8000 CLN GBDTs: don't split on last bin (explicitly) by NicolasHug · Pull Request #13919 · scikit-learn/scikit-learn · GitHub
[go: up one dir, main page]
Skip to content

CLN GBDTs: don't split on last bin (explicitly) #13919

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.

Sign up for GitHub

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 2 commits into from
May 30, 2019
Merged

CLN GBDTs: don't split on last bin (explicitly) #13919

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
b1d3186
dont consider splitting on last bin
NicolasHug May 21, 2019
594faf8
Merge branch 'master' of github.com:scikit-learn/scikit-learn into gb…
NicolasHug May 25, 2019
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 3 additions & 1 deletion sklearn/ensemble/_hist_gradient_boosting/splitting.pyx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -436,7 +436,9 @@ cdef class Splitter:
sum_gradient_left, sum_hessian_left = 0., 0.
n_samples_left = 0

for bin_idx in range(self.actual_n_bins[feature_idx]):
for bin_idx in range(self.actual_n_bins[feature_idx] - 1):
# Note that considering splitting on the last bin is useless since
# it would result in having 0 samples in the right node (forbidden)
n_samples_left += histograms[feature_idx, bin_idx].count
n_samples_right = n_samples_ - n_samples_left

Expand Down
0