computeSimilarityVar: Similarity

Description

Compute the similarity between variables (or classes)

Usage

computeSimilarityVar(outMixtComp)
computeSimilarityClass(outMixtComp)

Arguments

outMixtComp

object of class MixtCompLearn or MixtComp obtained using mixtCompLearn or mixtCompPredict functions from RMixtComp package or rmcMultiRun from RMixtCompIO package.

Value

a similarity matrix

Details

The similarities between variables j and h is defined by Delta(j,h) $$Delta(j,h)^2 = 1 - \sqrt{(1/n) * \sum_{i=1}^n \sum_{k=1}^K (P(Z_i=k|x_{ij}) - P(Z_i=k|x_{ih}))^2}$$

The similarities between classes k and g is defined by 1 - Sigma(k,g) $$Sigma(k,g)^2 = (1/n) * \sum_{i=1}^n (P(Z_i=k|x_i) - P(Z_i=g|x_i))^2$$

Examples

Run this code

# NOT RUN {
require(RMixtCompIO) # for learning a mixture model
dataLearn <- list(var1 = as.character(c(rnorm(50, -2, 0.8), rnorm(50, 2, 0.8))),
                  var2 = as.character(c(rnorm(50, 2), rpois(50, 8))))
                  
model <- list(var1 = list(type = "Gaussian", paramStr = ""),
              var2 = list(type = "Poisson", paramStr = ""))

algo <- list(
  nClass = 2,
  nInd = 100,
  nbBurnInIter = 100,
  nbIter = 100,
  nbGibbsBurnInIter = 100,
  nbGibbsIter = 100,
  nInitPerClass = 3,
  nSemTry = 20,
  confidenceLevel = 0.95,
  ratioStableCriterion = 0.95,
  nStableCriterion = 10,
  mode = "learn"
)

resLearn <- rmcMultiRun(algo, dataLearn, model, nRun = 3)

simVar <- computeSimilarityVar(resLearn)
simClass <- computeSimilarityClass(resLearn)

# }