fix some formats

microsoft · Nov 15, 2017 · 3d65d06 · 3d65d06
1 parent ba5c745
commit 3d65d06
Show file tree

Hide file tree

Showing 7 changed files with 67 additions and 70 deletions.
diff --git a/include/LightGBM/boosting.h b/include/LightGBM/boosting.h
@@ -121,8 +121,8 @@ class LIGHTGBM_EXPORT Boosting {
   virtual void PredictRaw(const double* features, double* output,
                           const PredictionEarlyStopInstance* early_stop) const = 0;
 
-  virtual void PredictRawByMap(const std::unordered_map<int, double>& features, double* output, 
-                  const PredictionEarlyStopInstance* early_stop) const = 0;
+  virtual void PredictRawByMap(const std::unordered_map<int, double>& features, double* output,
+                               const PredictionEarlyStopInstance* early_stop) const = 0;
 
 
   /*!
@@ -134,8 +134,8 @@ class LIGHTGBM_EXPORT Boosting {
   virtual void Predict(const double* features, double* output,
                        const PredictionEarlyStopInstance* early_stop) const = 0;
 
-  virtual void PredictByMap(const std::unordered_map<int, double>& features, double* output, 
-               const PredictionEarlyStopInstance* early_stop) const = 0;
+  virtual void PredictByMap(const std::unordered_map<int, double>& features, double* output,
+                            const PredictionEarlyStopInstance* early_stop) const = 0;
 
 
   /*!
@@ -210,7 +210,7 @@ class LIGHTGBM_EXPORT Boosting {
   * \param filename Filename that want to save to
   */
   virtual void SaveModelToProto(int num_iteration, const char* filename) const = 0;
-  
+
   /*!
   * \brief Restore from a serialized protobuf file
   * \param filename Filename that want to restore from

diff --git a/include/LightGBM/tree.h b/include/LightGBM/tree.h
@@ -478,8 +478,8 @@ inline void Tree::PredictContrib(const double* feature_values, int num_features,
   output[num_features] += ExpectedValue();
   // Run the recursion with preallocated space for the unique path data
   if (num_leaves_ > 1) {
-    const int max_path_len = MaxDepth()+1;
-    PathElement *unique_path_data = new PathElement[(max_path_len*(max_path_len+1))/2];
+    const int max_path_len = MaxDepth() + 1;
+    PathElement *unique_path_data = new PathElement[(max_path_len*(max_path_len + 1)) / 2];
     TreeSHAP(feature_values, output, 0, 0, unique_path_data, 1, 1, -1);
     delete[] unique_path_data;
   }
@@ -490,8 +490,8 @@ inline void Tree::RecomputeLeafDepths(int node, int depth) {
   if (node < 0) {
     leaf_depth_[~node] = depth;
   } else {
-    RecomputeLeafDepths(left_child_[node], depth+1);
-    RecomputeLeafDepths(right_child_[node], depth+1);
+    RecomputeLeafDepths(left_child_[node], depth + 1);
+    RecomputeLeafDepths(right_child_[node], depth + 1);
   }
 }
 

diff --git a/src/application/predictor.hpp b/src/application/predictor.hpp
@@ -65,7 +65,7 @@ class Predictor {
     if (is_predict_leaf_index) {
       predict_fun_ = [this](const std::vector<std::pair<int, double>>& features, double* output) {
         int tid = omp_get_thread_num();
-        if(num_feature_ > MAX_FEATURE && num_feature_/static_cast<int>(features.size()) > SPARSITY) {
+        if (num_feature_ > MAX_FEATURE && num_feature_ / static_cast<int>(features.size()) > SPARSITY) {
           CopyToPredictMap(tid, features);
           boosting_->PredictLeafIndexByMap(predict_buf_map_[tid], output);
           ClearPredictMap(tid);
@@ -88,7 +88,7 @@ class Predictor {
       if (is_raw_score) {
         predict_fun_ = [this](const std::vector<std::pair<int, double>>& features, double* output) {
           int tid = omp_get_thread_num();
-          if(num_feature_ > MAX_FEATURE && num_feature_/static_cast<int>(features.size()) > SPARSITY) {
+          if (num_feature_ > MAX_FEATURE && num_feature_ / static_cast<int>(features.size()) > SPARSITY) {
             CopyToPredictMap(tid, features);
             boosting_->PredictRawByMap(predict_buf_map_[tid], output, &early_stop_);
             ClearPredictMap(tid);
@@ -101,7 +101,7 @@ class Predictor {
       } else {
         predict_fun_ = [this](const std::vector<std::pair<int, double>>& features, double* output) {
           int tid = omp_get_thread_num();
-          if(num_feature_ > MAX_FEATURE && num_feature_/static_cast<int>(features.size()) > SPARSITY) {
+          if (num_feature_ > MAX_FEATURE && num_feature_ / static_cast<int>(features.size()) > SPARSITY) {
             CopyToPredictMap(tid, features);
             boosting_->PredictByMap(predict_buf_map_[tid], output, &early_stop_);
             ClearPredictMap(tid);
@@ -151,20 +151,20 @@ class Predictor {
     TextReader<data_size_t> predict_data_reader(data_filename, has_header);
     std::unordered_map<int, int> feature_names_map_;
     bool need_adjust = false;
-    if(has_header) {
+    if (has_header) {
       std::string first_line = predict_data_reader.first_line();
       std::vector<std::string> header = Common::Split(first_line.c_str(), "\t,");
       header.erase(header.begin() + boosting_->LabelIdx());
-      for(int i = 0; i < static_cast<int>(header.size()); ++i) {
-        for(int j = 0; j < static_cast<int>(boosting_->FeatureNames().size()); ++j) {
-          if(header[i] == boosting_->FeatureNames()[j]) {
+      for (int i = 0; i < static_cast<int>(header.size()); ++i) {
+        for (int j = 0; j < static_cast<int>(boosting_->FeatureNames().size()); ++j) {
+          if (header[i] == boosting_->FeatureNames()[j]) {
             feature_names_map_[i] = j;
             break;
           }
         }
       }
-      for(auto s:feature_names_map_) {
-        if(s.first != s.second) {
+      for (auto s : feature_names_map_) {
+        if (s.first != s.second) {
           need_adjust = true;
           break;
         }
@@ -176,14 +176,13 @@ class Predictor {
     parser_fun = [this, &parser, &tmp_label, &need_adjust, &feature_names_map_]
     (const char* buffer, std::vector<std::pair<int, double>>* feature) {
       parser->ParseOneLine(buffer, feature, &tmp_label);
-      if(need_adjust) {
+      if (need_adjust) {
         int i = 0, j = static_cast<int>(feature->size());
-        while(i < j) {
-          if(feature_names_map_.find((*feature)[i].first) != feature_names_map_.end()) {
+        while (i < j) {
+          if (feature_names_map_.find((*feature)[i].first) != feature_names_map_.end()) {
             (*feature)[i].first = feature_names_map_[(*feature)[i].first];
             ++i;
-          }
-          else {
+          } else {
             //move the non-used features to the end of the feature vector
             std::swap((*feature)[i], (*feature)[--j]);
           }

diff --git a/src/boosting/gbdt.cpp b/src/boosting/gbdt.cpp
@@ -30,16 +30,16 @@ std::chrono::duration<double, std::milli> tree_time;
 #endif // TIMETAG
 
 GBDT::GBDT() : iter_(0),
-    train_data_(nullptr),
-    objective_function_(nullptr),
-    early_stopping_round_(0),
-    max_feature_idx_(0),
-    num_tree_per_iteration_(1),
-    num_class_(1),
-    num_iteration_for_pred_(0),
-    shrinkage_rate_(0.1f),
-    num_init_iteration_(0),
-    need_re_bagging_(false) {
+train_data_(nullptr),
+objective_function_(nullptr),
+early_stopping_round_(0),
+max_feature_idx_(0),
+num_tree_per_iteration_(1),
+num_class_(1),
+num_iteration_for_pred_(0),
+shrinkage_rate_(0.1f),
+num_init_iteration_(0),
+need_re_bagging_(false) {
 
   #pragma omp parallel
   #pragma omp master
@@ -224,7 +224,7 @@ data_size_t GBDT::BaggingHelper(Random& cur_rand, data_size_t start, data_size_t
 
 void GBDT::Bagging(int iter) {
   // if need bagging
-  if ((bag_data_cnt_ < num_data_ && iter % gbdt_config_->bagging_freq == 0) 
+  if ((bag_data_cnt_ < num_data_ && iter % gbdt_config_->bagging_freq == 0)
       || need_re_bagging_) {
     need_re_bagging_ = false;
     const data_size_t min_inner_size = 1000;

diff --git a/src/boosting/gbdt.h b/src/boosting/gbdt.h
@@ -20,7 +20,7 @@ namespace LightGBM {
 /*!
 * \brief GBDT algorithm implementation. including Training, prediction, bagging.
 */
-class GBDT: public GBDTBase {
+class GBDT : public GBDTBase {
 public:
 
   /*!
@@ -187,14 +187,14 @@ class GBDT: public GBDTBase {
   void PredictRaw(const double* features, double* output,
                   const PredictionEarlyStopInstance* earlyStop) const override;
 
-  void PredictRawByMap(const std::unordered_map<int, double>& features, double* output, 
-                  const PredictionEarlyStopInstance* early_stop) const override;
+  void PredictRawByMap(const std::unordered_map<int, double>& features, double* output,
+                       const PredictionEarlyStopInstance* early_stop) const override;
 
   void Predict(const double* features, double* output,
                const PredictionEarlyStopInstance* earlyStop) const override;
 
-  void PredictByMap(const std::unordered_map<int, double>& features, double* output, 
-               const PredictionEarlyStopInstance* early_stop) const override;
+  void PredictByMap(const std::unordered_map<int, double>& features, double* output,
+                    const PredictionEarlyStopInstance* early_stop) const override;
 
   void PredictLeafIndex(const double* features, double* output) const override;
 
@@ -252,7 +252,7 @@ class GBDT: public GBDTBase {
   * \param filename Filename that want to save to
   */
   void SaveModelToProto(int num_iteration, const char* filename) const override;
-  
+
   /*!
   * \brief Restore from a serialized protobuf file
   * \param filename Filename that want to restore from

diff --git a/src/boosting/gbdt_model_text.cpp b/src/boosting/gbdt_model_text.cpp
@@ -104,10 +104,10 @@ std::string GBDT::ModelToIfElse(int num_iteration) const {
   // PredictRawByMap
   str_buf << "double (*PredictTreeByMapPtr[])(const std::unordered_map<int, double>&) = { ";
   for (int i = 0; i < num_used_model; ++i) {
-	  if (i > 0) {
-		  str_buf << " , ";
-	  }
-	  str_buf << "PredictTree" << i << "ByMap";
+    if (i > 0) {
+      str_buf << " , ";
+    }
+    str_buf << "PredictTree" << i << "ByMap";
   }
   str_buf << " };" << std::endl << std::endl;
 
@@ -185,10 +185,10 @@ std::string GBDT::ModelToIfElse(int num_iteration) const {
   //PredictLeafIndexByMap
   str_buf << "double (*PredictTreeLeafByMapPtr[])(const std::unordered_map<int, double>&) = { ";
   for (int i = 0; i < num_used_model; ++i) {
-	  if (i > 0) {
-		  str_buf << " , ";
-	  }
-	  str_buf << "PredictTree" << i << "LeafByMap";
+    if (i > 0) {
+      str_buf << " , ";
+    }
+    str_buf << "PredictTree" << i << "LeafByMap";
   }
   str_buf << " };" << std::endl << std::endl;
 

diff --git a/src/io/tree.cpp b/src/io/tree.cpp
@@ -381,30 +381,28 @@ std::string Tree::ToIfElse(int index, bool is_predict_leaf_index) const {
   //Predict func by Map to ifelse
   str_buf << "double PredictTree" << index;
   if (is_predict_leaf_index) {
-	  str_buf << "LeafByMap";
-  }
-  else {
-	  str_buf << "ByMap";
+    str_buf << "LeafByMap";
+  } else {
+    str_buf << "ByMap";
   }
   str_buf << "(const std::unordered_map<int, double>& arr) { ";
   if (num_leaves_ <= 1) {
-	  str_buf << "return " << leaf_value_[0] << ";";
-  }
-  else {
-	  str_buf << "const std::vector<uint32_t> cat_threshold = {";
-	  for (size_t i = 0; i < cat_threshold_.size(); ++i) {
-		  if (i != 0) {
-			  str_buf << ",";
-		  }
-		  str_buf << cat_threshold_[i];
-	  }
-	  str_buf << "};";
-	  // use this for the missing value conversion
-	  str_buf << "double fval = 0.0f; ";
-	  if (num_cat_ > 0) {
-		  str_buf << "int int_fval = 0; ";
-	  }
-	  str_buf << NodeToIfElseByMap(0, is_predict_leaf_index);
+    str_buf << "return " << leaf_value_[0] << ";";
+  } else {
+    str_buf << "const std::vector<uint32_t> cat_threshold = {";
+    for (size_t i = 0; i < cat_threshold_.size(); ++i) {
+      if (i != 0) {
+        str_buf << ",";
+      }
+      str_buf << cat_threshold_[i];
+    }
+    str_buf << "};";
+    // use this for the missing value conversion
+    str_buf << "double fval = 0.0f; ";
+    if (num_cat_ > 0) {
+      str_buf << "int int_fval = 0; ";
+    }
+    str_buf << NodeToIfElseByMap(0, is_predict_leaf_index);
   }
   str_buf << " }" << std::endl;
 
@@ -696,7 +694,7 @@ double Tree::ExpectedValue() const {
   const double total_count = internal_count_[0];
   double exp_value = 0.0;
   for (int i = 0; i < num_leaves(); ++i) {
-    exp_value += (leaf_count_[i]/total_count)*LeafOutput(i);
+    exp_value += (leaf_count_[i] / total_count)*LeafOutput(i);
   }
   return exp_value;
 }