# break
# X = sequence.pad_sequences(X, maxlen=max_len)
X = np.asarray(X)
y = np.asarray(y)
return X, y
def execute_model(X, y):
kf = KFold(y.shape[0], n_folds=n_fold, shuffle=True)
results_user = np.array([0.0, 0.0, 0.0, 0.0])
for train_index, test_index in kf:
X_train, X_test = X[train_index], X[test_index]
y_train, y_test = y[train_index], y[test_index]
accuracy, precision, recall, f1 = cnn_model(X_train, y_train, X_test, y_test)
# precision, recall, f1 = bidirectional_lstm(X_train, y_train, X_test, y_test)
results_user[0] += accuracy
results_user[1] += precision
results_user[2] += recall
results_user[3] += f1
results_user /= n_fold
return results_user
if __name__ == '__main__':
n_count = 0
data = util.read_data(path.join(util.data_path, util.file_name))
X, y = build_dataset(data)
results = execute_model(X, y)
print results
util.insert_results('CNN', results[0], results[2], results[1], results[3])
def prediction_model(X_train, y_train, X_test, y_test):
classifier = LogisticRegression()
classifier.fit(X_train, y_train)
pred_labels = classifier.predict(X_test)
accuracy = accuracy_score(y_test, pred_labels)
precision, recall, f1 = precision_recall_fscore_support(y_test, pred_labels, average='weighted')
return accuracy, precision, recall, f1
if __name__ == '__main__':
model = Doc2Vec(alpha=0.025, min_alpha=0.025, size=100, window=10, negative=5)
model.build_vocab(read_labeled_doc(path.join(util.data_path, util.file_name))[0])
for i in xrange(0, 1):
model.train(read_labeled_doc(path.join(util.data_path, util.file_name)))
print 'end of iteration ', i + 1
labels_ratings = get_labels_ratings(path.join(util.data_path, util.file_name))
X = []
y = []
for entry in labels_ratings:
current_data = model.docvecs[entry[0]]
current_rating = labels_ratings[entry[1]]
X.append(current_data)
y.append(y)
X = np.asarray(X)
y = np.asarray(y)
results = execute_model(X, y)
print 'Doc2vec'
print results
util.insert_results('Doc2Vec', results[0], results[2], results[1], results[3])
print("Building model...")
model = Sequential()
model.add(Dense(512, input_shape=(max_len,)))
model.add(Activation('relu'))
model.add(Dropout(0.5))
model.add(Dense(nb_classes))
model.add(Activation('softmax'))
model.compile(loss='categorical_crossentropy', optimizer='adam', class_mode='categorical')
history = model.fit(X_train, Y_train, nb_epoch=nb_epoch, batch_size=batch_size, verbose=1, show_accuracy=True, validation_split=0.1)
model.evaluate(X_test, Y_test, batch_size=batch_size, verbose=1, show_accuracy=True)
# print('Test score:', score[0])
# print('Test accuracy:', score[1])
pred_labels = model.predict_classes(X_test)
# print pred_labels
# print y_test
accuracy = accuracy_score(y_test, pred_labels)
precision, recall, f1, supp = precision_recall_fscore_support(y_test, pred_labels, average='weighted')
print precision, recall, f1, supp
return accuracy, precision, recall, f1
if __name__ == '__main__':
n_count = 0
data = util.read_data(path.join(util.data_path, util.file_name))
X, y = build_dataset(data)
results = execute_model(X, y)
print results
util.insert_results('MLP', results[0], results[2], results[1], results[3])
# X = sequence.pad_sequences(X, maxlen=max_len)
X = np.asarray(X)
y = np.asarray(y)
return X, y
def execute_model(X, y):
kf = KFold(y.shape[0], n_folds=n_fold, shuffle=True)
results_user = np.array([0.0, 0.0, 0.0, 0.0])
for train_index, test_index in kf:
X_train, X_test = X[train_index], X[test_index]
y_train, y_test = y[train_index], y[test_index]
# accuracy, precision, recall, f1 = lstm_model(X_train, y_train, X_test, y_test)
accuracy, precision, recall, f1 = bidirectional_lstm(X_train, y_train, X_test, y_test)
results_user[0] += accuracy
results_user[1] += precision
results_user[2] += recall
results_user[3] += f1
results_user /= n_fold
return results_user
if __name__ == '__main__':
n_count = 0
data = util.read_data(path.join(util.data_path, util.file_name))
X, y = build_dataset(data)
results = execute_model(X, y)
print results
util.insert_results('BI-LSTM', results[0], results[2], results[1], results[3])
