API Reference

The following APIs are the key ones for using SUOD:

• suod.models.base.SUOD.fit(): Fit estimator. y is optional for unsupervised methods.

• suod.models.base.SUOD.approximate(): Use supervised models to approximate unsupervised base detectors. Fit should be invoked first.

• suod.models.base.SUOD.predict(): Predict on a particular sample once the estimator is fitted.

• suod.models.base.SUOD.predict_proba(): Predict the probability of a sample is an anomaly once the estimator is fitted.

• suod.models.base.SUOD.decision_function(): Predict raw anomaly scores of X using the fitted detectors.

• suod.models.base.SUOD.get_params(): Get the parameters of the model.

• suod.models.base.SUOD.set_params(): Set the parameters of the model.

• Each base estimator can be accessed by calling clf[i] where i is the estimator index.

---

All Models

• suod.models package
  • Subpackages
    • suod.models.saved_models package
      • Module contents
  • Submodules
  • suod.models.base module
  • suod.models.cost_predictor module
  • suod.models.jl_projection module
    • jl_fit_transform()
    • jl_transform()
  • suod.models.parallel_processes module
    • balanced_scheduling()
    • cost_forecast_meta()
    • indices_to_one_hot()
  • Module contents
• suod.utils package
  • Submodules
  • suod.utils.utility module
    • build_codes()
    • get_estimators()
    • get_estimators_small()
    • raw_score_to_proba()
  • Module contents