This generic function let user extract base information about model. The function returns a named list of class model_info that contain about package of model, version and task type. For wrappers like mlr or caret both, package and wrapper information are stored

# S3 method for WrappedModel
model_info(model, is_multiclass = FALSE, ...)

# S3 method for H2ORegressionModel
model_info(model, is_multiclass = FALSE, ...)

# S3 method for H2OBinomialModel
model_info(model, is_multiclass = FALSE, ...)

# S3 method for H2OMultinomialModel
model_info(model, is_multiclass = FALSE, ...)

# S3 method for scikitlearn_model
model_info(model, is_multiclass = FALSE, ...)

# S3 method for keras
model_info(model, is_multiclass = FALSE, ...)

# S3 method for LearnerRegr
model_info(model, is_multiclass = FALSE, ...)

# S3 method for LearnerClassif
model_info(model, is_multiclass = FALSE, ...)

# S3 method for GraphLearner
model_info(model, is_multiclass = FALSE, ...)

# S3 method for xgb.Booster
model_info(model, is_multiclass = FALSE, ...)

# S3 method for workflow
model_info(model, is_multiclass = FALSE, ...)

# S3 method for model_stack
model_info(model, is_multiclass = FALSE, ...)

Arguments

model

- model object

is_multiclass

- if TRUE and task is classification, then multitask classification is set. Else is omitted. If model_info was executed withing explain function. DALEX will recognize subtype on it's own. @param is_multiclass

...

- another arguments

Value

A named list of class model_info

Details

Currently supported packages are:

  • mlr models created with mlr package

  • h2o models created with h2o package

  • scikit-learn models created with scikit-learn Python library and accessed via reticulate

  • keras models created with keras Python library and accessed via reticulate

  • mlr3 models created with mlr3 package

  • xgboost models created with xgboost package

  • tidymodels models created with tidymodels package