scudoModel: Generate model for 'caret::train'

In rScudo: Signature-based Clustering for Diagnostic Purposes

Description

This function generates a suitable input for the method argument of the function train from the package caret, that can be used to perform automatic parameter tuning (e.g. using cross-validation).

Usage

scudoModel(nTop, nBottom, N, maxDist = 1, weighted = TRUE,
    complete = FALSE, beta = 1, distFun = NULL)

Arguments

nTop	number of up-regulated features to include in the signatures
nBottom	number of down-regulated features to include in the signatures
N	a number between 0 and 1, representing the fraction of the signature-to-signature distances that will be used to draw the graph
maxDist	an integer. Only nodes with a distance from a testing node less or equal to maxDist are used to perform the classification
weighted	logical, whether to consider the distances associated to the edges to compute the scores for the classification
complete	logical, whether to consider all the nodes in the training set to perform the classification. If TRUE, the arguments N, maxDist, weighted and beta are ignored
beta	a coefficient used to down-weight the influence of distant nodes on the classification outcome
distFun	the function used to compute the distance between two samples. See Details for the specification of this function

Details

This function can be used in conjunction with the functions in the package caret to tune the parameters of scudoClassify. The input of this function are vector of parameter values that the tuning procedure should explore. All possible combination of parameter values are explored by default. The user can change this using the search argument of the trainControl function.

The output of this function is a list that represens a classification model using scudoClassify and that can be used as input for the method argument of the function train.

Value

A named list

Author(s)

Matteo Ciciani [e-mail], Thomas Cantore [e-mail]

See Also

scudoClassify, train, trainControl

Examples

# Generate example dataset
expData <- data.frame(a = 1:10, b = 2:11, c = 10:1, d = 11:2,
    e = c(1:4, 10:5), f = c(7:10, 6:1), g = c(8:4, 1:3, 10, 9),
    h = c(6:10, 5:1), i = c(5:1, 6:10))
rownames(expData) <- letters[1:10]
groups <- factor(c(1,1,1,2,2,2,1,1,1))

# Run bootstrap. Notice that the dataset is transposed
ctrl <- caret::trainControl(method = "boot", number = 5)
model <- scudoModel(nTop = 3:5, nBottom = 3:5, N = 0.5, complete = TRUE)
set.seed(1)
bootRes <- caret::train(x = t(expData), y = groups, method = model,
    trControl = ctrl)

rScudo documentation built on Nov. 8, 2020, 5:07 p.m.