calculate_oscillations {ingredients} | R Documentation |
Calculate Oscillations for Ceteris Paribus Explainer
Description
Oscillations are proxies for local feature importance at the instance level. Find more details in Ceteris Paribus Oscillations Chapter.
Usage
calculate_oscillations(x, sort = TRUE, ...)
Arguments
x |
a ceteris paribus explainer produced with the |
sort |
a logical value. If |
... |
other arguments |
Value
an object of the class ceteris_paribus_oscillations
References
Explanatory Model Analysis. Explore, Explain, and Examine Predictive Models. https://ema.drwhy.ai/
Examples
library("DALEX")
library("ingredients")
titanic_small <- select_sample(titanic_imputed, n = 500, seed = 1313)
# build a model
model_titanic_glm <- glm(survived ~ gender + age + fare,
data = titanic_small, family = "binomial")
explain_titanic_glm <- explain(model_titanic_glm,
data = titanic_small[,-8],
y = titanic_small[,8])
cp_rf <- ceteris_paribus(explain_titanic_glm, titanic_small[1,])
calculate_oscillations(cp_rf)
library("ranger")
apartments_rf_model <- ranger(m2.price ~ construction.year + surface + floor +
no.rooms + district, data = apartments)
explainer_rf <- explain(apartments_rf_model,
data = apartments_test[,-1],
y = apartments_test$m2.price,
label = "ranger forest",
verbose = FALSE)
apartment <- apartments_test[1,]
cp_rf <- ceteris_paribus(explainer_rf, apartment)
calculate_oscillations(cp_rf)
[Package ingredients version 2.3.0 Index]