orion.Orion

class orion.Orion(pipeline=None, hyperparameters=None)

Orion Class.

The Orion Class provides the main anomaly detection functionalities of Orion and is responsible for the interaction with the underlying MLBlocks pipelines.

Parameters

• pipeline (str, dict or MLPipeline) –

  Pipeline to use. It can be passed as:

  • An str with a path to a JSON file.

  • An str with the name of a registered pipeline.

  • An MLPipeline instance.

  • A dict with an MLPipeline specification.

• hyperparameters (dict) – Additional hyperparameters to set to the Pipeline.

__init__(pipeline=None, hyperparameters=None)

Initialize self. See help(type(self)) for accurate signature.

Methods

__init__([pipeline, hyperparameters])	Initialize self.
detect(data[, visualization])	Detect anomalies in the given data..
evaluate(data, ground_truth[, fit, …])	Evaluate the performance against ground truth anomalies.
fit(data, **kwargs)	Fit the pipeline to the given data.
fit_detect(data[, visualization])	Fit the pipeline to the data and then detect anomalies.
load(path)	Load an Orion instance from a pickle file.
save(path)	Save this object using pickle.

Attributes

DEFAULT_PIPELINE
PIPELINES
PIPELINES_DIR

orion orion.Orion.fit