Explainability Result

Contains the explainability results obtained from _ForecastingModelExplainer.explain().

class darts.explainability.explainability_result.ComponentBasedExplainabilityResult(explained_components)[source]

Bases: _ExplainabilityResult

Explainability result for general component objects. The explained components can describe anything.

Example

>>> explainer = SomeComponentBasedExplainer(model)
>>> explain_results = explainer.explain()
>>> output = explain_results.get_explanation(component="some_component")

Methods

get_explanation(component)

Returns one or several explanations for a given component.
get_explanation(component)[source]

Returns one or several explanations for a given component.

Parameters

component – The component for which to return the explanation.

Return type

Union[Any, List[Any]]

class darts.explainability.explainability_result.HorizonBasedExplainabilityResult(explained_forecasts)[source]

Bases: _ExplainabilityResult

Stores the explainability results of a _ForecastingModelExplainer with convenient access to the horizon based results.

The result is a multivariate TimeSeries instance containing the ‘explanation’ for the (horizon, target_component) forecast at any timestamp forecastable corresponding to the foreground TimeSeries input.

The component name convention of this multivariate TimeSeries is: "{name}_{type_of_cov}_lag_{idx}", where:

  • {name} is the component name from the original foreground series (target, past, or future).

  • {type_of_cov} is the covariates type. It can take 3 different values: "target", "past_cov" or "future_cov".

  • {idx} is the lag index.

Example

Say we have a model with 2 target components named "T_0" and "T_1", 3 past covariates with default component names "0", "1", and "2", and one future covariate with default component name "0". Also, horizons = [1, 2]. The model is a regression model, with lags = 3, lags_past_covariates=[-1, -3], lags_future_covariates = [0].

We provide foreground_series, foreground_past_covariates, foreground_future_covariates each of length 5.

>>> explainer = SomeHorizonBasedExplainer(model)
>>> explain_results = explainer.explain(
>>>     foreground_series=foreground_series,
>>>     foreground_past_covariates=foreground_past_covariates,
>>>     foreground_future_covariates=foreground_future_covariates,
>>>     horizons=[1, 2],
>>>     target_names=["T_0", "T_1"]
>>> )
>>> output = explain_results.get_explanation(horizon=1, target="T_1")

Then the method returns a multivariate TimeSeries containing the explanations of the corresponding _ForecastingModelExplainer, with the following component names:

  • T_0_target_lag-1

  • T_0_target_lag-2

  • T_0_target_lag-3

  • T_1_target_lag-1

  • T_1_target_lag-2

  • T_1_target_lag-3

  • 0_past_cov_lag-1

  • 0_past_cov_lag-3

  • 1_past_cov_lag-1

  • 1_past_cov_lag-3

  • 2_past_cov_lag-1

  • 2_past_cov_lag-3

  • 0_fut_cov_lag_0

This series has length 3, as the model can explain 5-3+1 forecasts (timestamp indexes 4, 5, and 6)

Methods

get_explanation(horizon[, component])

Returns one or several TimeSeries representing the explanations for a given horizon and component.
get_explanation(horizon, component=None)[source]

Returns one or several TimeSeries representing the explanations for a given horizon and component.

Parameters

  • horizon (int) – The horizon for which to return the explanation.

  • component (Optional[str]) – The component for which to return the explanation. Does not need to be specified for univariate series.

Return type

Union[TimeSeries, List[TimeSeries]]

class darts.explainability.explainability_result.ShapExplainabilityResult(explained_forecasts, feature_values, shap_explanation_object)[source]

Bases: HorizonBasedExplainabilityResult

Stores the explainability results of a ShapExplainer with convenient access to the results. It extends the HorizonBasedExplainabilityResult and carries additional information specific to the Shap explainers. In particular, in addition to the explained_forecasts (which in the case of the ShapExplainer are the shap values), it also provides access to the corresponding feature_values and the underlying shap.Explanation object.

Examples

>>> explainer = ShapExplainer(model)  # requires `background` if model was trained on multiple series
>>> explain_results = explainer.explain()
>>> exlained_fc = explain_results.get_explanation(horizon=1)
>>> feature_values = explain_results.get_feature_values(horizon=1)
>>> shap_objects = explain_results.get_shap_explanation_objects(horizon=1)

Methods

get_explanation(horizon[, component])

Returns one or several TimeSeries representing the explanations for a given horizon and component.

get_feature_values(horizon[, component])

Returns one or several TimeSeries representing the feature values for a given horizon and component.

get_shap_explanation_object(horizon[, component])

Returns the underlying shap.Explanation object for a given horizon and component.
get_explanation(horizon, component=None)

Returns one or several TimeSeries representing the explanations for a given horizon and component.

Parameters

  • horizon (int) – The horizon for which to return the explanation.

  • component (Optional[str]) – The component for which to return the explanation. Does not need to be specified for univariate series.

Return type

Union[TimeSeries, List[TimeSeries]]

get_feature_values(horizon, component=None)[source]

Returns one or several TimeSeries representing the feature values for a given horizon and component.

Parameters

  • horizon (int) – The horizon for which to return the feature values.

  • component (Optional[str]) – The component for which to return the feature values. Does not need to be specified for univariate series.

Return type

Union[TimeSeries, List[TimeSeries]]

get_shap_explanation_object(horizon, component=None)[source]

Returns the underlying shap.Explanation object for a given horizon and component.

Parameters

  • horizon (int) – The horizon for which to return the shap.Explanation object.

  • component (Optional[str]) – The component for which to return the shap.Explanation object. Does not need to be specified for univariate series.

Return type

Union[Explanation, List[Explanation]]

class darts.explainability.explainability_result.TFTExplainabilityResult(explanations)[source]

Bases: ComponentBasedExplainabilityResult

Stores the explainability results of a TFTExplainer with convenient access to the results. It extends the ComponentBasedExplainabilityResult and carries information specific to the TFT explainer.

Examples

>>> explainer = TFTExplainer(model)  # requires `background` if model was trained on multiple series
>>> explain_results = explainer.explain()
>>> attention = explain_results.get_attention()
>>> importances = explain_results.get_feature_importances()
>>> encoder_importance = explain_results.get_encoder_importance()
>>> decoder_importance = explain_results.get_decoder_importance()
>>> static_covariates_importance = explain_results.get_static_covariates_importance()

Methods

get_attention()

Returns the time-dependent attention on the encoder and decoder for each horizon in (1, output_chunk_length).

get_decoder_importance()

Returns the time-dependent decoder importances as a pd.DataFrames.

get_encoder_importance()

Returns the time-dependent encoder importances as a pd.DataFrames.

get_explanation(component)

Returns one or several explanations for a given component.

get_feature_importances()

Returns the feature importances for the encoder, decoder and static covariates as pd.DataFrames.

get_static_covariates_importance()

Returns the numeric and categorical static covariates importances as a pd.DataFrames.
get_attention()[source]

Returns the time-dependent attention on the encoder and decoder for each horizon in (1, output_chunk_length). The time index ranges from the prediction series’ start time - input_chunk_length and ends at the prediction series’ end time. If multiple series were used when calling TFTExplainer.explain(), returns a list of TimeSeries.

Return type

Union[TimeSeries, List[TimeSeries]]

get_decoder_importance()[source]

Returns the time-dependent decoder importances as a pd.DataFrames. If multiple series were used in TFTExplainer.explain(), returns a list of pd.DataFrames.

Return type

Union[DataFrame, List[DataFrame]]

get_encoder_importance()[source]

Returns the time-dependent encoder importances as a pd.DataFrames. If multiple series were used in TFTExplainer.explain(), returns a list of pd.DataFrames.

Return type

Union[DataFrame, List[DataFrame]]

get_explanation(component)

Returns one or several explanations for a given component.

Parameters

component – The component for which to return the explanation.

Return type

Union[Any, List[Any]]

get_feature_importances()[source]

Returns the feature importances for the encoder, decoder and static covariates as pd.DataFrames. If multiple series were used in TFTExplainer.explain(), returns a list of pd.DataFrames per importance.

Return type

Dict[str, Union[DataFrame, List[DataFrame]]]

get_static_covariates_importance()[source]

Returns the numeric and categorical static covariates importances as a pd.DataFrames. If multiple series were used in TFTExplainer.explain(), returns a list of pd.DataFrames.

Return type

Union[DataFrame, List[DataFrame]]

previous

<no title>

next

Shap Explainer for RegressionModels