Documentation

anomalydetection.mad() function

anomalydetection.mad() is a user-contributed function maintained by the package author.

anomalydetection.mad() uses the median absolute deviation (MAD) algorithm to detect anomalies in a data set.

Input data requires _time and _value columns. Output data is grouped by _time and includes the following columns of interest:

  • _value: difference between of the original _value from the computed MAD divided by the median difference.
  • MAD: median absolute deviation of the group.
  • level: anomaly indicator set to either anomaly or normal.
Function type signature
(<-table: stream[B], ?threshold: A) => stream[{C with level: string, _value_diff_med: D, _value_diff: D, _value: D}] where A: Comparable + Equatable, B: Record, D: Comparable + Divisible + Equatable

For more information, see Function type signatures.

Parameters

threshold

Deviation threshold for anomalies.

table

Input data. Default is piped-forward data (<-).

Examples

Use the MAD algorithm to detect anomalies

import "contrib/anaisdg/anomalydetection"
import "sampledata"

sampledata.float()
    |> anomalydetection.mad(threshold: 1.0)

View example input and output


Was this page helpful?

Thank you for your feedback!


The future of Flux

Flux is going into maintenance mode. You can continue using it as you currently are without any changes to your code.

Read more

New in InfluxDB 3.4

Key enhancements in InfluxDB 3.4 and the InfluxDB 3 Explorer 1.2.

See the Blog Post

InfluxDB 3.4 is now available for both Core and Enterprise, which introduces offline token generation for use in automated deployments and configurable license type selection that lets you bypass the interactive license prompt. InfluxDB 3 Explorer 1.2 is also available, which includes InfluxDB cache management and other new features.

For more information, check out: