fix model feature importances (microsoft#755)

* fix model feature importance * fix appveryor test * Revert "fix appveryor test" This reverts commit 3a10a17. * fix warning & boost_from_average_ * fix bug * alter num_used_model
Alnusjaponica · Aug 1, 2017 · 2e83a1c · 2e83a1c
1 parent 04e0db0
commit 2e83a1c
Show file tree

Hide file tree

Showing 2 changed files with 8 additions and 6 deletions.
diff --git a/src/boosting/gbdt.cpp b/src/boosting/gbdt.cpp
@@ -964,7 +964,7 @@ std::string GBDT::SaveModelToString(int num_iteration) const {
     ss << models_[i]->ToString() << std::endl;
   }
 
-  std::vector<std::pair<size_t, std::string>> pairs = FeatureImportance();
+  std::vector<std::pair<size_t, std::string>> pairs = FeatureImportance(num_used_model);
   ss << std::endl << "feature importances:" << std::endl;
   for (size_t i = 0; i < pairs.size(); ++i) {
     ss << pairs[i].second << "=" << std::to_string(pairs[i].first) << std::endl;
@@ -1088,10 +1088,10 @@ bool GBDT::LoadModelFromString(const std::string& model_str) {
   return true;
 }
 
-std::vector<std::pair<size_t, std::string>> GBDT::FeatureImportance() const {
+std::vector<std::pair<size_t, std::string>> GBDT::FeatureImportance(int num_used_model) const {
 
   std::vector<size_t> feature_importances(max_feature_idx_ + 1, 0);
-  for (size_t iter = 0; iter < models_.size(); ++iter) {
+  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) {
         ++feature_importances[models_[iter]->split_feature(split_idx)];

diff --git a/src/boosting/gbdt.h b/src/boosting/gbdt.h
@@ -175,15 +175,15 @@ class GBDT: public Boosting {
 
   /*!
   * \brief Save model to file
-  * \param num_used_model Number of model that want to save, -1 means save all
+  * \param num_iterations Number of model that want to save, -1 means save all
   * \param filename Filename that want to save to
   * \return is_finish Is training finished or not
   */
   virtual bool SaveModelToFile(int num_iterations, const char* filename) const override;
 
   /*!
   * \brief Save model to string
-  * \param num_used_model Number of model that want to save, -1 means save all
+  * \param num_iterations Number of model that want to save, -1 means save all
   * \return Non-empty string if succeeded
   */
   virtual std::string SaveModelToString(int num_iterations) const override;
@@ -296,8 +296,10 @@ class GBDT: public Boosting {
   std::string OutputMetric(int iter);
   /*!
   * \brief Calculate feature importances
+  * \param num_used_model Number of model that want to use for feature importance, -1 means use all 
+  * \return sorted pairs of (feature_importance, feature_name)
   */
-  std::vector<std::pair<size_t, std::string>> FeatureImportance() const;
+  std::vector<std::pair<size_t, std::string>> FeatureImportance(int num_used_model) const;
 
   /*! \brief current iteration */
   int iter_;