vi_firm: Variance-based variable importance

Description Usage Arguments Details Value References

View source: R/vi_firm.R

Description

Compute variance-based variable importance using a simple feature importance ranking measure (FIRM) approach; for details, see Greenwell et al. (2018) and Scholbeck et al. (2019).

Usage

1
2
3
4
vi_firm(object, ...)

## Default S3 method:
vi_firm(object, feature_names, FUN = NULL, var_fun = NULL, ice = FALSE, ...)

Arguments

object

A fitted model object (e.g., a "randomForest" object).

...

Additional optional arguments to be passed on to partial.

feature_names

Character string giving the names of the predictor variables (i.e., features) of interest.

FUN

Deprecated. Use var_fun instead.

var_fun

List with two components, "cat" and "con", containing the functions to use to quantify the variability of the feature effects (e.g., partial dependence values) for categorical and continuous features, respectively. If NULL, the standard deviation is used for continuous features. For categorical features, the range statistic is used (i.e., (max - min) / 4). Only applies when method = "firm".

ice

Logical indicating whether or not to estimate feature effects using individual conditional expectation (ICE) curves. Only applies when method = "firm". Default is FALSE. Setting ice = TRUE is preferred whenever strong interaction effects are potentially present.

Details

This approach to computing VI scores is based on quantifying the relative "flatness" of the effect of each feature. Feature effects can be assessed using partial dependence plots (PDPs) or individual conditional expectation (ICE) curves. These approaches are model-agnostic and can be applied to any supervised learning algorithm. By default, relative "flatness" is defined by computing the standard deviation of the y-axis values for each feature effect plot for numeric features; for categorical features, the default is to use range divided by 4. This can be changed via the 'var_fun' argument. See Greenwell et al. (2018) for details and additional examples.

Value

A tidy data frame (i.e., a "tibble" object) with two columns, Variable and Importance, containing the variable name and its associated importance score, respectively.

References

Greenwell, B. M., Boehmke, B. C., and McCarthy, A. J. A Simple and Effective Model-Based Variable Importance Measure. arXiv preprint arXiv:1805.04755 (2018).

Scholbeck, C. A. Scholbeck, and Molnar, C., and Heumann C., and Bischl, B., and Casalicchio, G. Sampling, Intervention, Prediction, Aggregation: A Generalized Framework for Model-Agnostic Interpretations. arXiv preprint arXiv:1904.03959 (2019).


vip documentation built on Dec. 17, 2020, 5:08 p.m.