mvpa_dataset: Create an MVPA Dataset Object

In bbuchsbaum/rMVPA: Multivoxel Pattern Analysis in R

Create an MVPA Dataset Object

Description

Creates a dataset object for MVPA analysis that encapsulates a training dataset, an optional test dataset, and a voxel mask.

Usage

mvpa_dataset(train_data, test_data = NULL, mask)

Arguments

train_data	The training data set: a NeuroVec instance
test_data	Optional test data set: a NeuroVec instance (default: NULL)
mask	The set of voxels to include: a NeuroVol instance

Value

An mvpa_dataset object (S3 class) containing:

train_data

The training data as a NeuroVec instance

test_data

The test data as a NeuroVec instance (if provided, otherwise NULL)

mask

The binary mask defining valid voxels as a NeuroVol instance

has_test_set

Logical flag indicating whether this dataset has a test set

See Also

mvpa_surface_dataset for creating surface-based MVPA datasets

mvpa_design for creating the corresponding design object

Examples

# Create dataset from NeuroVec objects
train_vec <- NeuroVec(array(rnorm(1000*100), c(10,10,10,100)))
mask_vol <- NeuroVol(array(1, c(10,10,10)))
dataset <- mvpa_dataset(train_vec, mask=mask_vol)

# Create dataset with test data
test_vec <- NeuroVec(array(rnorm(1000*20), c(10,10,10,20)))
dataset_with_test <- mvpa_dataset(train_vec, test_vec, mask=mask_vol)

bbuchsbaum/rMVPA documentation built on June 10, 2025, 8:23 p.m.