混淆矩阵
Predict | |||
Positive | Negative | ||
Real | Positive | TP | FN |
Negative | FP | TN |
准确率
准确率(Accuracy)是指有在所有的判断中有多少判断正确的(即正类被预测为正类,负类被预测为负类)
a
c
c
u
r
a
c
y
=
T
P
+
T
N
T
P
+
F
P
+
F
N
+
T
N
accuracy=\frac{TP+TN}{TP+FP+FN+TN}
accuracy=TP+FP+FN+TNTP+TN
精确率
精确率(Precision)是指在预测为正类的样本中有多少为真正的正类
P
r
e
c
i
s
i
o
n
=
T
P
T
P
+
F
P
Precision=\frac{TP}{TP+FP}
Precision=TP+FPTP
召回率
召回率(Recall)是指正类样本中有多少被预测为正类
R
e
c
a
l
l
=
T
P
T
P
+
F
N
Recall=\frac{TP}{TP+FN}
Recall=TP+FNTP
特异率
特异率(Specificity)是指负类样本中有多少被预测为负类
S
p
e
c
i
f
i
c
i
t
y
=
T
N
T
N
+
F
P
Specificity=\frac{TN}{TN + FP}
Specificity=TN+FPTN
F-Measure
有时精确率与召回率是矛盾的,F-Measure是精确率和召回率的加权调和平均
F
α
−
M
e
a
s
u
r
e
=
(
α
2
+
1
)
×
P
r
e
c
i
s
i
o
n
×
R
e
c
a
l
l
α
2
×
(
P
r
e
c
i
s
i
o
n
+
R
e
c
a
l
l
)
F_\alpha-Measure=\frac{(\alpha^2+1)\times Precision \times Recall}{\alpha^2 \times (Precision + Recall)}
Fα−Measure=α2×(Precision+Recall)(α2+1)×Precision×Recall
当
α
=
1
\alpha=1
α=1时,即为最常见的F1-Measure
F
1
=
2
×
P
r
e
c
i
s
i
o
n
×
R
e
c
a
l
l
P
r
e
c
i
s
i
o
n
+
R
e
c
a
l
l
F1=\frac{2 \times Precision \times Recall}{Precision + Recall}
F1=Precision+Recall2×Precision×Recall
马修斯相关系数
马修斯相关系数(Matthews Correlation Coefficient)本质上是一个描述实际分类与预测分类之间的相关系数,它的取值范围为
[
0
,
1
]
[0,1]
[0,1],取值为1时表示对受试对象的完美预测,取值为0时表示预测的结果还不如随机预测的结果,-1是指预测分类和实际分类完全不一致。
M
C
C
=
T
P
×
T
N
−
F
P
×
F
N
(
T
P
+
F
P
)
×
(
T
P
+
F
N
)
×
(
T
N
+
F
P
)
×
(
T
N
+
F
N
)
MCC=\frac{TP \times TN - FP \times FN}{\sqrt{(TP+FP) \times (TP+FN) \times (TN+FP) \times (TN+FN)}}
MCC=(TP+FP)×(TP+FN)×(TN+FP)×(TN+FN)TP×TN−FP×FN