predict.pelora: Predict Method for Pelora

Description

Yields fitted values, predicted class labels and conditional probability estimates for training and test data, which are based on the gene groups pelora found, and on its internal penalized logistic regression classifier.

Usage

# S3 method for pelora
predict(object, newdata = NULL, newclin = NULL,
               type = c("fitted", "probs", "class"), noc = object$noc, ...)

Arguments

object

An R object of class "pelora", typically the result of pelora().

newdata

Numeric matrix with the same number of explanatory variables as the original x-matrix (\(p\) variables in columns, \(r\) cases in rows). For example, these can be additional microarray gene expression data which should be predicted.

newclin

Numeric matrix with the same number of additional (clinical) explanatory variables as the original u-matrix (\(m\) variables in columns, \(r\) cases in rows) that are used in the (penalized logistic regression) prediction model, but neither grouped nor averaged. Only needs to be given, if the model fit included an u-matrix. For example, these can be 'traditional' clinical variables.

type

Character string, describing whether fitted values "fitted", estimated conditional probabilites "probs" or class labels "class" should be returned.

noc

Integer, saying with how many clusters the fitted values, probability estimates or class labels should be determined. Also numeric vectors are allowed as an argument. The output is then a numeric matrix with fitted values, probability estimates or class labels for a multiple number of clusters.

…

Further arguments passed to and from methods.

Value

Depending on whether noc is a single number or a numeric vector. In the first case, a numeric vector of length \(r\) is returned, which contains fitted values for noc clusters, or probability estimates/class label predictions with noc clusters.

In the latter case, a numeric matrix with length(noc) columns, each containing fitted values for noc clusters, or probability estimates/class label predictions with noc clusters, is returned.

Details

If newdata = NULL, then the in-sample fitted values, probability estimates and class label predictions are returned.

Examples

Run this code

# NOT RUN {
## Working with a "real" microarray dataset
data(leukemia, package="supclust")

## Generating random test data: 3 observations and 250 variables (genes)
set.seed(724)
xN <- matrix(rnorm(750), nrow = 3, ncol = 250)

## Fitting Pelora
fit <- pelora(leukemia.x, leukemia.y, noc = 3)

## Fitted values and class probabilities for the training data
predict(fit, type = "cla")
predict(fit, type = "prob")

## Predicting fitted values and class labels for the random test data
predict(fit, newdata = xN)
predict(fit, newdata = xN, type = "cla", noc = c(1,2,3))
predict(fit, newdata = xN, type = "pro", noc = c(1,3))

## Fitting Pelora such that the first 70 variables (genes) are not grouped
fit <- pelora(leukemia.x[, -(1:70)], leukemia.y, leukemia.x[,1:70])

## Fitted values and class probabilities for the training data
predict(fit, type = "cla")
predict(fit, type = "prob")

## Predicting fitted values and class labels for the random test data
predict(fit, newdata = xN[, -(1:70)], newclin = xN[, 1:70])
predict(fit, newdata = xN[, -(1:70)], newclin = xN[, 1:70], "cla", noc  = 1:10)
predict(fit, newdata = xN[, -(1:70)], newclin = xN[, 1:70], type = "pro")
# }