cpfa: Classification with Parallel Factor Analysis

Classification using Richard A. Harshman's Parallel Factors (Parafac) model fit to a 3-way or 4-way data array/tensor. See Harshman (1994) <doi:10.1016/0167-9473(94)90132-5>. Uses Parafac factor weights from one mode of this model as predictors to tune parameters for one or more classification methods. Supports penalized logistic regression, support vector machine, random forest, and feed-forward neural network. Supports binary and multiclass classification. Predicts class labels or class probabilities and calculates multiple classification performance measures. Parallel computing is implemented via the 'parallel' and 'doParallel' packages.

Version: 1.0-1
Depends: multiway, glmnet, e1071, randomForest, doParallel
Imports: foreach, nnet
Published: 2022-04-08
Author: Matthew A. Snodgress
Maintainer: Matthew A. Snodgress <snodg031 at umn.edu>
License: GPL-2 | GPL-3 [expanded from: GPL (≥ 2)]
NeedsCompilation: no
CRAN checks: cpfa results

Documentation:

Reference manual: cpfa.pdf

Downloads:

Package source: cpfa_1.0-1.tar.gz
Windows binaries: r-devel: cpfa_1.0-1.zip, r-release: cpfa_1.0-1.zip, r-oldrel: cpfa_1.0-1.zip
macOS binaries: r-release (arm64): cpfa_1.0-1.tgz, r-oldrel (arm64): cpfa_1.0-1.tgz, r-release (x86_64): cpfa_1.0-1.tgz, r-oldrel (x86_64): cpfa_1.0-1.tgz
Old sources: cpfa archive

Linking:

Please use the canonical form https://CRAN.R-project.org/package=cpfa to link to this page.