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

renamed cur_cat => cur_cat_idx and added some comments #5522

Merged
merged 5 commits into from
Oct 11, 2022
+12 −12
Merged

renamed cur_cat => cur_cat_idx and added some comments #5522

Changes from 2 commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
80bdd90
renamed cur_cat => cur_cat_index and added some comments
Oct 4, 2022
9d004c4
revert relocation of a line
Oct 5, 2022
b25c0ae
Merge branch 'master' into rename-in-find-bin
Oct 7, 2022
34f7e27
Merge branch 'master' into rename-in-find-bin
Oct 11, 2022
ff6ad50
addressed lint issues
Oct 11, 2022
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
24 changes: 12 additions & 12 deletions src/io/bin.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -352,7 +352,7 @@ namespace LightGBM {
int zero_cnt = static_cast<int>(total_sample_cnt - num_sample_values - na_cnt);
// find distinct_values first
std::vector<double> distinct_values;
std::vector<int> counts;
std::vector<int> counts; // count of data points for each distinct feature value.

std::stable_sort(values, values + num_sample_values);

Expand Down Expand Up @@ -389,7 +389,7 @@ namespace LightGBM {
}
min_val_ = distinct_values.front();
max_val_ = distinct_values.back();
std::vector<int> cnt_in_bin;
std::vector<int> cnt_in_bin; // count of data points in each bin.
int num_distinct_values = static_cast<int>(distinct_values.size());
if (bin_type_ == BinType::NumericalBin) {
if (missing_type_ == MissingType::Zero) {
Expand Down Expand Up @@ -446,12 +446,12 @@ namespace LightGBM {
Log::Warning("Met categorical feature which contains sparse values. "
"Consider renumbering to consecutive integers started from zero");
}
// sort by counts
// sort by counts in descending order
Common::SortForPair<int, int>(&counts_int, &distinct_values_int, 0, true);
// will ignore the categorical of small counts
int cut_cnt = static_cast<int>(
Common::RoundInt((total_sample_cnt - na_cnt) * 0.99f));
size_t cur_cat = 0;
size_t cur_cat_idx = 0; // index of current category.
categorical_2_bin_.clear();
bin_2_categorical_.clear();
int used_cnt = 0;
Expand All @@ -467,20 +467,20 @@ namespace LightGBM {
categorical_2_bin_[-1] = 0;
cnt_in_bin.push_back(0);
num_bin_ = 1;
while (cur_cat < distinct_values_int.size()
while (cur_cat_idx < distinct_values_int.size()
&& (used_cnt < cut_cnt || num_bin_ < max_bin)) {
if (counts_int[cur_cat] < min_data_in_bin && cur_cat > 1) {
if (counts_int[cur_cat_idx] < min_data_in_bin && cur_cat_idx > 1) {
break;
}
bin_2_categorical_.push_back(distinct_values_int[cur_cat]);
categorical_2_bin_[distinct_values_int[cur_cat]] = static_cast<unsigned int>(num_bin_);
used_cnt += counts_int[cur_cat];
cnt_in_bin.push_back(counts_int[cur_cat]);
bin_2_categorical_.push_back(distinct_values_int[cur_cat_idx]);
categorical_2_bin_[distinct_values_int[cur_cat_idx]] = static_cast<unsigned int>(num_bin_);
used_cnt += counts_int[cur_cat_idx];
cnt_in_bin.push_back(counts_int[cur_cat_idx]);
++num_bin_;
++cur_cat;
++cur_cat_idx;
}
// Use MissingType::None to represent this bin contains all categoricals
if (cur_cat == distinct_values_int.size() && na_cnt == 0) {
if (cur_cat_idx == distinct_values_int.size() && na_cnt == 0) {
missing_type_ = MissingType::None;
} else {
missing_type_ = MissingType::NaN;
Expand Down