Skip to content

[MRG] DOC User guide section for histogram-based GBDTs #14525

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

Merged
merged 17 commits into from
Aug 5, 2019

Conversation

NicolasHug
Copy link
Member

Long overdue, this PR adds a section in the user guide dedicated to the new GBDTs.

ping @adrinjalali @glemaitre @amueller @thomasjpfan

@NicolasHug
Copy link
Member Author

In the text I'm considering that #13911 (missing values support) and #14516 (early stopping by default) will be merged soon

Copy link
Member

@rth rth left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I don't know much about the new gradient boosting implementation but it was an interesting read. A few comments are below.

Great work on this new implementation in general @NicolasHug !

@NicolasHug
Copy link
Member Author

Thanks @rth! Comments were addressed

@NicolasHug NicolasHug changed the title [MRG] User guide section for histogram-based GBDTs [MRG] DOC User guide section for histogram-based GBDTs Jul 31, 2019
Copy link
Member

@rth rth left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM, pending a second opinion on #14525 (comment)

@NicolasHug
Copy link
Member Author

Thanks for the reviews!

I added a section d3e6ca0 with implementation details to explain why this implementation is faster. I think it can be useful for users for it to feel less like magic. WDYT?

@adrinjalali
Copy link
Member

looks good :)

for parallelization through Cython. The number of threads that is used can
be changed using the ``OMP_NUM_THREADS`` environment variable. By default,
all available cores are used. Please refer to the OpenMP documentation for
details.
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Link to OpenMP documentation?

Copy link
Member Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

(Weird that the previous comments got lost, we discussed this with Adrin already)

I don't want to add it because the openmp doc is a 300 pages pdf. Googling OMP_NUM_THREADS gives you the docs from intel and ibm but they're probably not official.

Copy link
Member

@adrinjalali adrinjalali left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM, should we merge or do you want another review since there's been a few changes?

@NicolasHug
Copy link
Member Author

I think we can merge, Thomas reviewed with the latest changes and I addressed his comments

@adrinjalali adrinjalali merged commit 2df8462 into scikit-learn:master Aug 5, 2019
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

4 participants