Metrics

A metric can refer to many things, but a fitting description (from wikipedia) goes as follows:

An adjective indicating relation to measurement in general, or a noun describing a specific type of measurement

In the world of programming languages, a typical use-case for metrics is for estimating performance of some algorithm. There are therefore many examples and implementations related to machine learning.

Below is a list of packages that implement metrics.

• AdversarialPrediction.jl

• Avalon.jl

• BetaML.jl

• ClinicalTrialUtilities.jl

• Distances.jl

• FastAI.jl

• EvalMetrics.jl

• KernelMethods.jl

• KnetMetrics.jl

• Lighthouse.jl

• LossFunctions.jl

• Metrics.jl

• MLBase.jl

• StatisticalMeasures.jl

• MLMetrics.jl

• MultivariateAnomalies.jl

• PredictMD.jl

• ROCAnalysis.jl

• ROCCurves.jl

If in doubt, a good bet is StatisticalMeasures.jl. It is a new effort to provide a wide set of metrics in a consistent manner, born from the JuliaAI ecosystem.

This section could still use a lot of love. If you have used or developed Julia packages in this domain, we would love your help! Please visit the "Contributing" section of the repository that hosts this website for information on contributions.