All functions

pull_importances()

Pull feature importances from a parsnip fitted model

recipeselectors

recipeselectors: A collection of steps for feature selection to use with the 'recipes' package

step_select_boruta() tidy(<step_select_boruta>)

Feature selection step using Boruta

step_select_carscore() tidy(<step_select_carscore>)

Information gain feature selection step

step_select_forests() tidy(<step_select_forests>)

Feature selection step using a random forest feature importance scores

step_select_infgain() tidy(<step_select_infgain>)

Information gain feature selection step

step_select_linear() tidy(<step_select_linear>)

Feature selection step using the magnitude of a linear models' coefficients

step_select_mrmr() tidy(<step_select_mrmr>)

Apply minimum Redundancy Maximum Relevance Feature Selection (mRMR)

step_select_roc() tidy(<step_select_roc>)

Filter Numeric Predictors using ROC Curve

step_select_tree() tidy(<step_select_tree>)

Feature selection step using a decision tree importance scores

step_select_vip() tidy(<step_select_vip>)

Feature selection step using a model's feature importance scores or coefficients

step_select_xtab() tidy(<step_select_xtab>)

Filter Categorical Predictors using Contingency Tables

top_p()

Parameter functions for feature selection recipes