def SA_sst():
(
(
x_train_idx_data,
y_train_valence,
y_train_labels,
x_test_idx_data,
y_test_valence,
y_test_labels,
x_valid_idx_data,
y_valid_valence,
y_valid_labels,
x_train_polarity_idx_data,
y_train_polarity,
x_test_polarity_idx_data,
y_test_polarity,
x_valid_polarity_idx_data,
y_valid_polarity,
),
W,
) = build_keras_input()
maxlen = 200 # cut texts after this number of words (among top max_features most common words)
batch_size = 32
(X_train, y_train), (X_test, y_test), (X_valid, y_valide) = (
(x_train_polarity_idx_data, y_train_polarity),
(x_test_polarity_idx_data, y_test_polarity),
(x_valid_polarity_idx_data, y_valid_polarity),
)
print(len(X_train), "train sequences")
print(len(X_test), "test sequences")
# m= 0
# for i in X_train:
# if len(i) >0:
# for j in i:
# if j > m:
# m=j
# print(m)
max_features = W.shape[0] # shape of W: (13631, 300)
print("Pad sequences (samples x time)")
X_train = sequence.pad_sequences(X_train, maxlen=maxlen)
X_test = sequence.pad_sequences(X_test, maxlen=maxlen)
print("X_train shape:", X_train.shape)
print("X_test shape:", X_test.shape)
model = dan_dropout_position(W)
# try using different optimizers and different optimizer configs
model.compile(loss="binary_crossentropy", optimizer="adagrad", class_mode="binary")
print("Train...")
model.fit(
X_train, y_train, batch_size=batch_size, nb_epoch=30, validation_data=(X_test, y_test), show_accuracy=True
)
score, acc = model.evaluate(X_test, y_test, batch_size=batch_size, show_accuracy=True)
print("Test score:", score)
print("Test accuracy:", acc)
def my_function(param1, param2, param3):
((x_train_idx_data, y_train_valence, y_train_labels,
x_test_idx_data, y_test_valence, y_test_labels,
x_valid_idx_data, y_valid_valence, y_valid_labels,
x_train_polarity_idx_data, y_train_polarity,
x_test_polarity_idx_data, y_test_polarity,
x_valid_polarity_idx_data, y_valid_polarity), W) = build_keras_input()
maxlen = 200 # cut texts after this number of words (among top max_features most common words)
batch_size = 32
(X_train, y_train), (X_test, y_test), (X_valid, y_valide) = (x_train_polarity_idx_data, y_train_polarity), (x_test_polarity_idx_data, y_test_polarity), (x_valid_polarity_idx_data, y_valid_polarity)
print(len(X_train), 'train sequences')
print(len(X_test), 'test sequences')
# m= 0
# for i in X_train:
# if len(i) >0:
# for j in i:
# if j > m:
# m=j
# print(m)
max_features = W.shape[0] # shape of W: (13631, 300) , changed to 14027 through min_df = 3
print("Pad sequences (samples x time)")
X_train = sequence.pad_sequences(X_train, maxlen=maxlen)
X_test = sequence.pad_sequences(X_test, maxlen=maxlen)
X_valid = sequence.pad_sequences(X_valid, maxlen=maxlen)
print('X_train shape:', X_train.shape)
print('X_test shape:', X_test.shape)
nb_classes = 2
y_train = np_utils.to_categorical(y_train, nb_classes)
y_test = np_utils.to_categorical(y_test, nb_classes)
y_valide = np_utils.to_categorical(y_valide, nb_classes)
model = dan_pre_trained(W, param1,param2,param3)
plot(model, to_file='./images/model.png')
# try using different optimizers and different optimizer configs
# model.compile(loss='binary_crossentropy', optimizer='adagrad', class_mode="binary")
model.compile(loss='categorical_crossentropy', optimizer='adagrad')
print("Train...")
early_stopping = EarlyStopping(monitor='val_loss', patience=10)
model.fit(X_train, y_train, batch_size=batch_size, nb_epoch=100, validation_data=(X_test, y_test), show_accuracy=True, callbacks=[early_stopping])
score, acc = model.evaluate(X_test, y_test, batch_size=batch_size, show_accuracy=True)
print('Test score:', score)
print('Test accuracy:', acc)
return acc
def SA_sst():
((x_train_idx_data, y_train_valence, y_train_labels,
x_test_idx_data, y_test_valence, y_test_labels,
x_valid_idx_data, y_valid_valence, y_valid_labels,
x_train_polarity_idx_data, y_train_polarity,
x_test_polarity_idx_data, y_test_polarity,
x_valid_polarity_idx_data, y_valid_polarity), W) = build_keras_input()
maxlen = 200 # cut texts after this number of words (among top max_features most common words)
batch_size = 32
(X_train, y_train), (X_test, y_test), (X_valid, y_valide) = (x_train_polarity_idx_data, y_train_polarity), (
x_test_polarity_idx_data, y_test_polarity), (x_valid_polarity_idx_data, y_valid_polarity)
print(len(X_train), 'train sequences')
print(len(X_test), 'test sequences')
# m= 0
# for i in X_train:
# if len(i) >0:
# for j in i:
# if j > m:
# m=j
# print(m)
max_features = W.shape[0] # shape of W: (13631, 300)
print("Pad sequences (samples x time)")
X_train = sequence.pad_sequences(X_train, maxlen=maxlen)
X_test = sequence.pad_sequences(X_test, maxlen=maxlen)
print('X_train shape:', X_train.shape)
print('X_test shape:', X_test.shape)
model = dan_dropout_position(W)
# try using different optimizers and different optimizer configs
model.compile(loss='binary_crossentropy', optimizer='adagrad', class_mode="binary")
print("Train...")
model.fit(X_train, y_train, batch_size=batch_size, nb_epoch=30, validation_data=(X_test, y_test),
show_accuracy=True)
score, acc = model.evaluate(X_test, y_test, batch_size=batch_size, show_accuracy=True)
print('Test score:', score)
print('Test accuracy:', acc)
