emil (version 1.1-6)

evaluate.modeling: Performance estimation of modeling procedures

Description

This function performs the important task of evaluating the performance of a modeling procedure with resampling, including tuning and pre-processing to not bias the results by information leakage.

Usage

evaluate.modeling(proc, x, y, ..., .save = list(fit = FALSE, pred = TRUE, vimp
  = FALSE, tuning = TRUE), .verbose = TRUE)

Arguments

proc

modeling procedure, or list of modeling procedures, as produced by modeling.procedure.

x

Dataset, observations as rows and descriptors as columns.

y

Response vector.

...

Sent to tune and batch.model.

.save

See batch.model.

.verbose

Whether to print an activity log.

Value

• A list of fitted models.

See Also

emil, modeling.procedure, fit, tune predict, vimp

Examples

proc <- modeling.procedure("lda")
cv <- resample("crossval", y=iris$Species, nfold=5, nrep=3)
perf <- evaluate.modeling(proc, x=iris[-5], y=iris$Species, resample=cv)
err <- subtree(perf, TRUE, "error")