def threshold_continuousW_from_shapefile(shapefile, threshold, p=2,
alpha=-1, idVariable=None, radius=None):
"""
Threshold distance based continuous weights from a shapefile.
Parameters
----------
shapefile : string
shapefile name with shp suffix
threshold : float
distance band
p : float
Minkowski p-norm distance metric parameter:
1<=p<=infinity
2: Euclidean distance
1: Manhattan distance
alpha : float
distance decay parameter for weight (default -1.0)
if alpha is positive the weights will not decline with
distance.
idVariable : string
name of a column in the shapefile's DBF to use for ids
radius : float
If supplied arc_distances will be calculated
based on the given radius. p will be ignored.
Returns
-------
w : W
instance; Weights object with continuous weights.
Examples
--------
>>> w = threshold_continuousW_from_shapefile(pysal.examples.get_path("columbus.shp"),0.62,idVariable="POLYID")
>>> w.weights[1]
[1.6702346893743334, 1.7250729841938093]
Notes
-----
Supports polygon or point shapefiles. For polygon shapefiles, distance is
based on polygon centroids. Distances are defined using coordinates in
shapefile which are assumed to be projected and not geographical
coordinates.
"""
data = get_points_array_from_shapefile(shapefile)
if radius is not None:
data = pysal.cg.KDTree(data, distance_metric='Arc', radius=radius)
if idVariable:
ids = get_ids(shapefile, idVariable)
w = DistanceBand(data, threshold=threshold, p=p, alpha=alpha, binary=False)
w.remap_ids(ids)
else:
w = threshold_continuousW_from_array(data, threshold, p=p, alpha=alpha)
w.set_shapefile(shapefile,idVariable)
return w
def threshold_binaryW_from_shapefile(shapefile,
threshold,
p=2,
idVariable=None,
radius=None):
"""
Threshold distance based binary weights from a shapefile.
Parameters
----------
shapefile : string
shapefile name with shp suffix
threshold : float
distance band
p : float
Minkowski p-norm distance metric parameter:
1<=p<=infinity
2: Euclidean distance
1: Manhattan distance
idVariable : string
name of a column in the shapefile's DBF to use for ids
radius : float
If supplied arc_distances will be calculated
based on the given radius. p will be ignored.
Returns
-------
w : W
instance
Weights object with binary weights
Examples
--------
>>> import libpysal.api as ps
>>> import libpysal
>>> w = ps.threshold_binaryW_from_shapefile(libpysal.examples.get_path("columbus.shp"),0.62,idVariable="POLYID")
>>> w.weights[1]
[1.0, 1.0]
Notes
-----
Supports polygon or point shapefiles. For polygon shapefiles, distance is
based on polygon centroids. Distances are defined using coordinates in
shapefile which are assumed to be projected and not geographical
coordinates.
"""
data = get_points_array_from_shapefile(shapefile)
if radius is not None:
data = cg.KDTree(data, distance_metric='Arc', radius=radius)
if idVariable:
ids = get_ids(shapefile, idVariable)
w = DistanceBand(data, threshold=threshold, p=p)
w.remap_ids(ids)
return w
return threshold_binaryW_from_array(data, threshold, p=p)
def threshold_binaryW_from_shapefile(shapefile, threshold, p=2, idVariable=None, radius=None):
"""
Threshold distance based binary weights from a shapefile.
Parameters
----------
shapefile : string
shapefile name with shp suffix
threshold : float
distance band
p : float
Minkowski p-norm distance metric parameter:
1<=p<=infinity
2: Euclidean distance
1: Manhattan distance
idVariable : string
name of a column in the shapefile's DBF to use for ids
radius : float
If supplied arc_distances will be calculated
based on the given radius. p will be ignored.
Returns
-------
w : W
instance
Weights object with binary weights
Examples
--------
>>> w = threshold_binaryW_from_shapefile(pysal.examples.get_path("columbus.shp"),0.62,idVariable="POLYID")
>>> w.weights[1]
[1, 1]
Notes
-----
Supports polygon or point shapefiles. For polygon shapefiles, distance is
based on polygon centroids. Distances are defined using coordinates in
shapefile which are assumed to be projected and not geographical
coordinates.
"""
data = get_points_array_from_shapefile(shapefile)
if radius is not None:
data = pysal.cg.KDTree(data, distance_metric='Arc', radius=radius)
if idVariable:
ids = get_ids(shapefile, idVariable)
w = DistanceBand(data, threshold=threshold, p=p)
w.remap_ids(ids)
return w
return threshold_binaryW_from_array(data, threshold, p=p)
def min_threshold_dist_from_shapefile(shapefile, radius=None, p=2):
"""
Kernel weights with adaptive bandwidths.
Parameters
----------
shapefile : string
shapefile name with shp suffix.
radius : float
If supplied arc_distances will be calculated
based on the given radius. p will be ignored.
p : float
Minkowski p-norm distance metric parameter:
1<=p<=infinity
2: Euclidean distance
1: Manhattan distance
Returns
-------
d : float
Maximum nearest neighbor distance between the n
observations.
Examples
--------
>>> import libpysal.api as ps
>>> import libpysal
>>> md = ps.min_threshold_dist_from_shapefile(libpysal.examples.get_path("columbus.shp"))
>>> md
0.61886415807685413
>>> ps.min_threshold_dist_from_shapefile(libpysal.examples.get_path("stl_hom.shp"), libpysal.cg.sphere.RADIUS_EARTH_MILES)
31.846942936393717
Notes
-----
Supports polygon or point shapefiles. For polygon shapefiles, distance is
based on polygon centroids. Distances are defined using coordinates in
shapefile which are assumed to be projected and not geographical
coordinates.
"""
points = get_points_array_from_shapefile(shapefile)
if radius is not None:
kdt = cg.kdtree.Arc_KDTree(points, radius=radius)
nn = kdt.query(kdt.data, k=2)
nnd = nn[0].max(axis=0)[1]
return nnd
return min_threshold_distance(points, p)
def min_threshold_dist_from_shapefile(shapefile, radius=None, p=2):
"""
Kernel weights with adaptive bandwidths.
Parameters
----------
shapefile : string
shapefile name with shp suffix.
radius : float
If supplied arc_distances will be calculated
based on the given radius. p will be ignored.
p : float
Minkowski p-norm distance metric parameter:
1<=p<=infinity
2: Euclidean distance
1: Manhattan distance
Returns
-------
d : float
Maximum nearest neighbor distance between the n
observations.
Examples
--------
>>> md = min_threshold_dist_from_shapefile(pysal.examples.get_path("columbus.shp"))
>>> md
0.61886415807685413
>>> min_threshold_dist_from_shapefile(pysal.examples.get_path("stl_hom.shp"), pysal.cg.sphere.RADIUS_EARTH_MILES)
31.846942936393717
Notes
-----
Supports polygon or point shapefiles. For polygon shapefiles, distance is
based on polygon centroids. Distances are defined using coordinates in
shapefile which are assumed to be projected and not geographical
coordinates.
"""
points = get_points_array_from_shapefile(shapefile)
if radius is not None:
kdt = pysal.cg.kdtree.Arc_KDTree(points, radius=radius)
nn = kdt.query(kdt.data, k=2)
nnd = nn[0].max(axis=0)[1]
return nnd
return min_threshold_distance(points, p)
def min_threshold_dist_from_shapefile(shapefile, radius=None, p=2):
"""
Kernel weights with adaptive bandwidths
Parameters
----------
shapefile : string
shapefile name with shp suffix
radius : If supplied arc_distances will be calculated
based on the given radius. p will be ignored.
p : float
Minkowski p-norm distance metric parameter:
1<=p<=infinity
2: Euclidean distance
1: Manhattan distance
Returns
-------
d : float
minimum nearest neighbor distance between the n observations
Examples
--------
>>> md = min_threshold_dist_from_shapefile(pysal.examples.get_path("columbus.shp"))
>>> md
0.61886415807685413
>>> min_threshold_dist_from_shapefile(pysal.examples.get_path("stl_hom.shp"), pysal.cg.sphere.RADIUS_EARTH_MILES)
31.846942936393717
Notes
-----
Supports polygon or point shapefiles. For polygon shapefiles, distance is
based on polygon centroids. Distances are defined using coordinates in
shapefile which are assumed to be projected and not geographical
coordinates.
"""
points = get_points_array_from_shapefile(shapefile)
if radius is not None:
points = pysal.cg.KDTree(points, distance_metric='Arc', radius=radius)
return min_threshold_distance(points, p)
def kernelW_from_shapefile(shapefile, k=2, function='triangular',
idVariable=None, fixed=True, radius=None, diagonal=False):
"""
Kernel based weights.
Parameters
----------
shapefile : string
shapefile name with shp suffix
k : int
the number of nearest neighbors to use for determining
bandwidth. Bandwidth taken as :math:`h_i=max(dknn) \\forall i`
where :math:`dknn` is a vector of k-nearest neighbor
distances (the distance to the kth nearest neighbor for each
observation).
function : {'triangular','uniform','quadratic','epanechnikov', 'quartic','bisquare','gaussian'}
.. math::
z_{i,j} = d_{i,j}/h_i
triangular
.. math::
K(z) = (1 - |z|) \ if |z| \le 1
uniform
.. math::
K(z) = |z| \ if |z| \le 1
quadratic
.. math::
K(z) = (3/4)(1-z^2) \ if |z| \le 1
epanechnikov
.. math::
K(z) = (1-z^2) \ if |z| \le 1
quartic
.. math::
K(z) = (15/16)(1-z^2)^2 \ if |z| \le 1
bisquare
.. math::
K(z) = (1-z^2)^2 \ if |z| \le 1
gaussian
.. math::
K(z) = (2\pi)^{(-1/2)} exp(-z^2 / 2)
idVariable : string
name of a column in the shapefile's DBF to use for ids
fixed : binary
If true then :math:`h_i=h \\forall i`. If false then
bandwidth is adaptive across observations.
radius : float
If supplied arc_distances will be calculated
based on the given radius. p will be ignored.
diagonal : boolean
If true, set diagonal weights = 1.0, if false (default)
diagonal weights are set to value according to kernel
function
Returns
-------
w : W
instance of spatial weights
Examples
--------
>>> kw = pysal.kernelW_from_shapefile(pysal.examples.get_path("columbus.shp"),idVariable='POLYID', function = 'gaussian')
>>> kwd = pysal.kernelW_from_shapefile(pysal.examples.get_path("columbus.shp"),idVariable='POLYID', function = 'gaussian', diagonal = True)
>>> set(kw.neighbors[1]) == set([4, 2, 3, 1])
True
>>> set(kwd.neighbors[1]) == set([4, 2, 3, 1])
True
>>>
>>> set(kw.weights[1]) == set( [0.2436835517263174, 0.29090631630909874, 0.29671172124745776, 0.3989422804014327])
True
>>> set(kwd.weights[1]) == set( [0.2436835517263174, 0.29090631630909874, 0.29671172124745776, 1.0])
True
Notes
-----
Supports polygon or point shapefiles. For polygon shapefiles, distance is
based on polygon centroids. Distances are defined using coordinates in
shapefile which are assumed to be projected and not geographical
coordinates.
"""
points = get_points_array_from_shapefile(shapefile)
if radius is not None:
points = pysal.cg.KDTree(points, distance_metric='Arc', radius=radius)
if idVariable:
ids = get_ids(shapefile, idVariable)
return Kernel(points, function=function, k=k, ids=ids, fixed=fixed,
diagonal = diagonal)
return kernelW(points, k=k, function=function, fixed=fixed,
diagonal=diagonal)
def knnW_from_shapefile(shapefile, k=2, p=2, idVariable=None, radius=None):
"""
Nearest neighbor weights from a shapefile.
Parameters
----------
shapefile : string
shapefile name with shp suffix
k : int
number of nearest neighbors
p : float
Minkowski p-norm distance metric parameter:
1<=p<=infinity
2: Euclidean distance
1: Manhattan distance
idVariable : string
name of a column in the shapefile's DBF to use for ids
radius : float
If supplied arc_distances will be calculated
based on the given radius. p will be ignored.
Returns
-------
w : W
instance; Weights object with binary weights
Examples
--------
Polygon shapefile
>>> wc=knnW_from_shapefile(pysal.examples.get_path("columbus.shp"))
>>> "%.4f"%wc.pct_nonzero
'4.0816'
>>> set([2,1]) == set(wc.neighbors[0])
True
>>> wc3=pysal.knnW_from_shapefile(pysal.examples.get_path("columbus.shp"),k=3)
>>> set(wc3.neighbors[0]) == set([2,1,3])
True
>>> set(wc3.neighbors[2]) == set([4,3,0])
True
1 offset rather than 0 offset
>>> wc3_1=knnW_from_shapefile(pysal.examples.get_path("columbus.shp"),k=3,idVariable="POLYID")
>>> set([4,3,2]) == set(wc3_1.neighbors[1])
True
>>> wc3_1.weights[2]
[1.0, 1.0, 1.0]
>>> set([4,1,8]) == set(wc3_1.neighbors[2])
True
Point shapefile
>>> w=knnW_from_shapefile(pysal.examples.get_path("juvenile.shp"))
>>> w.pct_nonzero
1.1904761904761905
>>> w1=knnW_from_shapefile(pysal.examples.get_path("juvenile.shp"),k=1)
>>> "%.3f"%w1.pct_nonzero
'0.595'
>>>
Notes
-----
Supports polygon or point shapefiles. For polygon shapefiles, distance is
based on polygon centroids. Distances are defined using coordinates in
shapefile which are assumed to be projected and not geographical
coordinates.
Ties between neighbors of equal distance are arbitrarily broken.
See Also
--------
:class:`pysal.weights.W`
"""
data = get_points_array_from_shapefile(shapefile)
if radius is not None:
kdtree = pysal.cg.KDTree(data, distance_metric='Arc', radius=radius)
else:
kdtree = pysal.cg.KDTree(data)
if idVariable:
ids = get_ids(shapefile, idVariable)
return knnW(kdtree, k=k, p=p, ids=ids)
return knnW(kdtree, k=k, p=p)
def adaptive_kernelW_from_shapefile(shapefile,
bandwidths=None,
k=2,
function='triangular',
idVariable=None,
radius=None):
"""
Kernel weights with adaptive bandwidths
Parameters
----------
shapefile : string
shapefile name with shp suffix
bandwidths : float or array-like (optional)
the bandwidth :math:`h_i` for the kernel.
if no bandwidth is specified k is used to determine the
adaptive bandwidth
k : int
the number of nearest neighbors to use for determining
bandwidth. For fixed bandwidth, :math:`h_i=max(dknn) \\forall i`
where :math:`dknn` is a vector of k-nearest neighbor
distances (the distance to the kth nearest neighbor for each
observation). For adaptive bandwidths, :math:`h_i=dknn_i`
function : string {'triangular','uniform','quadratic','quartic','gaussian'}
kernel function defined as follows with
.. math::
z_{i,j} = d_{i,j}/h_i
triangular
.. math::
K(z) = (1 - |z|) \ if |z| \le 1
uniform
.. math::
K(z) = |z| \ if |z| \le 1
quadratic
.. math::
K(z) = (3/4)(1-z^2) \ if |z| \le 1
quartic
.. math::
K(z) = (15/16)(1-z^2)^2 \ if |z| \le 1
gaussian
.. math::
K(z) = (2\pi)^{(-1/2)} exp(-z^2 / 2)
idVariable : string
name of a column in the shapefile's DBF to use for ids
radius : If supplied arc_distances will be calculated
based on the given radius. p will be ignored.
Returns
-------
w : W
instance of spatial weights
Examples
--------
>>> kwa = adaptive_kernelW_from_shapefile(pysal.examples.get_path("columbus.shp"))
>>> kwa.weights[0]
[1.0, 0.03178906767736345, 9.99999900663795e-08]
>>> kwa.bandwidth[:3]
array([[ 0.59871832],
[ 0.59871832],
[ 0.56095647]])
Notes
-----
Supports polygon or point shapefiles. For polygon shapefiles, distance is
based on polygon centroids. Distances are defined using coordinates in
shapefile which are assumed to be projected and not geographical
coordinates.
"""
points = get_points_array_from_shapefile(shapefile)
if radius is not None:
points = pysal.cg.KDTree(points, distance_metric='Arc', radius=radius)
if idVariable:
ids = get_ids(shapefile, idVariable)
return Kernel(points,
bandwidth=bandwidths,
fixed=False,
k=k,
function=function,
ids=ids)
return adaptive_kernelW(points,
bandwidths=bandwidths,
k=k,
function=function)
def kernelW_from_shapefile(shapefile,
k=2,
function='triangular',
idVariable=None,
fixed=True,
radius=None):
"""
Kernel based weights
Parameters
----------
shapefile : string
shapefile name with shp suffix
k : int
the number of nearest neighbors to use for determining
bandwidth. Bandwidth taken as :math:`h_i=max(dknn) \\forall i`
where :math:`dknn` is a vector of k-nearest neighbor
distances (the distance to the kth nearest neighbor for each
observation).
function : string {'triangular','uniform','quadratic','epanechnikov',
'quartic','bisquare','gaussian'}
.. math::
z_{i,j} = d_{i,j}/h_i
triangular
.. math::
K(z) = (1 - |z|) \ if |z| \le 1
uniform
.. math::
K(z) = |z| \ if |z| \le 1
quadratic
.. math::
K(z) = (3/4)(1-z^2) \ if |z| \le 1
epanechnikov
.. math::
K(z) = (1-z^2) \ if |z| \le 1
quartic
.. math::
K(z) = (15/16)(1-z^2)^2 \ if |z| \le 1
bisquare
.. math::
K(z) = (1-z^2)^2 \ if |z| \le 1
gaussian
.. math::
K(z) = (2\pi)^{(-1/2)} exp(-z^2 / 2)
idVariable : string
name of a column in the shapefile's DBF to use for ids
fixed : binary
If true then :math:`h_i=h \\forall i`. If false then
bandwidth is adaptive across observations.
radius : If supplied arc_distances will be calculated
based on the given radius. p will be ignored.
Returns
-------
w : W
instance of spatial weights
Examples
--------
>>> kw = kernelW_from_shapefile(pysal.examples.get_path("columbus.shp"),idVariable='POLYID')
>>> kw.weights[1]
[0.2052478782400463, 0.007078773148450623, 1.0, 0.23051223027663237]
>>> kw.bandwidth[:3]
array([[ 0.75333961],
[ 0.75333961],
[ 0.75333961]])
Notes
-----
Supports polygon or point shapefiles. For polygon shapefiles, distance is
based on polygon centroids. Distances are defined using coordinates in
shapefile which are assumed to be projected and not geographical
coordinates.
"""
points = get_points_array_from_shapefile(shapefile)
if radius is not None:
points = pysal.cg.KDTree(points, distance_metric='Arc', radius=radius)
if idVariable:
ids = get_ids(shapefile, idVariable)
return Kernel(points, function=function, k=k, ids=ids, fixed=fixed)
return kernelW(points, k=k, function=function, fixed=fixed)
#Hardcoded paths to my data for testing
shapefile = '/home/jlaura/Downloads/julia/us_tracts_data.shp'
subset = '/home/jlaura/Downloads/julia/subset.shp'
tiny = '/home/jlaura/Downloads/julia/tiny.shp'
a = '/home/jlaura/Downloads/julia/25.shp'
#Hardcoded parameters
k = 2
function = 'triangular'
fixed = False
diagonal = False
ta = time.time()
#Get the centroids from the polys
t1 = time.time()
points = get_points_array_from_shapefile(shapefile)
t2 = time.time()
print "Generating points array took {} seconds.".format(t2 - t1)
#Pickle and unpickle a class method - avoids instancemethod error in mp
#http://stackoverflow.com/questions/1816958/cant-pickle-type-instancemethod-when-using-pythons-multiprocessing-pool-ma/7309686#7309686
def _pickle_method(method):
func_name = method.im_func.__name__
obj = method.im_self
cls = method.im_class
return _unpickle_method, (func_name, obj, cls)
def _unpickle_method(func_name, obj, cls):
for cls in cls.mro():
try:
func = cls.__dict__[func_name]
def adaptive_kernelW_from_shapefile(shapefile, bandwidths=None, k=2, function='triangular',
idVariable=None, radius=None):
"""
Kernel weights with adaptive bandwidths
Parameters
----------
shapefile : string
shapefile name with shp suffix
bandwidths : float or array-like (optional)
the bandwidth :math:`h_i` for the kernel.
if no bandwidth is specified k is used to determine the
adaptive bandwidth
k : int
the number of nearest neighbors to use for determining
bandwidth. For fixed bandwidth, :math:`h_i=max(dknn) \\forall i`
where :math:`dknn` is a vector of k-nearest neighbor
distances (the distance to the kth nearest neighbor for each
observation). For adaptive bandwidths, :math:`h_i=dknn_i`
function : string {'triangular','uniform','quadratic','quartic','gaussian'}
kernel function defined as follows with
.. math::
z_{i,j} = d_{i,j}/h_i
triangular
.. math::
K(z) = (1 - |z|) \ if |z| \le 1
uniform
.. math::
K(z) = |z| \ if |z| \le 1
quadratic
.. math::
K(z) = (3/4)(1-z^2) \ if |z| \le 1
quartic
.. math::
K(z) = (15/16)(1-z^2)^2 \ if |z| \le 1
gaussian
.. math::
K(z) = (2\pi)^{(-1/2)} exp(-z^2 / 2)
idVariable : string
name of a column in the shapefile's DBF to use for ids
radius : If supplied arc_distances will be calculated
based on the given radius. p will be ignored.
Returns
-------
w : W
instance of spatial weights
Examples
--------
>>> kwa = adaptive_kernelW_from_shapefile(pysal.examples.get_path("columbus.shp"))
>>> kwa.weights[0]
[1.0, 0.03178906767736345, 9.99999900663795e-08]
>>> kwa.bandwidth[:3]
array([[ 0.59871832],
[ 0.59871832],
[ 0.56095647]])
Notes
-----
Supports polygon or point shapefiles. For polygon shapefiles, distance is
based on polygon centroids. Distances are defined using coordinates in
shapefile which are assumed to be projected and not geographical
coordinates.
"""
points = get_points_array_from_shapefile(shapefile)
if radius is not None:
points = pysal.cg.KDTree(points, distance_metric='Arc', radius=radius)
if idVariable:
ids = get_ids(shapefile, idVariable)
return Kernel(points, bandwidth=bandwidths, fixed=False, k=k, function=function, ids=ids)
return adaptive_kernelW(points, bandwidths=bandwidths, k=k, function=function)
def kernelW_from_shapefile(shapefile, k=2, function='triangular', idVariable=None, fixed=True, radius=None):
"""
Kernel based weights
Parameters
----------
shapefile : string
shapefile name with shp suffix
k : int
the number of nearest neighbors to use for determining
bandwidth. Bandwidth taken as :math:`h_i=max(dknn) \\forall i`
where :math:`dknn` is a vector of k-nearest neighbor
distances (the distance to the kth nearest neighbor for each
observation).
function : string {'triangular','uniform','quadratic','epanechnikov',
'quartic','bisquare','gaussian'}
.. math::
z_{i,j} = d_{i,j}/h_i
triangular
.. math::
K(z) = (1 - |z|) \ if |z| \le 1
uniform
.. math::
K(z) = |z| \ if |z| \le 1
quadratic
.. math::
K(z) = (3/4)(1-z^2) \ if |z| \le 1
epanechnikov
.. math::
K(z) = (1-z^2) \ if |z| \le 1
quartic
.. math::
K(z) = (15/16)(1-z^2)^2 \ if |z| \le 1
bisquare
.. math::
K(z) = (1-z^2)^2 \ if |z| \le 1
gaussian
.. math::
K(z) = (2\pi)^{(-1/2)} exp(-z^2 / 2)
idVariable : string
name of a column in the shapefile's DBF to use for ids
fixed : binary
If true then :math:`h_i=h \\forall i`. If false then
bandwidth is adaptive across observations.
radius : If supplied arc_distances will be calculated
based on the given radius. p will be ignored.
Returns
-------
w : W
instance of spatial weights
Examples
--------
>>> kw = kernelW_from_shapefile(pysal.examples.get_path("columbus.shp"),idVariable='POLYID')
>>> kw.weights[1]
[0.2052478782400463, 0.007078773148450623, 1.0, 0.23051223027663237]
>>> kw.bandwidth[:3]
array([[ 0.75333961],
[ 0.75333961],
[ 0.75333961]])
Notes
-----
Supports polygon or point shapefiles. For polygon shapefiles, distance is
based on polygon centroids. Distances are defined using coordinates in
shapefile which are assumed to be projected and not geographical
coordinates.
"""
points = get_points_array_from_shapefile(shapefile)
if radius is not None:
points = pysal.cg.KDTree(points, distance_metric='Arc', radius=radius)
if idVariable:
ids = get_ids(shapefile, idVariable)
return Kernel(points, function=function, k=k, ids=ids, fixed=fixed)
return kernelW(points, k=k, function=function, fixed=fixed)
def knnW_from_shapefile(shapefile, k=2, p=2, idVariable=None, radius=None):
"""
Nearest neighbor weights from a shapefile
Parameters
----------
shapefile : string
shapefile name with shp suffix
k : int
number of nearest neighbors
p : float
Minkowski p-norm distance metric parameter:
1<=p<=infinity
2: Euclidean distance
1: Manhattan distance
idVariable : string
name of a column in the shapefile's DBF to use for ids
radius : If supplied arc_distances will be calculated
based on the given radius. p will be ignored.
Returns
-------
w : W instance
Weights object with binary weights
Examples
--------
Polygon shapefile
>>> wc=knnW_from_shapefile(pysal.examples.get_path("columbus.shp"))
>>> wc.pct_nonzero
0.040816326530612242
>>> wc3=knnW_from_shapefile(pysal.examples.get_path("columbus.shp"),k=3,idVariable="POLYID")
>>> wc3.weights[1]
[1, 1, 1]
>>> wc3.neighbors[1]
[3, 2, 4]
>>> wc.neighbors[0]
[2, 1]
Point shapefile
>>> w=knnW_from_shapefile(pysal.examples.get_path("juvenile.shp"))
>>> w.pct_nonzero
0.011904761904761904
>>> w1=knnW_from_shapefile(pysal.examples.get_path("juvenile.shp"),k=1)
>>> w1.pct_nonzero
0.0059523809523809521
>>>
Notes
-----
Supports polygon or point shapefiles. For polygon shapefiles, distance is
based on polygon centroids. Distances are defined using coordinates in
shapefile which are assumed to be projected and not geographical
coordinates.
Ties between neighbors of equal distance are arbitrarily broken.
See Also
--------
:class:`pysal.weights.W`
"""
data = get_points_array_from_shapefile(shapefile)
if radius is not None:
data = pysal.cg.KDTree(data, distance_metric='Arc', radius=radius)
if idVariable:
ids = get_ids(shapefile, idVariable)
return knnW(data, k=k, p=p, ids=ids)
return knnW(data, k=k, p=p)
def adaptive_kernelW_from_shapefile(shapefile, bandwidths=None, k=2, function='triangular',
idVariable=None, radius=None,
diagonal = False):
"""
Kernel weights with adaptive bandwidths.
Parameters
----------
shapefile : string
shapefile name with shp suffix
bandwidths : float
or array-like (optional)
the bandwidth :math:`h_i` for the kernel.
if no bandwidth is specified k is used to determine the
adaptive bandwidth
k : int
the number of nearest neighbors to use for determining
bandwidth. For fixed bandwidth, :math:`h_i=max(dknn) \\forall i`
where :math:`dknn` is a vector of k-nearest neighbor
distances (the distance to the kth nearest neighbor for each
observation). For adaptive bandwidths, :math:`h_i=dknn_i`
function : {'triangular','uniform','quadratic','quartic','gaussian'}
kernel function defined as follows with
.. math::
z_{i,j} = d_{i,j}/h_i
triangular
.. math::
K(z) = (1 - |z|) \ if |z| \le 1
uniform
.. math::
K(z) = |z| \ if |z| \le 1
quadratic
.. math::
K(z) = (3/4)(1-z^2) \ if |z| \le 1
quartic
.. math::
K(z) = (15/16)(1-z^2)^2 \ if |z| \le 1
gaussian
.. math::
K(z) = (2\pi)^{(-1/2)} exp(-z^2 / 2)
idVariable : string
name of a column in the shapefile's DBF to use for ids
radius : float
If supplied arc_distances will be calculated
based on the given radius. p will be ignored.
diagonal : boolean
If true, set diagonal weights = 1.0, if false (default)
diagonal weights are set to value according to kernel
function
Returns
-------
w : W
instance of spatial weights
Examples
--------
>>> kwa = pysal.adaptive_kernelW_from_shapefile(pysal.examples.get_path("columbus.shp"), function='gaussian')
>>> kwad = pysal.adaptive_kernelW_from_shapefile(pysal.examples.get_path("columbus.shp"), function='gaussian', diagonal=True)
>>> kwa.neighbors[0]
[0, 2, 1]
>>> kwad.neighbors[0]
[0, 2, 1]
>>> kwa.weights[0]
[0.3989422804014327, 0.24966013701844503, 0.2419707487162134]
>>> kwad.weights[0]
[1.0, 0.24966013701844503, 0.2419707487162134]
>>>
Notes
-----
Supports polygon or point shapefiles. For polygon shapefiles, distance is
based on polygon centroids. Distances are defined using coordinates in
shapefile which are assumed to be projected and not geographical
coordinates.
"""
points = get_points_array_from_shapefile(shapefile)
if radius is not None:
points = pysal.cg.KDTree(points, distance_metric='Arc', radius=radius)
if idVariable:
ids = get_ids(shapefile, idVariable)
return Kernel(points, bandwidth=bandwidths, fixed=False, k=k,
function=function, ids=ids, diagonal=diagonal)
return adaptive_kernelW(points, bandwidths=bandwidths, k=k,
function=function, diagonal=diagonal)
#Hardcoded paths to my data for testing
shapefile = '/home/jlaura/Downloads/julia/us_tracts_data.shp'
subset = '/home/jlaura/Downloads/julia/subset.shp'
tiny = '/home/jlaura/Downloads/julia/tiny.shp'
a = '/home/jlaura/Downloads/julia/25.shp'
#Hardcoded parameters
k = 2
function = 'triangular'
fixed = False
diagonal = False
ta = time.time()
#Get the centroids from the polys
t1 = time.time()
points = get_points_array_from_shapefile(shapefile)
t2 = time.time()
print "Generating points array took {} seconds.".format(t2 - t1)
#Pickle and unpickle a class method - avoids instancemethod error in mp
#http://stackoverflow.com/questions/1816958/cant-pickle-type-instancemethod-when-using-pythons-multiprocessing-pool-ma/7309686#7309686
def _pickle_method(method):
func_name = method.im_func.__name__
obj = method.im_self
cls = method.im_class
return _unpickle_method, (func_name, obj, cls)
def _unpickle_method(func_name, obj, cls):
for cls in cls.mro():
def knnW_from_shapefile(shapefile, k=2, p=2, idVariable=None, radius=None):
"""
Nearest neighbor weights from a shapefile
Parameters
----------
shapefile : string
shapefile name with shp suffix
k : int
number of nearest neighbors
p : float
Minkowski p-norm distance metric parameter:
1<=p<=infinity
2: Euclidean distance
1: Manhattan distance
idVariable : string
name of a column in the shapefile's DBF to use for ids
radius : If supplied arc_distances will be calculated
based on the given radius. p will be ignored.
Returns
-------
w : W instance
Weights object with binary weights
Examples
--------
Polygon shapefile
>>> wc=knnW_from_shapefile(pysal.examples.get_path("columbus.shp"))
>>> wc.pct_nonzero
0.040816326530612242
>>> wc3=knnW_from_shapefile(pysal.examples.get_path("columbus.shp"),k=3,idVariable="POLYID")
>>> wc3.weights[1]
[1, 1, 1]
>>> wc3.neighbors[1]
[3, 2, 4]
>>> wc.neighbors[0]
[2, 1]
Point shapefile
>>> w=knnW_from_shapefile(pysal.examples.get_path("juvenile.shp"))
>>> w.pct_nonzero
0.011904761904761904
>>> w1=knnW_from_shapefile(pysal.examples.get_path("juvenile.shp"),k=1)
>>> w1.pct_nonzero
0.0059523809523809521
>>>
Notes
-----
Supports polygon or point shapefiles. For polygon shapefiles, distance is
based on polygon centroids. Distances are defined using coordinates in
shapefile which are assumed to be projected and not geographical
coordinates.
Ties between neighbors of equal distance are arbitrarily broken.
See Also
--------
:class:`pysal.weights.W`
"""
data = get_points_array_from_shapefile(shapefile)
if radius is not None:
data = pysal.cg.KDTree(data, distance_metric='Arc', radius=radius)
if idVariable:
ids = get_ids(shapefile, idVariable)
return knnW(data, k=k, p=p, ids=ids)
return knnW(data, k=k, p=p)
