Learn R Programming

ChemoSpec (version 6.1.10)

mclustSpectra: mclust Analysis of a Spectra Object PCA Results

Description

This function is a wrapper for the Mclust function and associated plotting functions.

Usage

mclustSpectra(
  spectra,
  pca,
  pcs = c(1:3),
  dims = c(1, 2),
  plot = c("BIC", "proj", "errors"),
  use.sym = FALSE,
  ...
)

Value

The Mclust model is returned invisibly, and a plot is made.

Arguments

spectra

An object of S3 class Spectra().

pca

An object of class prcomp.

pcs

An integer vector describing which PCs to use.

dims

A integer vector giving the PCA dimensions to use.

plot

A character string indicating what plot to make. Options are c("BIC", "proj", "error"); see Mclust for details.

use.sym

Logical; if true, the color scheme is changed to black and symbols are used for plotting.

...

Other parameters to be passed downstream.

Author

Bryan A. Hanson (DePauw University).

See Also

Mclust for background on the method. Additional documentation at https://bryanhanson.github.io/ChemoSpec/

Examples

Run this code
if (FALSE) {
require("mclust")
data(metMUD1)
cls <- c_pcaSpectra(metMUD1, choice = "autoscale")

p <- plotScores(metMUD1, cls)

mclustSpectra(metMUD1, cls, plot = "BIC")
mclustSpectra(metMUD1, cls, plot = "proj")
mclustSpectra(metMUD1, cls, plot = "errors", truth = metMUD1$groups)
}

Run the code above in your browser using DataLab