clean code

include/LightGBM/boosting.h

@@ -47,7 +47,7 @@ public:
   * \brief Training logic
   * \param gradient nullptr for using default objective, otherwise use self-defined boosting
   * \param hessian nullptr for using default objective, otherwise use self-defined boosting
-  * \param is_eval true if need evalulation or early stop
+  * \param is_eval true if need evaluation or early stop
   * \return True if meet early stopping or cannot boosting
   */
   virtual bool TrainOneIter(const score_t* gradient, const score_t* hessian, bool is_eval) = 0;
@@ -61,7 +61,7 @@ public:
 
   /*!
   * \brief Get current training score
-  * \param out_len lenght of returned score
+  * \param out_len length of returned score
   * \return training score
   */
   virtual const score_t* GetTrainingScore(data_size_t* out_len) const = 0;

include/LightGBM/c_api.h

@@ -8,7 +8,7 @@
 * Except following:
 * 1. gradients and hessians. 
 * 2. Get current score for training data and validation
-* The reason is becaused they are called frequently, the type-conversion on them maybe time cost. 
+* The reason is because they are called frequently, the type-conversion on them maybe time cost. 
 */
 
 #ifdef __cplusplus
@@ -40,7 +40,7 @@ typedef void* BoosterHandle;
 DllExport const char* LGBM_GetLastError();
 
 
-// --- start Dataset inferfaces
+// --- start Dataset interface
 
 /*!
 * \brief load data set from file like the command_line LightGBM do
@@ -71,7 +71,7 @@ DllExport int LGBM_CreateDatasetFromBinaryFile(const char* filename,
 * \param indices findex
 * \param data fvalue
 * \param data_type
-* \param nindptr number of rows in the matix + 1
+* \param nindptr number of rows in the matrix + 1
 * \param nelem number of nonzero elements in the matrix
 * \param num_col number of columns; when it's set to 0, then guess from data
 * \param parameters additional parameters
@@ -98,7 +98,7 @@ DllExport int LGBM_CreateDatasetFromCSR(const void* indptr,
 * \param indices findex
 * \param data fvalue
 * \param data_type
-* \param ncol_ptr number of rows in the matix + 1
+* \param ncol_ptr number of rows in the matrix + 1
 * \param nelem number of nonzero elements in the matrix
 * \param num_row number of rows; when it's set to 0, then guess from data
 * \param parameters additional parameters
@@ -206,7 +206,7 @@ DllExport int LGBM_DatasetGetNumFeature(DatesetHandle handle,
 
 /*!
 * \brief create an new boosting learner
-* \param train_data traning data set
+* \param train_data training data set
 * \param valid_datas validation data sets
 * \param valid_names names of validation data sets
 * \param n_valid_datas number of validation set
@@ -222,7 +222,7 @@ DllExport int LGBM_BoosterCreate(const DatesetHandle train_data,
   BoosterHandle* out);
 
 /*!
-* \brief load an exsiting boosting from model file
+* \brief load an existing boosting from model file
 * \param filename filename of model
 * \param out handle of created Booster
 * \return 0 when success, -1 when failure happens
@@ -261,7 +261,7 @@ DllExport int LGBM_BoosterUpdateOneIterCustom(BoosterHandle handle,
   int* is_finished);
 
 /*!
-* \brief get evaluation for training data and validation datas
+* \brief get evaluation for training data and validation data
 * \param handle handle
 * \param data 0:training data, 1: 1st valid data, 2:2nd valid data ...
 * \param out_len len of output result
@@ -285,7 +285,7 @@ DllExport int LGBM_BoosterGetScore(BoosterHandle handle,
   const float** out_result);
 
 /*!
-* \brief make prediction for training data and validation datas
+* \brief Get prediction for training data and validation data
 this can be used to support customized eval function
 * \param handle handle
 * \param data 0:training data, 1: 1st valid data, 2:2nd valid data ...
@@ -306,7 +306,7 @@ DllExport int LGBM_BoosterGetPredict(BoosterHandle handle,
 * \param indices findex
 * \param data fvalue
 * \param data_type
-* \param nindptr number of rows in the matix + 1
+* \param nindptr number of rows in the matrix + 1
 * \param nelem number of nonzero elements in the matrix
 * \param num_col number of columns; when it's set to 0, then guess from data
 * \param predict_type

include/LightGBM/dataset.h

@@ -81,7 +81,7 @@ public:
 
   void SetWeights(const float* weights, data_size_t len);
 
-  void SetQueryBoundaries(const data_size_t* QueryBoundaries, data_size_t len);
+  void SetQueryBoundaries(const data_size_t* query_boundaries, data_size_t len);
 
   /*!
   * \brief Set initial scores
@@ -292,7 +292,7 @@ public:
 
   std::vector<const BinMapper*> GetBinMappers() const;
 
-  void CopyFeatureBinMapperTo(Dataset *dataset, bool is_enable_sparse) const;
+  void CopyFeatureMapperFrom(const Dataset* dataset, bool is_enable_sparse);
 
   /*!
   * \brief Get a feature pointer for specific index

src/c_api.cpp

@@ -212,7 +212,7 @@ DllExport int LGBM_CreateDatasetFromMat(const void* data,
     ret = loader.CostructFromSampleData(sample_values, nrow);
   } else {
     ret = new Dataset(nrow, config.io_config.num_class);
-    reinterpret_cast<const Dataset*>(*reference)->CopyFeatureBinMapperTo(ret, config.io_config.is_enable_sparse);
+    ret->CopyFeatureMapperFrom(reinterpret_cast<const Dataset*>(*reference), config.io_config.is_enable_sparse);
   }
 
 #pragma omp parallel for schedule(guided)
@@ -274,7 +274,7 @@ DllExport int LGBM_CreateDatasetFromCSR(const void* indptr,
     ret = loader.CostructFromSampleData(sample_values, nrow);
   } else {
     ret = new Dataset(nrow, config.io_config.num_class);
-    reinterpret_cast<const Dataset*>(*reference)->CopyFeatureBinMapperTo(ret, config.io_config.is_enable_sparse);
+    ret->CopyFeatureMapperFrom(reinterpret_cast<const Dataset*>(*reference), config.io_config.is_enable_sparse);
   }
 
 #pragma omp parallel for schedule(guided)
@@ -322,7 +322,7 @@ DllExport int LGBM_CreateDatasetFromCSC(const void* col_ptr,
     ret = loader.CostructFromSampleData(sample_values, nrow);
   } else {
     ret = new Dataset(nrow, config.io_config.num_class);
-    reinterpret_cast<const Dataset*>(*reference)->CopyFeatureBinMapperTo(ret, config.io_config.is_enable_sparse);
+    ret->CopyFeatureMapperFrom(reinterpret_cast<const Dataset*>(*reference), config.io_config.is_enable_sparse);
   }
 
 #pragma omp parallel for schedule(guided)

src/io/dataset.cpp

@@ -42,18 +42,18 @@ void Dataset::FinishLoad() {
   }
 }
 
-void Dataset::CopyFeatureBinMapperTo(Dataset* dataset, bool is_enable_sparse) const {
-  dataset->features_.clear();
+void Dataset::CopyFeatureMapperFrom(const Dataset* dataset, bool is_enable_sparse) {
+  features_.clear();
   // copy feature bin mapper data
-  for (Feature* feature : features_) {
-    dataset->features_.push_back(new Feature(feature->feature_index(),
-      new BinMapper(*feature->bin_mapper()), dataset->num_data_, is_enable_sparse));
+  for (Feature* feature : dataset->features_) {
+    features_.push_back(new Feature(feature->feature_index(),
+      new BinMapper(*feature->bin_mapper()), num_data_, is_enable_sparse));
   }
-  dataset->num_class_ = num_class_;
-  dataset->used_feature_map_ = used_feature_map_;
-  dataset->num_features_ = static_cast<int>(dataset->features_.size());
-  dataset->num_total_features_ = num_total_features_;
-  dataset->feature_names_ = feature_names_;
+  num_class_ = dataset->num_class_;
+  used_feature_map_ = dataset->used_feature_map_;
+  num_features_ = static_cast<int>(features_.size());
+  num_total_features_ = dataset->num_total_features_;
+  feature_names_ = dataset->feature_names_;
 }
 
 std::vector<const BinMapper*> Dataset::GetBinMappers() const {

src/io/dataset_loader.cpp

@@ -219,7 +219,7 @@ Dataset* DatasetLoader::LoadFromFileAlignWithOtherDataset(const char* filename,
       dataset->num_data_ = static_cast<data_size_t>(text_data.size());
       // initialize label
       dataset->metadata_.Init(dataset->num_data_, dataset->num_class_, weight_idx_, group_idx_);
-      train_data->CopyFeatureBinMapperTo(dataset, io_config_.is_enable_sparse);
+      dataset->CopyFeatureMapperFrom(train_data, io_config_.is_enable_sparse);
       // extract features
       ExtractFeaturesFromMemory(text_data, parser, dataset);
       text_data.clear();
@@ -230,7 +230,7 @@ Dataset* DatasetLoader::LoadFromFileAlignWithOtherDataset(const char* filename,
       num_global_data = dataset->num_data_;
       // initialize label
       dataset->metadata_.Init(dataset->num_data_, dataset->num_class_, weight_idx_, group_idx_);
-      train_data->CopyFeatureBinMapperTo(dataset, io_config_.is_enable_sparse);
+      dataset->CopyFeatureMapperFrom(train_data, io_config_.is_enable_sparse);
       // extract features
       ExtractFeaturesFromFile(filename, parser, used_data_indices, dataset);
     }