| define_sklearn_modules {GeneSelectR} | R Documentation |
Define Python modules and scikit-learn submodules
Description
Define Python modules and scikit-learn submodules
Usage
define_sklearn_modules(python_modules)
Arguments
python_modules |
A list containing imported Python modules. |
Value
A list containing the initialized Python modules and scikit-learn submodules, each as a separate list element. The list includes:
@field preprocessing: Module for data preprocessing.
@field model_selection: Module for model selection and evaluation.
@field feature_selection: Module for feature selection methods.
@field ensemble: Module for ensemble methods.
@field pipeline: scikit-learn pipeline object.
@field forest: Random Forest classifier for feature selection.
@field randomized_grid: Randomized grid search for hyperparameter tuning.
@field grid: Grid search for hyperparameter tuning.
@field bayesianCV: Bayesian optimization using cross-validation.
@field lasso: Lasso method for feature selection.
@field univariate: Univariate feature selection method.
@field select_model: Model-based feature selection method.
@field GradBoost: Gradient Boosting classifier.
Examples
required_modules <- c("sklearn", "boruta")
modules_available <- sapply(required_modules, reticulate::py_module_available)
if (all(modules_available)) {
# All required Python modules are available
# Define scikit-learn modules and submodules
sklearn_modules <- define_sklearn_modules()
# Access different modules and submodules
preprocessing_module <- sklearn_modules$preprocessing
model_selection_module <- sklearn_modules$model_selection
feature_selection_module <- sklearn_modules$feature_selection
ensemble_module <- sklearn_modules$ensemble
# Additional code to explore each module as needed in your analysis
} else {
unavailable_modules <- names(modules_available[!modules_available])
message(paste(
"Required Python modules not available:",
paste(unavailable_modules, collapse=', '), ". Skipping example."))
}