def ObservationStabilizerWorker.fit(self, inputs, fx_choice=REG.AIG, **params) [source]
Execute the full outlier detection and filtering pipeline.
Trains Isolation Forest on the feature matrix, scores
all observations, and removes flagged outliers from the
training set.
Parameters
inputs : ObsStabilizerInput
Training data and feature lists.
fx_choice : str
The fitting strategy identifier. Defaults to REG.AIG.
**params : dict
Runtime parameters passed to the internal fitter
(th_outliers).
(th_outliers).
Returns
ObservationStabilizer
The fitted instance with the clean observation set
and outlier flags available.
and outlier flags available.