add create from csc

wrapper/xgboost.py

@@ -22,6 +22,7 @@ xglib = ctypes.cdll.LoadLibrary(XGBOOST_PATH)
 # DMatrix functions
 xglib.XGDMatrixCreateFromFile.restype = ctypes.c_void_p
 xglib.XGDMatrixCreateFromCSR.restype = ctypes.c_void_p
+xglib.XGDMatrixCreateFromCSC.restype = ctypes.c_void_p
 xglib.XGDMatrixCreateFromMat.restype = ctypes.c_void_p
 xglib.XGDMatrixSliceDMatrix.restype = ctypes.c_void_p
 xglib.XGDMatrixGetFloatInfo.restype = ctypes.POINTER(ctypes.c_float)
@@ -66,6 +67,8 @@ class DMatrix:
                 xglib.XGDMatrixCreateFromFile(ctypes.c_char_p(data.encode('utf-8')), 0))
         elif isinstance(data, scp.csr_matrix):
             self.__init_from_csr(data)
+        elif isinstance(data, scp.csc_matrix):
+            self.__init_from_csc(data)            
         elif isinstance(data, numpy.ndarray) and len(data.shape) == 2:
             self.__init_from_npy2d(data, missing)
         else:
@@ -88,6 +91,15 @@ class DMatrix:
             (ctypes.c_float * len(csr.data))(*csr.data),
             len(csr.indptr), len(csr.data)))
 
+    def __init_from_csc(self, csc):
+        """convert data from csr matrix"""
+        assert len(csc.indices) == len(csc.data)
+        self.handle = ctypes.c_void_p(xglib.XGDMatrixCreateFromCSC(
+            (ctypes.c_ulong  * len(csc.indptr))(*csc.indptr),
+            (ctypes.c_uint * len(csc.indices))(*csc.indices),
+            (ctypes.c_float * len(csc.data))(*csc.data),
+            len(csc.indptr), len(csc.data)))
+
     def __init_from_npy2d(self,mat,missing):
         """convert data from numpy matrix"""
         data = numpy.array(mat.reshape(mat.size), dtype='float32')

wrapper/xgboost_wrapper.cpp

@@ -14,6 +14,7 @@ using namespace std;
 #include "../src/learner/learner-inl.hpp"
 #include "../src/io/io.h"
 #include "../src/utils/utils.h"
+#include "../src/utils/matrix_csr.h"
 #include "../src/io/simple_dmatrix-inl.hpp"
 
 using namespace xgboost;
@@ -102,6 +103,31 @@ extern "C"{
     mat.info.info.num_row = nindptr - 1;
     return p_mat;
   }
+  XGB_DLL void* XGDMatrixCreateFromCSC(const bst_ulong *col_ptr,
+                                       const unsigned *indices,
+                                       const float *data,
+                                       bst_ulong nindptr,
+                                       bst_ulong nelem) {
+    DMatrixSimple *p_mat = new DMatrixSimple();
+    DMatrixSimple &mat = *p_mat;
+    utils::SparseCSRMBuilder<RowBatch::Entry, false> builder(mat.row_ptr_, mat.row_data_);
+    builder.InitBudget();
+    bst_ulong ncol = nindptr - 1;
+    for (bst_ulong i = 0; i < ncol; ++i) {
+      for (unsigned j = col_ptr[i]; j < col_ptr[i+1]; ++j) {
+        builder.AddBudget(indices[j]);
+      }
+    }
+    builder.InitStorage();
+    for (bst_ulong i = 0; i < ncol; ++i) {
+      for (unsigned j = col_ptr[i]; j < col_ptr[i+1]; ++j) {
+        builder.PushElem(indices[j], RowBatch::Entry(static_cast<bst_uint>(i), data[j]));
+      }
+    }
+    mat.info.info.num_row = mat.row_ptr_.size() - 1;
+    mat.info.info.num_col = static_cast<size_t>(ncol);
+    return p_mat;
+  }
   void* XGDMatrixCreateFromMat(const float *data,
                                bst_ulong nrow,
                                bst_ulong ncol,

wrapper/xgboost_wrapper.h

@@ -22,7 +22,7 @@ extern "C" {
    * \return a loaded data matrix
    */
   XGB_DLL void* XGDMatrixCreateFromFile(const char *fname, int silent);
-  /*! 
+  /*!
    * \brief create a matrix content from csr format
    * \param indptr pointer to row headers
    * \param indices findex
@@ -36,6 +36,20 @@ extern "C" {
                                        const float *data,
                                        bst_ulong nindptr,
                                        bst_ulong nelem);
+  /*!
+   * \brief create a matrix content from CSC format
+   * \param col_ptr pointer to col headers
+   * \param indices findex
+   * \param data fvalue
+   * \param nindptr number of rows in the matix + 1 
+   * \param nelem number of nonzero elements in the matrix
+   * \return created dmatrix
+   */
+  XGB_DLL void* XGDMatrixCreateFromCSC(const bst_ulong *col_ptr,
+                                       const unsigned *indices,
+                                       const float *data,
+                                       bst_ulong nindptr,
+                                       bst_ulong nelem);  
   /*!
    * \brief create matrix content from dense matrix
    * \param data pointer to the data space