I'm new and have searched many questions about this problem in this stack, but those answers aren't clear enough for me.
The point is the area under PR curve of my binary classes is the same as the version I took SMOTE.
Here is my pseudo code:
X_train, y_train, X_test, y_test = split(data) smote_X_train, smote_y_train = SMOTE(X_train, y_train) myclassifier.fit(smote_X_train, smote_y_train) myclassifire.predit(X_test)
And here is the result that I've got:
Yellow - SMOTE
Blue - Imbalanced classes
Should yellow increase, right? This confuses me.
I guess the possible causes of this is either an algorithm or features. Am I right?