def __init__(self,
data,
threshold,
p=2,
alpha=-1.0,
binary=True,
ids=None):
"""Casting to floats is a work around for a bug in scipy.spatial.
See detail in pysal issue #126.
"""
if isKDTree(data):
self.kd = data
self.data = self.kd.data
else:
try:
data = np.asarray(data)
if data.dtype.kind != 'f':
data = data.astype(float)
self.data = data
self.kd = KDTree(self.data)
except:
raise ValueError("Could not make array from data")
self.p = p
self.threshold = threshold
self.binary = binary
self.alpha = alpha
self._band()
neighbors, weights = self._distance_to_W(ids)
W.__init__(self, neighbors, weights, ids)
def __init__(self,
data,
k=2,
p=2,
ids=None,
radius=None,
distance_metric='euclidean'):
if isKDTree(data):
self.kdtree = data
self.data = data.data
else:
self.data = data
self.kdtree = KDTree(data,
radius=radius,
distance_metric=distance_metric)
self.k = k
self.p = p
this_nnq = self.kdtree.query(self.data, k=k + 1, p=p)
to_weight = this_nnq[1]
if ids is None:
ids = list(range(to_weight.shape[0]))
neighbors = {}
for i, row in enumerate(to_weight):
row = row.tolist()
row.remove(i)
row = [ids[j] for j in row]
focal = ids[i]
neighbors[focal] = row
W.__init__(self, neighbors, id_order=ids)
def __init__(self, data, bandwidth=None, fixed=True, k=2,
function='triangular', eps=1.0000001, ids=None,
diagonal=False):
if issubclass(type(data), scipy.spatial.KDTree):
self.kdt = data
self.data = self.kdt.data
data = self.data
else:
self.data = data
self.kdt = KDTree(self.data)
self.k = k + 1
self.function = function.lower()
self.fixed = fixed
self.eps = eps
if bandwidth:
try:
bandwidth = np.array(bandwidth)
bandwidth.shape = (len(bandwidth), 1)
except:
bandwidth = np.ones((len(data), 1), 'float') * bandwidth
self.bandwidth = bandwidth
else:
self._set_bw()
self._eval_kernel()
neighbors, weights = self._k_to_W(ids)
if diagonal:
for i in neighbors:
weights[i][neighbors[i].index(i)] = 1.0
W.__init__(self, neighbors, weights, ids)
def kdtree(self):
if 'kd' in self._propData:
return self._propData['kd']
else:
pts = self.points
if pts is not None:
if self.distMethod == 0: # not Euclidean Distance
kd = KDTree(pts)
elif self.distMethod == 1: # 'Arc Distance (miles)'
kd = KDTree(pts,
distance_metric="Arc",
radius=pysal.cg.RADIUS_EARTH_MILES)
elif self.distMethod == 2: # 'Arc Distance (kilometers)'
kd = KDTree(pts,
distance_metric="Arc",
radius=pysal.cg.RADIUS_EARTH_KM)
self._propData['kd'] = kd
return kd
return None
def knnW(data, k=2, p=2, ids=None):
"""
Creates nearest neighbor weights matrix based on k nearest
neighbors.
Parameters
----------
kdtree : object
PySAL KDTree or ArcKDTree where KDtree.data is array (n,k)
n observations on k characteristics used to measure
distances between the n objects
k : int
number of nearest neighbors
p : float
Minkowski p-norm distance metric parameter:
1<=p<=infinity
2: Euclidean distance
1: Manhattan distance
Ignored if the KDTree is an ArcKDTree
ids : list
identifiers to attach to each observation
Returns
-------
w : W
instance
Weights object with binary weights
Examples
--------
>>> points = [(10, 10), (20, 10), (40, 10), (15, 20), (30, 20), (30, 30)]
>>> kd = pysal.cg.kdtree.KDTree(np.array(points))
>>> wnn2 = pysal.knnW(kd, 2)
>>> [1,3] == wnn2.neighbors[0]
True
ids
>>> wnn2 = knnW(kd,2)
>>> wnn2[0]
{1: 1.0, 3: 1.0}
>>> wnn2[1]
{0: 1.0, 3: 1.0}
now with 1 rather than 0 offset
>>> wnn2 = knnW(kd, 2, ids=range(1,7))
>>> wnn2[1]
{2: 1.0, 4: 1.0}
>>> wnn2[2]
{1: 1.0, 4: 1.0}
>>> 0 in wnn2.neighbors
False
Notes
-----
Ties between neighbors of equal distance are arbitrarily broken.
See Also
--------
pysal.weights.W
"""
if isKDTree(data):
kdt = data
data = kdt.data
else:
kdt = KDTree(data)
nnq = kdt.query(data, k=k + 1, p=p)
info = nnq[1]
neighbors = {}
for i, row in enumerate(info):
row = row.tolist()
if i in row:
row.remove(i)
focal = i
if ids:
row = [ids[j] for j in row]
focal = ids[i]
neighbors[focal] = row
return pysal.weights.W(neighbors, id_order=ids)
def knnW(data, k=2, p=2, ids=None, pct_unique=0.25):
"""
Creates nearest neighbor weights matrix based on k nearest
neighbors.
Parameters
----------
data : array (n,k) or KDTree where KDtree.data is array (n,k)
n observations on k characteristics used to measure
distances between the n objects
k : int
number of nearest neighbors
p : float
Minkowski p-norm distance metric parameter:
1<=p<=infinity
2: Euclidean distance
1: Manhattan distance
ids : list
identifiers to attach to each observation
pct_unique : float
threshold percentage of unique points in data. Below this
threshold tree is built on unique values only
Returns
-------
w : W instance
Weights object with binary weights
Examples
--------
>>> x,y=np.indices((5,5))
>>> x.shape=(25,1)
>>> y.shape=(25,1)
>>> data=np.hstack([x,y])
>>> wnn2=knnW(data,k=2)
>>> wnn4=knnW(data,k=4)
>>> set([1,5,6,2]) == set(wnn4.neighbors[0])
True
>>> set([0,6,10,1]) == set(wnn4.neighbors[5])
True
>>> set([1,5]) == set(wnn2.neighbors[0])
True
>>> set([0,6]) == set(wnn2.neighbors[5])
True
>>> "%.2f"%wnn2.pct_nonzero
'0.08'
>>> wnn4.pct_nonzero
0.16
>>> wnn3e=knnW(data,p=2,k=3)
>>> set([1,5,6]) == set(wnn3e.neighbors[0])
True
>>> wnn3m=knnW(data,p=1,k=3)
>>> a = set([1,5,2])
>>> b = set([1,5,6])
>>> c = set([1,5,10])
>>> w0n = set(wnn3m.neighbors[0])
>>> a==w0n or b==w0n or c==w0n
True
ids
>>> wnn2 = knnW(data,2)
>>> wnn2[0]
{1: 1.0, 5: 1.0}
>>> wnn2[1]
{0: 1.0, 2: 1.0}
now with 1 rather than 0 offset
>>> wnn2 = knnW(data,2, ids = range(1,26))
>>> wnn2[1]
{2: 1.0, 6: 1.0}
>>> wnn2[2]
{1: 1.0, 3: 1.0}
>>> 0 in wnn2.neighbors
False
Notes
-----
Ties between neighbors of equal distance are arbitrarily broken.
See Also
--------
pysal.weights.W
"""
if issubclass(type(data), scipy.spatial.KDTree):
kd = data
data = kd.data
nnq = kd.query(data, k=k+1, p=p)
info = nnq[1]
elif type(data).__name__ == 'ndarray':
# check if unique points are a small fraction of all points
ind = np.lexsort(data.T)
u = data[np.concatenate(([True],np.any(data[ind[1:]]!=data[ind[:-1]],axis=1)))]
pct_u = len(u)*1. / len(data)
if pct_u < pct_unique:
tree = KDTree(u)
nnq = tree.query(data, k=k+1, p=p)
info = nnq[1]
uid = [np.where((data == ui).all(axis=1))[0][0] for ui in u]
new_info = np.zeros((len(data), k + 1), 'int')
for i, row in enumerate(info):
new_info[i] = [uid[j] for j in row]
info = new_info
else:
kd = KDTree(data)
# calculate
nnq = kd.query(data, k=k + 1, p=p)
info = nnq[1]
else:
print 'Unsupported type'
return None
neighbors = {}
for i, row in enumerate(info):
row = row.tolist()
if i in row:
row.remove(i)
focal = i
if ids:
row = [ ids[j] for j in row]
focal = ids[i]
neighbors[focal] = row
return pysal.weights.W(neighbors, id_order=ids)
