-
Notifications
You must be signed in to change notification settings - Fork 87
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
fix cat encode #50
fix cat encode #50
Conversation
@@ -56,7 +56,6 @@ def __init__(self): | |||
def fit(self,testx, y=None): | |||
### Do not change this since Rare class combiner requires this test ## | |||
if isinstance(testx, tuple): | |||
y = testx[1] |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
No need in fit .
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
You have made a mistake in below code:
test_result = MLB.fit_transform(train[everycol])
Instead it should be:
test_result = MLB.transform(test[everycol])
Do you see the difference?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Right , my mistake , now fixed
@AutoViML If , tuple return is only used for something relate to rare class . Don't you think two label_encoder are more correct ?
|
@AutoViML Let's think about OOT (out of time) Testing , we usually have 3 datasets ,
Acually there is no need to allow input both train and test in one funtion .
Just call same funtion again if new data comming .Or do you have another consideration ? |
At the moment let's close this thread with this change. If you feel another change is needed elsewhere, you can open another pull request. Okay? |
OK, I won't make pr in recently I think , just gona make some discussion :) |
No description provided.