def forecast_hr_begin(site_metadata):
return 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('1h'),
interval_label='beginning')
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:
utils.get_data_start_end(observation, forecast, run_time)
assert 'observation.interval_length <= 1h' in str(excinfo.value)
def test_run_persistence_fx_too_short(session, site_metadata, obs_5min_begin):
forecast = default_forecast(site_metadata,
issue_time_of_day=dt.time(hour=23),
lead_time_to_start=pd.Timedelta('1h'),
interval_length=pd.Timedelta('1min'),
run_length=pd.Timedelta('3min'),
interval_label='beginning')
issue_time = pd.Timestamp('20190423T2300Z')
run_time = pd.Timestamp('20190422T1945Z')
with pytest.raises(ValueError) as excinfo:
main.run_persistence(session, obs_5min_begin, forecast, run_time,
issue_time)
assert 'requires observation.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 = utils.get_data_start_end(observation, forecast,
run_time)
assert data_start == pd.Timestamp('20190422T1940Z')
assert data_end == pd.Timestamp('20190422T1945Z')
def test_get_forecast_start_end_time_instant(site_metadata):
# 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('1h'),
interval_label='instant')
issue_time = pd.Timestamp('20190422T0500')
fx_start, fx_end = main.get_forecast_start_end(forecast, issue_time)
assert fx_start == pd.Timestamp('20190422T0600')
assert fx_end == pd.Timestamp('20190422T065959')
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:
utils.get_data_start_end(observation, forecast, run_time)
assert 'made from interval average obs' in str(excinfo.value)
def test_run_persistence_incompatible_instant_fx(session, site_metadata,
obs_5min_begin):
forecast = default_forecast(site_metadata,
issue_time_of_day=dt.time(hour=23),
lead_time_to_start=pd.Timedelta('1h'),
interval_length=pd.Timedelta('1h'),
run_length=pd.Timedelta('1h'),
interval_label='instantaneous')
issue_time = pd.Timestamp('20190423T2300Z')
run_time = pd.Timestamp('20190422T1945Z')
with pytest.raises(ValueError) as excinfo:
main.run_persistence(session, obs_5min_begin, forecast, run_time,
issue_time)
assert 'instantaneous forecast' in str(excinfo.value).lower()
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 = utils.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 = utils.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_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:
utils.get_data_start_end(observation, forecast, run_time)
assert 'with identical interval length' in str(excinfo.value)
def test_run_persistence_interval_not_midnight_to_midnight(
session, site_metadata, obs_5min_begin):
# not midnight to midnight
forecast = default_forecast(site_metadata,
issue_time_of_day=dt.time(hour=22),
lead_time_to_start=pd.Timedelta('1h'),
interval_length=pd.Timedelta('1h'),
run_length=pd.Timedelta('24h'),
interval_label='beginning')
issue_time = pd.Timestamp('20190423T2200Z')
run_time = pd.Timestamp('20190422T1945Z')
with pytest.raises(ValueError) as excinfo:
main.run_persistence(session, obs_5min_begin, forecast, run_time,
issue_time)
assert 'midnight to midnight' in str(excinfo.value)
def test_get_data_start_end_labels_obs_instant_fx_avg(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=23),
lead_time_to_start=pd.Timedelta('1h'),
interval_length=pd.Timedelta('5min'),
run_length=pd.Timedelta('1d'),
interval_label='beginning')
run_time = pd.Timestamp('20190422T1945Z')
issue_time = pd.Timestamp('20190422T2300Z')
data_start, data_end = utils.get_data_start_end(observation, forecast,
run_time, issue_time)
assert data_start == pd.Timestamp('20190421T0000Z')
assert data_end == pd.Timestamp('20190421T235959Z')
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 = utils.get_data_start_end(observation, forecast,
run_time)
assert data_start == pd.Timestamp('20190421T0000Z')
assert data_end == pd.Timestamp('20190421T235959Z')
def test_run_persistence_interval_index(session, site_metadata,
obs_5min_begin):
# index=True not supported for day ahead
forecast = default_forecast(
site_metadata,
issue_time_of_day=dt.time(hour=23),
lead_time_to_start=pd.Timedelta('1h'),
interval_length=pd.Timedelta('1h'),
run_length=pd.Timedelta('24h'),
interval_label='beginning')
issue_time = pd.Timestamp('20190423T2300Z')
run_time = pd.Timestamp('20190422T1945Z')
with pytest.raises(ValueError) as excinfo:
main.run_persistence(session, obs_5min_begin, forecast, run_time,
issue_time, index=True)
assert 'index=True not supported' in str(excinfo.value)
def test_get_forecast_start_end_time_instant(site_metadata,
adjust_for_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('1h'),
interval_label='instant')
issue_time = pd.Timestamp('20190422T0500')
fx_start, fx_end = utils.get_forecast_start_end(forecast, issue_time,
adjust_for_interval_label)
assert fx_start == pd.Timestamp('20190422T0600')
fx_end_exp = pd.Timestamp('20190422T0700')
if adjust_for_interval_label:
fx_end_exp -= pd.Timedelta('1n')
assert fx_end == fx_end_exp
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 = utils.get_data_start_end(observation, forecast,
run_time)
assert data_start == pd.Timestamp('20190421T0000Z')
assert data_end == pd.Timestamp('20190422T0000Z')
def test_run_persistence_scalar(session, site_metadata, obs_5min_begin,
interval_label, mocker):
run_time = pd.Timestamp('20190101T1945Z')
# intraday, index=False
forecast = default_forecast(site_metadata,
issue_time_of_day=dt.time(hour=23),
lead_time_to_start=pd.Timedelta('1h'),
interval_length=pd.Timedelta('1h'),
run_length=pd.Timedelta('1h'),
interval_label=interval_label)
issue_time = pd.Timestamp('20190101T2300Z')
mocker.spy(main.persistence, 'persistence_scalar')
out = main.run_persistence(session, obs_5min_begin, forecast, run_time,
issue_time)
assert isinstance(out, pd.Series)
assert len(out) == 1
assert main.persistence.persistence_scalar.call_count == 1
def test_check_persistence_compatibility(obs_kw, fx_kw, index, site_metadata):
obs_dict = {
'interval_label': 'ending',
'interval_value_type': 'interval_mean',
'interval_length': pd.Timedelta('30min')
}
fx_dict = {
'interval_label': 'ending',
'interval_value_type': 'interval_mean',
'interval_length': pd.Timedelta('1h'),
'run_length': pd.Timedelta('12h')
}
obs_dict.update(obs_kw)
fx_dict.update(fx_kw)
obs = default_observation(site_metadata, **obs_dict)
fx = default_forecast(site_metadata, **fx_dict)
with pytest.raises(ValueError):
utils.check_persistence_compatibility(obs, fx, index)
def test_get_data_start_end_time_tz(site_metadata, variable, rl, issue, run,
expected_start, expected_end):
observation = default_observation(site_metadata,
variable=variable,
interval_length=pd.Timedelta('5min'),
interval_label='ending')
forecast = default_forecast(site_metadata,
variable=variable,
issue_time_of_day=dt.time(hour=23),
lead_time_to_start=pd.Timedelta('1h'),
interval_length=pd.Timedelta('1h'),
run_length=pd.Timedelta(rl),
interval_label='beginning')
data_start, data_end = utils.get_data_start_end(observation, forecast,
pd.Timestamp(run),
pd.Timestamp(issue))
assert data_start == pd.Timestamp(expected_start)
assert data_end == pd.Timestamp(expected_end)
def test_get_data_start_end_time_dayahead(site_metadata, rl, rt, lt,
expected_start, expected_end):
observation = default_observation(site_metadata,
interval_length=pd.Timedelta('5min'),
interval_label='beginning')
run_time = pd.Timestamp(rt)
issue_time = pd.Timestamp('20190410T2300Z')
forecast = default_forecast(site_metadata,
issue_time_of_day=dt.time(hour=23),
lead_time_to_start=pd.Timedelta(lt),
interval_length=pd.Timedelta('1h'),
run_length=pd.Timedelta(rl),
interval_label='beginning')
data_start, data_end = utils.get_data_start_end(observation, forecast,
run_time, issue_time)
assert data_start == pd.Timestamp(expected_start)
assert data_end == pd.Timestamp(expected_end)
def test_get_data_start_end_labels_obs_fx_instant(site_metadata, lead, issue,
it):
observation = default_observation(site_metadata,
interval_length=pd.Timedelta('5min'),
interval_label='instant')
# interval length of forecast and obs must be equal if interval label is
# instant
forecast = default_forecast(site_metadata,
issue_time_of_day=dt.time(hour=it),
lead_time_to_start=pd.Timedelta(lead),
interval_length=pd.Timedelta('5min'),
run_length=pd.Timedelta('1d'),
interval_label='instant')
issue_time = pd.Timestamp(issue)
run_time = issue_time - pd.Timedelta('75min')
data_start, data_end = utils.get_data_start_end(observation, forecast,
run_time, issue_time)
assert data_start == pd.Timestamp('20190421T0000Z')
assert data_end == pd.Timestamp('20190421T235959Z')
def test_get_forecast_start_end_time_weekahead(site_metadata, variable,
expected_start, expected_end):
observation = default_observation(site_metadata,
variable=variable,
interval_length=pd.Timedelta('5min'),
interval_label='beginning')
run_time = pd.Timestamp('20190410T0630Z')
forecast = default_forecast(site_metadata,
variable=variable,
issue_time_of_day=dt.time(hour=10),
lead_time_to_start=pd.Timedelta('1h'),
interval_length=pd.Timedelta('1h'),
run_length=pd.Timedelta('1d'),
interval_label='beginning')
data_start, data_end = utils.get_data_start_end(observation, forecast,
run_time)
assert data_start == pd.Timestamp(expected_start)
assert data_end == pd.Timestamp(expected_end)
def test_get_data_start_end_time_weekahead_not_midnight(site_metadata):
variable = 'net_load'
observation = default_observation(site_metadata,
variable=variable,
interval_length=pd.Timedelta('5min'),
interval_label='beginning')
run_time = pd.Timestamp('20190410T1030Z')
issue_time = pd.Timestamp('20190410T1200Z')
# fx from 2019-04-11 12:00
forecast = default_forecast(site_metadata,
variable=variable,
issue_time_of_day=dt.time(hour=12),
lead_time_to_start=pd.Timedelta('1d'),
interval_length=pd.Timedelta('1h'),
run_length=pd.Timedelta('1d'),
interval_label='beginning')
data_start, data_end = utils.get_data_start_end(observation, forecast,
run_time, issue_time)
assert data_start == pd.Timestamp('20190404T1200Z')
assert data_end == pd.Timestamp('20190405T1200Z')
def test_run_persistence_weekahead(session, site_metadata, mocker):
variable = 'net_load'
observation = default_observation(site_metadata,
variable=variable,
interval_length=pd.Timedelta('5min'),
interval_label='beginning')
run_time = pd.Timestamp('20190110T1945Z')
forecast = default_forecast(site_metadata,
variable=variable,
issue_time_of_day=dt.time(hour=23),
lead_time_to_start=pd.Timedelta('1h'),
interval_length=pd.Timedelta('1h'),
run_length=pd.Timedelta('1d'),
interval_label='beginning')
issue_time = pd.Timestamp('20190111T2300Z')
mocker.spy(main.persistence, 'persistence_interval')
out = main.run_persistence(session, observation, forecast, run_time,
issue_time)
assert isinstance(out, pd.Series)
assert len(out) == 24
assert main.persistence.persistence_interval.call_count == 1
def test_find_next_issue_time_from_last_forecast(fxargs, last_time, expected,
site_metadata):
fx = default_forecast(site_metadata, **fxargs)
out = utils.find_next_issue_time_from_last_forecast(fx, last_time)
assert out == expected
