def train_lstm(model_filename, weights_filename, l1_d=128, l2_d=128, b_s=128, bi=False):
"""
Trains a 2 layer lstm and saves the model in the files specified.
Args:
model_filename: The filename to save the model
weights_filename: The filename to save the weights
l1_d: Layer one dimensions
l2_d: Layer two dimensions
b_s: Batch size
Returns:
model: The lstm model fit on the training data
"""
dm=DataModel()
texts, labels=dm.get_train_data()
word_index, data=utils.get_word_index(texts)
x_train, y_train, x_val, y_val, _, _=utils.get_train_val_test_data(
data, labels)
word_embeddings=utils.get_glove_embeddings()
embedding_matrix=utils.get_embedding_matrix(word_embeddings, word_index)
if bi:
model=_bi_lstm(embedding_matrix, x_train, y_train, x_val,
y_val, 3, word_index, l1_d, l2_d, b_s)
else:
model=_lstm(embedding_matrix, x_train, y_train, x_val,
y_val, 3, word_index, l1_d, l2_d, b_s)
save_model(model, model_filename, weights_filename)
return model
def accuracy_test(model_filename, weights_filename):
dm = DataModel()
x_train, y_train = dm.get_train_data()
train_samples = int(0.8 * len(x_train))
x_test = x_train[train_samples:]
y_test = y_train[train_samples:]
_, data = utils.get_word_index(x_test)
labels = to_categorical(np.asarray(y_test))
# word_embeddings = utils.get_glove_embeddings()
# _ = utils.get_embedding_matrix(word_embeddings, word_index)
md = utils.load_model(model_filename, weights_filename)
result = md.evaluate(data, labels)
print('\nTest loss:', result[0])
print('Test accuracy:', result[1])
def generate_w2c_word_embeddings():
"""
Generates word 2 vector embeddings.
"""
dm = DataModel()
train_x, _ = dm.get_train_data()
w2c = Word2Vec(method="skipgram",
corpus=list(train_x),
window_size=5,
n_hidden=128,
n_epochs=3,
learning_rate=0.08)
W1, W2, loss_vs_epoch = w2c.run()
pkl_dump = [W1, W2, loss_vs_epoch]
with open('embeddings.pickle', 'wb') as handle:
pickle.dump(pkl_dump, handle)