ROC与AUC
http://alexkong.net/2013/06/introduction-to-auc-and-roc/
机器学习 F1-Score, recall, precision
https://blog.csdn.net/matrix_space/article/details/50384518
True positive rate (or sensitivity):
TPR=TP/(TP+FN)
T
P
R
=
T
P
/
(
T
P
+
F
N
)
False positive rate:
FPR=FP/(FP+TN)
F
P
R
=
F
P
/
(
F
P
+
T
N
)
True negative rate (or specificity):
TNR=TN/(FP+TN)
T
N
R
=
T
N
/
(
F
P
+
T
N
)
What is the difference between a ROC curve and a precision-recall curve? When should I use each?
[PDF]The Relationship Between Precision-Recall and ROC Curves
精确率、召回率、F1 值、ROC、AUC 各自的优缺点是什么?