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 number of features mismatching in continual training (fix #5156) #5157

Open
wants to merge 14 commits into
base: master
Choose a base branch
from
Open

Fix number of features mismatching in continual training (fix #5156) #5157

Changes from 3 commits
Commits
Show all changes
14 commits
Select commit Hold shift + click to select a range
24b7df0
consider number of features from model in continual training
shiyu1994 Apr 17, 2022
442c03a
rollback changes
shiyu1994 Apr 21, 2022
2887ac0
handle mismatches only within gbdt_model_text.cpp
shiyu1994 Apr 21, 2022
0a20a13
remove useless debug information
shiyu1994 May 5, 2022
bda5bdb
add a test case
shiyu1994 May 9, 2022
7e7190f
Update tests/python_package_test/test_engine.py
shiyu1994 May 10, 2022
adb8982
Merge branch 'master' of https://github.com/Microsoft/LightGBM into f…
shiyu1994 May 10, 2022
c823137
provide warning instead of enlarging feature importances
shiyu1994 May 10, 2022
750d35c
Merge branch 'fix-5156' of https://github.com/shiyu1994/LightGBM into…
shiyu1994 May 10, 2022
3e52538
remove useless comments
shiyu1994 May 10, 2022
23e9991
ensure the warning is raised in test case
shiyu1994 May 11, 2022
d719d78
add suggestion for the warning
shiyu1994 May 30, 2022
aab8d1f
Merge branch 'master' into fix-5156
shiyu1994 Mar 1, 2023
1f09936
Merge remote-tracking branch 'origin/master' into fix-5156
shiyu1994 Mar 15, 2023
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
37 changes: 31 additions & 6 deletions src/boosting/gbdt_model_text.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -104,7 +104,16 @@ std::string GBDT::DumpModel(int start_iteration, int num_iteration, int feature_
for (size_t i = 0; i < feature_importances.size(); ++i) {
size_t feature_importances_int = static_cast<size_t>(feature_importances[i]);
if (feature_importances_int > 0) {
pairs.emplace_back(feature_importances_int, feature_names_[i]);
Log::Warning("i = %d, feature_names_.size() = %d", i, feature_names_.size());
shiyu1994 marked this conversation as resolved.
Show resolved Hide resolved
if (i < feature_names_.size()) {
pairs.emplace_back(feature_importances_int, feature_names_[i]);
} else {
// with LibSVM format and continual training, the number of features in dataset can be fewer than in the intial model
// in that case FeatureImportance returns with the number of features in the intial model
std::stringstream str_buf;
str_buf << "Column_" << i << "_from_init_model";
pairs.emplace_back(feature_importances_int, str_buf.str());
}
}
}
str_buf << '\n' << "\"feature_importances\":" << "{";
Expand Down Expand Up @@ -377,7 +386,15 @@ std::string GBDT::SaveModelToString(int start_iteration, int num_iteration, int
for (size_t i = 0; i < feature_importances.size(); ++i) {
size_t feature_importances_int = static_cast<size_t>(feature_importances[i]);
if (feature_importances_int > 0) {
pairs.emplace_back(feature_importances_int, feature_names_[i]);
if (i < feature_names_.size()) {
pairs.emplace_back(feature_importances_int, feature_names_[i]);
} else {
// with LibSVM format and continual training, the number of features in dataset can be fewer than in the intial model
// in that case FeatureImportance returns with the number of features in the intial model
std::stringstream str_buf;
str_buf << "Column_" << i << "_from_init_model";
pairs.emplace_back(feature_importances_int, str_buf.str());
}
}
}
// sort the importance
Expand Down Expand Up @@ -636,21 +653,29 @@ std::vector<double> GBDT::FeatureImportance(int num_iteration, int importance_ty
for (int iter = 0; iter < num_used_model; ++iter) {
for (int split_idx = 0; split_idx < models_[iter]->num_leaves() - 1; ++split_idx) {
if (models_[iter]->split_gain(split_idx) > 0) {
const int real_feature_index = models_[iter]->split_feature(split_idx);
#ifdef DEBUG
CHECK_GE(models_[iter]->split_feature(split_idx), 0);
CHECK_GE(real_feature_index, 0);
#endif
feature_importances[models_[iter]->split_feature(split_idx)] += 1.0;
if (static_cast<size_t>(real_feature_index) >= feature_importances.size()) {
feature_importances.resize(real_feature_index + 1);
}
feature_importances[real_feature_index] += 1.0;
}
}
}
} else if (importance_type == 1) {
for (int iter = 0; iter < num_used_model; ++iter) {
for (int split_idx = 0; split_idx < models_[iter]->num_leaves() - 1; ++split_idx) {
if (models_[iter]->split_gain(split_idx) > 0) {
const int real_feature_index = models_[iter]->split_feature(split_idx);
#ifdef DEBUG
CHECK_GE(models_[iter]->split_feature(split_idx), 0);
CHECK_GE(real_feature_index, 0);
#endif
feature_importances[models_[iter]->split_feature(split_idx)] += models_[iter]->split_gain(split_idx);
if (static_cast<size_t>(real_feature_index) >= feature_importances.size()) {
feature_importances.resize(real_feature_index + 1);
}
feature_importances[real_feature_index] += models_[iter]->split_gain(split_idx);
}
}
}
Expand Down