def test_get_data_start_end_labels_obs_longer_than_1h(site_metadata):
observation = default_observation(
site_metadata,
interval_length=pd.Timedelta('2h'))
forecast = default_forecast(
site_metadata,
run_length=pd.Timedelta('5min'))
run_time = pd.Timestamp('20190422T1945Z')
# obs interval cannot be longer than 1 hr
with pytest.raises(ValueError) as excinfo:
main.get_data_start_end(observation, forecast, run_time)
assert 'observation.interval_length <= 1h' in str(excinfo.value)
def test_get_data_start_end_labels_obs_avg_fx_instant(site_metadata):
run_time = pd.Timestamp('20190422T1945Z')
observation = default_observation(
site_metadata,
interval_length=pd.Timedelta('5min'), interval_label='ending')
forecast = default_forecast(
site_metadata,
issue_time_of_day=dt.time(hour=5),
lead_time_to_start=pd.Timedelta('1h'),
interval_length=pd.Timedelta('5min'),
run_length=pd.Timedelta('1d'),
interval_label='instant')
with pytest.raises(ValueError) as excinfo:
main.get_data_start_end(observation, forecast, run_time)
assert 'made from interval average obs' in str(excinfo.value)
def test_get_data_start_end_labels_obs_fx_instant_mismatch(site_metadata):
observation = default_observation(
site_metadata,
interval_length=pd.Timedelta('5min'), interval_label='instant')
forecast = default_forecast(
site_metadata,
issue_time_of_day=dt.time(hour=5),
lead_time_to_start=pd.Timedelta('1h'),
interval_length=pd.Timedelta('1h'), # interval_length must be equal
run_length=pd.Timedelta('1d'),
interval_label='instant') # if interval_label also instant
run_time = pd.Timestamp('20190422T1945Z')
with pytest.raises(ValueError) as excinfo:
main.get_data_start_end(observation, forecast, run_time)
assert 'with identical interval length' in str(excinfo.value)
def test_get_data_start_end_labels_subhourly_window_limit(site_metadata):
observation = default_observation(
site_metadata,
interval_length=pd.Timedelta('5min'), interval_label='beginning')
forecast = default_forecast(
site_metadata,
run_length=pd.Timedelta('5min'), # test subhourly limit on window
interval_label='beginning')
run_time = pd.Timestamp('20190422T1945Z')
data_start, data_end = main.get_data_start_end(observation, forecast,
run_time)
assert data_start == pd.Timestamp('20190422T1940Z')
assert data_end == pd.Timestamp('20190422T1945Z')
def test_get_data_start_end_labels_1h_window_limit(site_metadata):
observation = default_observation(
site_metadata,
interval_length=pd.Timedelta('5min'), interval_label='beginning')
forecast = default_forecast(
site_metadata,
run_length=pd.Timedelta('12h'), # test 1 hr limit on window
interval_label='beginning')
# ensure data no later than run time
run_time = pd.Timestamp('20190422T1945Z')
data_start, data_end = main.get_data_start_end(observation, forecast,
run_time)
assert data_start == pd.Timestamp('20190422T1845Z')
assert data_end == pd.Timestamp('20190422T1945Z')
def test_get_data_start_end_labels_obs_instant_fx_avg_intraday(site_metadata):
run_time = pd.Timestamp('20190422T1945Z')
observation = default_observation(
site_metadata,
interval_length=pd.Timedelta('5min'), interval_label='instant')
forecast = default_forecast(
site_metadata,
issue_time_of_day=dt.time(hour=5),
lead_time_to_start=pd.Timedelta('1h'),
interval_length=pd.Timedelta('5min'),
run_length=pd.Timedelta('15min'),
interval_label='ending')
data_start, data_end = main.get_data_start_end(observation, forecast,
run_time)
assert data_start == pd.Timestamp('20190422T193001Z')
assert data_end == pd.Timestamp('20190422T1945Z')
def test_get_data_start_end_labels_obs_fx_instant(site_metadata):
observation = default_observation(
site_metadata,
interval_length=pd.Timedelta('5min'), interval_label='instant')
forecast = default_forecast(
site_metadata,
issue_time_of_day=dt.time(hour=5),
lead_time_to_start=pd.Timedelta('1h'),
interval_length=pd.Timedelta('5min'), # interval_length must be equal
run_length=pd.Timedelta('1d'),
interval_label='instant') # if interval_label also instant
run_time = pd.Timestamp('20190422T1945Z')
data_start, data_end = main.get_data_start_end(observation, forecast,
run_time)
assert data_start == pd.Timestamp('20190421T0000Z')
assert data_end == pd.Timestamp('20190421T235959Z')
def test_get_data_start_end_labels_obs_longer_than_1h_day_ahead(site_metadata):
observation = default_observation(
site_metadata,
interval_length=pd.Timedelta('2h'), interval_label='beginning')
forecast = default_forecast(
site_metadata,
issue_time_of_day=dt.time(hour=5),
lead_time_to_start=pd.Timedelta('1h'),
interval_length=pd.Timedelta('1h'),
run_length=pd.Timedelta('1d'), # day ahead
interval_label='beginning')
run_time = pd.Timestamp('20190422T1945Z')
# day ahead doesn't care about obs interval length
data_start, data_end = main.get_data_start_end(observation, forecast,
run_time)
assert data_start == pd.Timestamp('20190421T0000Z')
assert data_end == pd.Timestamp('20190422T0000Z')