def ObservationStabilizerWorker.transform(self, data) [source]
Apply the trained outlier filter to new data.
Parameters
data : pDF
Input data to filter.
Returns
ObsStabilizerResult
Cleaned data (outliers removed) + outlier flags.
As the final step of the Screening phase, returned
Pandas/NumPy dtypes. This single-conversion boundary minimizes peak pipeline
memory footprint by preventing redundant downstream allocations and ensuring
full compatibility with numpy, LightGBM, XGBoost, and Scikit-Learn.
As the final step of the Screening phase, returned
data is converted to nativePandas/NumPy dtypes. This single-conversion boundary minimizes peak pipeline
memory footprint by preventing redundant downstream allocations and ensuring
full compatibility with numpy, LightGBM, XGBoost, and Scikit-Learn.