def test_get_data_inventory():
dl = DataLoader()
file_names = dl.get_data_inventory()
assert set(file_names) == {
"online_retail", "minute_energy_appliance", "minute_household_power",
"minute_yosemite_temps", "hourly_parking", "hourly_traffic_volume",
"hourly_bikesharing", "hourly_beijing_pm",
"daily_temperature_australia", "daily_demand_order",
"daily_female_births", "daily_istanbul_stock", "daily_peyton_manning",
"monthly_shampoo", "monthly_sunspot"
}
def test_load_data():
dl = DataLoader()
df = dl.load_data(data_name="daily_peyton_manning")
expected_df = dl.load_peyton_manning()
assert_equal(df, expected_df)
df = dl.load_data(data_name="hourly_parking", system_code_number="Shopping")
expected_df = dl.load_parking(system_code_number="Shopping")
assert_equal(df, expected_df)
# Error due to unavailable data name
data_name = "dummy"
data_inventory = dl.get_data_inventory()
with pytest.raises(ValueError, match=fr"Input data name '{data_name}' is not recognized. "
fr"Must be one of \{data_inventory}\."):
dl.load_data(data_name=data_name)
def test_init():
dl = DataLoader()
assert dl.available_datasets == dl.get_data_inventory()