refresher test

src/data.h

@@ -199,6 +199,10 @@ class FMatrixS : public FMatrixInterface<FMatrixS>{
     utils::Check(this->HaveColAccess(), "NumCol:need column access");
     return col_ptr_.size() - 1;
   }
+  /*! \brief get number of buffered rows */  
+  inline size_t NumBufferedRow(void) const {
+    return num_buffered_row_;
+  }
   /*! \brief get col sorted iterator */
   inline ColIter GetSortedCol(size_t cidx) const {
     utils::Assert(cidx < this->NumCol(), "col id exceed bound");

src/learner/learner-inl.hpp

@@ -9,6 +9,7 @@
 #include <vector>
 #include <utility>
 #include <string>
+#include <limits>
 #include "./objective.h"
 #include "./evaluation.h"
 #include "../gbm/gbm.h"
@@ -28,6 +29,8 @@ class BoostLearner {
     gbm_ = NULL;
     name_obj_ = "reg:linear";
     name_gbm_ = "gbtree";
+    silent= 0;
+    max_buffer_row = std::numeric_limits<size_t>::max();
   }
   ~BoostLearner(void) {
     if (obj_ != NULL) delete obj_;
@@ -77,6 +80,7 @@ class BoostLearner {
    */
   inline void SetParam(const char *name, const char *val) {
     if (!strcmp(name, "silent")) silent = atoi(val);
+    if (!strcmp(name, "max_buffer_row")) sscanf(val, "%lu", &max_buffer_row);
     if (!strcmp(name, "eval_metric")) evaluator_.AddEval(val);
     if (!strcmp("seed", name)) random::Seed(atoi(val));
     if (!strcmp(name, "num_class")) this->SetParam("num_output_group", val);
@@ -87,7 +91,9 @@ class BoostLearner {
     }
     if (gbm_ != NULL) gbm_->SetParam(name, val);
     if (obj_ != NULL) obj_->SetParam(name, val);
-    cfg_.push_back(std::make_pair(std::string(name), std::string(val)));
+    if (gbm_ == NULL || obj_ == NULL) {
+      cfg_.push_back(std::make_pair(std::string(name), std::string(val)));
+    }
   }
   /*!
    * \brief initialize the model
@@ -144,8 +150,8 @@ class BoostLearner {
    *  if not intialize it
    * \param p_train pointer to the matrix used by training
    */
-  inline void CheckInit(DMatrix<FMatrix> *p_train) const {
-    p_train->fmat.InitColAccess();
+  inline void CheckInit(DMatrix<FMatrix> *p_train) {
+    p_train->fmat.InitColAccess(max_buffer_row);
   }
   /*!
    * \brief update the model for one iteration
@@ -286,6 +292,8 @@ class BoostLearner {
   // data fields
   // silent during training
   int silent;
+  // maximum buffred row value
+  size_t max_buffer_row;
   // evaluation set
   EvalSet evaluator_;
   // model parameter

src/tree/updater_colmaker-inl.hpp

@@ -110,22 +110,22 @@ class ColMaker: public IUpdater<FMatrix> {
                          const std::vector<unsigned> &root_index, const RegTree &tree) {
       utils::Assert(tree.param.num_nodes == tree.param.num_roots, "ColMaker: can only grow new tree");
       {// setup position
-        position.resize(gpair.size());
+        position.resize(fmat.NumBufferedRow());
         if (root_index.size() == 0) {
           std::fill(position.begin(), position.end(), 0);
         } else {
-          for (size_t i = 0; i < root_index.size(); ++i) {
+          for (size_t i = 0; i < position.size(); ++i) {
             position[i] = root_index[i];
             utils::Assert(root_index[i] < (unsigned)tree.param.num_roots, "root index exceed setting");
           }
         }
         // mark delete for the deleted datas
-        for (size_t i = 0; i < gpair.size(); ++i) {
+        for (size_t i = 0; i < position.size(); ++i) {
           if (gpair[i].hess < 0.0f) position[i] = -1;
         }
         // mark subsample
         if (param.subsample < 1.0f) {
-          for (size_t i = 0; i < gpair.size(); ++i) {
+          for (size_t i = 0; i < position.size(); ++i) {
             if (gpair[i].hess < 0.0f) continue;
             if (random::SampleBinary(param.subsample) == 0) position[i] = -1;
           }
@@ -271,7 +271,9 @@ class ColMaker: public IUpdater<FMatrix> {
       }
       // start enumeration
       const unsigned nsize = static_cast<unsigned>(feat_set.size());
+      #if defined(_OPENMP)
       const int batch_size = std::max(static_cast<int>(nsize / this->nthread / 32), 1);
+      #endif
       #pragma omp parallel for schedule(dynamic, batch_size)
       for (unsigned i = 0; i < nsize; ++i) {
         const unsigned fid = feat_set[i];

src/tree/updater_refresh-inl.hpp

@@ -20,7 +20,6 @@ class TreeRefresher: public IUpdater<FMatrix> {
   // set training parameter
   virtual void SetParam(const char *name, const char *val) {
     param.SetParam(name, val);
-    if (!strcmp(name, "silent")) silent = atoi(val);
   }
   // update the tree, do pruning
   virtual void Update(const std::vector<bst_gpair> &gpair,
@@ -127,8 +126,6 @@ class TreeRefresher: public IUpdater<FMatrix> {
   }
   // number of thread in the data
   int nthread;
-  // shutup
-  int silent;
   // training parameter
   TrainParam param;
 };