# load packages and data
library(mlr)
library(DALEXtra)
library(modelStudio)

data <- DALEX::apartments

# split the data
index <- sample(1:nrow(data), 0.7*nrow(data))
train <- data[index,]
test <- data[-index,]

# fit a model
task <- makeRegrTask(id = "apartments", data = train, target = "m2.price")
learner <- makeLearner("regr.ranger", predict.type = "response")
model <- train(learner, task)

# create an explainer for the model
explainer <- explain_mlr(model,
                         data = test,
                         y = test$m2.price,
                         label = "mlr")

# pick observations
new_observation <- test[1:2,]
rownames(new_observation) <- c("id1", "id2")

# make a studio for the model
modelStudio(explainer, new_observation)

# load packages and data
library(xgboost)
library(DALEX)
library(modelStudio)

data <- DALEX::titanic_imputed

# split the data
index <- sample(1:nrow(data), 0.7*nrow(data))
train <- data[index,]
test <- data[-index,]

train_matrix <- model.matrix(survived ~.-1, train)
test_matrix <- model.matrix(survived ~.-1, test)

# fit a model
xgb_matrix <- xgb.DMatrix(train_matrix, label = train$survived)
params <- list(max_depth = 3, objective = "binary:logistic", eval_metric = "auc")
model <- xgb.train(params, xgb_matrix, nrounds = 500)

# create an explainer for the model
explainer <- explain(model,
                     data = test_matrix,
                     y = test$survived,
                     label = "xgboost")

# pick observations
new_observation <- test_matrix[1:2, , drop=FALSE]
rownames(new_observation) <- c("id1", "id2")

# make a studio for the model
modelStudio(explainer, new_observation,
            options = ms_options(margin_left = 140))

First, use dalex in Python:

# load packages and data
import dalex as dx
from sklearn.model_selection import train_test_split
from sklearn.pipeline import Pipeline
from sklearn.preprocessing import StandardScaler
from sklearn.svm import SVR
from numpy import log

data = dx.datasets.load_fifa()
X = data.drop(columns=['overall', 'potential', 'value_eur', 'wage_eur', 'nationality'], axis=1)
y = log(data.value_eur)

# split the data
X_train, X_test, y_train, y_test = train_test_split(X, y)

# fit a pipeline model
model = Pipeline([('scale', StandardScaler()), ('svm', SVR())])
model.fit(X_train, y_train)

# create an explainer for the model
explainer = dx.Explainer(model, data=X_test, y=y_test, label='scikit-learn')

# pack the explainer into a pickle file
explainer.dump(open('explainer_scikitlearn.pickle', 'wb'))

Then, use modelStudio in R:

# load the explainer from the pickle file
library(reticulate)
explainer <- py_load_object("explainer_scikitlearn.pickle", pickle = "pickle")

# make a studio for the model
library(modelStudio)
modelStudio(explainer, B = 5,
            options = ms_options(margin_left = 160))

First, use dalex in Python:

# load packages and data
import dalex as dx
from sklearn.model_selection import train_test_split
from sklearn.pipeline import Pipeline
from sklearn.preprocessing import StandardScaler, OneHotEncoder
from sklearn.impute import SimpleImputer
from sklearn.compose import ColumnTransformer
from lightgbm import LGBMClassifier

data = dx.datasets.load_titanic()
X = data.drop(columns='survived')
y = data.survived

# split the data
X_train, X_test, y_train, y_test = train_test_split(X, y)

# fit a pipeline model
numerical_features = ['age', 'fare', 'sibsp', 'parch']
numerical_transformer = Pipeline(
  steps=[
    ('imputer', SimpleImputer(strategy='median')),
    ('scaler', StandardScaler())
  ]
)
categorical_features = ['gender', 'class', 'embarked']
categorical_transformer = Pipeline(
  steps=[
    ('imputer', SimpleImputer(strategy='constant', fill_value='missing')),
    ('onehot', OneHotEncoder(handle_unknown='ignore'))
  ]
)

preprocessor = ColumnTransformer(
  transformers=[
    ('num', numerical_transformer, numerical_features),
    ('cat', categorical_transformer, categorical_features)
  ]
)

classifier = LGBMClassifier(n_estimators=300)

model = Pipeline(
  steps=[
    ('preprocessor', preprocessor),
    ('classifier', classifier)
  ]
)
model.fit(X_train, y_train)

# create an explainer for the model
explainer = dx.Explainer(model, data=X_test, y=y_test, label='lightgbm')

# pack the explainer into a pickle file
explainer.dump(open('explainer_lightgbm.pickle', 'wb')) 

Then, use modelStudio in R:

# load the explainer from the pickle file
library(reticulate)
explainer <- py_load_object("explainer_lightgbm.pickle", pickle = "pickle")

# make a studio for the model
library(modelStudio)
modelStudio(explainer)