RCLRMIX-methods {rebmix}

Predicts Cluster Membership Based Upon a Model Trained by REBMIX

Description

Returns as default the RCLRMIX algorithm output for mixtures of conditionally independent normal, lognormal, Weibull, gamma, Gumbel, binomial, Poisson, Dirac, uniform or von Mises component densities, following the methodology proposed in the article cited in the references. If model equals "RCLRMVNORM" output for mixtures of multivariate normal component densities with unrestricted variance-covariance matrices is returned.

Usage

## S4 method for signature 'RCLRMIX'
RCLRMIX(model = "RCLRMIX", x = NULL, Dataset = NULL, 
        pos = 1, Zt = factor(), Rule = character(), ...)
## ... and for other signatures
## S4 method for signature 'RCLRMIX'
summary(object, ...)
## ... and for other signatures

Arguments

model

see Methods section below.

x

an object of class REBMIX.

Dataset

a data frame or an object of class Histogram to be clustered.

pos

a desired row number in x@summary for which the clustering is performed. The default value is 1.

Zt

a factor of true cluster membership. The default value is factor().

Rule

a character containing the merging rule. One of "Entropy" or "Demp". The default value is "Entropy".

object

see Methods section below.

...

currently not used.

Value

Returns an object of class RCLRMIX or RCLRMVNORM.

Methods

signature(model = "RCLRMIX")

a character giving the default class name "RCLRMIX" for mixtures of conditionally independent normal, lognormal, Weibull, gamma, Gumbel, binomial, Poisson, Dirac, uniform or von Mises component densities.

signature(model = "RCLRMVNORM")

a character giving the class name "RCLRMVNORM" for mixtures of multivariate normal component densities with unrestricted variance-covariance matrices.

signature(object = "RCLRMIX")

an object of class RCLRMIX.

signature(object = "RCLRMVNORM")

an object of class RCLRMVNORM.

Author(s)

Marko Nagode

References

J. P. Baudry, A. E. Raftery, G. Celeux, K. Lo and R. Gottardo. Combining mixture components for clustering. Journal of Computational and Graphical Statistics, 19(2):332-353, 2010. doi:10.1198/jcgs.2010.08111

Examples

devAskNewPage(ask = TRUE)

# Generate Poisson dataset.

n <- c(500, 200, 400)

Theta <- new("RNGMIX.Theta", c = 3, pdf = "Poisson")

a.theta1(Theta) <- c(3, 12, 36)

poisson <- RNGMIX(Dataset.name = "Poisson_1", n = n, Theta = a.Theta(Theta))

# Estimate number of components, component weights and component parameters.

EM <- new("EM.Control", strategy = "exhaustive")

poissonest <- REBMIX(Dataset = a.Dataset(poisson),
  Preprocessing = "histogram",
  cmax = 6,
  Criterion = "BIC",
  pdf = rep("Poisson", 1),
  EMcontrol = EM)

summary(poissonest)

# Plot finite mixture.

plot(poissonest)

# Cluster dataset.

poissonclu <- RCLRMIX(x = poissonest, Zt = a.Zt(poisson))

summary(poissonclu)

# Plot clusters.

plot(poissonclu)

# Create new dataset.

Dataset <- sample.int(n = 50, size = 10, replace = TRUE)

Dataset <- as.data.frame(Dataset)

# Cluster the dataset.

poissonclu <- RCLRMIX(x = poissonest, Dataset = Dataset, Rule = "Demp")

a.Dataset(poissonclu)