举个例子:
-
Accuracy(准确率): Overall, how often is the classifier correct?
Accuracy = (TP+TN)/(P+N)= (TP+TN)/(TP+TN+FP+FN)
(TP+TN)/total = (100+50)/165 = 0.91
真“我爱你”+真“我不爱你”: 所有爱你和不爱你的人里,有多少人讲的是真心话
地震预测:真的无地震,放心 + 真的有地震,提前转移
嫌疑人定罪:真的有罪 定罪 + 真的无罪 释放
病理检测:真的有病 住院 + 真的没病 回家 -
Misclassification Rate(Error Rate 错误率): Overall, how often is it wrong?
Error Rate = 1 – Accuracy = (FP+FN)/(P+N)=(FP+FN)/(TP+TN+FP+FN)
(FP+FN)/total = (10+5)/165 = 0.09
equivalent to 1 minus Accuracy
also known as “Error Rate”
伪“我不爱你”+伪“我爱