def train_mlp_model(data,
learning_rate=1e-3,
epochs=1000,
batch_size=128,
layers=2,
units=64,
dropout_rate=0.3):
(train_texts, train_labels), (val_texts, val_labels) = data
num_classes = explore_data.get_num_classes(train_labels)
unexpected_labels = [i for i in val_labels if i not in range(num_classes)]
if len(unexpected_labels) > 0:
raise ValueError(
'Unexpected label values found in validation set: '
'{unexpected_labels}. Please make sure that the '
'labels in the validation set are in the same range '
'as training labels.'.format(unexpected_labels=unexpected_labels))
x_train, x_val = vectorize_data.tfidf_vectorize(train_texts, train_labels,
val_texts)
model = build_model.mlp_model(layers=layers,
units=units,
dropout_rate=dropout_rate,
input_shape=x_train.shape[1:],
num_classes=num_classes)
if num_classes == 2:
loss = 'binary_crossentropy'
else:
loss = 'sparse_categorical_crossentropy'
optimizer = tf.keras.optimizers.Adam(lr=learning_rate)
model.compile(optimizer=optimizer, loss=loss, metrics=['acc'])
callbacks = [
tf.keras.callbacks.EarlyStopping(monitor='val_loss', patience=2)
]
history = model.fit(x_train,
train_labels,
epochs=epochs,
callbacks=callbacks,
validation_data=(x_val, val_labels),
verbose=2,
batch_size=batch_size)
history = history.history
print('Validation accuracy: {acc}, loss: {loss}'.format(
acc=history['val_acc'][-1], loss=history['val_loss'][-1]))
model.save('mlp_model.h5')
return history['val_acc'][-1], history['val_loss'][-1]
def train_ngram_model(data,
learning_rate=1e-3,
epochs=1000,
batch_size=128,
layers=2,
units=64,
dropout_rate=0.2):
"""Trains n-gram model on the given dataset.
# Arguments
data: tuples of training and test texts and labels.
learning_rate: float, learning rate for training model.
epochs: int, number of epochs.
batch_size: int, number of samples per batch.
layers: int, number of `Dense` layers in the model.
units: int, output dimension of Dense layers in the model.
dropout_rate: float: percentage of input to drop at Dropout layers.
# Raises
ValueError: If validation data has label values which were not seen
in the training data.
"""
# Get the data.
(train_texts, train_labels), (val_texts, val_labels) = data
# Verify that validation labels are in the same range as training labels.
num_classes = explore_data.get_num_classes(train_labels)
unexpected_labels = [v for v in val_labels if v not in range(num_classes)]
if len(unexpected_labels):
raise ValueError(
'Unexpected label values found in the validation set:'
' {unexpected_labels}. Please make sure that the '
'labels in the validation set are in the same range '
'as training labels.'.format(unexpected_labels=unexpected_labels))
# Vectorize texts.
x_train, x_val = vectorize_data.ngram_vectorize(train_texts, train_labels,
val_texts)
# Create model instance.
model = build_model.mlp_model(layers=layers,
units=units,
dropout_rate=dropout_rate,
input_shape=x_train.shape[1:],
num_classes=num_classes)
# Compile model with learning parameters.
if num_classes == 2:
loss = 'binary_crossentropy'
else:
loss = 'sparse_categorical_crossentropy'
optimizer = tf.keras.optimizers.Adam(lr=learning_rate)
model.compile(optimizer=optimizer, loss=loss, metrics=['acc'])
# Create callback for early stopping on validation loss. If the loss does
# not decrease in two consecutive tries, stop training.
callbacks = [
tf.keras.callbacks.EarlyStopping(monitor='val_loss', patience=2)
]
# Train and validate model.
history = model.fit(
x_train,
train_labels,
epochs=epochs,
callbacks=callbacks,
validation_data=(x_val, val_labels),
verbose=2, # Logs once per epoch.
batch_size=batch_size)
# Print results.
history = history.history
print('Validation accuracy: {acc}, loss: {loss}'.format(
acc=history['val_acc'][-1], loss=history['val_loss'][-1]))
# Save model.
model.save('tuned_model.h5')
return model, history['val_acc'][-1], history['val_loss'][-1]
X_train, X_val, y_train, y_val = train_test_split(
training_data['article_words'],
training_data['topic'],
test_size=0.10,
random_state=42)
X_train, X_val, vectorizer = ngram_vectorize(X_train, y_train, X_val)
LB = LabelEncoder()
train_labels = LB.fit_transform(y_train)
val_labels = LB.fit_transform(y_val)
num_classes = len(list((training_data['topic'].value_counts()).keys()))
model = build_model.mlp_model(layers=2,
units=32,
dropout_rate=0.2,
input_shape=X_train.shape[1:],
num_classes=num_classes)
# Compile model with learning parameters.
if num_classes == 2:
loss = 'binary_crossentropy'
else:
loss = 'sparse_categorical_crossentropy'
optimizer = Adam(lr=1e-3)
model.compile(optimizer='adam', loss=loss, metrics=['acc'])
# Create callback for early stopping on validation loss. If the loss does
# not decrease in two consecutive tries, stop training.
callbacks = [EarlyStopping(monitor='val_loss', patience=2)]
