def test_semantic_model(weights_path, file_path, transfer=False):
_, _, _, _, test_X, test_y, embedding_matrix = load_data()
embedding_matrix = normalize(embedding_matrix,
axis=1,
norm='l2',
copy=False)
shape = test_X[0].shape
if transfer:
model = cnn_bidirectional_lstm_model(13, shape, embedding_matrix, 150)
model.layers.pop()
model.add(kl.Dense(test_y.shape[1], activation='sigmoid'))
model.load_weights(weights_path)
else:
model = cnn_bidirectional_lstm_model(test_y.shape[1], shape,
embedding_matrix, 150)
model.load_weights(weights_path)
opt = k.optimizers.Adam(lr=0.001, amsgrad=True)
model.compile(optimizer=opt, loss='binary_crossentropy')
preds = model.predict(test_X, verbose=True)
preds[preds >= 0.4] = 1
preds[preds < 0.4] = 0
score = [
accuracy_score(test_y, preds),
precision_score(test_y, preds, average='micro'),
recall_score(test_y, preds, average='micro'),
f1_score(test_y, preds, average='micro'),
precision_score(test_y, preds, average='macro'),
recall_score(test_y, preds, average='macro'),
f1_score(test_y, preds, average='macro')
]
print(score)
np.savetxt(file_path, np.array(score))
def train_semantic_sentiment_merged_model():
model_filepath = 'models/multi_emotion_sentiment_semantic_merged_model-{epoch:02d}-{val_loss:.2f}.h5'
logs_filepath = 'logs/multi_emotion_sentiment_semantic_merged_model.log'
train_X, train_y, val_X, val_y, _, _, embedding_matrix = load_data()
train_X2, val_X2, _, lexicon_matrix = load_sentiment_data()
train_X = np.vstack((train_X, val_X))
train_X2 = np.vstack((train_X2, val_X2))
train_y = np.vstack((train_y, val_y))
embedding_matrix = normalize(embedding_matrix,
axis=1,
norm='l2',
copy=False)
shape1 = train_X[0].shape
shape2 = train_X2[0].shape
model1 = cnn_bidirectional_lstm_model(train_y.shape[1], shape1,
embedding_matrix, 150)
model1.load_weights('models/multi_emotion_semantic_model-w2v-emoji.h5')
model1.pop()
model2 = cnn_bidirectional_lstm_model(train_y.shape[1], shape2,
lexicon_matrix, 150)
model2.load_weights('models/multi_emotion_semantic_lexicon_model.h5')
model2.pop()
merged_out = kl.Add()([model1.output, model2.output])
merged_out = kl.Dense(128, activation='relu')(merged_out)
merged_out = kl.Dropout(0.1)(merged_out)
merged_out = kl.Dense(train_y.shape[1], activation='sigmoid')(merged_out)
model = k.Model(inputs=[model1.input, model2.input], outputs=[merged_out])
opt = k.optimizers.Adam(lr=0.001, amsgrad=True)
model.compile(optimizer=opt,
loss='binary_crossentropy',
metrics=['accuracy'])
# checkpoint
checkpoint = k.callbacks.ModelCheckpoint(model_filepath,
monitor='val_loss',
verbose=1,
save_best_only=True,
save_weights_only=True,
mode='min')
csv_logger = k.callbacks.CSVLogger(logs_filepath)
model.fit([train_X, train_X2],
train_y,
epochs=200,
batch_size=1000,
shuffle=True,
callbacks=[checkpoint, csv_logger],
validation_split=0.1)
def train_semantic_lexicon_model():
model_filepath = 'models/multi_emotion_semantic_lexicon_model-{epoch:02d}-{val_loss:.2f}.h5'
logs_filepath = 'logs/multi_emotion_semantic_lexicon_model.log'
train_X, train_y, val_X, val_y, _, _, _ = load_data()
train_X, val_X, _, lexicon_matrix = load_sentiment_data()
train_X = np.vstack((train_X, val_X))
train_y = np.vstack((train_y, val_y))
shape = train_X[0].shape
model = cnn_bidirectional_lstm_model(train_y.shape[1], shape,
lexicon_matrix, 150)
opt = k.optimizers.Adam(lr=0.001, amsgrad=True)
model.compile(optimizer=opt,
loss='binary_crossentropy',
metrics=['accuracy'])
checkpoint = k.callbacks.ModelCheckpoint(model_filepath,
monitor='val_loss',
verbose=1,
save_best_only=True,
save_weights_only=True,
mode='min')
csv_logger = k.callbacks.CSVLogger(logs_filepath)
model.fit(train_X,
train_y,
epochs=200,
batch_size=1000,
shuffle=True,
callbacks=[checkpoint, csv_logger],
validation_split=0.1)
def test_semantic_sentiment_merged_model(weights_path, file_name):
_, _, _, _, test_X, test_y, embedding_matrix = load_data()
embedding_matrix = normalize(embedding_matrix,
axis=1,
norm='l2',
copy=False)
shape1 = test_X[0].shape
_, _, test_X2, lexicon_matrix = load_sentiment_data()
shape2 = test_X2[0].shape
model1 = cnn_bidirectional_lstm_model(test_y.shape[1], shape1,
embedding_matrix, 150)
model1.pop()
model2 = cnn_bidirectional_lstm_model(test_y.shape[1], shape2,
lexicon_matrix, 150)
model2.pop()
merged_out = kl.Add()([model1.output, model2.output])
merged_out = kl.Dense(128, activation='relu')(merged_out)
merged_out = kl.Dropout(0.1)(merged_out)
merged_out = kl.Dense(test_y.shape[1], activation='sigmoid')(merged_out)
model = k.Model(inputs=[model1.input, model2.input], outputs=[merged_out])
opt = k.optimizers.Adam(lr=0.001, amsgrad=True)
model.compile(optimizer=opt, loss='binary_crossentropy')
model.load_weights(weights_path)
preds = model.predict([test_X, test_X2], verbose=True)
preds[preds >= 0.4] = 1
preds[preds < 0.4] = 0
score = [
accuracy_score(test_y, preds),
precision_score(test_y, preds, average='micro'),
recall_score(test_y, preds, average='micro'),
f1_score(test_y, preds, average='micro'),
precision_score(test_y, preds, average='macro'),
recall_score(test_y, preds, average='macro'),
f1_score(test_y, preds, average='macro')
]
print(score)
np.savetxt(file_name, np.array(score))
def transfer_learning_semantic_model():
model_filepath = 'models/multi_emotion_semantic_model_transfer-{epoch:02d}-{val_loss:.2f}.h5'
logs_filepath = 'logs/multi_emotion_semantic_model_transfer.log'
model_weights = 'models/emotion_bi_lstm_semantic_model.h5'
train_X, train_y, val_X, val_y, _, _, embedding_matrix = load_data()
train_X = np.vstack((train_X, val_X))
train_y = np.vstack((train_y, val_y))
embedding_matrix = normalize(embedding_matrix,
axis=1,
norm='l2',
copy=False)
shape = train_X[0].shape
model = cnn_bidirectional_lstm_model(13, shape, embedding_matrix, 150)
model.load_weights(model_weights)
model.layers.pop()
for layer in model.layers:
layer.trainable = False
model.add(kl.Dense(train_y.shape[1], activation='sigmoid'))
opt = k.optimizers.Adam(lr=0.01, amsgrad=True)
model.compile(optimizer=opt,
loss='binary_crossentropy',
metrics=['accuracy'])
checkpoint = k.callbacks.ModelCheckpoint(model_filepath,
monitor='val_loss',
verbose=1,
save_best_only=True,
save_weights_only=True,
mode='min')
csv_logger = k.callbacks.CSVLogger(logs_filepath)
model.fit(train_X,
train_y,
epochs=250,
batch_size=500,
shuffle=True,
callbacks=[checkpoint, csv_logger],
validation_split=0.1)