Timeseries Features DSLedit

Defines how time series data must be aggregated into features for learning and inference.

Features define how to aggregate numerical data from one or more buckets.

Accepted parameters to define model features are:


Name given to this feature


TSDB column name


DEPRECATED. Define measurement in the bucket settings.


list of TSDB tag names and values that must be matched when fetching the data


An aggregation operator supported by the TSDB


A default float value to replace NaN values returned by the TSDB, or previous in order to fill the series with previous non-NaN value


low_high, low, or high according to the type of abnormal values to detect

The list below defines the aggregation operators can be used to define features. These values can be extracted by using numeric fields in the bucket documents.


This version does not support feature generation by a provided script, nor extracting features from categories ie, non numeric fields.

The metric operators that are supported consist of: count, min, max, sum, avg, sum_of_squares, variance, and std_deviation.


This version supports the following additional operators with InfluxDB: derivative, integral, spread, mode, 5percentile, 10percentile, 90percentile, 95percentile, stddev