remake the wrapper

src/README.md

@@ -0,0 +1,25 @@
+Coding Guide
+======
+
+Project Logical Layout
+=======
+* Dependency order: io->learner->gbm->tree
+  - All module depends on data.h
+* tree are implementations of tree construction algorithms.
+* gbm is gradient boosting interface, that takes trees and other base learner to do boosting.
+  - gbm only takes gradient as sufficient statistics, it does not compute the gradient.
+* learner is learning module that computes gradient for specific object, and pass it to GBM
+
+File Naming Convention
+======= 
+* The project is templatized, to make it easy to adjust input data structure.
+* .h files are data structures and interface, which are needed to use functions in that layer.
+* -inl.hpp files are implementations of interface, like cpp file in most project.
+  - You only need to understand the interface file to understand the usage of that layer
+
+How to Hack the Code
+======
+* Add objective function: add to learner/objective-inl.hpp and register it in learner/objective.h ```CreateObjFunction``` 
+  - You can also directly do it in python
+* Add new evaluation metric: add to learner/evaluation-inl.hpp and register it in learner/evaluation.h ```CreateEvaluator``` 
+* Add wrapper for a new language, most likely you can do it by taking the functions in python/xgboost_wrapper.h, which is purely C based, and call these C functions to use xgboost

src/data.h

@@ -226,8 +226,12 @@ class FMatrixS : public FMatrixInterface<FMatrixS>{
     if (this->HaveColAccess()) return;
     this->InitColData(max_nrow);
   }
-  /*! \brief get the row iterator associated with FMatrix */
+  /*! 
+   * \brief get the row iterator associated with FMatrix 
+   *  this function is not threadsafe, returns iterator stored in FMatrixS
+   */
   inline utils::IIterator<SparseBatch>* RowIterator(void) const {
+    iter_->BeforeFirst();
     return iter_;
   }
   /*! \brief set iterator */

src/io/io.cpp

@@ -2,6 +2,7 @@
 #define _CRT_SECURE_NO_DEPRECATE
 #include <string>
 #include "./io.h"
+#include "../utils/utils.h"
 #include "simple_dmatrix-inl.hpp"
 // implements data loads using dmatrix simple for now
 
@@ -12,5 +13,10 @@ DataMatrix* LoadDataMatrix(const char *fname, bool silent, bool savebuffer) {
   dmat->CacheLoad(fname, silent, savebuffer);
   return dmat;
 }
+
+void SaveDataMatrix(const DataMatrix &dmat, const char *fname, bool silent) {
+  utils::Error("not implemented");
+}
+
 }  // namespace io
 }  // namespace xgboost

src/io/io.h

@@ -28,8 +28,9 @@ DataMatrix* LoadDataMatrix(const char *fname, bool silent = false, bool savebuff
  *  SaveDMatrix will choose the best way to materialize the dmatrix.
  * \param dmat the dmatrix to be saved
  * \param fname file name to be savd
+ * \param silent whether print message during saving
  */
-void SaveDMatrix(const DataMatrix &dmat, const char *fname);  
+void SaveDataMatrix(const DataMatrix &dmat, const char *fname, bool silent = false);  
 
 }  // namespace io
 }  // namespace xgboost

src/io/simple_dmatrix-inl.hpp

@@ -23,7 +23,7 @@ namespace io {
 class DMatrixSimple : public DataMatrix {
  public:
   // constructor
-  DMatrixSimple(void) {
+  DMatrixSimple(void) : DataMatrix(kMagic) {
     this->fmat.set_iter(new OneBatchIter(this));
     this->Clear();
   }
@@ -36,6 +36,24 @@ class DMatrixSimple : public DataMatrix {
     row_data_.clear();
     info.Clear();
   }
+  /*! \brief copy content data from source matrix */
+  inline void CopyFrom(const DataMatrix &src) {
+    this->info = src.info;
+    this->Clear();
+    // clone data content in thos matrix
+    utils::IIterator<SparseBatch> *iter = src.fmat.RowIterator();
+    iter->BeforeFirst();
+    while (iter->Next()) {
+      const SparseBatch &batch = iter->Value();
+      for (size_t i = 0; i < batch.size; ++i) {
+        SparseBatch::Inst inst = batch[i];
+        row_data_.resize(row_data_.size() + inst.length);
+        memcpy(&row_data_[row_ptr_.back()], inst.data,
+               sizeof(SparseBatch::Entry) * inst.length);
+        row_ptr_.push_back(row_ptr_.back() + inst.length);
+      }
+    }
+  }
   /*!
    * \brief add a row to the matrix
    * \param feats features
@@ -183,7 +201,7 @@ class DMatrixSimple : public DataMatrix {
  protected:
   // one batch iterator that return content in the matrix
   struct OneBatchIter: utils::IIterator<SparseBatch> {
-    OneBatchIter(DMatrixSimple *parent)
+    explicit OneBatchIter(DMatrixSimple *parent)
         : at_first_(true), parent_(parent) {}
     virtual ~OneBatchIter(void) {}
     virtual void BeforeFirst(void) {

src/learner/dmatrix.h

@@ -6,6 +6,7 @@
  *        used for regression/classification/ranking
  * \author Tianqi Chen
  */
+#include <vector>
 #include "../data.h"
 
 namespace xgboost {
@@ -43,7 +44,7 @@ struct MetaInfo {
   }
   /*! \brief get weight of each instances */
   inline float GetWeight(size_t i) const {
-    if(weights.size() != 0) {
+    if (weights.size() != 0) {
       return weights[i];
     } else {
       return 1.0f;
@@ -51,7 +52,7 @@ struct MetaInfo {
   }
   /*! \brief get root index of i-th instance */
   inline float GetRoot(size_t i) const {
-    if(root_index.size() != 0) {
+    if (root_index.size() != 0) {
       return static_cast<float>(root_index[i]);
     } else {
       return 0;
@@ -76,7 +77,7 @@ struct MetaInfo {
   // try to load group information from file, if exists
   inline bool TryLoadGroup(const char* fname, bool silent = false) {
     FILE *fi = fopen64(fname, "r");
-    if (fi == NULL) return false;       
+    if (fi == NULL) return false;
     group_ptr.push_back(0);
     unsigned nline;
     while (fscanf(fi, "%u", &nline) == 1) {
@@ -110,6 +111,11 @@ struct MetaInfo {
  */
 template<typename FMatrix>
 struct DMatrix {
+  /*! 
+   * \brief magic number associated with this object 
+   *    used to check if it is specific instance
+   */
+  const int magic;
   /*! \brief meta information about the dataset */
   MetaInfo info;
   /*! \brief feature matrix about data content */
@@ -120,7 +126,7 @@ struct DMatrix {
    */
   void *cache_learner_ptr_;
   /*! \brief default constructor */
-  DMatrix(void) : cache_learner_ptr_(NULL) {}
+  explicit DMatrix(int magic) : magic(magic), cache_learner_ptr_(NULL) {}
   // virtual destructor
   virtual ~DMatrix(void){}
 };

src/learner/evaluation.h

@@ -39,7 +39,7 @@ inline IEvaluator* CreateEvaluator(const char *name) {
   if (!strcmp(name, "merror")) return new EvalMatchError();
   if (!strcmp(name, "logloss")) return new EvalLogLoss();
   if (!strcmp(name, "auc")) return new EvalAuc();
-  if (!strncmp(name, "ams@",4)) return new EvalAMS(name);
+  if (!strncmp(name, "ams@", 4)) return new EvalAMS(name);
   if (!strncmp(name, "pre@", 4)) return new EvalPrecision(name);
   if (!strncmp(name, "map", 3)) return new EvalMAP(name);
   if (!strncmp(name, "ndcg", 3)) return new EvalNDCG(name);

src/learner/learner-inl.hpp

@@ -78,6 +78,7 @@ class BoostLearner {
   inline void SetParam(const char *name, const char *val) {
     if (!strcmp(name, "silent")) silent = atoi(val);
     if (!strcmp(name, "eval_metric")) evaluator_.AddEval(val);
+    if (!strcmp("seed", name)) random::Seed(atoi(val));
     if (gbm_ == NULL) {
       if (!strcmp(name, "objective")) name_obj_ = val;
       if (!strcmp(name, "booster")) name_gbm_ = val;
@@ -132,16 +133,24 @@ class BoostLearner {
     utils::FileStream fo(utils::FopenCheck(fname, "wb"));
     this->SaveModel(fo);
     fo.Close();
-  }  
+  }
+  /*!
+   * \brief check if data matrix is ready to be used by training,
+   *  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();
+  }
   /*!
    * \brief update the model for one iteration
    * \param iter current iteration number
    * \param p_train pointer to the data matrix
    */
-  inline void UpdateOneIter(int iter, DMatrix<FMatrix> *p_train) {
-    this->PredictRaw(*p_train, &preds_);
-    obj_->GetGradient(preds_, p_train->info, iter, &gpair_);
-    gbm_->DoBoost(gpair_, p_train->fmat, p_train->info.root_index);
+  inline void UpdateOneIter(int iter, const DMatrix<FMatrix> &train) {
+    this->PredictRaw(train, &preds_);
+    obj_->GetGradient(preds_, train.info, iter, &gpair_);
+    gbm_->DoBoost(gpair_, train.fmat, train.info.root_index);
   }
   /*!
    * \brief evaluate the model for specific iteration

src/xgboost_main.cpp

@@ -48,7 +48,6 @@ class BoostLearnTask{
   inline void SetParam(const char *name, const char *val) {
     if (!strcmp("silent", name)) silent = atoi(val);
     if (!strcmp("use_buffer", name)) use_buffer = atoi(val);
-    if (!strcmp("seed", name)) random::Seed(atoi(val));
     if (!strcmp("num_round", name)) num_round = atoi(val);
     if (!strcmp("save_period", name)) save_period = atoi(val);
     if (!strcmp("eval_train", name)) eval_train = atoi(val);
@@ -103,9 +102,6 @@ class BoostLearnTask{
     } else {
       // training
       data = io::LoadDataMatrix(train_path.c_str(), silent != 0, use_buffer != 0);
-      {// intialize column access
-        data->fmat.InitColAccess();
-      }
       utils::Assert(eval_data_names.size() == eval_data_paths.size(), "BUG");
       for (size_t i = 0; i < eval_data_names.size(); ++i) {
         deval.push_back(io::LoadDataMatrix(eval_data_paths[i].c_str(), silent != 0, use_buffer != 0));
@@ -139,10 +135,11 @@ class BoostLearnTask{
   inline void TaskTrain(void) {
     const time_t start = time(NULL);
     unsigned long elapsed = 0;
+    learner.CheckInit(data);
     for (int i = 0; i < num_round; ++i) {
       elapsed = (unsigned long)(time(NULL) - start);
       if (!silent) printf("boosting round %d, %lu sec elapsed\n", i, elapsed);
-      learner.UpdateOneIter(i,data); 
+      learner.UpdateOneIter(i, *data); 
       std::string res = learner.EvalOneIter(i, devalall, eval_data_names);
       fprintf(stderr, "%s\n", res.c_str());
       if (save_period != 0 && (i + 1) % save_period == 0) {