vcr.da.train: Carry out discriminant analysis on training data, and prepare...

In classmap: Visualizing Classification Results

Carry out discriminant analysis on training data, and prepare to visualize its results.

Description

Custom DA function which prepares for graphical displays such as the classmap. The disciminant analysis itself is carried out by the maximum a posteriori rule, which maximizes the density of the mixture.

Usage

vcr.da.train(X, y, rule = "QDA", estmethod = "meancov")

Arguments

X	a numerical matrix containing the predictors in its columns. Missing values are not allowed.
y	a factor with the given class labels.
rule	either "QDA" for quadratic discriminant analysis or "LDA" for linear discriminant analysis.
estmethod	function for location and covariance estimation. Should return a list with the center $m and the covariance matrix $S. The default is "meancov" (classical mean and covariance matrix), and the option "DetMCD" (based on robustbase::covMcd) is also provided.

Value

A list with components:

yint	number of the given class of each case. Can contain NA's.
y	given class label of each case. Can contain NA's.
levels	levels of y
predint	predicted class number of each case. For each case this is the class with the highest posterior probability. Always exists.
pred	predicted label of each case.
altint	number of the alternative class. Among the classes different from the given class, it is the one with the highest posterior probability. Is NA for cases whose y is missing.
altlab	label of the alternative class. Is NA for cases whose y is missing.
PAC	probability of the alternative class. Is NA for cases whose y is missing.
figparams	parameters for computing fig, can be used for new data.
fig	distance of each case i from each class g. Always exists.
farness	farness of each case from its given class. Is NA for cases whose y is missing.
ofarness	for each case i, its lowest fig[i,g] to any class g. Always exists.
classMS	list with center and covariance matrix of each class
lCurrent	log of mixture density of each case in its given class. Is NA for cases with missing y.
lPred	log of mixture density of each case in its predicted class. Always exists.
lAlt	log of mixture density of each case in its alternative class. Is NA for cases with missing y.

Author(s)

Raymaekers J., Rousseeuw P.J.

References

Raymaekers J., Rousseeuw P.J., Hubert M. (2021). Class maps for visualizing classification results. Technometrics, appeared online. \Sexpr[results=rd]{tools:::Rd_expr_doi("10.1080/00401706.2021.1927849")}(link to open access pdf)

See Also

vcr.da.newdata, classmap, silplot, stackedplot

Examples

data("data_floralbuds")
X <- data_floralbuds[, 1:6]; y <- data_floralbuds[, 7]
vcrout <- vcr.da.train(X, y, rule = "QDA")
# For linear discriminant analysis, put rule = "LDA".
confmat.vcr(vcrout) # There are a few outliers
cols <- c("saddlebrown", "orange", "olivedrab4", "royalblue3")
stackedplot(vcrout, classCols = cols)
classmap(vcrout, "bud", classCols = cols)

# For more examples, we refer to the vignette:
## Not run: 
vignette("Discriminant_analysis_examples")

## End(Not run)

classmap documentation built on April 23, 2023, 5:09 p.m.