calcPerfCompound: Calculate compound performance metrics (e.g. roc)

In luannnguyen/mltoolkit: Various tools for training machine learning classifiers

Description

Calculate compound performance metrics (e.g. roc)

Usage

calcPerfCompound(
  confusion,
  compound.metric,
  avg.method = NULL,
  metric.names.as.x.y = F
)

Arguments

confusion	A matrix or data frame with each row being a confusion matrix. The output of confusionMatrix(probs.predicted, logicals.expected, cutoff = 'all')
compound.metric	The name of the compound metric
avg.method	How to average performance metrics in multiclass classification. Can be NULL, 'weighted' or 'macro'
metric.names.as.x.y	If TRUE, will convert colnames: 'tpr' and 'ppv', to: 'x' and 'y'

Value

A matrix of the two performance metrics that the compound metric is composed of

luannnguyen/mltoolkit documentation built on Aug. 29, 2020, 8:31 a.m.