Model Evaluation with Weighted Threshold Optimization

"mewto" (Model Evaluation with Weighted Threshold Optimization) is an R package that allows users to experiment with different thresholds for classification of prediction results in the case of binary classification problems and visualize various model evaluation metrics, confusion matrices and the ROC curve. It also allows users to calculate the optimal threshold based on a weighted evaluation criterion.

mewto（全称Model Evaluation with Weighted Threshold Optimization，即加权阈值优化模型评估工具）是一款R语言包，可支持用户在二分类（binary classification）任务中针对预测结果的分类环节尝试不同阈值，并可视化各类模型评估指标（model evaluation metrics）、混淆矩阵（confusion matrix）与ROC曲线（ROC curve）。此外，该工具还可基于加权评估准则计算最优阈值。