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

[MRG+2] FIX make StandardScaler & scale more numerically stable #4436

Merged
merged 3 commits into from
Mar 23, 2015

Conversation

ogrisel
Copy link
Member

@ogrisel ogrisel commented Mar 23, 2015

This is a rebased and fixed version of #3747. I will merge if travis is still green.

Detect common numerical stability problems in the standardization
routines and try simple mitigation strategies while alos issuing
a warning.
@ogrisel
Copy link
Member Author

ogrisel commented Mar 23, 2015

Alright so the numerical stability issues seems to depend on either the version of numpy or Python... We will have to relax the tests...

@landscape-bot
Copy link

Code Health
Repository health increased by 0.00% when pulling cbe8053 on ogrisel:rebased-pr-3747 into ad26ae4 on scikit-learn:master.

1 similar comment
@landscape-bot
Copy link

Code Health
Repository health increased by 0.00% when pulling cbe8053 on ogrisel:rebased-pr-3747 into ad26ae4 on scikit-learn:master.

@landscape-bot
Copy link

Code Health
Repository health increased by 0.00% when pulling b596dfc on ogrisel:rebased-pr-3747 into ad26ae4 on scikit-learn:master.

amueller added a commit that referenced this pull request Mar 23, 2015
[MRG+2] FIX make StandardScaler & scale more numerically stable
@amueller amueller merged commit 574ebfd into scikit-learn:master Mar 23, 2015
@coveralls
Copy link

Coverage Status

Coverage decreased (-0.0%) to 95.09% when pulling b596dfc on ogrisel:rebased-pr-3747 into ad26ae4 on scikit-learn:master.

@ogrisel
Copy link
Member Author

ogrisel commented Mar 23, 2015

I did the backport to 0.16.X.

@ngoix
Copy link
Contributor

ngoix commented Mar 24, 2015

Sorry for the slow reply. Yes this is perfect, thanks for your fixes!

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

Successfully merging this pull request may close these issues.

None yet

5 participants