def train():
settings = Settings()
batch_size = settings.get_training_parameters('batch_size')
epochs = settings.get_training_parameters('epochs')
dictionary_size = settings.get_training_parameters('dictionary_size')
max_headline_length = settings.get_training_parameters('max_headline_length')
glove = Glove(dictionary_size)
glove.load_embedding()
model_builder = Model1Builder() \
.set_input('glove', glove) \
.set_parameter('max_headline_length', max_headline_length)
model = model_builder()
preprocessor = Preprocessor(model)
preprocessor.set_encoder('glove', glove)
preprocessor.set_parameter('max_headline_length', max_headline_length)
preprocessor.load_data(['headline', 'is_top_submission'])
training_input = [preprocessor.training_data['headline']]
validation_input = [preprocessor.validation_data['headline']]
training_output = [preprocessor.training_data['is_top_submission']]
validation_output = [preprocessor.validation_data['is_top_submission']]
class_weights = calculate_class_weights(preprocessor.training_data['is_top_submission'],
[ol.name for ol in model.output_layers])
callbacks = CallbackBuilder(model, [CsvLogger, CsvPlotter, ConfigLogger, ModelSaver])()
model.fit(training_input, training_output, batch_size=batch_size, epochs=epochs,
callbacks=callbacks, validation_data=(validation_input, validation_output), class_weight=class_weights)
def train():
settings = Settings()
batch_size = settings.get_training_parameters('batch_size')
epochs = settings.get_training_parameters('epochs')
model_builder = Model4Builder()
model = model_builder()
preprocessor = Preprocessor(model)
preprocessor.load_data(['category', 'is_top_submission'])
training_input = [preprocessor.training_data['category']]
validation_input = [preprocessor.validation_data['category']]
training_output = [preprocessor.training_data['is_top_submission']]
validation_output = [preprocessor.validation_data['is_top_submission']]
class_weights = calculate_class_weights(preprocessor.training_data['is_top_submission'],
[ol.name for ol in model.output_layers])
callbacks = CallbackBuilder(model, [CsvLogger, CsvPlotter, ConfigLogger, ModelSaver])()
model.fit(training_input, training_output, batch_size=batch_size, epochs=epochs,
callbacks=callbacks, validation_data=(validation_input, validation_output), class_weight=class_weights)
def train():
settings = Settings()
batch_size = settings.get_training_parameters('batch_size')
epochs = settings.get_training_parameters('epochs')
max_headline_length = settings.get_training_parameters(
'max_headline_length')
max_article_length = settings.get_training_parameters('max_article_length')
headline_numeric_log = NumericLog(max_headline_length)
article_numeric_log = NumericLog(max_article_length)
model_builder = Model6Builder() \
.set_input('headline_numeric_log', headline_numeric_log) \
.set_input('article_numeric_log', article_numeric_log)
model = model_builder()
preprocessor = Preprocessor(model)
preprocessor.set_encoder('headline_numeric_log', headline_numeric_log)
preprocessor.set_encoder('article_numeric_log', article_numeric_log)
preprocessor.load_data([
'headline_log_representation', 'article_log_representation',
'is_top_submission'
])
training_input = [
preprocessor.training_data['headline_log_representation'],
preprocessor.training_data['article_log_representation']
]
validation_input = [
preprocessor.validation_data['headline_log_representation'],
preprocessor.validation_data['article_log_representation']
]
training_output = [preprocessor.training_data['is_top_submission']]
validation_output = [preprocessor.validation_data['is_top_submission']]
class_weights = calculate_class_weights(
preprocessor.training_data['is_top_submission'],
[ol.name for ol in model.output_layers])
callbacks = CallbackBuilder(
model, [CsvLogger, CsvPlotter, ConfigLogger, ModelSaver])()
model.fit(training_input,
training_output,
batch_size=batch_size,
epochs=epochs,
callbacks=callbacks,
validation_data=(validation_input, validation_output),
class_weight=class_weights)