search

Optimization-AI / LibAUC

LibAUC: A Deep Learning Library for X-Risk Optimization
https://libauc.org/
MIT License
273 stars 37 forks source link

Label in CheXpert dataset. #47

Closed mxadorable closed 6 months ago

mxadorable commented 6 months ago

Hi, thank you for share your great work. Could you please explain why the labels of 'Edema', 'Atelectasis' are replaced in this way? if col in ['Edema', 'Atelectasis']: self.df[col].replace(-1, 1, inplace=True)

As far as I know, in the chexpert labels, -1 represents negative, and 1 represent positive. I see that some diseases replace -1 with 0, but why the two diseases are different?

Thank you so much!

optmai commented 6 months ago

Thank you for your interest! Please let us know if you have additional questions.