def test_persistence_scalar_index_invalid_times_instant(site_metadata):
data = pd.Series(100., index=[0])
load_data = partial(load_data_base, data)
tz = 'America/Phoenix'
interval_label = 'instant'
observation = default_observation(site_metadata,
interval_length='5min',
interval_label=interval_label)
# instant obs that cover the whole interval - not allowed!
data_start = pd.Timestamp('20190404 1200', tz=tz)
data_end = pd.Timestamp('20190404 1300', tz=tz)
forecast_start = pd.Timestamp('20190404 1300', tz=tz)
forecast_end = pd.Timestamp('20190404 1400', tz=tz)
interval_length = pd.Timedelta('30min')
with pytest.raises(ValueError):
persistence.persistence_scalar_index(observation, data_start, data_end,
forecast_start, forecast_end,
interval_length, interval_label,
load_data)
def test_persistence_scalar_index_invalid_times_invalid_label(site_metadata):
data = pd.Series(100., index=[0])
load_data = partial(load_data_base, data)
tz = 'America/Phoenix'
interval_length = pd.Timedelta('30min')
interval_label = 'invalid'
observation = default_observation(site_metadata, interval_length='5min')
object.__setattr__(observation, 'interval_label', interval_label)
data_start = pd.Timestamp('20190404 1200', tz=tz)
data_end = pd.Timestamp('20190404 1300', tz=tz)
forecast_start = pd.Timestamp('20190404 1300', tz=tz)
forecast_end = pd.Timestamp('20190404 1400', tz=tz)
with pytest.raises(ValueError) as excinfo:
persistence.persistence_scalar_index(observation, data_start, data_end,
forecast_start, forecast_end,
interval_length, interval_label,
load_data)
assert "invalid interval_label" in str(excinfo.value)
def test_persistence_scalar_index_low_solar_elevation(site_metadata,
powerplant_metadata):
interval_label = 'beginning'
observation = default_observation(site_metadata,
interval_length='5min',
interval_label=interval_label)
observation_ac = default_observation(powerplant_metadata,
interval_length='5min',
interval_label=interval_label,
variable='ac_power')
# at ABQ Baseline, solar apparent zenith for these points is
# 2019-05-13 12:00:00+00:00 91.62
# 2019-05-13 12:05:00+00:00 90.09
# 2019-05-13 12:10:00+00:00 89.29
# 2019-05-13 12:15:00+00:00 88.45
# 2019-05-13 12:20:00+00:00 87.57
# 2019-05-13 12:25:00+00:00 86.66
tz = 'UTC'
data_start = pd.Timestamp('20190513 1200', tz=tz)
data_end = pd.Timestamp('20190513 1230', tz=tz)
index = pd.date_range(start=data_start,
end=data_end,
freq='5min',
closed='left')
# clear sky 5 min avg (from 1 min avg) GHI is
# [0., 0.10932908, 1.29732454, 4.67585122, 10.86548521, 19.83487399]
# create data series that could produce obs / clear of
# 0/0, 1/0.1, -1/1.3, 5/5, 10/10, 20/20
# average without limits is (10 - 1 + 1 + 1 + 1) / 5 = 2.4
# average with element limits of [0, 2] = (2 + 0 + 1 + 1 + 1) / 5 = 1
data = pd.Series([0, 1, -1, 5, 10, 20.], index=index)
forecast_start = pd.Timestamp('20190513 1230', tz=tz)
forecast_end = pd.Timestamp('20190513 1300', tz=tz)
interval_length = pd.Timedelta('5min')
load_data = partial(load_data_base, data)
expected_index = pd.date_range(start=forecast_start,
end=forecast_end,
freq='5min',
closed='left')
# clear sky 5 min avg GHI is
# [31.2, 44.5, 59.4, 75.4, 92.4, 110.1]
expected_vals = [31.2, 44.5, 59.4, 75.4, 92.4, 110.1]
expected = pd.Series(expected_vals, index=expected_index)
fx = persistence.persistence_scalar_index(observation, data_start,
data_end, forecast_start,
forecast_end, interval_length,
interval_label, load_data)
assert_series_equal(fx, expected, check_less_precise=1, check_names=False)
expected = pd.Series([0.2, 0.7, 1.2, 1.6, 2., 8.9], index=expected_index)
fx = persistence.persistence_scalar_index(observation_ac, data_start,
data_end, forecast_start,
forecast_end, interval_length,
interval_label, load_data)
assert_series_equal(fx, expected, check_less_precise=1, check_names=False)
def run_persistence(session,
observation,
forecast,
run_time,
issue_time,
index=False):
"""
Run a persistence *forecast* for an *observation*.
For intraday forecasts, the *index* argument controls if the
forecast is constructed using persistence of the measured values
(*index = False*) or persistence using clear sky index or AC power
index.
For day ahead forecasts, only persistence of measured values
(*index = False*) is supported.
Forecasts may be run operationally or retrospectively. For
operational forecasts, *run_time* is typically set to now. For
retrospective forecasts, *run_time* is the time by which the
forecast should be run so that it could have been be delivered for
the *issue_time*. Forecasts will only use data with timestamps
before *run_time*.
The persistence *window* is the time over which the persistence
quantity (irradiance, power, clear sky index, or power index) is
averaged. The persistence window is automatically determined
from the *forecast* attributes:
* Intraday persistence forecasts:
*window = forecast.run_length*.
No longer than 1 hour.
* Day ahead forecasts (all but net load) and week ahead forecasts (net
load only):
*window = forecast.interval_length*.
Users that would like more flexibility may use the lower-level
functions in
:py:mod:`solarforecastarbiter.reference_forecasts.persistence`.
Parameters
----------
session : api.Session
The session object to use to request data from the
SolarForecastArbiter API.
observation : datamodel.Observation
The metadata of the observation to be used to create the
forecast.
forecast : datamodel.Forecast
The metadata of the desired forecast.
run_time : pd.Timestamp
Run time of the forecast.
issue_time : pd.Timestamp
Issue time of the forecast run.
index : bool, default False
If False, use persistence of observed value. If True, use
persistence of clear sky or AC power index.
Returns
-------
forecast : pd.Series
Forecast conforms to the metadata specified by the *forecast*
argument.
Raises
------
ValueError
If forecast and issue_time are incompatible.
ValueError
If persistence window < observation.interval_length.
ValueError
If forecast.run_length = 1 day and forecast period is not
midnight to midnight.
ValueError
If forecast.run_length = 1 day and index=True.
ValueError
If instantaneous forecast and instantaneous observation interval
lengths do not match.
ValueError
If average observations are used to make instantaneous forecast.
Notes
-----
For non-intraday net load forecasts, this function will use a weekahead
persistence due to the fact that net load exhibits stronger correlation
week-to-week than day-to-day. For example, the net load on a Monday tends
to look more similar to the previous Monday that it does to the previous
day (Sunday).
"""
utils.check_persistence_compatibility(observation, forecast, index)
forecast_start, forecast_end = utils.get_forecast_start_end(
forecast, issue_time, False)
intraday = utils._is_intraday(forecast)
if not intraday:
# raise ValueError if not intraday and not midnight to midnight
utils._check_midnight_to_midnight(forecast_start, forecast_end)
data_start, data_end = utils.get_data_start_end(observation, forecast,
run_time)
def load_data(observation, data_start, data_end):
df = session.get_observation_values(observation.observation_id,
data_start, data_end,
observation.interval_label)
df = df.tz_convert(observation.site.timezone)
return df['value']
if intraday and index:
fx = persistence.persistence_scalar_index(
observation, data_start, data_end, forecast_start, forecast_end,
forecast.interval_length, forecast.interval_label, load_data)
elif intraday and not index:
fx = persistence.persistence_scalar(observation, data_start, data_end,
forecast_start, forecast_end,
forecast.interval_length,
forecast.interval_label, load_data)
elif not intraday and not index:
fx = persistence.persistence_interval(observation, data_start,
data_end, forecast_start,
forecast.interval_length,
forecast.interval_label,
load_data)
else: # pragma: no cover
raise ValueError(
'index=True not supported for forecasts with run_length >= 1day')
return fx
def run_persistence(session,
observation,
forecast,
run_time,
issue_time,
index=False,
load_data=None):
"""
Run a persistence *forecast* for an *observation*.
For intraday forecasts, the *index* argument controls if the
forecast is constructed using persistence of the measured values
(*index = False*) or persistence using clear sky index or AC power
index.
For day ahead forecasts, only persistence of measured values
(*index = False*) is supported.
Forecasts may be run operationally or retrospectively. For
operational forecasts, *run_time* is typically set to now. For
retrospective forecasts, *run_time* is the time by which the
forecast should be run so that it could have been be delivered for
the *issue_time*. Forecasts will only use data with timestamps
before *run_time*.
The persistence *window* is the time over which the persistence
quantity (irradiance, power, clear sky index, or power index) is
averaged. The persistence window is automatically determined
from the *forecast* attributes:
- Intraday persistence forecasts:
+ ``window = forecast.run_length``. No longer than 1 hour.
- Day ahead forecasts (all but net load) and week ahead forecasts (net
load only):
+ ``window = forecast.interval_length``.
Users that would like more flexibility may use the lower-level
functions in
:py:mod:`solarforecastarbiter.reference_forecasts.persistence`.
Parameters
----------
session : api.Session
The session object to use to request data from the
SolarForecastArbiter API.
observation : datamodel.Observation
The metadata of the observation to be used to create the
forecast.
forecast : datamodel.Forecast
The metadata of the desired forecast.
run_time : pd.Timestamp
Run time of the forecast.
issue_time : pd.Timestamp
Issue time of the forecast run.
index : bool, default False
If False, use persistence of observed value. If True, use
persistence of clear sky or AC power index.
load_data : function
Function to load the observation data 'value' series given
(observation, data_start, data_end) arguments. Typically,
calls `session.get_observation_values` and selects the 'value'
column. May also have data preloaded to then slice from
data_start to data_end.
Returns
-------
forecast : pd.Series
Forecast conforms to the metadata specified by the *forecast*
argument.
Raises
------
ValueError
If forecast and issue_time are incompatible.
ValueError
If data is required from after run_time.
ValueError
If persistence window < observation.interval_length.
ValueError
If forecast.run_length => 1 day and index=True.
ValueError
If instantaneous forecast and instantaneous observation interval
lengths do not match.
ValueError
If average observations are used to make instantaneous forecast.
Notes
-----
For non-intraday net load forecasts, this function will use a weekahead
persistence due to the fact that net load exhibits stronger correlation
week-to-week than day-to-day. For example, the net load on a Monday tends
to look more similar to the previous Monday that it does to the previous
day (Sunday).
"""
utils.check_persistence_compatibility(observation, forecast, index)
forecast_start, forecast_end = utils.get_forecast_start_end(
forecast, issue_time, False)
intraday = utils._is_intraday(forecast)
if load_data is None:
load_data = _default_load_data(session)
data_start, data_end = utils.get_data_start_end(observation, forecast,
run_time, issue_time)
if data_end > run_time:
raise ValueError(
'Persistence forecast requires data from after run_time')
if isinstance(forecast, datamodel.ProbabilisticForecast):
cvs = [f.constant_value for f in forecast.constant_values]
fx = persistence.persistence_probabilistic(
observation, data_start, data_end, forecast_start, forecast_end,
forecast.interval_length, forecast.interval_label, load_data,
forecast.axis, cvs)
elif intraday and index:
fx = persistence.persistence_scalar_index(
observation, data_start, data_end, forecast_start, forecast_end,
forecast.interval_length, forecast.interval_label, load_data)
elif intraday and not index:
fx = persistence.persistence_scalar(observation, data_start, data_end,
forecast_start, forecast_end,
forecast.interval_length,
forecast.interval_label, load_data)
elif not intraday and not index:
fx = persistence.persistence_interval(observation, data_start,
data_end, forecast_start,
forecast.interval_length,
forecast.interval_label,
load_data)
else: # pragma: no cover
raise ValueError(
'index=True not supported for forecasts with run_length >= 1day')
return fx