Classification with Parallel Factor Analysis
Overview
Classification using Richard A. Harshman's Parallel Factor Analysis-1 (Parafac) model or Parallel Factor Analysis-2 (Parafac2) model fit to a three-way or four-way data array. See Harshman and Lundy (1994): doi:10.1016/0167-9473(94)90132-5. Classification using principal component analysis (PCA) fit to a two-way data matrix is also supported. Uses component weights from one mode of a Parafac, Parafac2, or PCA model as features to tune parameters for one or more classification methods via a k-fold cross-validation procedure. Allows for constraints on different tensor modes. Allows for inclusion of additional features alongside features generated by the component model. Supports penalized logistic regression, support vector machine, random forest, feed-forward neural network, regularized discriminant analysis, and gradient boosting machine. Supports binary and multiclass classification. Predicts class labels or class probabilities and calculates multiple classification performance measures. Uses the 'clue' package to align Parafac or Parafac2 models across data splits in the cross-validation procedure. Calculates classification importance of individual features using permutation feature importance. Implements parallel computing via the 'foreach', 'doParallel', and 'doRNG' packages.
Install
Health
- OK13 OK2026-08-05
- NOTE12 OK, 1 NOTE2026-08-01
- OK14 OK2026-04-15
- ERROR13 OK, 1 ERROR2026-03-30
- OK14 OK2026-03-10
Documentation
- Help pages
- 10 (1 internal)
- Examples that run
- 0%9 never run
- Exported functions with examples
- 100%
- Documented parameters
- not tracked
- Return-value docs
- not tracked
- Help pages citing references
- 90%
Downloads
Repository
Stars over time
Releases over time
Commits over time
4 development-tooling and community-health practices detected across 2 families in the upstream repository
Checks run against github.com/matthewasisgress/cpfa on 2026-10-18.
GitHub Pages site last deployed 2026-09-22 · The repository has a site deploy workflow
Dependencies
Installing cpfa adds 21 packages (12 with compiled code, 19 MB of source tarballs). Heaviest: data.table 5.7 MB, glmnet 2.7 MB, Rcpp 1.8 MB.
Code & Tests
People & History
Show 3 peopleHide 3 people
Pick two releases to compare their code metrics.
- 1.3.3Latest
- 1.3.22026-08-02 · diff ↗
- 1.3.12026-07-13 · diff ↗
- 1.3.02026-06-02 · diff ↗
- 1.2-92026-05-08 · diff ↗
- RR 4.6.0 released · 2026-04-24
- 1.2-82026-04-14 · diff ↗
- 1.2-72026-03-29 · diff ↗
- 1.2-62026-02-06 · diff ↗
- 1.2-52026-01-15 · diff ↗
- 1.2-42025-12-15 · diff ↗
- 1.2-32025-11-02 · diff ↗
- 1.2-22025-10-19 · diff ↗
- 1.2-12025-07-08 · diff ↗
- 1.2-02025-06-11 · diff ↗
- 1.1-92025-05-23 · diff ↗
Show 24 earlier eventsHide 24 earlier events
- 1.1-82025-04-15 · diff ↗
- RR 4.5.0 released · 2025-04-11
- 1.1-72025-02-23 · diff ↗
- 1.1-62024-11-01 · diff ↗
- 1.1-52024-10-01 · diff ↗
- 1.1-42024-04-26 · diff ↗
- RR 4.4.0 released · 2024-04-24
- 1.1-32024-04-07 · diff ↗
- 1.1-22024-02-15 · diff ↗
- 1.1-12024-02-03 · diff ↗
- 1.1-02023-12-02 · diff ↗
- 1.0-92023-11-19 · diff ↗
- 1.0-82023-10-15 · diff ↗
- 1.0-72023-10-07 · diff ↗
- 1.0-62023-09-07 · diff ↗
- 1.0-52023-08-07 · diff ↗
- RR 4.3.0 released · 2023-04-21
- 1.0-42022-06-20 · diff ↗
- 1.0-32022-06-16 · diff ↗
- 1.0-22022-05-16 · diff ↗
- RR 4.2.0 released · 2022-04-22
- 1.0-12022-04-09 · diff ↗
- 1.0-02022-03-09
- RR 4.1.0 released · 2021-05-18
Package metadata
- First published
- 2022-03-09
- Total releases
- 34 / 4 yrs
- License
- GPL (>= 2) OSI
- Minimum R
- ≥ 4.3.0
- Download size
- 351 KB
Cite
Cite this package
Run in R for the authors' preferred citation:
citation("cpfa")This package has no citation file, so citation() returns this entry built from DESCRIPTION.
Cite the R Observatory
For a number measured here: a download total, a coverage figure, an archival date.
From data release v2026-10-21, which the citation names so these numbers can be found later. More on citing and the projects behind them.