Skip to contents

Load a Pre-defined MVPA Model

load_model.Rd

Retrieves a model specification from either the pre-defined set of MVPA models or from caret's model library.

Usage

load_model(name)

Arguments

name

Character string specifying the model to load. Can be either:

  • A pre-defined MVPA model name:

    corclass

    Correlation-based classifier with template matching

    sda_notune

    Simple Shrinkage Discriminant Analysis without tuning

    sda_boot

    SDA with bootstrap resampling

    glmnet_opt

    Elastic net with EPSGO parameter optimization

    sparse_sda

    SDA with sparsity constraints

    sda_ranking

    SDA with automatic feature ranking

    mgsda

    Multi-Group Sparse Discriminant Analysis

    lda_thomaz

    Modified LDA for high-dimensional data

    hdrda

    High-Dimensional Regularized Discriminant Analysis

  • Any valid model name from caret's model library (e.g., "rf" for random forest, "svmRadial" for SVM)

Value

A list containing the model specification with the following components:

type

Model type: "Classification" or "Regression"

library

Required R package(s) for the model

label

Human-readable model name

parameters

Data frame describing tunable parameters

grid

Function to generate parameter tuning grid

fit

Function to fit the model

predict

Function to generate predictions

prob

Function to generate class probabilities (classification only)

See also

MVPAModels for the complete list of available custom MVPA models

getModelInfo for the complete list of available caret models

mvpa_model for using these models in MVPA analyses

Examples

# Load custom MVPA model
model <- load_model("sda_notune")

# Load correlation classifier with parameter tuning options
corr_model <- load_model("corclass")
print(corr_model$parameters)  # View tunable parameters
#>   parameters     class                                           label
#> 1     method character correlation type: pearson, spearman, or kendall
#> 2     robust   logical                                   mean or huber

# Load caret's random forest model
rf_model <- load_model("rf")
print(rf_model$parameters)  # View RF parameters
#>   parameter   class                         label
#> 1      mtry numeric #Randomly Selected Predictors

# Load caret's SVM model
svm_model <- load_model("svmRadial")