classmap (version 1.2.3)

confmat.vcr: Build a confusion matrix from the output of a function vcr.*.*.

Description

Build a confusion matrix from the output of a function vcr.*.*. Optionally, a separate column for outliers can be added to the confusion matrix.

Usage

confmat.vcr(vcrout, cutoff = 0.99, showClassNumbers = FALSE,
            showOutliers = TRUE, silent = FALSE)

Value

A confusion matrix

Arguments

vcrout

output of vcr.*.train or vcr.*.newdata.

cutoff

cases with overall farness vcrout$ofarness > cutoff are flagged as outliers.

showClassNumbers

if TRUE, the row and column names are the number of each level instead of the level itself. Useful for long level names.

showOutliers

if TRUE and some points were flagged as outliers, it adds an extra column on the right of the confusion matrix for these outliers, with label "outl".

silent

if FALSE, the confusion matrix and accuracy are shown on the screen.

Author

Raymaekers J., Rousseeuw P.J.

References

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

See Also

vcr.da.train, vcr.da.newdata,
vcr.knn.train, vcr.knn.newdata,
vcr.svm.train, vcr.svm.newdata,
vcr.rpart.train, vcr.rpart.newdata,
vcr.forest.train, vcr.forest.newdata,
vcr.neural.train, vcr.neural.newdata

Examples

vcrout <- vcr.knn.train(scale(iris[, 1:4]), iris[, 5], k = 5)
# The usual confusion matrix:
confmat.vcr(vcrout, showOutliers = FALSE)

# Cases with ofarness > cutoff are flagged as outliers:
confmat.vcr(vcrout, cutoff = 0.98)

# With the default cutoff = 0.99 only one case is flagged here:
confmat.vcr(vcrout)
# Note that the accuracy is computed before any cases
# are flagged, so it does not depend on the cutoff.

confmat.vcr(vcrout, showClassNumbers = TRUE)
# Shows class numbers instead of labels. This option can
# be useful for long level names.

# For more examples, we refer to the vignettes:
if (FALSE) {
vignette("Discriminant_analysis_examples")
vignette("K_nearest_neighbors_examples")
vignette("Support_vector_machine_examples")
vignette("Rpart_examples")
vignette("Random_forest_examples")
vignette("Neural_net_examples")
}