Investigate First Order Interactions — first_order_interaction

This function investigates all two-way interactions in the forest by measuring how many times splits of one variable is nested in splits of another variable.

Usage

first_order_interaction_investigator(
  yarf_mod,
  plot = TRUE,
  only_non_self_interactions = FALSE,
  num_var_plot = 50
)

Arguments

yarf_mod: The YARF model in which to query
plot: This controls whether or not the function plots the interaction strengths. If so, it plots in order of strength from highest to lowest. Default is TRUE.
only_non_self_interactions: Should we only show interactions between different variables? Default is FALSE to show interactions of variables with themselves.
num_var_plot: How many first order interactions to plot? All would be p-choose-2 which can be large. The default is 50. Use Inf to plot all p-choose-2.

Value

A list with two components: (1) interaction_counts is a p x p sized matrix of interaction counts between the variables and (2) sorted_counts is a vector of the top interactions in order. Returns invisibly.

Author

Adam Kapelner