class DeepLearningTest(unittest.TestCase):
PATH_DATASET_HOURLY = '../../../' + PATH_DATASET.get('hourly')
PATH_DATASET_DAILY = '../../../' + PATH_DATASET.get('daily')
df_hourly = load_dataframe_from_csv(PATH_DATASET_HOURLY)
df_daily = load_dataframe_from_csv(PATH_DATASET_DAILY)
def test_create_net(self):
# TODO
pass
class ModelingUtilsTest(unittest.TestCase):
PATH_DATASET_HOURLY = '../../../' + PATH_DATASET.get('hourly')
PATH_DATASET_DAILY = '../../../' + PATH_DATASET.get('daily')
df_hourly = load_dataframe_from_csv(PATH_DATASET_HOURLY)
df_daily = load_dataframe_from_csv(PATH_DATASET_DAILY)
def test_split_data(self):
print(self.df_hourly.dtypes)
train, test = split_data(self.df_hourly, test_size=TEST_SIZE)
expected_size = 524
self.assertEqual(expected_size, train.shape[0])
def runner(args: Namespace) -> None:
dataset = load_dataframe_from_csv(
create_path(args.home_path, PATH_DATASET.get(args.sampling_frequency)))
xgb_model, metrics = xgboost_model(dataset, args.sampling_frequency)
metrics = {
metric_name: str(metric_value)
for metric_name, metric_value in metrics.items()
}
# TODO implement saving XGB model in create_path(args.home_path, PATH_RESULTS[args.sampling_frequency]['xgboost']['model']))
with open(
create_path(
args.home_path,
PATH_RESULTS[args.sampling_frequency]['xgboost']['metrics']),
'w') as metrics_file: # TODO refactor this as a function
metrics_file.write(json.dumps(metrics))
def runner(args: Namespace) -> None:
df_bikes_clean = load_dataframe_from_csv(create_path(
args.home_path, PATH_BIKES_CLEAN),
parse_dates=[COL_BIKES_DATE])
df_weather = load_dataframe_from_json(create_path(args.home_path,
PATH_AEMET_PER_DAY),
parse_dates=[COL_WEATHER_DATE])
df_weather = clean_weather_data(df_weather)
if args.sampling_frequency == 'daily': # extract daily/hourly value as constant
df_prepared = prepare_daily_data(df_bikes_clean, df_weather)
elif args.sampling_frequency == 'hourly':
df_prepared = prepare_hourly_data(df_bikes_clean, df_weather)
pass
# TODO implement else, return error
save_dataframe(
df_prepared,
create_path(args.home_path, PATH_DATASET.get(args.sampling_frequency)))
def runner(args: Namespace) -> None:
dataset = load_dataframe_from_csv(
create_path(args.home_path, PATH_DATASET.get(args.sampling_frequency)))
net, metrics = deep_learning_model(dataset)
metrics = {
metric_name: str(metric_value)
for metric_name, metric_value in metrics.items()
}
save_model(
net,
create_path(
args.home_path,
PATH_RESULTS[args.sampling_frequency]['deep-learning']['model']))
with open(
create_path(
args.home_path, PATH_RESULTS[args.sampling_frequency]
['deep-learning']['metrics']),
'w') as metrics_file: # TODO refactor this as a function
metrics_file.write(json.dumps(metrics))
def main():
print("[data-preparation] Starting ... ")
parser = argparse.ArgumentParser(
description='[BiciMad Project] Data Cleaning')
parser.add_argument('--home-path',
type=str,
default='.',
metavar='H',
help='home path')
parser.add_argument('--sampling-frequency',
type=str,
default='hourly',
metavar='S',
help='Sampling frequency of data: daily/hourly ')
args: Namespace = parser.parse_args()
print("[data-preparation] Setting home path as: {}".format(args.home_path))
print("[data-preparation] Preparing [{}] data".format(
args.sampling_frequency))
runner(args)
print("[data-preparation] Success: Prepared data stored in {}.".format(
create_path(args.home_path,
PATH_DATASET.get(args.sampling_frequency))))
class XGBoostTest(unittest.TestCase):
PATH_DATASET_DAILY = '../../../' + PATH_DATASET.get('daily')
df_daily = load_dataframe_from_csv(PATH_DATASET_DAILY)
PATH_DATASET_HOURLY = '../../../' + PATH_DATASET.get('hourly')
df_hourly = load_dataframe_from_csv(PATH_DATASET_HOURLY)