Per-element maximal concordance between a hard and a fuzzy partition

Per-element maximal concordance between a hard clustering and hard and fuzzy ground truth labels.

Usage

fuzzyHardSpotConcordance(
  hardTrue,
  fuzzyTrue,
  hardPred,
  useNegatives = TRUE,
  verbose = TRUE
)

Arguments

hardTrue: A vector of true cluster labels
fuzzyTrue: A object coercible to a numeric matrix with membership probability of elements (rows) in clusters (columns). Must have the same number of rows as the length of hardTrue.
hardPred: A vector of predicted cluster labels
useNegatives: Logical; whether to include negative pairs in the concordance score (tends to result in a larger overall concordance and lower dynamic range of the score). Default TRUE.
verbose: Logical; whether to print expected memory usage for large datasets.

Value

A numeric vector of concordance scores for each element of hardPred

Examples

# generate a fuzzy truth:
fuzzyTrue <- matrix(c(
  0.95, 0.025, 0.025, 
  0.98, 0.01, 0.01, 
  0.96, 0.02, 0.02, 
  0.95, 0.04, 0.01, 
  0.95, 0.01, 0.04, 
  0.99, 0.005, 0.005, 
  0.025, 0.95, 0.025, 
  0.97, 0.02, 0.01, 
  0.025, 0.025, 0.95), 
  ncol = 3, byrow=TRUE)
# a hard truth:
hardTrue <- apply(fuzzyTrue,1,FUN=which.max)
# some predicted labels:
hardPred <- c(1,1,1,1,1,1,2,2,2)
fuzzyHardSpotConcordance(hardTrue, fuzzyTrue, hardPred)
#> [1] 0.87750 0.87625 0.87625 0.87750 0.87875 0.87750 0.76625 0.02750 0.76625