R/print_ceteris_paribus.R
print.ceteris_paribus_explainer.RdPrints Individual Variable Explainer Summary
# S3 method for ceteris_paribus_explainer
print(x, ...)an individual variable profile explainer produced with the ceteris_paribus() function
other arguments that will be passed to head()
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])
#> Preparation of a new explainer is initiated
#> -> model label : lm ( default )
#> -> data : 500 rows 7 cols
#> -> target variable : 500 values
#> -> predict function : yhat.glm will be used ( default )
#> -> predicted values : No value for predict function target column. ( default )
#> -> model_info : package stats , ver. 4.2.2 , task classification ( default )
#> -> predicted values : numerical, min = 0.0795294 , mean = 0.302 , max = 0.9859411
#> -> residual function : difference between y and yhat ( default )
#> -> residuals : numerical, min = -0.8204691 , mean = 8.796651e-12 , max = 0.8567173
#> A new explainer has been created!
cp_glm <- ceteris_paribus(explain_titanic_glm, titanic_small[1,])
cp_glm
#> Top profiles :
#> gender age class embarked fare sibsp parch _yhat_ _vname_ _ids_
#> 515 female 45.00 2nd Southampton 10.1 0 0 0.5595687 gender 515
#> 515.1 male 45.00 2nd Southampton 10.1 0 0 0.1448038 gender 515
#> 5151 male 0.75 2nd Southampton 10.1 0 0 0.3135247 age 515
#> 515.110 male 2.99 2nd Southampton 10.1 0 0 0.3028164 age 515
#> 515.2 male 4.98 2nd Southampton 10.1 0 0 0.2934793 age 515
#> 515.3 male 7.00 2nd Southampton 10.1 0 0 0.2841757 age 515
#> _label_
#> 515 lm
#> 515.1 lm
#> 5151 lm
#> 515.110 lm
#> 515.2 lm
#> 515.3 lm
#>
#>
#> Top observations:
#> gender age class embarked fare sibsp parch _yhat_ _label_ _ids_
#> 515 male 45 2nd Southampton 10.1 0 0 0.1448038 lm 1
# \donttest{
library("ranger")
apartments_rf_model <- ranger(m2.price ~., data = apartments)
explainer_rf <- explain(apartments_rf_model,
data = apartments_test[,-1],
y = apartments_test[,1],
label = "ranger forest",
verbose = FALSE)
apartments_small <- select_sample(apartments_test, 10)
cp_rf <- ceteris_paribus(explainer_rf, apartments_small)
cp_rf
#> Top profiles :
#> construction.year surface floor no.rooms district _yhat_
#> 9707 1920 98 3 3 Srodmiescie 4880.584
#> 9707.1 1921 98 3 3 Srodmiescie 4890.136
#> 9707.2 1922 98 3 3 Srodmiescie 4897.864
#> 9707.3 1923 98 3 3 Srodmiescie 4866.403
#> 9707.4 1924 98 3 3 Srodmiescie 4836.051
#> 9707.5 1925 98 3 3 Srodmiescie 4833.932
#> _vname_ _ids_ _label_
#> 9707 construction.year 9707 ranger forest
#> 9707.1 construction.year 9707 ranger forest
#> 9707.2 construction.year 9707 ranger forest
#> 9707.3 construction.year 9707 ranger forest
#> 9707.4 construction.year 9707 ranger forest
#> 9707.5 construction.year 9707 ranger forest
#>
#>
#> Top observations:
#> construction.year surface floor no.rooms district _yhat_
#> 9707 2008 98 3 3 Srodmiescie 4739.858
#> 9796 1932 110 10 4 Ursus 2922.596
#> 9644 1980 73 10 2 Mokotow 3703.307
#> 7567 1940 63 8 3 Praga 3271.446
#> 4090 1955 105 3 3 Ochota 3594.067
#> 8594 1999 36 9 2 Ursus 3695.560
#> _label_ _ids_
#> 9707 ranger forest 1
#> 9796 ranger forest 2
#> 9644 ranger forest 3
#> 7567 ranger forest 4
#> 4090 ranger forest 5
#> 8594 ranger forest 6
# }