8000 BUG: linear model inputs are not normalized when fit_intercept=False · Issue #5799 · scikit-learn/scikit-learn · GitHub
[go: up one dir, main page]

Skip to content
8000

BUG: linear model inputs are not normalized when fit_intercept=False #5799

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

Closed
giorgiop opened this issue Nov 12, 2015 · 2 comments
Closed

BUG: linear model inputs are not normalized when fit_intercept=False #5799

giorgiop opened this issue Nov 12, 2015 · 2 comments

Comments

@giorgiop
Copy link
Contributor

From #5357 as a separated issue. The problem in the code is here: normalize is not used in the branch of fit_intercept=False.

Proposed strategy, rielaborated from a discussion with @agramfort:

  • write test that would fail
  • add a boolean option to the helper for centering data, such that it can be used to normalize also when fit_intercept=False
  • use this option to pass the test
  • raise a deprecation warning when fit_intercept=False and normalize=True, suggesting to switch to normalize=False to obtain the same result. In 2 releases time, the behaviour with those options will be changed
  • fix the faulty behaviour in 2 releases

Feedback appreciated 🍻

@agramfort
Copy link
Member
agramfort commented Nov 12, 2015 via email

@cmarmo
Copy link
Contributor
cmarmo commented Dec 9, 2021

I think this is related to #3020 and can be closed now.
@agramfort do you mind reopening if this is not the case? Thanks!

@cmarmo cmarmo closed this as completed Dec 9, 2021
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
None yet
Development

No branches or pull requests

3 participants
0