module change_detection.tornado.hddm_a

Hoeffding's Bound based Drift Detection Method (A_test Scheme).

The source code was adopted from tornado, please cite:

The Tornado Framework By Ali Pesaranghader University of Ottawa, Ontario, Canada E-mail: apesaran -at- uottawa -dot- ca / alipsgh -at- gmail -dot- com

Original Paper: Frías-Blanco, Isvani, et al. "Online and non-parametric drift detection methods based on Hoeffding’s bounds." Published in: IEEE Transactions on Knowledge and Data Engineering 27.3 (2015): 810-823. URL: http://ieeexplore.ieee.org/abstract/document/6871418/

Copyright (C) 2022 Johannes Haug.

class HDDMA

HDDMA change detector.

method HDDMA.__init__

__init__(
    drift_confidence: float = 0.001,
    warning_confidence: float = 0.005,
    test_type: str = 'two-sided',
    reset_after_drift: bool = False
)

Inits the change detector.

Args:

  • drift_confidence: Todo (left unspecified by the Tornado library).
  • warning_confidence: Todo (left unspecified by the Tornado library).
  • test_type: Todo (left unspecified by the Tornado library).
  • reset_after_drift: A boolean indicating if the change detector will be reset after a drift was detected.

method HDDMA.detect_change

detect_change() → bool

Detects global concept drift.

Returns:

  • bool: True, if a concept drift was detected, False otherwise.

method HDDMA.detect_partial_change

detect_partial_change() → Tuple[bool, list]

Detects partial concept drift.

Notes:

HDDMA does not detect partial change.

method HDDMA.detect_warning_zone

detect_warning_zone() → bool

Detects a warning zone.

Returns:

  • bool: True, if the change detector has detected a warning zone, False otherwise.

method HDDMA.partial_fit

partial_fit(pr_scores: List[bool])

Updates the change detector.

Args:

  • pr_scores: A boolean vector indicating correct predictions. 'True' values indicate that the prediction by the online learner was correct, otherwise the vector contains 'False'.

method HDDMA.reset

reset()

Resets the change detector.

This file was automatically generated via lazydocs.