def fit_line_type(self,
training_data_dir_path,
model_dir_path,
batch_size=None,
epochs=None,
test_size=None,
random_state=None):
text_data_model = fit_text(training_data_dir_path,
label_type='line_type')
text_label_pairs = load_text_label_pairs(training_data_dir_path,
label_type='line_type')
if batch_size is None:
batch_size = 64
if epochs is None:
epochs = 20
history = self.line_label_classifier.fit(
text_data_model=text_data_model,
model_dir_path=os.path.join(model_dir_path, 'line_type'),
text_label_pairs=text_label_pairs,
batch_size=batch_size,
epochs=epochs,
test_size=test_size,
random_state=random_state)
return history
def main():
random_state = 42
np.random.seed(random_state)
output_dir_path = './models'
data_file_path = '../data/training_data'
text_data_model = fit_text(data_file_path)
text_label_pairs = load_text_label_pairs(data_file_path)
classifier = WordVecCnn()
batch_size = 64
epochs = 20
history = classifier.fit(text_data_model=text_data_model,
model_dir_path=output_dir_path,
text_label_pairs=text_label_pairs,
batch_size=batch_size, epochs=epochs,
test_size=0.3,
random_state=random_state)