Skip to content
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: SMOTENC should use half of the median of the std. dev. #491

Merged
merged 1 commit into from Oct 21, 2018

Conversation

@glemaitre
Copy link
Member

@glemaitre glemaitre commented Oct 21, 2018

bug fix in SMOTE-NC

@pep8speaks
Copy link

@pep8speaks pep8speaks commented Oct 21, 2018

Hello @glemaitre! Thanks for submitting the PR.

@glemaitre glemaitre merged commit b424cf7 into scikit-learn-contrib:master Oct 21, 2018
0 of 4 checks passed
0 of 4 checks passed
LGTM analysis: Python Running analyses for revisions
Details
ci/circleci: python3 CircleCI is running your tests
Details
continuous-integration/appveyor/pr Waiting for AppVeyor build to complete
Details
continuous-integration/travis-ci/pr The Travis CI build is in progress
Details
@Eugene1518
Copy link

@Eugene1518 Eugene1518 commented Jul 7, 2020

Hi. I am confused with the way of SmoteNC solving categorical variables. Could you tell me the difference between using median of the std. dev, and using one hot encoder to transform categorical feature into continuous feature with Smote. If I use one hot encoder with Smote instead of SmoteNC, what's the drawback? Thanks very much

@glemaitre
Copy link
Member Author

@glemaitre glemaitre commented Jul 8, 2020

It is the way this is proposed in the original paper to which you should refer for more detailed explanations. Be aware that OneHotEncoder does not transform a categorical feature into a continuous feature but rather encodes a categorical feature into features that do not impose any order.

@Eugene1518
Copy link

@Eugene1518 Eugene1518 commented Jul 10, 2020

thanks~

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Linked issues

Successfully merging this pull request may close these issues.

None yet

3 participants