def run_test(features, labels, train_classes, test_classes, train_index, test_index):
cpu_time = 0
features = np.array(features)
labels = np.array(labels)
xtrain = features[np.isin(labels,train_classes),:]
ytrain = labels[np.isin(labels,train_classes)]
xtest = features[np.isin(labels,test_classes),:]
ytest = labels[np.isin(labels,test_classes)]
X_train, X_test = xtrain[train_index], xtrain[test_index]
y_train, y_test = ytrain[train_index], ytrain[test_index]
y_test_l = y_test.tolist()
model = sor.HierarchicalClassifierModel(input_size = X_train[0].size, num_classes = len(risk_class_files), learning_rate = 1e-3, num_epochs = 1000, batch_size = 100, l1 = 0, l2 = 0, train_classes = train_classes)
model_s = pickle.load(open('test_results/trained_model_'+sys.argv[1] + '_joint.m', 'rb'))
model.evt_fit_threshold(X_train, y_train)
y_pred = model.predict(X_test, 0)
np.savetxt('test_results/' +sys.argv[1] + '_joint_seen.pred', y_pred)
for classk in range(len(test_classes)):
print('test class', test_classes[classk])
xtest_ri = xtest[ytest == test_classes[classk]]
y_pred_ri = model.predict(xtest_ri, 0)
np.savetxt('test_results/' + sys.argv[1] + '_joint_unseen_' + str(classk) + '.pred', y_pred_ri)
def run_test(features, labels, train_classes, test_classes, train_index,
test_index):
cpu_time = 0
features = np.array(features)
labels = np.array(labels)
xtrain = features[np.isin(labels, train_classes), :]
ytrain = labels[np.isin(labels, train_classes)]
xtest = features[np.isin(labels, test_classes), :]
ytest = labels[np.isin(labels, test_classes)]
RR = 0
R2Ri = 0
RNR = 0
NRNR = 0
NRR = 0
RiR = np.zeros(len(test_classes))
RiNR = np.zeros(len(test_classes))
X_train, X_test = xtrain[train_index], xtrain[test_index]
y_train, y_test = ytrain[train_index], ytrain[test_index]
y_test_l = y_test.tolist()
model = sor.HierarchicalClassifierModel(input_size=X_train[0].size,
num_classes=len(risk_class_files),
learning_rate=1e-3,
num_epochs=1000,
batch_size=100,
l1=0,
l2=0,
train_classes=train_classes)
parameters = {
'l1': np.logspace(-2, 2, 5),
'l2': np.append(np.logspace(-3, 1, 5), 0)
}
splitter = cv_split.UnseenTestSplit()
cmodel = GridSearchCV(model, parameters, cv=splitter, verbose=5, n_jobs=10)
cmodel.fit(X_train, y_train.ravel())
print('best params: l1=', cmodel.best_params_['l1'], 'l2=',
cmodel.best_params_['l2'])
model = sor.HierarchicalClassifierModel(input_size=X_train[0].size,
num_classes=len(risk_class_files),
learning_rate=1e-3,
num_epochs=1000,
batch_size=100,
l1=cmodel.best_params_['l1'],
l2=cmodel.best_params_['l2'],
train_classes=train_classes)
model.fit(X_train, y_train)
np.savetxt('test_results/' + sys.argv[1] + '_loss.out', model.loss_trace)
np.savetxt('test_results/' + sys.argv[1] + '_grad_norm.out',
model.grad_norm)
y_pred = model.predict(X_test, 0)
y_pred_score = model.predict_score(X_test, 0)
np.savetxt('test_results/' + sys.argv[1] + '_joint_seen.out', y_pred_score)
for j in range(len(y_test)):
if y_test_l[j] >= 1:
if y_pred[j] == 1:
RR += 1
y_pred_class = model.predict(X_test[j, :], int(y_test[j]))
if y_pred_class == 1:
R2Ri += 1
else:
RNR += 1
else:
if y_pred[j] < 1:
NRNR += 1
else:
NRR += 1
for classk in range(len(test_classes)):
xtest_ri = xtest[ytest == test_classes[classk]]
y_pred_ri = model.predict(xtest_ri, 0)
y_pred_ri_score = model.predict_score(xtest_ri, 0)
np.savetxt(
'test_results/' + sys.argv[1] + '_joint_unseen_' + str(classk) +
'.out', y_pred_ri_score)
for j in range(len(y_pred_ri)):
if y_pred_ri[j] == 1:
RiR[classk] += 1
else:
RiNR[classk] += 1
print(RR, RNR, NRR, NRNR, RiR, RiNR, R2Ri)
pickle.dump(
model,
open('test_results/trained_model_' + sys.argv[1] + '_joint.m', 'wb'))
def run_setup(features, labels, train_classes, test_classes, test_fold):
features = np.array(features)
labels = np.array(labels)
xtrain = features[np.isin(labels, train_classes), :]
ytrain = labels[np.isin(labels, train_classes)]
xtest = features[np.isin(labels, test_classes), :]
ytest = labels[np.isin(labels, test_classes)]
train_ids = np.arange(len(ytrain))
np.random.shuffle(train_ids)
train_index = train_ids[:int(len(ytrain) * 0.8)]
test_index = train_ids[int(len(ytrain) * 0.8 + 1):]
X_train, X_test = xtrain[train_index], xtrain[test_index]
y_train, y_test = ytrain[train_index], ytrain[test_index]
model = sor.HierarchicalClassifierModel(input_size=X_train[0].size,
num_classes=len(risk_class_files),
learning_rate=1e-3,
num_epochs=1000,
batch_size=100,
model_name='wSOR',
l1=0.1,
l2=0)
model.fit_wk(X_train, y_train)
model.save('test_data/trained_model_' + str(test_fold) + '_wk.m')
np.savez('test_data/test_' + str(test_fold) + '.npz',
train_classes=train_classes,
test_classes=test_classes,
train_index=train_index,
test_index=test_index)
tfidf = TfidfVectorizer(ngram_range=(1, 1),
stop_words='english',
token_pattern=u'(?ui)\\b\\w*[a-z]+\\w*\\b')
features = tfidf.fit_transform(X).toarray()
features = np.array(features)
xtrain = features[np.isin(labels, train_classes), :]
ytrain = labels[np.isin(labels, train_classes)]
X_train, X_test = xtrain[train_index], xtrain[test_index]
y_train, y_test = ytrain[train_index], ytrain[test_index]
scaler.fit(X_train)
X_train_std = scaler.transform(X_train)
pca.fit(X_train_std)
model = sor.HierarchicalClassifierModel(
input_size=pca.transform(X_train_std)[0].size,
num_classes=len(risk_class_files),
learning_rate=1e-3,
num_epochs=1000,
batch_size=100,
model_name='wSOR',
l1=0.1,
l2=0)
model.fit_wk(pca.transform(X_train_std), y_train)
model.save('test_data/trained_model_' + str(test_fold) + '_pca_wk.m')
transformer = FastICA(n_components=pca.n_components_,
random_state=0,
max_iter=500)
xtrain_transformed = transformer.fit_transform(X_train_std)
model = sor.HierarchicalClassifierModel(
input_size=transformer.transform(X_train_std)[0].size,
num_classes=len(risk_class_files),
learning_rate=1e-3,
num_epochs=1000,
batch_size=100,
model_name='wSOR',
l1=0.1,
l2=0)
model.fit_wk(transformer.transform(X_train_std), y_train)
model.save('test_data/trained_model_' + str(test_fold) + '_ica_wk.m')
pickle.dump(transformer,
open('test_data/' + str(test_fold) + '_ica.sav', 'wb'),
protocol=4)