
for i in [8]:
acc1, _, _, _, _, _, _, _, _ = lcrModel.main(
BASE_train + str(i) + '.txt', test + str(i) + '.txt',
accuracyOnt, test_size[i], remaining_size)
acc.append(acc1)
tf.reset_default_graph()
print('iteration: ' + str(i))
with open(
"cross_results_" + str(FLAGS.year) + "/LCRROT_" +
str(FLAGS.year) + '.txt', 'w') as result:
result.write(str(acc) + '\n')
result.write('Accuracy: {}, St Dev:{} /n'.format(
np.mean(np.asarray(acc)), np.std(np.asarray(acc))))
print(str(split_size) + '-fold cross validation results')
print('Accuracy: {}, St Dev:{}'.format(np.mean(np.asarray(acc)),
np.std(np.asarray(acc))))
if runLCRROTINVERSE == True:
acc = []
#k-fold cross validation
for i in range(split_size):
acc1, _, _, _, _, _ = lcrModelInverse.main(
BASE_train + str(i) + '.txt', test + str(i) + '.txt',
accuracyOnt, test_size[i], remaining_size)
acc.append(acc1)
tf.reset_default_graph()
print('iteration: ' + str(i))
with open(
"cross_results_" + str(FLAGS.year) + "/LCRROT_INVERSE_" +
str(FLAGS.year) + '.txt', 'w') as result:
result.write(str(acc))
result.write('Accuracy: {}, St Dev:{} /n'.format(
np.mean(np.asarray(acc)), np.std(np.asarray(acc))))
print(str(split_size) + '-fold cross validation results')
print('Accuracy: {}, St Dev:{}'.format(np.mean(np.asarray(acc)),
np.std(np.asarray(acc))))
if runLCRROTALT == True:
acc = []
#k-fold cross validation
for i in range(split_size):
acc1, _, _, _, _, _ = lcrModelAlt.main(
BASE_train + str(i) + '.txt', test + str(i) + '.txt',
accuracyOnt, test_size[i], remaining_size)
acc.append(acc1)
tf.reset_default_graph()
print('iteration: ' + str(i))
with open(
"cross_results_" + str(FLAGS.year) + "/LCRROT_ALT_" +
str(FLAGS.year) + '.txt', 'w') as result:
result.write(str(acc))
result.write('Accuracy: {}, St Dev:{} /n'.format(
np.mean(np.asarray(acc)), np.std(np.asarray(acc))))
print(str(split_size) + '-fold cross validation results')
print('Accuracy: {}, St Dev:{}'.format(np.mean(np.asarray(acc)),
np.std(np.asarray(acc))))
if runCABASC == True:
acc = []
#k-fold cross validation
for i in range(split_size):
acc1, _, _ = cabascModel.main(BASE_train + str(i) + '.txt',
REMAIN_val + str(i) + '.txt',
accuracyOnt, test_size[i],
remaining_size)
acc.append(acc1)
tf.reset_default_graph()
print('iteration: ' + str(i))
with open(
"cross_results_" + str(FLAGS.year) + "/CABASC_" +
str(FLAGS.year) + '.txt', 'w') as result:
result.write(str(acc))
result.write('Accuracy: {}, St Dev:{} /n'.format(
np.mean(np.asarray(acc)), np.std(np.asarray(acc))))
print(str(split_size) + '-fold cross validation results')
print('Accuracy: {}, St Dev:{}'.format(np.mean(np.asarray(acc)),
np.std(np.asarray(acc))))
if runSVM == True:
acc = []
#k-fold cross validation
for i in range(split_size):
acc1 = svmModel.main(BASE_svm_train + str(i) + '.txt',
test + str(i) + '.txt', accuracyOnt,
test_size[i], remaining_size)
acc.append(acc1)
tf.reset_default_graph()
with open(
"cross_results_" + str(FLAGS.year) + "/SVM_" +
str(FLAGS.year) + '.txt', 'w') as result:
print(str(split_size) + '-fold cross validation results')
print('Accuracy: {:.5f}, St Dev:{:.4f}'.format(
np.mean(np.asarray(acc)), np.std(np.asarray(acc))))
result.write(str(acc))
result.write('Accuracy: {:.5f}, St Dev:{:.4f} /n'.format(
np.mean(np.asarray(acc)), np.std(np.asarray(acc))))
print('Finished program succesfully')
#k-fold cross validation
for i in range(split_size):
acc1, _, _ = cabascModel.main(BASE_train+str(i)+'.txt',REMAIN_val+str(i)+'.txt', accuracyOnt, test_size[i], remaining_size)
acc.append(acc1)
tf.reset_default_graph()
print('iteration: '+ str(i))
with open("cross_results_"+str(FLAGS.year)+"/CABASC_"+str(FLAGS.year)+'.txt', 'w') as result:
result.write(str(acc))
result.write('Accuracy: {}, St Dev:{} /n'.format(np.mean(np.asarray(acc)), np.std(np.asarray(acc))))
print(str(split_size)+'-fold cross validation results')
print('Accuracy: {}, St Dev:{}'.format(np.mean(np.asarray(acc)), np.std(np.asarray(acc))))
if runSVM == True:
acc = []
#k-fold cross validation
for i in range(split_size):
acc1 = svmModel.main(BASE_svm_train+str(i)+'.txt',test+str(i)+'.txt', accuracyOnt, test_size[i], remaining_size)
acc.append(acc1)
tf.reset_default_graph()
with open("cross_results_"+str(FLAGS.year)+"/SVM_"+str(FLAGS.year)+'.txt', 'w') as result:
print(str(split_size)+'-fold cross validation results')
print('Accuracy: {:.5f}, St Dev:{:.4f}'.format(np.mean(np.asarray(acc)), np.std(np.asarray(acc))))
result.write(str(acc))
result.write('Accuracy: {:.5f}, St Dev:{:.4f} /n'.format(np.mean(np.asarray(acc)), np.std(np.asarray(acc))))
print('Finished program succesfully')
if __name__ == '__main__':
# wrapper that handles flag parsing and then dispatches the main
tf.app.run()
def main(_):
loadData = False
useOntology = False
runCABASC = False
runLCRROT = True
runLCRROTINVERSE = False
runLCRROTALT = False
runSVM = False
# determine if backupmethod is used
if runCABASC or runLCRROT or runLCRROTALT or runLCRROTINVERSE or runSVM:
backup = True
else:
backup = False
BASE_train = "data/programGeneratedData/crossValidation" + str(
FLAGS.year) + '/cross_train_'
BASE_val = "data/programGeneratedData/crossValidation" + str(
FLAGS.year) + '/cross_val_'
BASE_svm_train = "data/programGeneratedData/crossValidation" + str(
FLAGS.year) + '/svm/cross_train_svm_'
BASE_svm_val = "data/programGeneratedData/crossValidation" + str(
FLAGS.year) + '/svm/cross_val_svm_'
REMAIN_val = "data/programGeneratedData/crossValidation" + str(
FLAGS.year) + '/cross_val_remainder_'
REMAIN_svm_val = "data/programGeneratedData/crossValidation" + str(
FLAGS.year) + '/svm/cross_val_remainder_'
# Number of k-fold cross validations
split_size = 10
# retrieve data and wordembeddings
# train_size, test_size, train_polarity_vector, test_polarity_vector = loadCrossValidation(FLAGS, split_size,
# loadData)
remaining_size = 248
accuracyOnt = 0.87
test = BASE_val
# if useOntology == True:
# print('Starting Ontology Reasoner')
# acc = []
# remaining_size_vec = []
# k-fold cross validation
# for i in range(split_size):
# Ontology = OntReasoner()
# accuracyOnt, remaining_size = Ontology.run(backup, BASE_val + str(i) + 'cross_train_10.txt', runSVM, True, i)
# acc.append(accuracyOnt)
# remaining_size_vec.append(remaining_size)
# with open("C:/Users/Maria/Desktop/data/programGeneratedData/crossValidation" + str(
# FLAGS.year) + "/cross_results_" + str(FLAGS.year) + "/ONTOLOGY_" + str(FLAGS.year) + 'cross_train_10.txt',
# 'w') as result:
# print(str(split_size) + '-fold cross validation results')
# print('Accuracy: {}, St Dev:{}'.format(np.mean(np.asarray(acc)), np.std(np.asarray(acc))))
# print(acc)
# result.write('size:' + str(test_size))
# result.write('accuracy: ' + str(acc) + '\n')
# result.write('remaining size: ' + str(remaining_size_vec) + '\n')
# result.write('Accuracy: {}, St Dev:{} \n'.format(np.mean(np.asarray(acc)), np.std(np.asarray(acc))))
# if runSVM == True:
# test = REMAIN_svm_val
# else:
# test = REMAIN_val
# else:
# if runSVM == True:
# test = BASE_svm_val
# else:
# test = BASE_val
# test = REMAIN_val
if runLCRROT == True:
acc = []
# k-fold cross validation
for i in range(split_size):
# input is the complete training data and the indices make sure that only the correct 9/10th of the data is selected. The other 1/10th can be found in test (BASE_val)
acc1 = lcrModelAlt_hierarchical_v4_baby_steps.main(
FLAGS.train_path, testdata, accuracyOnt, test_size,
remaining_size, sort_ind, FLAGS.num_buckets)
acc.append(acc1)
tf.reset_default_graph()
print('iteration: ' + str(i))
with open(
"cross_results_" + str(FLAGS.year) + "/LCRROT_" +
str(FLAGS.year) + 'cross_train_10.txt', 'w') as result:
result.write(str(acc) + '\n')
result.write('Accuracy: {}, St Dev:{} /n'.format(
np.mean(np.asarray(acc)), np.std(np.asarray(acc))))
print(str(split_size) + '-fold cross validation results')
print('Accuracy: {}, St Dev:{}'.format(np.mean(np.asarray(acc)),
np.std(np.asarray(acc))))
if runLCRROTINVERSE == True:
acc = []
# k-fold cross validation
for i in range(split_size):
acc1, _, _, _, _, _ = lcrModelInverse.main(
BASE_train + str(i) + 'cross_train_10.txt',
test + str(i) + 'cross_train_10.txt', accuracyOnt,
test_size[i], remaining_size)
acc.append(acc1)
tf.reset_default_graph()
print('iteration: ' + str(i))
with open(
"cross_results_" + str(FLAGS.year) + "/LCRROT_INVERSE_" +
str(FLAGS.year) + 'cross_train_10.txt', 'w') as result:
result.write(str(acc))
result.write('Accuracy: {}, St Dev:{} /n'.format(
np.mean(np.asarray(acc)), np.std(np.asarray(acc))))
print(str(split_size) + '-fold cross validation results')
print('Accuracy: {}, St Dev:{}'.format(np.mean(np.asarray(acc)),
np.std(np.asarray(acc))))
if runLCRROTALT == True:
acc = []
# k-fold cross validation
for i in range(split_size):
acc1, _, _, _, _, _ = lcrModelAlt_hierarchical_v3.main(
BASE_train + str(i) + 'cross_train_10.txt',
test + str(i) + 'cross_train_10.txt', accuracyOnt,
test_size[i], remaining_size)
acc.append(acc1)
tf.reset_default_graph()
print('iteration: ' + str(i))
with open(
"C:/Users/Maria/Desktop/data/programGeneratedData/crossValidation"
+ str(FLAGS.year) + "/cross_results_" + str(FLAGS.year) +
"/LCRROT_ALT_" + str(FLAGS.year) + 'cross_train_10.txt',
'w') as result:
result.write(str(acc))
result.write('Accuracy: {}, St Dev:{} /n'.format(
np.mean(np.asarray(acc)), np.std(np.asarray(acc))))
print(str(split_size) + '-fold cross validation results')
print('Accuracy: {}, St Dev:{}'.format(np.mean(np.asarray(acc)),
np.std(np.asarray(acc))))
if runCABASC == True:
acc = []
# k-fold cross validation
for i in range(split_size):
acc1, _, _ = cabascModel.main(
BASE_train + str(i) + 'cross_train_10.txt',
REMAIN_val + str(i) + 'cross_train_10.txt', accuracyOnt,
test_size[i], remaining_size)
acc.append(acc1)
tf.reset_default_graph()
print('iteration: ' + str(i))
with open(
"cross_results_" + str(FLAGS.year) + "/CABASC_" +
str(FLAGS.year) + 'cross_train_10.txt', 'w') as result:
result.write(str(acc))
result.write('Accuracy: {}, St Dev:{} /n'.format(
np.mean(np.asarray(acc)), np.std(np.asarray(acc))))
print(str(split_size) + '-fold cross validation results')
print('Accuracy: {}, St Dev:{}'.format(np.mean(np.asarray(acc)),
np.std(np.asarray(acc))))
if runSVM == True:
acc = []
# k-fold cross validation
for i in range(split_size):
acc1 = svmModel.main(
BASE_svm_train + str(i) + 'cross_train_10.txt',
test + str(i) + 'cross_train_10.txt', accuracyOnt,
test_size[i], remaining_size)
acc.append(acc1)
tf.reset_default_graph()
with open(
"cross_results_" + str(FLAGS.year) + "/SVM_" +
str(FLAGS.year) + 'cross_train_10.txt', 'w') as result:
print(str(split_size) + '-fold cross validation results')
print('Accuracy: {:.5f}, St Dev:{:.4f}'.format(
np.mean(np.asarray(acc)), np.std(np.asarray(acc))))
result.write(str(acc))
result.write('Accuracy: {:.5f}, St Dev:{:.4f} /n'.format(
np.mean(np.asarray(acc)), np.std(np.asarray(acc))))
print('Finished program succesfully')
