def apply_prophet_model_components_defaults(self,
model_components=None,
time_properties=None):
"""Sets default values for ``model_components``.
Called by ``get_hyperparameter_grid`` after ``time_properties` is defined.
Requires ``time_properties`` as well as ``model_components``
so we do not simply override
`~greykite.framework.templates.forecast_config_defaults.ForecastConfigDefaults.apply_model_components_defaults`.
Parameters
----------
model_components : :class:`~greykite.framework.templates.autogen.forecast_config.ModelComponentsParam` or None, default None
Configuration of model growth, seasonality, events, etc.
See the docstring of this class for details.
time_properties : `dict` [`str`, `any`] or None, default None
Time properties dictionary (likely produced by
`~greykite.common.time_properties_forecast.get_forecast_time_properties`)
with keys:
``"period"`` : `int`
Period of each observation (i.e. minimum time between observations, in seconds).
``"simple_freq"`` : `SimpleTimeFrequencyEnum`
``SimpleTimeFrequencyEnum`` member corresponding to data frequency.
``"num_training_points"`` : `int`
Number of observations for training.
``"num_training_days"`` : `int`
Number of days for training.
``"start_year"`` : `int`
Start year of the training period.
``"end_year"`` : `int`
End year of the forecast period.
``"origin_for_time_vars"`` : `float`
Continuous time representation of the first date in ``df``.
If None, start_year is set to 2015 and end_year to 2030.
Returns
-------
model_components : :class:`~greykite.framework.templates.autogen.forecast_config.ModelComponentsParam`
The provided ``model_components`` with default values set
"""
if model_components is None:
model_components = ModelComponentsParam()
else:
# makes a copy to avoid mutating input
model_components = dataclasses.replace(model_components)
if time_properties is None:
time_properties = {
"start_year": 2015,
"end_year": 2030,
}
# seasonality
default_seasonality = {
"seasonality_mode": ["additive"],
"seasonality_prior_scale": [10.0],
"yearly_seasonality": ['auto'],
"weekly_seasonality": ['auto'],
"daily_seasonality": ['auto'],
"add_seasonality_dict": [None]
}
# If seasonality params are not provided, uses default params. Otherwise, prefers provided params.
# `allow_unknown_keys=False` requires `model_components.seasonality` keys to be a subset of
# `default_seasonality` keys.
model_components.seasonality = update_dictionary(
default_dict=default_seasonality,
overwrite_dict=model_components.seasonality,
allow_unknown_keys=False)
# growth
default_growth = {"growth_term": ["linear"]}
model_components.growth = update_dictionary(
default_dict=default_growth,
overwrite_dict=model_components.growth,
allow_unknown_keys=False)
# events
default_events = {
"holiday_lookup_countries":
"auto", # see `get_prophet_holidays` for defaults
"holiday_pre_num_days": [2],
"holiday_post_num_days": [2],
"start_year": time_properties["start_year"],
"end_year": time_properties["end_year"],
"holidays_prior_scale": [10.0]
}
model_components.events = update_dictionary(
default_dict=default_events,
overwrite_dict=model_components.events,
allow_unknown_keys=False)
# Creates events dictionary for prophet estimator
# Expands the range of holiday years by 1 year on each end, to ensure we have coverage of most relevant holidays.
year_list = list(
range(model_components.events["start_year"] - 1,
model_components.events["end_year"] + 2))
# Currently we support only one set of holiday_lookup_countries, holiday_pre_num_days and holiday_post_num_days.
# Shows a warning if user supplies >1 set.
if len(model_components.events["holiday_pre_num_days"]) > 1:
warnings.warn(
f"`events['holiday_pre_num_days']` list has more than 1 element. We currently support only 1 element. "
f"Using {model_components.events['holiday_pre_num_days'][0]}.")
if len(model_components.events["holiday_post_num_days"]) > 1:
warnings.warn(
f"`events['holiday_post_num_days']` list has more than 1 element. We currently support only 1 element. "
f"Using {model_components.events['holiday_post_num_days'][0]}."
)
# If events["holiday_lookup_countries"] has multiple options, picks the first option
if (model_components.events["holiday_lookup_countries"] is not None and
model_components.events["holiday_lookup_countries"] != "auto"):
if len(model_components.events["holiday_lookup_countries"]) > 1:
# There are multiple elements
if (any(
isinstance(x, list) for x in
model_components.events["holiday_lookup_countries"])
or None
in model_components.events["holiday_lookup_countries"]
or "auto" in
model_components.events["holiday_lookup_countries"]):
# Not a flat list of country names
warnings.warn(
f"`events['holiday_lookup_countries']` contains multiple options. "
f"We currently support only 1 option. Using {model_components.events['holiday_lookup_countries'][0]}."
)
model_components.events[
"holiday_lookup_countries"] = model_components.events[
"holiday_lookup_countries"][0]
elif isinstance(
model_components.events["holiday_lookup_countries"][0],
(list, tuple)):
# There's only one element, and it's a list of countries
model_components.events[
"holiday_lookup_countries"] = model_components.events[
"holiday_lookup_countries"][0]
model_components.events = {
"holidays_df":
self.get_prophet_holidays(
year_list=year_list,
countries=model_components.events["holiday_lookup_countries"],
# holiday effect is modeled from "holiday_pre_num_days" days before
# to "holiday_post_num_days" days after the holiday
lower_window=-model_components.events["holiday_pre_num_days"]
[0], # Prophet expects a negative value for `lower_window`
upper_window=model_components.events["holiday_post_num_days"]
[0]),
"holidays_prior_scale":
model_components.events["holidays_prior_scale"]
}
# changepoints_dict
default_changepoints = {
"changepoint_prior_scale": [0.05],
"changepoints": [None],
"n_changepoints": [25],
"changepoint_range": [0.8]
}
model_components.changepoints = update_dictionary(
default_dict=default_changepoints,
overwrite_dict=model_components.changepoints,
allow_unknown_keys=False)
# uncertainty
default_uncertainty = {
"mcmc_samples": [0],
"uncertainty_samples": [1000]
}
model_components.uncertainty = update_dictionary(
default_dict=default_uncertainty,
overwrite_dict=model_components.uncertainty,
allow_unknown_keys=False)
# regressors
default_regressors = {"add_regressor_dict": [None]}
model_components.regressors = update_dictionary(
default_dict=default_regressors,
overwrite_dict=model_components.regressors,
allow_unknown_keys=False)
# there are no custom parameters for Prophet
# sets to {} if None, for each item if
# `model_components.hyperparameter_override` is a list of dictionaries
model_components.hyperparameter_override = update_dictionaries(
{}, overwrite_dicts=model_components.hyperparameter_override)
return model_components
def apply_default_model_components(model_components=None,
time_properties=None):
"""Sets default values for ``model_components``.
Parameters
----------
model_components : :class:`~greykite.framework.templates.autogen.forecast_config.ModelComponentsParam` or None, default None
Configuration of model growth, seasonality, events, etc.
See :func:`~greykite.framework.templates.silverkite_templates.silverkite_template` for details.
time_properties : `dict` [`str`, `any`] or None, default None
Time properties dictionary (likely produced by
`~greykite.common.time_properties_forecast.get_forecast_time_properties`)
with keys:
``"period"`` : `int`
Period of each observation (i.e. minimum time between observations, in seconds).
``"simple_freq"`` : `SimpleTimeFrequencyEnum`
``SimpleTimeFrequencyEnum`` member corresponding to data frequency.
``"num_training_points"`` : `int`
Number of observations for training.
``"num_training_days"`` : `int`
Number of days for training.
``"start_year"`` : `int`
Start year of the training period.
``"end_year"`` : `int`
End year of the forecast period.
``"origin_for_time_vars"`` : `float`
Continuous time representation of the first date in ``df``.
Returns
-------
model_components : :class:`~greykite.framework.templates.autogen.forecast_config.ModelComponentsParam`
The provided ``model_components`` with default values set
"""
if model_components is None:
model_components = ModelComponentsParam()
else:
# makes a copy to avoid mutating input
model_components = dataclasses.replace(model_components)
# sets default values
default_seasonality = {
"fs_components_df": [
pd.DataFrame({
"name": ["tod", "tow", "tom", "toq", "toy"],
"period": [24.0, 7.0, 1.0, 1.0, 1.0],
"order": [3, 3, 1, 1, 5],
"seas_names":
["daily", "weekly", "monthly", "quarterly", "yearly"]
})
],
}
model_components.seasonality = update_dictionary(
default_seasonality,
overwrite_dict=model_components.seasonality,
allow_unknown_keys=False)
# model_components.growth must be empty.
# Pass growth terms via `extra_pred_cols` instead.
default_growth = {}
model_components.growth = update_dictionary(
default_growth,
overwrite_dict=model_components.growth,
allow_unknown_keys=False)
default_events = {
"daily_event_df_dict": [None],
}
model_components.events = update_dictionary(
default_events,
overwrite_dict=model_components.events,
allow_unknown_keys=False)
default_changepoints = {
"changepoints_dict": [None],
"seasonality_changepoints_dict": [None],
# Not allowed, to prevent leaking future information
# into the past. Pass `changepoints_dict` with method="auto" for
# automatic detection.
# "changepoint_detector": [None],
}
model_components.changepoints = update_dictionary(
default_changepoints,
overwrite_dict=model_components.changepoints,
allow_unknown_keys=False)
default_autoregression = {
"autoreg_dict": [None],
}
model_components.autoregression = update_dictionary(
default_autoregression,
overwrite_dict=model_components.autoregression,
allow_unknown_keys=False)
default_regressors = {}
model_components.regressors = update_dictionary(
default_regressors,
overwrite_dict=model_components.regressors,
allow_unknown_keys=False)
default_lagged_regressors = {
"lagged_regressor_dict": [None],
}
model_components.lagged_regressors = update_dictionary(
default_lagged_regressors,
overwrite_dict=model_components.lagged_regressors,
allow_unknown_keys=False)
default_uncertainty = {
"uncertainty_dict": [None],
}
model_components.uncertainty = update_dictionary(
default_uncertainty,
overwrite_dict=model_components.uncertainty,
allow_unknown_keys=False)
if time_properties is not None:
origin_for_time_vars = time_properties.get("origin_for_time_vars")
else:
origin_for_time_vars = None
default_custom = {
"silverkite":
[SilverkiteForecast()], # NB: sklearn creates a copy in grid search
"silverkite_diagnostics": [SilverkiteDiagnostics()],
# The same origin for every split, based on start year of full dataset.
# To use first date of each training split, set to `None` in model_components.
"origin_for_time_vars": [origin_for_time_vars],
"extra_pred_cols": ["ct1"], # linear growth
"fit_algorithm_dict": [{
"fit_algorithm": "linear",
"fit_algorithm_params": None,
}],
"min_admissible_value": [None],
"max_admissible_value": [None],
}
model_components.custom = update_dictionary(
default_custom,
overwrite_dict=model_components.custom,
allow_unknown_keys=False)
# sets to {} if None, for each item if
# `model_components.hyperparameter_override` is a list of dictionaries
model_components.hyperparameter_override = update_dictionaries(
{}, overwrite_dicts=model_components.hyperparameter_override)
return model_components