Merge pull request #106 from tqchen/master

pull master into unity

wrapper/README.md

@@ -7,6 +7,10 @@ Python
 * To make the python module, type ```make``` in the root directory of project
 * Refer also to the walk through example in [demo folder](../demo/guide-python)
 
-R 
+R
 =====
 * See [R-package](../R-package)
+
+Julia
+=====
+* See [XGBoost.jl](https://github.com/antinucleon/XGBoost.jl)

wrapper/xgboost.py

@@ -436,7 +436,11 @@ def train(params, dtrain, num_boost_round = 10, evals = [], obj=None, feval=None
     for i in range(num_boost_round):
         bst.update( dtrain, i, obj )
         if len(evals) != 0:
-            sys.stderr.write(bst.eval_set(evals, i, feval).decode()+'\n')
+            bst_eval_set=bst.eval_set(evals, i, feval)
+            if isinstance(bst_eval_set,str):
+                sys.stderr.write(bst_eval_set+'\n')
+            else:
+                sys.stderr.write(bst_eval_set.decode()+'\n')
     return bst
 
 class CVPack:
@@ -467,7 +471,7 @@ def mknfold(dall, nfold, param, seed, evals=[], fpreproc = None):
             dtrain, dtest, tparam = fpreproc(dtrain, dtest, param.copy())
         else:
             tparam = param
-        plst = tparam.items() + [('eval_metric', itm) for itm in evals]
+        plst = list(tparam.items()) + [('eval_metric', itm) for itm in evals]
         ret.append(CVPack(dtrain, dtest, plst))
     return ret
 
@@ -481,12 +485,16 @@ def aggcv(rlist, show_stdv=True):
         arr = line.split()
         assert ret == arr[0]
         for it in arr[1:]:
+            if not isinstance(it,str):
+                it=it.decode()
             k, v  = it.split(':')
             if k not in cvmap:
                 cvmap[k] = []
             cvmap[k].append(float(v))
     for k, v in sorted(cvmap.items(), key = lambda x:x[0]):
         v = np.array(v)
+        if not isinstance(ret,str):
+            ret = ret.decode()
         if show_stdv:
             ret += '\tcv-%s:%f+%f' % (k, np.mean(v), np.std(v))
         else:

wrapper/xgboost_wrapper.cpp

@@ -132,6 +132,7 @@ extern "C"{
                                bst_ulong nrow,
                                bst_ulong ncol,
                                float  missing) {
+    bool nan_missing = std::isnan(missing);
     DMatrixSimple *p_mat = new DMatrixSimple();
     DMatrixSimple &mat = *p_mat;
     mat.info.info.num_row = nrow;
@@ -139,9 +140,13 @@ extern "C"{
     for (bst_ulong i = 0; i < nrow; ++i, data += ncol) {
       bst_ulong nelem = 0;
       for (bst_ulong j = 0; j < ncol; ++j) {
-        if (data[j] != missing) {
-          mat.row_data_.push_back(RowBatch::Entry(j, data[j]));
-          ++nelem;
+        if (std::isnan(data[j])) {
+          utils::Check(nan_missing, "There are NAN in the matrix, however, you did not set missing=NAN");          
+        } else {
+          if (nan_missing || data[j] != missing) {
+            mat.row_data_.push_back(RowBatch::Entry(j, data[j]));
+            ++nelem;
+          }
         }
       }
       mat.row_ptr_.push_back(mat.row_ptr_.back() + nelem);

wrapper/xgboost_wrapper.h

@@ -6,7 +6,6 @@
  * \brief a C style wrapper of xgboost
  *  can be used to create wrapper of other languages
  */
-#include <cstdio>
 #ifdef _MSC_VER
 #define XGB_DLL __declspec(dllexport)
 #else
@@ -15,8 +14,9 @@
 // manually define unsign long
 typedef unsigned long bst_ulong;
 
-
+#ifdef __cplusplus
 extern "C" {
+#endif
   /*!
    * \brief load a data matrix 
    * \return a loaded data matrix
@@ -205,5 +205,7 @@ extern "C" {
    */
   XGB_DLL const char **XGBoosterDumpModel(void *handle, const char *fmap,
                                           bst_ulong *out_len);
+#ifdef __cplusplus
 }
+#endif
 #endif  // XGBOOST_WRAPPER_H_