Wrappers for River Anomaly Detectors

Ver. 1.0.1 (2024-04-10)

This module provides wrapper functionalities to incorporate anomaly detector algorithms of the River ecosystem. This module includes two algorithms from River that are embedded to MLPro, such as:

1) Half Space Tree (HST) 1) One Class SVM

Learn more: https://www.riverml.xyz/

class mlpro_int_river.wrappers.anomalydetectors.HST(p_no_trees=5, p_height=3, p_window_size=3, p_sizeof_instance_list=100, p_name: str = None, p_range_max=1, p_ada: bool = True, p_duplicate_data: bool = False, p_visualize: bool = False, p_logging=True, **p_kwargs)

Bases: WrapperRiver, AnomalyDetector

C_TYPE = 'Anomaly Detector'

C_NAME = 'River-HST'

_run(p_inst_new: list, p_inst_del: list)

Custom method that is called by method run().

Parameters:

p_inst (InstDict) – Instances to be processed.

class mlpro_int_river.wrappers.anomalydetectors.SVM(p_kernel='rbf', p_nu=0.01, p_sizeof_instance_list=100, p_name: str = None, p_range_max=1, p_ada: bool = True, p_duplicate_data: bool = False, p_visualize: bool = False, p_logging=True, **p_kwargs)

Bases: AnomalyDetector

C_NAME = 'OneClassSVM Anomaly Detector'

C_TYPE = 'Anomaly Detector'

_run(p_inst_new: list, p_inst_del: list)

Custom method that is called by method run().

Parameters:

p_inst (InstDict) – Instances to be processed.