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.

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

fix the bug in bin with small values #2342

Merged
merged 3 commits into from
Aug 20, 2019
Merged

fix the bug in bin with small values #2342

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
661d4fc
fix the bug in bin with small values
guolinke Aug 20, 2019
d7725b5
Update bin.cpp
guolinke Aug 20, 2019
e555345
Update test_engine.py
guolinke Aug 20, 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
27 changes: 7 additions & 20 deletions src/io/bin.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -181,6 +181,9 @@ namespace LightGBM {
int left_max_bin = static_cast<int>(static_cast<double>(left_cnt_data) / (total_sample_cnt - cnt_zero) * (max_bin - 1));
left_max_bin = std::max(1, left_max_bin);
bin_upper_bound = GreedyFindBin(distinct_values, counts, left_cnt, left_max_bin, left_cnt_data, min_data_in_bin);
if (bin_upper_bound.size() > 0) {
bin_upper_bound.back() = -kZeroThreshold;
}
}

int right_start = -1;
Expand All @@ -191,32 +194,16 @@ namespace LightGBM {
}
}

if (bin_upper_bound.size() == 0) {
if (max_bin > 2) {
// create zero bin
bin_upper_bound.push_back(-kZeroThreshold);
bin_upper_bound.push_back(kZeroThreshold);
}
else if (max_bin > 1) {
bin_upper_bound.push_back(kZeroThreshold);
}
} else {
bin_upper_bound.back() = -kZeroThreshold;
if (max_bin > 2) {
// create zero bin
bin_upper_bound.push_back(kZeroThreshold);
}
}

int right_max_bin = max_bin - static_cast<int>(bin_upper_bound.size());
if ((right_start >= 0) && (right_max_bin > 0)) {
int right_max_bin = max_bin - 1 - static_cast<int>(bin_upper_bound.size());
if (right_start >= 0 && right_max_bin > 0) {
auto right_bounds = GreedyFindBin(distinct_values + right_start, counts + right_start,
num_distinct_values - right_start, right_max_bin, right_cnt_data, min_data_in_bin);
bin_upper_bound.push_back(kZeroThreshold);
bin_upper_bound.insert(bin_upper_bound.end(), right_bounds.begin(), right_bounds.end());
} else {
bin_upper_bound.push_back(std::numeric_limits<double>::infinity());
}
CHECK(bin_upper_bound.size() <= max_bin);
CHECK(bin_upper_bound.size() <= static_cast<size_t>(max_bin));
return bin_upper_bound;
}

Expand Down
2 changes: 1 addition & 1 deletion tests/python_package_test/test_engine.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -921,7 +921,7 @@ def test_max_bin_by_feature(self):
}
lgb_data = lgb.Dataset(X, label=y)
est = lgb.train(params, lgb_data, num_boost_round=1)
self.assertEqual(len(np.unique(est.predict(X))), 99)
self.assertEqual(len(np.unique(est.predict(X))), 100)
params['max_bin_by_feature'] = [2, 100]
lgb_data = lgb.Dataset(X, label=y)
est = lgb.train(params, lgb_data, num_boost_round=1)
Expand Down