build.grid: Build grid used for weights in distilled surrogate model

In forestry-labs/interpretability_sandbox: Model Distillation and Interpretability Methods for Machine Learning Models

Build grid used for weights in distilled surrogate model

Description

A dataframe storing the true predictions and the PDP predictions

Usage

build.grid(object, feat.ind = 1:length(object$features))

Arguments

object	The Interpreter object
feat.ind	The indices of the features in the Interpreter's features that we want to include as PDP functions in the distilled model.

Value

A dataframe used to find weights in regression (one-hot encoding for categorical features)

Note

This function is mainly used as a subroutine for the distill function. We include this as a public function to allow users to create their own weights and surrogate functions outside of our implemented method.

forestry-labs/interpretability_sandbox documentation built on April 26, 2023, 4:14 p.m.