注册
登录
Docker
>>
explaining-black-boxes
>>
返回
项目作者：
bipinkc19
项目描述 ：
Explaining complex ML models
高级语言：
Jupyter Notebook
项目主页：
项目地址:
git://github.com/bipinkc19/explaining-black-boxes.git
创建时间：
2019-09-02T15:23:05Z
项目社区：
https://github.com/bipinkc19/explaining-black-boxes
开源协议：
下载
Explaining black boxes
Using SHAP (SHapely Additive exPlanation)
Random Forest
Overall weight
Shap values of all the records representing which variable play what kind of role in predicting the output. Eg: Sex when High (Male) playe a negative role in survival but female have very high chances of survival spread across other factors too
Per prediction
Using eli5 (Explain like I’m 5)
Logistic Regression
Overall weight
Per prediction
Random Forest
Overall weight
Per prediction
Lime
Per prediction as it is local
