Lecture 9: Classification metrics

Metrics for classification

Slides

View slides in full screen

Outline

• Issues with using accuracy
• Components of a confusion matrix
• Precision, recall, and f1-score and use them to evaluate different classifiers
• Precision-recall curves
• Average precision score
• ROC curves and ROC AUC using scikit-learn
• Dealing with class imbalance
• Model performance on specific groups in a dataset.