I don't think that we rescale the sample_weight and therefore the results should be different. On Fri, 24 Apr 2020 at 12:41, Francesco basciani <faf96@hotmail.it> wrote:

Hi, i have a question regarding the class weights in SVC. I have an imbalanced binary classification problem. In my case the ratio between the positive class and the negative class is 4:1. I just want to know if setting class weight to:

class_weight = {1: 0.25, 0: 1} is the same to setting it to:

class_weight = {1: 1, 0: 4}.

Because in my case i obtain differents results using the two definition of the class weight

Inviato da Posta <https://go.microsoft.com/fwlink/?LinkId=550986> per Windows 10

_______________________________________________ scikit-learn mailing list scikit-learn@python.org https://mail.python.org/mailman/listinfo/scikit-learn

-- Guillaume Lemaitre Scikit-learn @ Inria Foundation https://glemaitre.github.io/