def test_get_data_names():
dl = DataLoader()
# Returns empty set as there is no .csv file in 'data' folder
data_path = dl.get_data_home()
file_names = dl.get_data_names(data_path=data_path)
assert file_names == []
data_path = dl.get_data_home(data_sub_dir="daily")
file_names = dl.get_data_names(data_path=data_path)
assert set(file_names) == {
"daily_temperature_australia", "daily_demand_order",
"daily_female_births", "daily_istanbul_stock", "daily_peyton_manning"
}
def test_get_df():
dl = DataLoader()
# Daily data
data_path = dl.get_data_home(data_dir=None, data_sub_dir="daily")
df = dl.get_df(data_path=data_path, data_name="daily_peyton_manning")
assert list(df.columns) == ["ts", "y"]
assert df.shape == (2905, 2)
# Hourly data
data_path = dl.get_data_home(data_dir=None, data_sub_dir="hourly")
df = dl.get_df(data_path=data_path, data_name="hourly_parking")
assert list(df.columns) == [
"SystemCodeNumber", "Capacity", "Occupancy", "LastUpdated"
]
assert df.shape == (35717, 4)
# Error due to wrong file name
data_path = dl.get_data_home(data_dir=None, data_sub_dir="daily")
file_path = os.path.join(data_path, "parking.csv")
file_names = dl.get_data_names(data_path=data_path)
with pytest.raises(
ValueError,
match=
fr"Given file path '{file_path}' is not found. Available datasets "
fr"in data directory '{data_path}' are \{file_names}\."):
dl.get_df(data_path=data_path, data_name="parking")