MakeModelDefaults: Model parameters for ModelTrain

In jrash/chemmodlab: A Cheminformatics Modeling Laboratory for Fitting and Assessing Machine Learning Models

Model parameters for ModelTrain

Description

Makes a list containing the default parameters for all models implemented in ModelTrain.

Usage

MakeModelDefaults(n, p, classify, nfolds)

Arguments

n	The number of observations in the data.
p	The number of descriptors in the data.
classify	A logical. Will classification models be used? (is the response binary?) If false, regression models will be assumed.
nfolds	The number of folds used for k-fold cross validation.

Details

Sensible default values are selected for each tunable model parameter, however users may set any parameter manually by generating a list with this function and assigning the parameters.

See https://pages.github.ncsu.edu/jrash/chemmodlab/ for more information about the models available (including model default parameters).

Value

A list whose elements are dataframes containing the default parameter values for models implemented in ModelTrain.

Author(s)

Jeremy Ash

See Also

ModelTrain, chemmodlab

Examples

params <- MakeModelDefaults(n = nrow(USArrests),
 p = ncol(USArrests[, -1]), classify = TRUE, nfolds = 10)
params$Forest$mtry <- ncol(USArrests[, -1])-1
params

cml <- ModelTrain(USArrests, models = "RF", nsplits = 3,
 user.params = params)

jrash/chemmodlab documentation built on May 18, 2023, 8:42 p.m.