Add. Classification

pull/2/head
benjas 5 years ago
parent fd055ed939
commit 16f97323e9

@ -171,3 +171,41 @@ Generative model and discriminant model
判别方法:![1617695090214](assets/1617695090214.png) 判别方法:![1617695090214](assets/1617695090214.png)
例子:如何知道女孩子的姓名呢?
生成方法:我要是把她爸妈建模出来,直接问她爸妈不就行了吗?
判别方法:她叫小红的概率是多少?她叫小刘的概率是多少?
### 分类问题
Classification
TP——将正类预测为正类数
FN——将正类预测为负类数
FP——将负类预测为正类数
TN——将负类预测为负类数
精确率:预测为正类的样本中有多少分对了;
![1617695936634](assets/1617695936634.png)
召回率:在实际正类中,有多少正类被模型发现了
![1617695964734](assets/1617695964734.png)
F1值
![1617695979979](assets/1617695979979.png)
![1617695988131](assets/1617695988131.png)
一般会配合一个混淆矩阵:
![1617696087388](assets/1617696087388.png)

Binary file not shown.

After

Width:  |  Height:  |  Size: 11 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 12 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 11 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 18 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 124 KiB

Loading…
Cancel
Save