Sign in

v2

latestSwagger 2.02026-07-13103553.7 KB

Detect change point for the entire series

Evaluate the change point score of every series point.

post/timeseries/changepoint/detect

Request body

granularity'yearly' | 'monthly' | 'weekly' | 'daily' | 'hourly' | 'minutely' | 'secondly' | 'microsecond' | 'none' required
customIntervalinteger

A custom interval is used to set a nonstandard time interval. For example, if the series is 5 minutes, the request can be set as {"granularity":"minutely", "customInterval":5}.

periodinteger

Argument that indicates the periodic value of a time series. If the value is null or not present, the API will determine the period automatically.

stableTrendWindowinteger

Argument that indicates an advanced model parameter. A default stableTrendWindow value will be used in detection.

thresholdnumber float

Argument that indicates an advanced model parameter between 0.0 and 1.0. The lower the value is, the larger the trend error is, which means less change point will be accepted.

Response

The request has succeeded.

periodinteger

Frequency extracted from the series. Zero means no recurrent pattern has been found.

isChangePointboolean[]

Change point properties for each input point. True means an anomaly (either negative or positive) has been detected. The index of the array is consistent with the input series.

confidenceScoresnumber[]

Change point confidence of each point.