Applies the transform `transformed_series = scale * series + translation`. Parameters ---------- sca

Subtracts off the time-averaged mean of each component in a `TimeSeries`. If `global_fit` is `True`, then all of the `TimeSe

Applies the (invertible) transform `transformed_series = scale * series + translation`. Parameters ----------

Subtracts off the time-averaged mean of each component in a `TimeSeries`. If `global_fit` is `True`, then all of the `TimeSe

IQR Detector Flags values that lie outside of the interquartile range (IQR) by more than a certain factor of IQR's value as anomalies

Threshold Detector Flags values that are either below or above the `low_threshold` and `high_threshold`, respectively. If a

Quantile Detector Flags values that are either below or above the `low_quantile` and `high_quantile` quantiles of historical data, re

k-means Scorer When calling `fit(series)`, a moving window is applied, which results in a set of vectors of size `W`, where `W` is th

NLL Gamma Scorer Parameters ---------- window Integer value indicating the size of the window W used by the score

Difference Scorer

Wasserstein Scorer When calling `fit(series)`, a moving window is applied, which results in a set of vectors of size `W`, where `W` i

NLL Cauchy Scorer

PyOD Scorer When calling ``fit(series)``, a moving window is applied, which results in a set of vectors of size `W`, where `W` is the

NLL Gaussian Scorer Parameters ---------- window Integer value indicating the size of the window W used by the sc

Norm Scorer Returns the element-wise norm of a given order between two series' values. If `component_wise` is `False`, the norm is c

NLL Laplace Scorer Parameters ---------- window Integer value indicating the size of the window W used by the sco

NLL Exponential Scorer Parameters ---------- window Integer value indicating the size of the window W used by the

Parameters ---------- is_univariate Whether the scorer is a univariate scorer. window Integer

Parameters ---------- is_univariate Whether the scorer is a univariate scorer. window Integer

Parameters ---------- is_univariate Whether the scorer is a univariate scorer. If `True` and when using multivari

NLL Poisson Scorer Parameters ---------- window Integer value indicating the size of the window W used by the sco

Filtering-based Anomaly Detection Model The filtering model may or may not be already fitted. The underlying assumption is that this model

Forecasting-based Anomaly Detection Model The forecasting model must be a `GlobalForecastingModel` that may or may not be already fitted. The

OR Aggregator Aggregator that identifies a time step as anomalous if any of the components is flagged as anomalous (logical OR).

AND Aggregator Aggregator that identifies a time step as anomalous if all the components are flagged as anomalous (logical AND).

Ensemble scikit-learn aggregator Aggregator wrapped around the sklearn ensemble model `sklearn ensemble model <https://scikit-learn.o

Parameters ---------- multivariate: bool Whether to return a single multivariate timeseries - if False returns a

Parameters ---------- sample_freq: str The sampling frequency of the data. Can be "hourly" or "daily". Default is

Parameters ---------- multivariate: bool Whether to return a single multivariate timeseries - if False returns a

Parameters ---------- multivariate: bool Whether to return a single multivariate timeseries - if False returns a

Parameters ---------- multivariate: bool Whether to return a single multivariate timeseries - if False returns a

HuggingFaceConnector enables loading a model configuration and weights from HuggingFace Hub. This class provides methods to download the mode

Construct a layernorm module in the T5 style. No bias and no subtraction of mean.

Parameters ---------- ffn One of Darts' Position-wise Feed-Forward Network variants from darts.models.components.

FFN module [1]_. Parameters ---------- d_model The number of features in a token embedding. d_ff