def ODW(Wo, Wd, transform='r'):
"""
Constructs an o*d by o*d origin-destination style spatial weight for o*d
flows using standard spatial weights on o origins and d destinations. Input
spatial weights must be binary or able to be sutiably transformed to binary.
Parameters
----------
Wo : W object for origin locations
o x o spatial weight object amongst o origins
Wd : W object for destination locations
d x d spatial weight object amongst d destinations
transform : Transformation for standardization of final OD spatial weight; default
is 'r' for row standardized
Returns
-------
W : spatial contiguity W object for assocations between flows
o*d x o*d spatial weight object amongst o*d flows between o
origins and d destinations
Examples
--------
>>> O = pysal.weights.lat2W(2,2)
>>> D = pysal.weights.lat2W(2,2)
>>> OD = pysal.weights.spintW.ODW(O,D)
>>> OD.weights[0]
[0.25, 0.25, 0.25, 0.25]
>>> OD.neighbors[0]
array([ 5, 6, 9, 10], dtype=int32)
>>> OD.full()[0][0]
array([ 0. , 0. , 0. , 0. , 0. , 0.25, 0.25, 0. , 0. ,
0.25, 0.25, 0. , 0. , 0. , 0. , 0. ])
"""
if Wo.transform is not 'b':
try:
Wo.tranform = 'b'
except:
raise AttributeError(
'Wo is not binary and cannot be transformed to '
'binary. Wo must be binary or suitably transformed to binary.')
if Wd.transform is not 'b':
try:
Wd.tranform = 'b'
except:
raise AttributeError(
'Wd is not binary and cannot be transformed to '
'binary. Wd must be binary or suitably transformed to binary.')
Wo = Wo.sparse
Wo.eliminate_zeros()
Wd = Wd.sparse
Wd.eliminate_zeros()
Ww = kron(Wo, Wd, format='csr')
Ww.eliminate_zeros()
Ww = WSP2W(WSP(Ww))
Ww.transform = transform
return Ww
def _distance_to_W(self, ids=None):
if self.binary:
self.dmat[self.dmat > 0] = 1
self.dmat.eliminate_zeros()
tempW = WSP2W(WSP(self.dmat), silent_island_warning=self.silent)
neighbors = tempW.neighbors
weight_keys = tempW.weights.keys()
weight_vals = tempW.weights.values()
weights = dict(zip(weight_keys, map(list, weight_vals)))
return neighbors, weights
else:
weighted = self.dmat.power(self.alpha)
weighted[weighted == np.inf] = 0
weighted.eliminate_zeros()
tempW = WSP2W(WSP(weighted), silent_island_warning=self.silent)
neighbors = tempW.neighbors
weight_keys = tempW.weights.keys()
weight_vals = tempW.weights.values()
weights = dict(zip(weight_keys, map(list, weight_vals)))
return neighbors, weights