DALEX (version 0.4.9)

plot.variable_response_explainer: Plot Marginal Model Explanations (Single Variable Responses)

Description

Function plot.variable_response_explainer plots marginal responses for one or more explainers.

Usage

# S3 method for variable_response_explainer
plot(x, ..., use_facets = FALSE)

Arguments

x

a single variable exlainer produced with the single_variable function

...

other explainers that shall be plotted together

use_facets

logical. If TRUE then separate models are on different facets

Value

a ggplot2 object

Examples

# NOT RUN {
HR$evaluation <- factor(HR$evaluation)

HR_glm_model <- glm(status == "fired"~., data = HR, family = "binomial")
explainer_glm <- explain(HR_glm_model, data = HR)
expl_glm <- variable_response(explainer_glm, "age", "pdp")
plot(expl_glm)

 
# }
# NOT RUN {
library("randomForest")
HR_rf_model <- randomForest(status == "fired" ~., data = HR)
explainer_rf  <- explain(HR_rf_model, data = HR)
expl_rf  <- variable_response(explainer_rf, variable = "age",
                       type = "pdp")
plot(expl_rf)
plot(expl_rf, expl_glm)

# Example for factor variable (with factorMerger)
expl_rf  <- variable_response(explainer_rf, variable =  "evaluation", type = "factor")
plot(expl_rf)

expl_glm  <- variable_response(explainer_glm, variable =  "evaluation", type = "factor")
plot(expl_glm)

# both models
plot(expl_rf, expl_glm)
 
# }
# NOT RUN {
# }