DALEX (version 0.3.0)

variable_importance: Loss from Variable Dropout

Description

Loss from Variable Dropout

Usage

variable_importance(explainer, loss_function = loss_sum_of_squares, ...,
  type = "raw", n_sample = 1000)

Arguments

explainer

a model to be explained, preprocessed by the 'explain' function

loss_function

a function thet will be used to assess variable importance

...

other parameters

type

character, type of transformation that should be applied for dropout loss. 'raw' results raw drop lossess, 'ratio' returns drop_loss/drop_loss_full_model while 'difference' returns drop_loss - drop_loss_full_model

n_sample

number of observations that should be sampled for calculation of variable importance. If negative then variable importance will be calculated on whole dataset (no sampling).

Value

An object of the class 'variable_leverage_explainer'. It's a data frame with calculated average response.

References

Predictive Models: Visual Exploration, Explanation and Debugging https://pbiecek.github.io/PM_VEE/

Examples

# NOT RUN {
 
# }
# NOT RUN {
library("breakDown")
library("randomForest")
HR_rf_model <- randomForest(status == "fired"~., data = HR, ntree = 100)
explainer_rf  <- explain(HR_rf_model, data = HR, y = HR$status == "fired")
vd_rf <- variable_importance(explainer_rf, type = "raw")
vd_rf

HR_glm_model <- glm(status == "fired"~., data = HR, family = "binomial")
explainer_glm <- explain(HR_glm_model, data = HR, y = HR$status == "fired")
logit <- function(x) exp(x)/(1+exp(x))
vd_glm <- variable_importance(explainer_glm, type = "raw",
                        loss_function = function(observed, predicted)
                                     sum((observed - logit(predicted))^2))
vd_glm

library("xgboost")
model_martix_train <- model.matrix(status == "fired" ~ .-1, HR)
data_train <- xgb.DMatrix(model_martix_train, label = HR$status == "fired")
param <- list(max_depth = 2, eta = 1, silent = 1, nthread = 2,
              objective = "binary:logistic", eval_metric = "auc")
HR_xgb_model <- xgb.train(param, data_train, nrounds = 50)
explainer_xgb <- explain(HR_xgb_model, data = model_martix_train,
                     y = HR$status == "fired", label = "xgboost")
vd_xgb <- variable_importance(explainer_xgb, type = "raw")
vd_xgb
plot(vd_xgb)
 
# }
# NOT RUN {
# }