bagging.wrapper: Bagging Wrapper for Ensemble Features Selection

In OmicsMarkeR: Classification and Feature Selection for 'Omics' Datasets

Description

Compiles results of ensemble feature selection

Usage

bagging.wrapper(X, Y, method, bags, f, aggregation.metric, k.folds, repeats,
  res, tuning.grid, optimize, optimize.resample, metric, model.features,
  allowParallel, verbose, theDots)

Arguments

X	A matrix containing numeric values of each feature
Y	A factor vector containing group membership of samples
method	A vector listing models to be fit
bags	Number of bags to be run
f	Number of features desired
aggregation.metric	string indicating the type of ensemble aggregation. Avialable options are "CLA" (Complete Linear), "EM" (Ensemble Mean), "ES" (Ensemble Stability), and "EE" (Ensemble Exponential)
k.folds	Number of folds generated during cross-validation
repeats	Number of times cross-validation repeated
res	Optional - Resolution of model optimization grid
tuning.grid	Optional list of grids containing parameters to optimize for each algorithm. Default "tuning.grid = NULL" lets function create grid determined by "res"
optimize	Logical argument determining if each model should be optimized. Default "optimize = TRUE"
optimize.resample	Logical argument determining if each resample should be re-optimized. Default "optimize.resample = FALSE" - Only one optimization run, subsequent models use initially determined parameters
metric	Criteria for model optimization. Available options are "Accuracy" (Predication Accuracy), "Kappa" (Kappa Statistic), and "AUC-ROC" (Area Under the Curve - Receiver Operator Curve)
model.features	Logical argument if should have number of features selected to be determined by the individual model runs. Default "model.features = FALSE"
allowParallel	Logical argument dictating if parallel processing is allowed via foreach package. Default allowParallel = FALSE
verbose	Logical argument if should output progress
theDots	Optional arguments provided for specific models or user defined parameters if "optimize = FALSE".

Value

results

List with the following elements:

• Methods: Vector of models fit to data

• ensemble.results: List of length = length(method) containing aggregated features

• Number.bags: Number of bagging iterations

• Agg.metric: Aggregation method applied

• Number.features: Number of user-defined features

bestTunes

If "optimize.resample = TRUE" then returns list of best parameters for each iteration

Author(s)

Charles Determan Jr

OmicsMarkeR documentation built on April 28, 2020, 6:54 p.m.