fixed modifiers indent (#1997)

src/network/linkers.h

@@ -32,7 +32,7 @@ namespace LightGBM {
 * This class will wrap all linkers to other machines if needs
 */
 class Linkers {
-public:
+ public:
   Linkers() {
     is_init_ = false;
   }
@@ -136,7 +136,7 @@ public:
   #endif  // USE_SOCKET
 
 
-private:
+ private:
   /*! \brief Rank of local machine */
   int rank_;
   /*! \brief Total number machines */

src/network/socket_wrapper.hpp

@@ -86,7 +86,7 @@ const bool kNoDelay = true;
 }
 
 class TcpSocket {
-public:
+ public:
   TcpSocket() {
     sockfd_ = socket(AF_INET, SOCK_STREAM, IPPROTO_TCP);
     if (sockfd_ == INVALID_SOCKET) {
@@ -291,7 +291,7 @@ public:
     }
   }
 
-private:
+ private:
   SOCKET sockfd_;
 };
 

src/objective/binary_objective.hpp

@@ -11,7 +11,7 @@ namespace LightGBM {
 * \brief Objective function for binary classification
 */
 class BinaryLogloss: public ObjectiveFunction {
-public:
+ public:
   explicit BinaryLogloss(const Config& config, std::function<bool(label_t)> is_pos = nullptr) {
     sigmoid_ = static_cast<double>(config.sigmoid);
     if (sigmoid_ <= 0.0) {
@@ -172,7 +172,7 @@ public:
 
   bool NeedAccuratePrediction() const override { return false; }
 
-private:
+ private:
   /*! \brief Number of data */
   data_size_t num_data_;
   /*! \brief Pointer of label */

src/objective/multiclass_objective.hpp

@@ -14,7 +14,7 @@ namespace LightGBM {
 * \brief Objective function for multiclass classification, use softmax as objective functions
 */
 class MulticlassSoftmax: public ObjectiveFunction {
-public:
+ public:
   explicit MulticlassSoftmax(const Config& config) {
     num_class_ = config.num_class;
   }
@@ -146,7 +146,7 @@ public:
     }
   }
 
-private:
+ private:
   /*! \brief Number of data */
   data_size_t num_data_;
   /*! \brief Number of classes */
@@ -164,7 +164,7 @@ private:
 * \brief Objective function for multiclass classification, use one-vs-all binary objective function
 */
 class MulticlassOVA: public ObjectiveFunction {
-public:
+ public:
   explicit MulticlassOVA(const Config& config) {
     num_class_ = config.num_class;
     for (int i = 0; i < num_class_; ++i) {
@@ -246,7 +246,7 @@ public:
     return binary_loss_[class_id]->ClassNeedTrain(0);
   }
 
-private:
+ private:
   /*! \brief Number of data */
   data_size_t num_data_;
   /*! \brief Number of classes */

src/objective/rank_objective.hpp

@@ -17,7 +17,7 @@ namespace LightGBM {
 * \brief Objective function for Lambdrank with NDCG
 */
 class LambdarankNDCG: public ObjectiveFunction {
-public:
+ public:
   explicit LambdarankNDCG(const Config& config) {
     sigmoid_ = static_cast<double>(config.sigmoid);
     label_gain_ = config.label_gain;
@@ -205,7 +205,7 @@ public:
 
   bool NeedAccuratePrediction() const override { return false; }
 
-private:
+ private:
   /*! \brief Gains for labels */
   std::vector<double> label_gain_;
   /*! \brief Cache inverse max DCG, speed up calculation */

src/objective/regression_objective.hpp

@@ -69,7 +69,7 @@ namespace LightGBM {
 * \brief Objective function for regression
 */
 class RegressionL2loss: public ObjectiveFunction {
-public:
+ public:
   explicit RegressionL2loss(const Config& config) {
     sqrt_ = config.reg_sqrt;
   }
@@ -165,7 +165,7 @@ public:
     return suml / sumw;
   }
 
-protected:
+ protected:
   bool sqrt_;
   /*! \brief Number of data */
   data_size_t num_data_;
@@ -180,7 +180,7 @@ protected:
 * \brief L1 regression loss
 */
 class RegressionL1loss: public RegressionL2loss {
-public:
+ public:
   explicit RegressionL1loss(const Config& config): RegressionL2loss(config) {
   }
 
@@ -298,7 +298,7 @@ public:
 * \brief Huber regression loss
 */
 class RegressionHuberLoss: public RegressionL2loss {
-public:
+ public:
   explicit RegressionHuberLoss(const Config& config): RegressionL2loss(config) {
     alpha_ = static_cast<double>(config.alpha);
     if (sqrt_) {
@@ -352,7 +352,7 @@ public:
     return false;
   }
 
-private:
+ private:
   /*! \brief delta for Huber loss */
   double alpha_;
 };
@@ -360,7 +360,7 @@ private:
 
 // http://research.microsoft.com/en-us/um/people/zhang/INRIA/Publis/Tutorial-Estim/node24.html
 class RegressionFairLoss: public RegressionL2loss {
-public:
+ public:
   explicit RegressionFairLoss(const Config& config): RegressionL2loss(config) {
     c_ = static_cast<double>(config.fair_c);
   }
@@ -397,7 +397,7 @@ public:
     return false;
   }
 
-private:
+ private:
   /*! \brief c for Fair loss */
   double c_;
 };
@@ -407,7 +407,7 @@ private:
 * \brief Objective function for Poisson regression
 */
 class RegressionPoissonLoss: public RegressionL2loss {
-public:
+ public:
   explicit RegressionPoissonLoss(const Config& config): RegressionL2loss(config) {
     max_delta_step_ = static_cast<double>(config.poisson_max_delta_step);
     if (sqrt_) {
@@ -481,13 +481,13 @@ public:
     return false;
   }
 
-private:
+ private:
   /*! \brief used to safeguard optimization */
   double max_delta_step_;
 };
 
 class RegressionQuantileloss : public RegressionL2loss {
-public:
+ public:
   explicit RegressionQuantileloss(const Config& config): RegressionL2loss(config) {
     alpha_ = static_cast<score_t>(config.alpha);
     CHECK(alpha_ > 0 && alpha_ < 1);
@@ -607,7 +607,7 @@ public:
     }
   }
 
-private:
+ private:
   score_t alpha_;
 };
 
@@ -616,7 +616,7 @@ private:
 * \brief Mape Regression Loss
 */
 class RegressionMAPELOSS : public RegressionL1loss {
-public:
+ public:
   explicit RegressionMAPELOSS(const Config& config) : RegressionL1loss(config) {
   }
 
@@ -725,7 +725,7 @@ public:
     return true;
   }
 
-private:
+ private:
   std::vector<label_t> label_weight_;
 };
 
@@ -735,7 +735,7 @@ private:
 * \brief Objective function for Gamma regression
 */
 class RegressionGammaLoss : public RegressionPoissonLoss {
-public:
+ public:
   explicit RegressionGammaLoss(const Config& config) : RegressionPoissonLoss(config) {
   }
 
@@ -770,7 +770,7 @@ public:
 * \brief Objective function for Tweedie regression
 */
 class RegressionTweedieLoss: public RegressionPoissonLoss {
-public:
+ public:
   explicit RegressionTweedieLoss(const Config& config) : RegressionPoissonLoss(config) {
     rho_ = config.tweedie_variance_power;
   }
@@ -803,7 +803,7 @@ public:
     return "tweedie";
   }
 
-private:
+ private:
   double rho_;
 };
 

src/objective/xentropy_objective.hpp

@@ -36,7 +36,7 @@ namespace LightGBM {
 * \brief Objective function for cross-entropy (with optional linear weights)
 */
 class CrossEntropy: public ObjectiveFunction {
-public:
+ public:
   explicit CrossEntropy(const Config&) {
   }
 
@@ -127,7 +127,7 @@ public:
     return initscore;
   }
 
-private:
+ private:
   /*! \brief Number of data points */
   data_size_t num_data_;
   /*! \brief Pointer for label */
@@ -140,7 +140,7 @@ private:
 * \brief Objective function for alternative parameterization of cross-entropy (see top of file for explanation)
 */
 class CrossEntropyLambda: public ObjectiveFunction {
-public:
+ public:
   explicit CrossEntropyLambda(const Config&) {
     min_weight_ = max_weight_ = 0.0f;
   }

src/treelearner/data_partition.hpp

@@ -15,7 +15,7 @@ namespace LightGBM {
 * \brief DataPartition is used to store the the partition of data on tree.
 */
 class DataPartition {
-public:
+ public:
   DataPartition(data_size_t num_data, int num_leaves)
     :num_data_(num_data), num_leaves_(num_leaves) {
     leaf_begin_.resize(num_leaves_);
@@ -188,7 +188,7 @@ public:
   /*! \brief Get number of leaves */
   int num_leaves() const { return num_leaves_; }
 
-private:
+ private:
   /*! \brief Number of all data */
   data_size_t num_data_;
   /*! \brief Number of all leaves */

src/treelearner/feature_histogram.hpp

@@ -12,7 +12,7 @@
 namespace LightGBM {
 
 class FeatureMetainfo {
-public:
+ public:
   int num_bin;
   MissingType missing_type;
   int8_t bias = 0;
@@ -27,7 +27,7 @@ public:
 * \brief FeatureHistogram is used to construct and store a histogram for a feature.
 */
 class FeatureHistogram {
-public:
+ public:
   FeatureHistogram() {
     data_ = nullptr;
   }
@@ -449,7 +449,7 @@ public:
     }
   }
 
-private:
+ private:
   static double GetSplitGains(double sum_left_gradients, double sum_left_hessians,
                               double sum_right_gradients, double sum_right_hessians,
                               double l1, double l2, double max_delta_step,
@@ -644,7 +644,7 @@ private:
   std::function<void(double, double, data_size_t, double, double, SplitInfo*)> find_best_threshold_fun_;
 };
 class HistogramPool {
-public:
+ public:
   /*!
   * \brief Constructor
   */
@@ -804,7 +804,7 @@ public:
     inverse_mapper_[slot] = dst_idx;
   }
 
-private:
+ private:
   std::vector<std::unique_ptr<FeatureHistogram[]>> pool_;
   std::vector<std::vector<HistogramBinEntry>> data_;
   std::vector<FeatureMetainfo> feature_metas_;

src/treelearner/gpu_tree_learner.h

@@ -36,7 +36,7 @@ namespace LightGBM {
 * \brief GPU-based parallel learning algorithm.
 */
 class GPUTreeLearner: public SerialTreeLearner {
-public:
+ public:
   explicit GPUTreeLearner(const Config* tree_config);
   ~GPUTreeLearner();
   void Init(const Dataset* train_data, bool is_constant_hessian) override;
@@ -57,14 +57,14 @@ public:
     use_bagging_ = false;
   }
 
-protected:
+ protected:
   void BeforeTrain() override;
   bool BeforeFindBestSplit(const Tree* tree, int left_leaf, int right_leaf) override;
   void FindBestSplits() override;
   void Split(Tree* tree, int best_Leaf, int* left_leaf, int* right_leaf) override;
   void ConstructHistograms(const std::vector<int8_t>& is_feature_used, bool use_subtract) override;
 
-private:
+ private:
   /*! \brief 4-byte feature tuple used by GPU kernels */
   struct Feature4 {
       uint8_t s[4];
@@ -269,7 +269,7 @@ private:
 namespace LightGBM {
 
 class GPUTreeLearner: public SerialTreeLearner {
-public:
+ public:
   #pragma warning(disable : 4702)
   explicit GPUTreeLearner(const Config* tree_config) : SerialTreeLearner(tree_config) {
     Log::Fatal("GPU Tree Learner was not enabled in this build.\n"

src/treelearner/leaf_splits.hpp

@@ -14,7 +14,7 @@ namespace LightGBM {
 * \brief used to find split candidates for a leaf
 */
 class LeafSplits {
-public:
+ public:
   LeafSplits(data_size_t num_data)
     :num_data_in_leaf_(num_data), num_data_(num_data),
     data_indices_(nullptr) {
@@ -141,7 +141,7 @@ public:
   const data_size_t* data_indices() const { return data_indices_; }
 
 
-private:
+ private:
   /*! \brief current leaf index */
   int leaf_index_;
   /*! \brief number of data on current leaf */

src/treelearner/parallel_tree_learner.h

@@ -20,15 +20,16 @@ namespace LightGBM {
 */
 template <typename TREELEARNER_T>
 class FeatureParallelTreeLearner: public TREELEARNER_T {
-public:
+ public:
   explicit FeatureParallelTreeLearner(const Config* config);
   ~FeatureParallelTreeLearner();
   void Init(const Dataset* train_data, bool is_constant_hessian) override;
 
-protected:
+ protected:
   void BeforeTrain() override;
   void FindBestSplitsFromHistograms(const std::vector<int8_t>& is_feature_used, bool use_subtract) override;
-private:
+
+ private:
   /*! \brief rank of local machine */
   int rank_;
   /*! \brief Number of machines of this parallel task */
@@ -46,13 +47,13 @@ private:
 */
 template <typename TREELEARNER_T>
 class DataParallelTreeLearner: public TREELEARNER_T {
-public:
+ public:
   explicit DataParallelTreeLearner(const Config* config);
   ~DataParallelTreeLearner();
   void Init(const Dataset* train_data, bool is_constant_hessian) override;
   void ResetConfig(const Config* config) override;
 
-protected:
+ protected:
   void BeforeTrain() override;
   void FindBestSplits() override;
   void FindBestSplitsFromHistograms(const std::vector<int8_t>& is_feature_used, bool use_subtract) override;
@@ -66,7 +67,7 @@ protected:
     }
   }
 
-private:
+ private:
   /*! \brief Rank of local machine */
   int rank_;
   /*! \brief Number of machines of this parallel task */
@@ -100,13 +101,13 @@ private:
 */
 template <typename TREELEARNER_T>
 class VotingParallelTreeLearner: public TREELEARNER_T {
-public:
+ public:
   explicit VotingParallelTreeLearner(const Config* config);
   ~VotingParallelTreeLearner() { }
   void Init(const Dataset* train_data, bool is_constant_hessian) override;
   void ResetConfig(const Config* config) override;
 
-protected:
+ protected:
   void BeforeTrain() override;
   bool BeforeFindBestSplit(const Tree* tree, int left_leaf, int right_leaf) override;
   void FindBestSplits() override;
@@ -136,7 +137,7 @@ protected:
   void CopyLocalHistogram(const std::vector<int>& smaller_top_features,
     const std::vector<int>& larger_top_features);
 
-private:
+ private:
   /*! \brief Tree config used in local mode */
   Config local_config_;
   /*! \brief Voting size */

src/treelearner/serial_tree_learner.h

@@ -32,7 +32,7 @@ namespace LightGBM {
 * \brief Used for learning a tree by single machine
 */
 class SerialTreeLearner: public TreeLearner {
-public:
+ public:
   explicit SerialTreeLearner(const Config* config);
 
   ~SerialTreeLearner();
@@ -75,7 +75,7 @@ public:
   void RenewTreeOutput(Tree* tree, const ObjectiveFunction* obj, double prediction,
                        data_size_t total_num_data, const data_size_t* bag_indices, data_size_t bag_cnt) const override;
 
-protected:
+ protected:
   /*!
   * \brief Some initial works before training
   */

src/treelearner/split_info.hpp

@@ -15,7 +15,7 @@ namespace LightGBM {
 * \brief Used to store some information for gain split point
 */
 struct SplitInfo {
-public:
+ public:
   /*! \brief Feature index */
   int feature = -1;
   /*! \brief Split threshold */
@@ -188,7 +188,7 @@ public:
 };
 
 struct LightSplitInfo {
-public:
+ public:
   /*! \brief Feature index */
   int feature = -1;
   /*! \brief Split gain */