Package index
-
aggregate_results() - Aggregate Nested Cross-Validation Results for Classification or Survival Tasks
-
calculate_accuracy() - Calculates accuracy values from prediction
-
calculate_auprc() - Calculate AUC from Precision-Recall Curve
-
calculate_auroc() - Calculate AUC from ROC Curve
-
calculate_confusion_values() - Calculate confusion values
-
calculate_f1() - Compute F1 Score
-
calculate_feature_importance_stacking() - Compute Weighted Feature Importance from Base Models and Meta-Learner for Stacking Models
-
calculate_mcc() - Compute Matthews Correlation Coefficient (MCC) Score
-
calculate_precision() - Calculate precision values
-
calculate_recall() - Calculate recall values
-
choose_base_models() - Choose Top Base Models for Stacking Based on Accuracy or AUC Scores
-
compute_boruta() - Compute Boruta algorithm
-
compute_custom_k_fold_CV() - Train and evaluate machine learning models on previously constructed k folds
-
compute_cv_AUC() - Compute Cross-Validated AUC Values for Machine Learning Models
-
compute_cv_CINDEX() - Summarize and Visualize C-index Results from Survival Model Cross-Validation
-
compute_cv_accuracy() - Compute Cross-Validation Accuracy for ML Models
-
compute_features.ML() - Train and evaluate machine learning models for classification or survival analysis
-
compute_features.training.ML() - Train machine learning or survival models with optional stacking and custom cross-validation
-
compute_k_fold_CV() - Perform repeated stratified k-fold cross-validation for model training and tuning
-
compute_k_fold_CV_survival() - Nested Cross-Validation for Survival Models with Optional Custom Fold Construction
-
compute_ml_survival() - Train and Evaluate a Survival Model
-
compute_prediction() - Compute Prediction Metrics for a Trained Machine Learning Model
-
compute_variable.importance() - Compute variable importance using SHAP values
-
deconvolution - Deconvolution matrix
-
feature.selection.boruta() - Compute Feature Selection Using Repeated Boruta Algorithm
-
find.ML.models() - Extract ML models from a directory based on specific AUC score
-
get_curves() - Get performance curves
-
get_default_hyperparams() - Get default hyperparameter grids for supported survival models
-
get_pooled_boxplots() - Plot Pooled AUROC and AUPRC Boxplots Across Multiple Folders
-
get_pooled_roc_curves() - Plot Pooled AUROC and AUPRC Performance Curves
-
get_sensitivity_specificity() - Calculate Sensitivity and Specificity Values
-
merge_boruta_results() - Merge Boruta Results
-
plot_shap_values() - Plot SHAP values
-
plot_survival_performance() - Plot and save survival performance of a model on test data
-
predict_and_evaluate_survival() - Predict and Evaluate Survival Model Performance
-
preprocess_features() - Preprocess Features for Machine Learning
-
raw.counts - Raw counts
-
traitData - Clinical data
-
wrapper_train_best_hyperparams_classification() - Train model with optimized hyperparameters for classification tasks
-
wrapper_train_best_hyperparams_survival() - Train the Best Survival Model Using Optimized Hyperparameters