Merge branch 'master' of https://github.com/Microsoft/LightGBM

Conflicts:
	include/LightGBM/application.h
	include/LightGBM/bin.h

include/LightGBM/application.h

@@ -15,10 +15,10 @@ class Metric;
 
 /*!
 * \brief The main entrance of LightGBM. this application has two tasks:
-* Train and Predict.
-* Train task will train a new model
-* Predict task will predicting the scores of test data using exsiting model,
-* and saving the score to disk.
+*        Train and Predict.
+*        Train task will train a new model
+*        Predict task will predicting the scores of test data using exsiting model,
+*        and saving the score to disk.
 */
 class Application {
 public:

include/LightGBM/bin.h

@@ -255,7 +255,7 @@ public:
   virtual OrderedBin* CreateOrderedBin() const = 0;
 
   /*!
-  * \brief After pushed all feature data, should call this to have better refactor for bin data
+  * \brief After pushed all feature data, call this could have better refactor for bin data
   */
   virtual void FinishLoad() = 0;
 
@@ -263,7 +263,7 @@ public:
   * \brief Create object for bin data of one feature, will call CreateDenseBin or CreateSparseBin according to "is_sparse"
   * \param num_data Total number of data
   * \param num_bin Number of bin
-  * \param is_sparse True if this feature is saprese
+  * \param is_sparse True if this feature is sparse
   * \param sparse_rate Sparse rate of this bins( num_bin0/num_data )
   * \param is_enable_sparse True if enable sparse feature
   * \param is_sparse Will set to true if this bin is sparse

include/LightGBM/boosting.h

@@ -47,14 +47,14 @@ public:
   virtual void Train() = 0;
 
   /*!
-  * \brief Predtion for one record, not sigmoid transform
+  * \brief Prediction for one record, not sigmoid transform
   * \param feature_values Feature value on this record
   * \return Prediction result for this record
   */
   virtual double PredictRaw(const double * feature_values) const = 0;
 
   /*!
-  * \brief Predtion for one record, will use sigmoid transform if needed
+  * \brief Prediction for one record, will use sigmoid transform if needed
   * \param feature_values Feature value on this record
   * \return Prediction result for this record
   */

include/LightGBM/config.h

@@ -20,7 +20,7 @@ public:
   virtual ~ConfigBase() {}
 
   /*!
-  * \brief SetLabelAt current config object by params
+  * \brief Set current config object by params
   * \param params Store the key and value for params
   */
   virtual void Set(
@@ -30,7 +30,7 @@ public:
   * \brief Get string value by specific name of key
   * \param params Store the key and value for params
   * \param name Name of key
-  * \param out Value will asign to out if key exists
+  * \param out Value will assign to out if key exists
   * \return True if key exists
   */
   inline bool GetString(
@@ -41,7 +41,7 @@ public:
   * \brief Get int value by specific name of key
   * \param params Store the key and value for params
   * \param name Name of key
-  * \param out Value will asign to out if key exists
+  * \param out Value will assign to out if key exists
   * \return True if key exists
   */
   inline bool GetInt(
@@ -52,7 +52,7 @@ public:
   * \brief Get double value by specific name of key
   * \param params Store the key and value for params
   * \param name Name of key
-  * \param out Value will asign to out if key exists
+  * \param out Value will assign to out if key exists
   * \return True if key exists
   */
   inline bool GetDouble(
@@ -63,7 +63,7 @@ public:
   * \brief Get bool value by specific name of key
   * \param params Store the key and value for params
   * \param name Name of key
-  * \param out Value will asign to out if key exists
+  * \param out Value will assign to out if key exists
   * \return True if key exists
   */
   inline bool GetBool(

include/LightGBM/dataset.h

@@ -17,7 +17,7 @@ namespace LightGBM {
 class Feature;
 
 /*!
-* \brief This class is used to store some meta(non-feature) data for tranining data,
+* \brief This class is used to store some meta(non-feature) data for training data,
 *        e.g. labels, weights, initial scores, qurey level informations.
 *
 * Some details:
@@ -110,14 +110,14 @@ public:
   }
 
   /*!
-  * \brief Get weights, if not exists, will return nullput
+  * \brief Get weights, if not exists, will return nullptr
   * \return Pointer of weights
   */
   inline const float* weights()
             const { return weights_; }
 
   /*!
-  * \brief Get data boundaries on queries, if not exists, will return nullput
+  * \brief Get data boundaries on queries, if not exists, will return nullptr
   *        we assume data will order by query, 
   *        the interval of [query_boundaris[i], query_boundaris[i+1])
   *        is the data indices for query i.
@@ -133,13 +133,13 @@ public:
   inline const data_size_t num_queries() const { return num_queries_; }
 
   /*!
-  * \brief Get weights for queries, if not exists, will return nullput
+  * \brief Get weights for queries, if not exists, will return nullptr
   * \return Pointer of weights for queries
   */
   inline const float* query_weights() const { return query_weights_; }
 
   /*!
-  * \brief Get initial scores, if not exists, will return nullput
+  * \brief Get initial scores, if not exists, will return nullptr
   * \return Pointer of initial scores
   */
   inline const score_t* init_score() const { return init_score_; }
@@ -231,7 +231,7 @@ public:
   * \param max_bin The maximal number of bin that feature values will bucket in
   * \param random_seed The seed for random generator
   * \param is_enable_sparse True for sparse feature
-  * \param predict_fun Used for initial model, will give a prediction score based on this function, thenn set as initial score
+  * \param predict_fun Used for initial model, will give a prediction score based on this function, then set as initial score
   */
   Dataset(const char* data_filename, const char* init_score_filename,
     int max_bin, int random_seed, bool is_enable_sparse, const PredictFunction& predict_fun);
@@ -243,7 +243,7 @@ public:
   * \param max_bin The maximal number of bin that feature values will bucket in
   * \param random_seed The seed for random generator
   * \param is_enable_sparse True for sparse feature
-  * \param predict_fun Used for initial model, will give a prediction score based on this function, thenn set as initial score
+  * \param predict_fun Used for initial model, will give a prediction score based on this function, then set as initial score
   */
   Dataset(const char* data_filename,
     int max_bin, int random_seed, bool is_enable_sparse,

include/LightGBM/network.h

@@ -37,7 +37,7 @@ public:
 
 /*!
 * \brief node type on recursive halving algorithm
-* When number of machines is not power of 2, need group maiches into power of 2 group.
+* When number of machines is not power of 2, need group machines into power of 2 group.
 * And we can let each group has at most 2 machines.
 * if the group only has 1 machine. this machine is the normal node
 * if the grou has 2 machines, this group will have two type of nodes, one is the leader.

src/boosting/gbdt.cpp

@@ -152,7 +152,7 @@ void GBDT::Bagging(int iter) {
 }
 
 void GBDT::UpdateScoreOutOfBag(const Tree* tree) {
-  // we need to predict out-of-bag data's socres for boosing
+  // we need to predict out-of-bag socres of data for boosting
   if (out_of_bag_data_indices_ != nullptr) {
     train_score_updater_->
       AddScore(tree, out_of_bag_data_indices_, out_of_bag_data_cnt_);
@@ -169,12 +169,12 @@ void GBDT::Train() {
     Bagging(iter);
     // train a new tree
     Tree * new_tree = TrainOneTree();
-    // if cannon learn a new tree, stop
+    // if cannot learn a new tree, then stop
     if (new_tree->num_leaves() <= 1) {
       Log::Stdout("Cannot do any boosting for tree cannot split");
       break;
     }
-    // Shrinkage by learning rate
+    // shrinkage by learning rate
     new_tree->Shrinkage(gbdt_config_->learning_rate);
     // update score
     UpdateScore(new_tree);
@@ -183,12 +183,12 @@ void GBDT::Train() {
     OutputMetric(iter + 1);
     // add model
     models_.push_back(new_tree);
-    // write model to file on every iteration
+    // save model to file per iteration
     fprintf(output_model_file, "Tree=%d\n", iter);
     fprintf(output_model_file, "%s\n", new_tree->ToString().c_str());
     fflush(output_model_file);
     auto end_time = std::chrono::high_resolution_clock::now();
-    // output used time on each iteration
+    // output used time per iteration
     Log::Stdout("%f seconds elapsed, finished %d iteration", std::chrono::duration<double,
                                      std::milli>(end_time - start_time) * 1e-3, iter + 1);
   }
@@ -223,7 +223,7 @@ void GBDT::OutputMetric(int iter) {
 }
 
 void GBDT::Boosting() {
-  // objective function will calculation gradients and hessians
+  // objective function will calculate gradients and hessians
   object_function_->
     GetGradients(train_score_updater_->score(), gradients_, hessians_);
 }