def fit(self,
x,
y,
x_test=None,
y_test=None,
batch_size=None,
time_limit=None):
"""Find the best neural architecture and train it.
Based on the given dataset, the function will find the best neural architecture for it.
The dataset is in numpy.ndarray format.
So they training data should be passed through `x_train`, `y_train`.
Args:
x: A numpy.ndarray instance containing the training data.
y: A numpy.ndarray instance containing the label of the training data.
y_test: A numpy.ndarray instance containing the testing data.
x_test: A numpy.ndarray instance containing the label of the testing data.
batch_size: int, define the batch size.
time_limit: The time limit for the search in seconds.
"""
x = text_preprocess(x, path=self.path)
x = np.array(x)
y = np.array(y)
validate_xy(x, y)
y = self.transform_y(y)
if batch_size is None:
batch_size = Constant.MAX_BATCH_SIZE
# Divide training data into training and testing data.
if x_test is None or y_test is None:
x_train, x_test, y_train, y_test = train_test_split(
x,
y,
test_size=min(Constant.VALIDATION_SET_SIZE, int(len(y) * 0.2)),
random_state=42)
else:
x_train = x
y_train = y
# Wrap the data into DataLoaders
if self.data_transformer is None:
self.data_transformer = TextDataTransformer()
train_data = self.data_transformer.transform_train(
x_train, y_train, batch_size=batch_size)
test_data = self.data_transformer.transform_test(x_test, y_test)
# Save the classifier
pickle.dump(self, open(os.path.join(self.path, 'text_classifier'),
'wb'))
pickle_to_file(self, os.path.join(self.path, 'text_classifier'))
if time_limit is None:
time_limit = 24 * 60 * 60
self.cnn.fit(self.get_n_output_node(), x_train.shape, train_data,
test_data, time_limit)
def init_transformer(self, x):
# Wrap the data into DataLoaders
if self.data_transformer is None:
self.data_transformer = TextDataTransformer()