More robust DMatrix creation from a sparse matrix (#1606)

* [CORE] DMatrix from sparse w/ explicit #col #row; safer arg types

* [python-package] c-api change for _init_from_csr _init_from_csc

* fix spaces

* [R-package] adopt the new XGDMatrixCreateFromCSCEx interface

* [CORE] redirect old sparse creators to new ones
This commit is contained in:
Vadim Khotilovich
2016-09-25 12:01:22 -05:00
committed by Tianqi Chen
parent e06f6a0df7
commit 693ddb860e
8 changed files with 167 additions and 41 deletions

View File

@@ -287,11 +287,12 @@ class DMatrix(object):
if len(csr.indices) != len(csr.data):
raise ValueError('length mismatch: {} vs {}'.format(len(csr.indices), len(csr.data)))
self.handle = ctypes.c_void_p()
_check_call(_LIB.XGDMatrixCreateFromCSR(c_array(ctypes.c_ulong, csr.indptr),
c_array(ctypes.c_uint, csr.indices),
c_array(ctypes.c_float, csr.data),
len(csr.indptr), len(csr.data),
ctypes.byref(self.handle)))
_check_call(_LIB.XGDMatrixCreateFromCSREx(c_array(ctypes.c_size_t, csr.indptr),
c_array(ctypes.c_uint, csr.indices),
c_array(ctypes.c_float, csr.data),
len(csr.indptr), len(csr.data),
csr.shape[1],
ctypes.byref(self.handle)))
def _init_from_csc(self, csc):
"""
@@ -300,11 +301,12 @@ class DMatrix(object):
if len(csc.indices) != len(csc.data):
raise ValueError('length mismatch: {} vs {}'.format(len(csc.indices), len(csc.data)))
self.handle = ctypes.c_void_p()
_check_call(_LIB.XGDMatrixCreateFromCSC(c_array(ctypes.c_ulong, csc.indptr),
c_array(ctypes.c_uint, csc.indices),
c_array(ctypes.c_float, csc.data),
len(csc.indptr), len(csc.data),
ctypes.byref(self.handle)))
_check_call(_LIB.XGDMatrixCreateFromCSCEx(c_array(ctypes.c_size_t, csc.indptr),
c_array(ctypes.c_uint, csc.indices),
c_array(ctypes.c_float, csc.data),
len(csc.indptr), len(csc.data),
csc.shape[0],
ctypes.byref(self.handle)))
def _init_from_npy2d(self, mat, missing):
"""