Merge pull request #36 from xuehui1991/update_for_dcg

update for typo.

src/boosting/gbdt.h

@@ -115,7 +115,7 @@ private:
   */
   void UpdateScore(const Tree* tree);
   /*!
-  * \brief Print Metric result of current iteration
+  * \brief Print metric result of current iteration
   * \param iter Current interation
   */
   bool OutputMetric(int iter);
@@ -126,11 +126,11 @@ private:
   const Dataset* train_data_;
   /*! \brief Config of gbdt */
   const GBDTConfig* gbdt_config_;
-  /*! \brief Tree learner, will use tihs class to learn trees */
+  /*! \brief Tree learner, will use this class to learn trees */
   TreeLearner* tree_learner_;
   /*! \brief Objective function */
   const ObjectiveFunction* object_function_;
-  /*! \brief Store and update traning data's score */
+  /*! \brief Store and update training data's score */
   ScoreUpdater* train_score_updater_;
   /*! \brief Metrics for training data */
   std::vector<const Metric*> training_metrics_;

src/boosting/score_updater.hpp

@@ -57,8 +57,8 @@ public:
   * \brief Using tree model to get prediction number, then adding to scores for parts of data
   *        Used for prediction of training out-of-bag data
   * \param tree Trained tree model
-  * \param data_indices Indices of data that want proccess to
-  * \param data_cnt Number of data that want proccess to
+  * \param data_indices Indices of data that will be proccessed
+  * \param data_cnt Number of data that will be proccessed
   */
   inline void AddScore(const Tree* tree, const data_size_t* data_indices,
                                                   data_size_t data_cnt) {

src/io/dataset.cpp

@@ -36,7 +36,7 @@ Dataset::Dataset(const char* data_filename, const char* init_score_filename,
     // create text reader
     text_reader_ = new TextReader<data_size_t>(data_filename);
   } else {
-    // only need to load initilize score, other meta data will load from bin flie
+    // only need to load initilize score, other meta data will be loaded from bin flie
     metadata_.Init(init_score_filename);
     Log::Info("Loading data set from binary file");
     parser_ = nullptr;
@@ -613,7 +613,7 @@ void Dataset::LoadDataFromBinFile(int rank, int num_machines, bool is_pre_partit
 
   size_t size_of_metadata = *(reinterpret_cast<size_t*>(buffer));
 
-  // re-allocmate space if not enough
+  // re-allocate space if not enough
   if (size_of_metadata > buffer_size) {
     delete[] buffer;
     buffer_size = size_of_metadata;
@@ -673,7 +673,7 @@ void Dataset::LoadDataFromBinFile(int rank, int num_machines, bool is_pre_partit
       Log::Fatal("Binary file format error at feature %d's size", i);
     }
     size_t size_of_feature = *(reinterpret_cast<size_t*>(buffer));
-    // re-allocmate space if not enough
+    // re-allocate space if not enough
     if (size_of_feature > buffer_size) {
       delete[] buffer;
       buffer_size = size_of_feature;

src/io/dense_bin.hpp

@@ -10,7 +10,7 @@
 namespace LightGBM {
 
 /*!
-* \brief Used to Store bins for dense feature
+* \brief Used to store bins for dense feature
 * Use template to reduce memory cost
 */
 template <typename VAL_T>

src/metric/binary_metric.hpp

@@ -238,7 +238,7 @@ public:
   }
 
 private:
-  /*! \brief Output frequently */
+  /*! \brief Output frequency */
   int output_freq_;
   /*! \brief Number of data */
   data_size_t num_data_;

src/metric/regression_metric.hpp

@@ -72,7 +72,7 @@ public:
   }
 
 private:
-  /*! \brief Output frequently */
+  /*! \brief Output frequency */
   int output_freq_;
   /*! \brief Number of data */
   data_size_t num_data_;

src/network/network.cpp

@@ -9,7 +9,7 @@
 
 namespace LightGBM {
 
-// static member defination
+// static member definition
 int Network::num_machines_;
 int Network::rank_;
 Linkers* Network::linkers_;
@@ -141,7 +141,7 @@ void Network::ReduceScatter(char* input, int input_size, int* block_start, int*
       // send local data to neighbor first
       linkers_->Send(recursive_halving_map_.neighbor, input, input_size);
     } else if (recursive_halving_map_.type == RecursiveHalvingNodeType::GroupLeader) {
-      // recieve neighbor data first
+      // receive neighbor data first
       int need_recv_cnt = input_size;
       linkers_->Recv(recursive_halving_map_.neighbor, output, need_recv_cnt);
       // reduce

src/objective/rank_objective.hpp

@@ -50,7 +50,7 @@ public:
       Log::Fatal("For NDCG metric, should have query information");
     }
     num_queries_ = metadata.num_queries();
-    // cache inverse max DCG, avoid compution many times
+    // cache inverse max DCG, avoid computation many times
     inverse_max_dcgs_ = new score_t[num_queries_];
     for (data_size_t i = 0; i < num_queries_; ++i) {
       inverse_max_dcgs_[i] = static_cast<score_t>(

src/treelearner/feature_histogram.hpp

@@ -40,7 +40,7 @@ public:
   * \brief Construct a histogram
   * \param num_data number of data in current leaf
   * \param sum_gradients sum of gradients of current leaf
-  * \param sum_hessians sum of hissians of current leaf
+  * \param sum_hessians sum of hessians of current leaf
   * \param ordered_gradients Orederd gradients
   * \param ordered_hessians  Ordered hessians
   * \param data_indices data indices of current leaf
@@ -59,7 +59,7 @@ public:
   * \param leaf current leaf
   * \param num_data number of data in current leaf
   * \param sum_gradients sum of gradients of current leaf
-  * \param sum_hessians sum of hissians of current leaf
+  * \param sum_hessians sum of hessians of current leaf
   * \param gradients
   * \param hessian
   */
@@ -76,7 +76,7 @@ public:
   * \brief Set sumup information for current histogram
   * \param num_data number of data in current leaf
   * \param sum_gradients sum of gradients of current leaf
-  * \param sum_hessians sum of hissians of current leaf
+  * \param sum_hessians sum of hessians of current leaf
   */
   void SetSumup(data_size_t num_data, score_t sum_gradients, score_t sum_hessians) {
     num_data_ = num_data;

src/treelearner/leaf_splits.hpp

@@ -26,6 +26,7 @@ public:
   }
 
   /*!
+
   * \brief Init split on current leaf on partial data. 
   * \param leaf Index of current leaf
   * \param data_partition current data partition
@@ -43,7 +44,7 @@ public:
   }
 
   /*!
-  * \brief Init splits on current leaf, it will travese all data to sum up the results
+  * \brief Init splits on current leaf, it will traverse all data to sum up the results
   * \param gradients
   * \param hessians
   */

src/treelearner/parallel_tree_learner.h

@@ -77,9 +77,9 @@ private:
   int* block_start_;
   /*! \brief Block size for reduce scatter */
   int* block_len_;
-  /*! \brief Write positions for feature histgrams */
+  /*! \brief Write positions for feature histograms */
   int* buffer_write_start_pos_;
-  /*! \brief Read positions for local feature histgrams */
+  /*! \brief Read positions for local feature histograms */
   int* buffer_read_start_pos_;
   /*! \brief Size for reduce scatter */
   int reduce_scatter_size_;

src/treelearner/serial_tree_learner.cpp

@@ -107,7 +107,7 @@ void SerialTreeLearner::Init(const Dataset* train_data) {
   // initialize ordered gradients and hessians
   ordered_gradients_ = new score_t[num_data_];
   ordered_hessians_ = new score_t[num_data_];
-  // if has ordered bin, need allocata a buffer to fast split
+  // if has ordered bin, need allocate a buffer to fast split
   if (has_ordered_bin_) {
     is_data_in_leaf_ = new char[num_data_];
   }
@@ -269,14 +269,14 @@ bool SerialTreeLearner::BeforeFindBestSplit(int left_leaf, int right_leaf) {
   } else if (num_data_in_left_child < num_data_in_right_child) {
     smaller_leaf = left_leaf;
     larger_leaf = right_leaf;
-    // put parent(left) leaf's histograms into larger leaf's histgrams
+    // put parent(left) leaf's histograms into larger leaf's histograms
     if (histogram_pool_.Get(left_leaf, &larger_leaf_histogram_array_)) { parent_leaf_histogram_array_ = larger_leaf_histogram_array_; }
     histogram_pool_.Move(left_leaf, right_leaf);
     histogram_pool_.Get(left_leaf, &smaller_leaf_histogram_array_);
   } else {
     smaller_leaf = right_leaf;
     larger_leaf = left_leaf;
-    // put parent(left) leaf's histograms to larger leaf's histgrams
+    // put parent(left) leaf's histograms to larger leaf's histograms
     if (histogram_pool_.Get(left_leaf, &larger_leaf_histogram_array_)) { parent_leaf_histogram_array_ = larger_leaf_histogram_array_; }
     histogram_pool_.Get(right_leaf, &smaller_leaf_histogram_array_);
   }

src/treelearner/serial_tree_learner.h

@@ -121,7 +121,7 @@ protected:
   DataPartition* data_partition_;
   /*! \brief used for generate used features */
   Random random_;
-  /*! \brief used for sub feature training, is_feature_used_[i] = falase means don't used feature i */
+  /*! \brief used for sub feature training, is_feature_used_[i] = false means don't used feature i */
   bool* is_feature_used_;
   /*! \brief pointer to histograms array of parent of current leaves */
   FeatureHistogram* parent_leaf_histogram_array_;