Package index • featR

Working with results

Every selection function returns an fs_result. These are its accessor and display methods.

selected(): Extract the selected features from a featR result
print(<fs_result>): Print a featR result
summary(<fs_result>): Summarize a featR result

Filters

Score each feature without fitting a predictive model. Cheap, and suitable for a first cut on wide data, but they judge features one at a time.

fs_supervised(): Supervised Filter-Based Feature Selection
fs_unsupervised(): Unsupervised Filter-Based Feature Selection
fs_chi(): Chi-square feature selection for categorical features
fs_infogain(): Feature Selection via Information Gain
fs_correlation(): Correlation-based feature selection

Regularization and embedded importance

One model fit whose own structure names the survivors.

fs_lasso(): Lasso Feature Selection with Cross-Validation
fs_elastic(): Elastic Net Feature Selection and Model Training
fs_randomforest(): Random forest importance and held-out evaluation
fs_mars(): MARS (earth) feature selection

Wrappers

Refit a model over candidate subsets. The most expensive family, and the one most closely tied to the model you intend to use.

fs_recursivefeature(): Recursive feature elimination with held-out evaluation
fs_svm(): Train and evaluate an SVM, with optional SVM-RFE feature selection
fs_boruta(): Feature selection using Boruta
fs_stepwise(): Stepwise linear-regression feature selection via AIC
fs_bayes(): Bayesian feature selection for model optimization

Dimensionality reduction

Replace the original columns with new components instead of keeping a subset. These return their own list rather than an fs_result.

fs_pca(): Principal component analysis with tidy results and optional plotting
fs_svd(): Singular Value Decomposition with Optional Scaling and Truncation

Package

featR featR-package: featR: A Unified Toolkit for Feature Selection