make DMatrix._init_from_npy2d only copy data when necessary (#1637)

* make DMatrix._init_from_npy2d only copy data when necessary

When creating DMatrix from a 2d ndarray, it can unnecessarily copy the input data. This can be problematic when the data is already very large--running out of memory. The copy is temporary (going out of scope at the end of this function) but it still adds to peak memory usage.

``numpy.array`` copies its input no matter what by default. By adding ``copy=False``, it will only do so when necessary. Since XGDMatrixCreateFromMat is readonly on the input buffer, this copy is not needed.

Also added comments explaining when a copy can happen (if data ordering/layout is wrong or if type is not 32-bit float).

* remove whitespace

python-package/xgboost/core.py

@@ -311,10 +311,21 @@ class DMatrix(object):
     def _init_from_npy2d(self, mat, missing):
         """
         Initialize data from a 2-D numpy matrix.
+
+        If ``mat`` does not have ``order='C'`` (aka row-major) or is not contiguous,
+        a temporary copy will be made.
+
+        If ``mat`` does not have ``dtype=numpy.float32``, a temporary copy will be made.
+
+        So there could be as many as two temporary data copies; be mindful of input layout
+        and type if memory use is a concern.
         """
         if len(mat.shape) != 2:
             raise ValueError('Input numpy.ndarray must be 2 dimensional')
-        data = np.array(mat.reshape(mat.size), dtype=np.float32)
+        # flatten the array by rows and ensure it is float32.
+        # we try to avoid data copies if possible (reshape returns a view when possible
+        # and we explicitly tell np.array to try and avoid copying)
+        data = np.array(mat.reshape(mat.size), copy=False, dtype=np.float32)
         self.handle = ctypes.c_void_p()
         missing = missing if missing is not None else np.nan
         _check_call(_LIB.XGDMatrixCreateFromMat(data.ctypes.data_as(ctypes.POINTER(ctypes.c_float)),