Class AnomalyDetector

Delete an existing multivariate model according to the modelId

Submit detection multivariate anomaly task with the trained model of modelId, the input schema should be the same with the training request. Thus request will be complete asynchronously and will return a resultId for querying the detection result.The request should be a source link to indicate an externally accessible Azure storage Uri (preferably a Shared Access Signature Uri). All time-series used in generate the model must be zipped into one single file. Each time-series will be as follows: the first column is timestamp and the second column is value.

Evaluate change point score of every series point

This operation generates a model with an entire series, each point is detected with the same model. With this method, points before and after a certain point are used to determine whether it is an anomaly. The entire detection can give user an overall status of the time series.

This operation generates a model using points before the latest one. With this method, only historical points are used to determine whether the target point is an anomaly. The latest point detecting operation matches the scenario of real-time monitoring of business metrics.

Export multivariate anomaly detection model based on modelId

Get multivariate anomaly detection result based on resultId returned by the DetectAnomalyAsync api

Get detailed information of multivariate model, including the training status and variables used in the model.

Synchronized API for anomaly detection.

List models of a subscription

Create and train a multivariate anomaly detection model. The request must include a source parameter to indicate an externally accessible Azure storage Uri (preferably a Shared Access Signature Uri). All time-series used in generate the model must be zipped into one single file. Each time-series will be in a single CSV file in which the first column is timestamp and the second column is value.