克服机器学习中的混杂和协变量
confounds的Python项目详细描述
愿景/目标
这个包的高级目标是开发高质量的库来克服ml应用程序中的混淆和协变量。通过征服,我们指的是方法和工具
- visualize and establish the presence of confounds (e.g. quantifying confound-to-target relationships),
- offer solutions to handle them appropriately via correction or removal etc, and
- analyze the effect of the deconfounding methods in the processed data (e.g. ability to check if they worked at all, or if they introduced new or unwanted biases etc).
方法
- Residualize (e.g. via regression)
- Augment (include confounds as predictors)
- Harmonize (correct batch effects via rescaling or normalization etc)
- Stratify (sub- or resampling procedures to minimize confounding)
- Utilities (Goals 1 and 3)
主页:https://github.com/raamana/confounds 作者:Pradeep Reddy Raamana 作者电子邮件:raamana@gmail.com 许可证:apache软件许可证2.0 描述:克服机器学习中的混杂和协变量 关键词:混淆 平台:未知 分类器:开发状态::2-pre-alpha 分类器:目标受众::开发人员 分类器:license::osi approved::apache软件许可证 分类器:自然语言:英语 分类器:编程语言::python::2 分类器:编程语言::python::2.7 分类器:编程语言::python::3 分类器:编程语言::python::3.4 分类器:编程语言::python::3.5 分类器:编程语言::python::3.6 分类器:编程语言::python::3.7