An implementation of the Random Cut Forest data structure for sketching streaming data, with support for anomaly detection, density estimation, imputation, and more.
A thresholded random cut forest runner is similar to the anomaly score runners of the core package. In addition to showing the anomaly score associated with a given input point, this new runner outputs the anomaly grade.
Issue #, if available:
n/a
Description of changes:
Add a ThresholdedRandomCutForestRunner class. Similar to AnomalyScoreRunner and others.
Add a ThresholdedArgumentParser class for allowing configuration of thresholder hyperparameters.
Provide usage example (and external test) in a package-level README.
Edited parkservices's pom file to allow compilation to a single jar file with dependencies.
By submitting this pull request, I confirm that you can use, modify, copy, and redistribute this contribution, under the terms of your choice.
A thresholded random cut forest runner is similar to the anomaly score runners of the core package. In addition to showing the anomaly score associated with a given input point, this new runner outputs the anomaly grade.
Issue #, if available:
n/a
Description of changes:
ThresholdedRandomCutForestRunner
class. Similar toAnomalyScoreRunner
and others.ThresholdedArgumentParser
class for allowing configuration of thresholder hyperparameters.