Ensemble scikit-learn aggregator¶

class darts.ad.aggregators.ensemble_sklearn_aggregator.EnsembleSklearnAggregator(model)[source]¶

Bases: FittableAggregator

Ensemble scikit-learn aggregator

Aggregator wrapped around the sklearn ensemble model sklearn ensemble model.

Parameters: model (BaseEnsemble) – The sklearn ensemble model.

Methods

`eval_metric`(anomalies, series[, window, metric])	Aggregates the (sequence of) multivariate series given as input into one (sequence of) series and evaluates the results against the ground truth anomaly labels.
`fit`(anomalies, series)	Fit the aggregators on the (sequence of) multivariate binary anomaly series.
`predict`(series[, name])	Aggregates the (sequence of) multivariate binary series given as input into a (sequence of) univariate binary series.

eval_metric(anomalies, series, window=1, metric='recall')¶

Aggregates the (sequence of) multivariate series given as input into one (sequence of) series and evaluates the results against the ground truth anomaly labels.

Parameters

anomalies (Union[TimeSeries, Sequence[TimeSeries]]) – The (sequence of) binary ground truth anomaly labels (1 if it is an anomaly and 0 if not).
series (Union[TimeSeries, Sequence[TimeSeries]]) – The (sequence of) predicted multivariate binary series to aggregate.
window (int) – (Sequence of) integer value indicating the number of past samples each point represents in the (sequence of) series. The parameter will be used by the function _window_adjustment_anomalies() in darts.ad.utils to transform anomalies.
metric (Literal[‘recall’, ‘precision’, ‘f1’, ‘accuracy’]) – The name of the metric function to use. Must be one of “recall”, “precision”, “f1”, and “accuracy”. Default: “recall”.

Returns

(Sequence of) score for the (sequence of) series.

Return type

Union[float, Sequence[float]]

fit(anomalies, series)¶

Fit the aggregators on the (sequence of) multivariate binary anomaly series.

If a list of series is given, they must have the same number of components.

Parameters

anomalies (Union[TimeSeries, Sequence[TimeSeries]]) – The (sequence of) binary ground truth anomaly labels (1 if it is an anomaly and 0 if not).
series (Union[TimeSeries, Sequence[TimeSeries]]) – The (sequence of) multivariate binary series (predicted labels) to aggregate.

Return type

Self

predict(series, name='series')¶

Aggregates the (sequence of) multivariate binary series given as input into a (sequence of) univariate binary series.

Parameters

series (Union[TimeSeries, Sequence[TimeSeries]]) – The (sequence of) multivariate binary series to aggregate.
name (str) – The name of series.

Returns

(Sequence of) aggregated results.

Return type

TimeSeries

AND Aggregator

OR Aggregator