def prepare_multi_modal_data(files_path, task: Task, images_size=(128, 128), with_split=True):
path = os.path.join(str(fedot_project_root()), files_path)
unpack_archived_data(path)
data = InputData.from_json_files(path, fields_to_use=['votes', 'year'],
label='rating', task=task)
class_labels = np.asarray([0 if t <= 7 else 1 for t in data.target])
data.target = class_labels
ratio = 0.5
img_files_path = f'{files_path}/*.jpeg'
img_path = os.path.join(str(fedot_project_root()), img_files_path)
data_img = InputData.from_image(images=img_path, labels=class_labels, task=task, target_size=images_size)
data_text = InputData.from_json_files(path, fields_to_use=['plot'],
label='rating', task=task,
data_type=DataTypesEnum.text)
data_text.target = class_labels
if with_split:
train_num, test_num = train_test_data_setup(data, shuffle_flag=False, split_ratio=ratio)
train_img, test_img = train_test_data_setup(data_img, shuffle_flag=False, split_ratio=ratio)
train_text, test_text = train_test_data_setup(data_text, shuffle_flag=False, split_ratio=ratio)
else:
train_num, test_num = data, data
train_img, test_img = data_img, data_img
train_text, test_text = data_text, data_text
return train_num, test_num, train_img, test_img, train_text, test_text
def test_data_from_json():
# several features
files_path = os.path.join('test', 'data', 'multi_modal')
path = os.path.join(str(fedot_project_root()), files_path)
data = InputData.from_json_files(path,
fields_to_use=['votes', 'year'],
label='rating',
task=Task(TaskTypesEnum.regression))
assert data.features.shape[1] == 2 # check there is two features
assert len(data.target) == data.features.shape[0] == len(data.idx)
# single feature
data = InputData.from_json_files(path,
fields_to_use=['votes'],
label='rating',
task=Task(TaskTypesEnum.regression))
assert len(data.features.shape) == 1 # check there is one feature
assert len(data.target) == len(data.features) == len(data.idx)
