def get_hist_slice(gsum0, hsum0, nodeids, nodecansplit, factor, gcovariate, hcovariate,
start, length, slicelen):
nodeslices = VectorSlicer(nodeids)(start, length, slicelen)
factorslices = factor.slicer(start, length, slicelen)
gslices = gcovariate.slicer(start, length, slicelen)
hslices = hcovariate.slicer(start, length, slicelen)
zipslices = Seq.zip(nodeslices, factorslices, gslices, hslices)
return Seq.reduce(f_hist, (gsum0, hsum0, nodecansplit), zipslices)
def __call__(self, start, length, slicelen):
dtypes = [f.slicer.dtype for f in self.factors]
alluint8 = all([d == np.uint8 for d in dtypes])
dtype = np.uint8 if alluint8 else np.uint16
k = len(self.factors)
buf = np.empty((k, slicelen), dtype=dtype)
def f(slices):
n = len(slices[0])
for i in range(k):
if dtypes[i] == dtype:
buf[i, :n] = slices[i]
else:
buf[i, :n] = slices[i].astype(dtype)
if n == slicelen:
return buf
else:
return buf[:, :n]
return Seq.map(
f,
Seq.zip(*[f.slicer(start, length, slicelen)
for f in self.factors]))
def splitnodeidsslice(nodeids, factors, issplitnode, nodemap, leftpartitions, factorindex,
start, length, slicelength):
if len(factors) > 0:
factorslices = NFactorSlicer(factors)(start, length, slicelength)
nodeslices = VectorSlicer(nodeids)(start, length, slicelength)
Seq.foreach(lambda x: f_splitnode(x[0], x[1], issplitnode, leftpartitions, factorindex, nodemap), Seq.zip(nodeslices, factorslices))