Python scipy.spatial.distance.cityblock() Examples
The following are 14
code examples of scipy.spatial.distance.cityblock().
You can vote up the ones you like or vote down the ones you don't like,
and go to the original project or source file by following the links above each example.
You may also want to check out all available functions/classes of the module
scipy.spatial.distance
, or try the search function
.
.
Example #1
| Source File: distance.py From rltk with MIT License | 6 votes |
|
def manhattan_distance(vec1, vec2, weights=None):
"""
Manhattan distance.
Args:
vec1 (list): Vector 1. List of integer or float.
vec2 (list): Vector 2. List of integer or float. It should have the same length to vec1.
weights (list): Weights for each value in vectors. If it's None, all weights will be 1.0. Defaults to None.
Returns:
float: Manhattan distance.
"""
utils.check_for_none(vec1, vec2)
utils.check_for_type(list, vec1, vec2)
if weights:
utils.check_for_type(list, weights)
if len(vec1) != len(vec2):
raise ValueError('vec1 and vec2 should have same length')
return cityblock(vec1, vec2, weights)
Example #2
| Source File: make_handcrafted_33_features.py From wsdm19cup with MIT License | 5 votes |
|
def __calc_distances__(self, v1s, v2s, is_sparse=True):
if is_sparse:
dcosine = np.array([cosine(x.toarray(), y.toarray()) for (x, y) in zip(v1s, v2s)]).reshape((-1,1))
dcityblock = np.array([cityblock(x.toarray(), y.toarray()) for (x, y) in zip(v1s, v2s)]).reshape((-1,1))
dcanberra = np.array([canberra(x.toarray(), y.toarray()) for (x, y) in zip(v1s, v2s)]).reshape((-1,1))
deuclidean = np.array([euclidean(x.toarray(), y.toarray()) for (x, y) in zip(v1s, v2s)]).reshape((-1,1))
dminkowski = np.array([minkowski(x.toarray(), y.toarray(), 3) for (x, y) in zip(v1s, v2s)]).reshape((-1,1))
dbraycurtis = np.array([braycurtis(x.toarray(), y.toarray()) for (x, y) in zip(v1s, v2s)]).reshape((-1,1))
dskew_q1 = [skew(x.toarray().ravel()) for x in v1s]
dskew_q2 = [skew(x.toarray().ravel()) for x in v2s]
dkur_q1 = [kurtosis(x.toarray().ravel()) for x in v1s]
dkur_q2 = [kurtosis(x.toarray().ravel()) for x in v2s]
dskew_diff = np.abs(np.array(dskew_q1) - np.array(dskew_q2)).reshape((-1,1))
dkur_diff = np.abs(np.array(dkur_q1) - np.array(dkur_q2)).reshape((-1,1))
else:
dcosine = np.array([cosine(x, y) for (x, y) in zip(v1s, v2s)]).reshape((-1,1))
dcityblock = np.array([cityblock(x, y) for (x, y) in zip(v1s, v2s)]).reshape((-1,1))
dcanberra = np.array([canberra(x, y) for (x, y) in zip(v1s, v2s)]).reshape((-1,1))
deuclidean = np.array([euclidean(x, y) for (x, y) in zip(v1s, v2s)]).reshape((-1,1))
dminkowski = np.array([minkowski(x, y, 3) for (x, y) in zip(v1s, v2s)]).reshape((-1,1))
dbraycurtis = np.array([braycurtis(x, y) for (x, y) in zip(v1s, v2s)]).reshape((-1,1))
dskew_q1 = [skew(x) for x in v1s]
dskew_q2 = [skew(x) for x in v2s]
dkur_q1 = [kurtosis(x) for x in v1s]
dkur_q2 = [kurtosis(x) for x in v2s]
dskew_diff = np.abs(np.array(dskew_q1) - np.array(dskew_q2)).reshape((-1,1))
dkur_diff = np.abs(np.array(dkur_q1) - np.array(dkur_q2)).reshape((-1,1))
return np.hstack((dcosine,dcityblock,dcanberra,deuclidean,dminkowski,dbraycurtis,dskew_diff,dkur_diff))
Example #3
| Source File: train_predict_trees_batch2.py From wsdm19cup with MIT License | 5 votes |
|
def __calc_distances__(self, v1s, v2s, is_sparse=True):
if is_sparse:
dcosine = np.array([cosine(x.toarray(), y.toarray()) for (x, y) in zip(v1s, v2s)]).reshape((-1,1))
dcityblock = np.array([cityblock(x.toarray(), y.toarray()) for (x, y) in zip(v1s, v2s)]).reshape((-1,1))
dcanberra = np.array([canberra(x.toarray(), y.toarray()) for (x, y) in zip(v1s, v2s)]).reshape((-1,1))
deuclidean = np.array([euclidean(x.toarray(), y.toarray()) for (x, y) in zip(v1s, v2s)]).reshape((-1,1))
dminkowski = np.array([minkowski(x.toarray(), y.toarray(), 3) for (x, y) in zip(v1s, v2s)]).reshape((-1,1))
dbraycurtis = np.array([braycurtis(x.toarray(), y.toarray()) for (x, y) in zip(v1s, v2s)]).reshape((-1,1))
dskew_q1 = [skew(x.toarray().ravel()) for x in v1s]
dskew_q2 = [skew(x.toarray().ravel()) for x in v2s]
dkur_q1 = [kurtosis(x.toarray().ravel()) for x in v1s]
dkur_q2 = [kurtosis(x.toarray().ravel()) for x in v2s]
dskew_diff = np.abs(np.array(dskew_q1) - np.array(dskew_q2)).reshape((-1,1))
dkur_diff = np.abs(np.array(dkur_q1) - np.array(dkur_q2)).reshape((-1,1))
else:
dcosine = np.array([cosine(x, y) for (x, y) in zip(v1s, v2s)]).reshape((-1,1))
dcityblock = np.array([cityblock(x, y) for (x, y) in zip(v1s, v2s)]).reshape((-1,1))
dcanberra = np.array([canberra(x, y) for (x, y) in zip(v1s, v2s)]).reshape((-1,1))
deuclidean = np.array([euclidean(x, y) for (x, y) in zip(v1s, v2s)]).reshape((-1,1))
dminkowski = np.array([minkowski(x, y, 3) for (x, y) in zip(v1s, v2s)]).reshape((-1,1))
dbraycurtis = np.array([braycurtis(x, y) for (x, y) in zip(v1s, v2s)]).reshape((-1,1))
dskew_q1 = [skew(x) for x in v1s]
dskew_q2 = [skew(x) for x in v2s]
dkur_q1 = [kurtosis(x) for x in v1s]
dkur_q2 = [kurtosis(x) for x in v2s]
dskew_diff = np.abs(np.array(dskew_q1) - np.array(dskew_q2)).reshape((-1,1))
dkur_diff = np.abs(np.array(dkur_q1) - np.array(dkur_q2)).reshape((-1,1))
return np.hstack((dcosine,dcityblock,dcanberra,deuclidean,dminkowski,dbraycurtis,dskew_diff,dkur_diff))
Example #4
| Source File: train_predict_trees_batch1.py From wsdm19cup with MIT License | 5 votes |
|
def __calc_distances__(self, v1s, v2s, is_sparse=True):
if is_sparse:
dcosine = np.array([cosine(x.toarray(), y.toarray()) for (x, y) in zip(v1s, v2s)]).reshape((-1,1))
dcityblock = np.array([cityblock(x.toarray(), y.toarray()) for (x, y) in zip(v1s, v2s)]).reshape((-1,1))
dcanberra = np.array([canberra(x.toarray(), y.toarray()) for (x, y) in zip(v1s, v2s)]).reshape((-1,1))
deuclidean = np.array([euclidean(x.toarray(), y.toarray()) for (x, y) in zip(v1s, v2s)]).reshape((-1,1))
dminkowski = np.array([minkowski(x.toarray(), y.toarray(), 3) for (x, y) in zip(v1s, v2s)]).reshape((-1,1))
dbraycurtis = np.array([braycurtis(x.toarray(), y.toarray()) for (x, y) in zip(v1s, v2s)]).reshape((-1,1))
dskew_q1 = [skew(x.toarray().ravel()) for x in v1s]
dskew_q2 = [skew(x.toarray().ravel()) for x in v2s]
dkur_q1 = [kurtosis(x.toarray().ravel()) for x in v1s]
dkur_q2 = [kurtosis(x.toarray().ravel()) for x in v2s]
dskew_diff = np.abs(np.array(dskew_q1) - np.array(dskew_q2)).reshape((-1,1))
dkur_diff = np.abs(np.array(dkur_q1) - np.array(dkur_q2)).reshape((-1,1))
else:
dcosine = np.array([cosine(x, y) for (x, y) in zip(v1s, v2s)]).reshape((-1,1))
dcityblock = np.array([cityblock(x, y) for (x, y) in zip(v1s, v2s)]).reshape((-1,1))
dcanberra = np.array([canberra(x, y) for (x, y) in zip(v1s, v2s)]).reshape((-1,1))
deuclidean = np.array([euclidean(x, y) for (x, y) in zip(v1s, v2s)]).reshape((-1,1))
dminkowski = np.array([minkowski(x, y, 3) for (x, y) in zip(v1s, v2s)]).reshape((-1,1))
dbraycurtis = np.array([braycurtis(x, y) for (x, y) in zip(v1s, v2s)]).reshape((-1,1))
dskew_q1 = [skew(x) for x in v1s]
dskew_q2 = [skew(x) for x in v2s]
dkur_q1 = [kurtosis(x) for x in v1s]
dkur_q2 = [kurtosis(x) for x in v2s]
dskew_diff = np.abs(np.array(dskew_q1) - np.array(dskew_q2)).reshape((-1,1))
dkur_diff = np.abs(np.array(dkur_q1) - np.array(dkur_q2)).reshape((-1,1))
return np.hstack((dcosine,dcityblock,dcanberra,deuclidean,dminkowski,dbraycurtis,dskew_diff,dkur_diff))
Example #5
| Source File: train_predict_trees_batch3.py From wsdm19cup with MIT License | 5 votes |
|
def __calc_distances__(self, v1s, v2s, is_sparse=True):
if is_sparse:
dcosine = np.array([cosine(x.toarray(), y.toarray()) for (x, y) in zip(v1s, v2s)]).reshape((-1,1))
dcityblock = np.array([cityblock(x.toarray(), y.toarray()) for (x, y) in zip(v1s, v2s)]).reshape((-1,1))
dcanberra = np.array([canberra(x.toarray(), y.toarray()) for (x, y) in zip(v1s, v2s)]).reshape((-1,1))
deuclidean = np.array([euclidean(x.toarray(), y.toarray()) for (x, y) in zip(v1s, v2s)]).reshape((-1,1))
dminkowski = np.array([minkowski(x.toarray(), y.toarray(), 3) for (x, y) in zip(v1s, v2s)]).reshape((-1,1))
dbraycurtis = np.array([braycurtis(x.toarray(), y.toarray()) for (x, y) in zip(v1s, v2s)]).reshape((-1,1))
dskew_q1 = [skew(x.toarray().ravel()) for x in v1s]
dskew_q2 = [skew(x.toarray().ravel()) for x in v2s]
dkur_q1 = [kurtosis(x.toarray().ravel()) for x in v1s]
dkur_q2 = [kurtosis(x.toarray().ravel()) for x in v2s]
dskew_diff = np.abs(np.array(dskew_q1) - np.array(dskew_q2)).reshape((-1,1))
dkur_diff = np.abs(np.array(dkur_q1) - np.array(dkur_q2)).reshape((-1,1))
else:
dcosine = np.array([cosine(x, y) for (x, y) in zip(v1s, v2s)]).reshape((-1,1))
dcityblock = np.array([cityblock(x, y) for (x, y) in zip(v1s, v2s)]).reshape((-1,1))
dcanberra = np.array([canberra(x, y) for (x, y) in zip(v1s, v2s)]).reshape((-1,1))
deuclidean = np.array([euclidean(x, y) for (x, y) in zip(v1s, v2s)]).reshape((-1,1))
dminkowski = np.array([minkowski(x, y, 3) for (x, y) in zip(v1s, v2s)]).reshape((-1,1))
dbraycurtis = np.array([braycurtis(x, y) for (x, y) in zip(v1s, v2s)]).reshape((-1,1))
dskew_q1 = [skew(x) for x in v1s]
dskew_q2 = [skew(x) for x in v2s]
dkur_q1 = [kurtosis(x) for x in v1s]
dkur_q2 = [kurtosis(x) for x in v2s]
dskew_diff = np.abs(np.array(dskew_q1) - np.array(dskew_q2)).reshape((-1,1))
dkur_diff = np.abs(np.array(dkur_q1) - np.array(dkur_q2)).reshape((-1,1))
return np.hstack((dcosine,dcityblock,dcanberra,deuclidean,dminkowski,dbraycurtis,dskew_diff,dkur_diff))
Example #6
| Source File: test_pairwise.py From Mastering-Elasticsearch-7.0 with MIT License | 5 votes |
|
def test_pairwise_distances_chunked():
# Test the pairwise_distance helper function.
rng = np.random.RandomState(0)
# Euclidean distance should be equivalent to calling the function.
X = rng.random_sample((400, 4))
check_pairwise_distances_chunked(X, None, working_memory=1,
metric='euclidean')
# Test small amounts of memory
for power in range(-16, 0):
check_pairwise_distances_chunked(X, None, working_memory=2 ** power,
metric='euclidean')
# X as list
check_pairwise_distances_chunked(X.tolist(), None, working_memory=1,
metric='euclidean')
# Euclidean distance, with Y != X.
Y = rng.random_sample((200, 4))
check_pairwise_distances_chunked(X, Y, working_memory=1,
metric='euclidean')
check_pairwise_distances_chunked(X.tolist(), Y.tolist(), working_memory=1,
metric='euclidean')
# absurdly large working_memory
check_pairwise_distances_chunked(X, Y, working_memory=10000,
metric='euclidean')
# "cityblock" uses scikit-learn metric, cityblock (function) is
# scipy.spatial.
check_pairwise_distances_chunked(X, Y, working_memory=1,
metric='cityblock')
# Test that a value error is raised if the metric is unknown
assert_raises(ValueError, next,
pairwise_distances_chunked(X, Y, metric="blah"))
# Test precomputed returns all at once
D = pairwise_distances(X)
gen = pairwise_distances_chunked(D,
working_memory=2 ** -16,
metric='precomputed')
assert isinstance(gen, GeneratorType)
assert next(gen) is D
assert_raises(StopIteration, next, gen)
Example #7
| Source File: searchlight.py From brainiak with Apache License 2.0 | 5 votes |
|
def __init__(self, rad):
super().__init__(rad)
self.mask_ = np.zeros((2*rad+1, 2*rad+1, 2*rad+1), dtype=np.bool)
for r1 in range(2*self.rad+1):
for r2 in range(2*self.rad+1):
for r3 in range(2*self.rad+1):
if(cityblock((r1, r2, r3),
(self.rad, self.rad, self.rad)) <= self.rad):
self.mask_[r1, r2, r3] = True
Example #8
| Source File: test_distance.py From alibi-detect with Apache License 2.0 | 5 votes |
|
def test_cityblock_batch(random_matrix):
X = random_matrix
y = X[np.random.choice(X.shape[0])]
batch_dists = cityblock_batch(X, y)
single_dists = np.array([cityblock(x, y) for x in X]).reshape(X.shape[0], -1)
assert np.allclose(batch_dists, single_dists)
Example #9
| Source File: clustering.py From Load-Forecasting with MIT License | 5 votes |
|
def getDistLambda(metric):
if (metric == "manhattan"):
return lambda x,y : distance.cityblock(x,y)
elif (metric == "cosine"):
return lambda x,y : distance.cosine(x,y)
else:
return lambda x,y : distance.euclidean(x,y)
Example #10
| Source File: utils.py From teneto with GNU General Public License v3.0 | 5 votes |
|
def get_distance_function(requested_metric):
"""
This function returns a specified distance function.
Paramters
---------
requested_metric: str
Distance function. Can be any function in: https://docs.scipy.org/doc/scipy/reference/spatial.distance.html.
Returns
-------
requested_metric : distance function
"""
distance_options = {
'braycurtis': distance.braycurtis,
'canberra': distance.canberra,
'chebyshev': distance.chebyshev,
'cityblock': distance.cityblock,
'correlation': distance.correlation,
'cosine': distance.cosine,
'euclidean': distance.euclidean,
'sqeuclidean': distance.sqeuclidean,
'dice': distance.dice,
'hamming': distance.hamming,
'jaccard': distance.jaccard,
'kulsinski': distance.kulsinski,
'matching': distance.matching,
'rogerstanimoto': distance.rogerstanimoto,
'russellrao': distance.russellrao,
'sokalmichener': distance.sokalmichener,
'sokalsneath': distance.sokalsneath,
'yule': distance.yule,
}
if requested_metric in distance_options:
return distance_options[requested_metric]
else:
raise ValueError('Distance function cannot be found.')
Example #11
| Source File: test_distance.py From alibi with Apache License 2.0 | 5 votes |
|
def test_cityblock_batch(random_matrix):
X = random_matrix
y = X[np.random.choice(X.shape[0])]
batch_dists = cityblock_batch(X, y)
single_dists = np.array([cityblock(x, y) for x in X]).reshape(X.shape[0], -1)
assert np.allclose(batch_dists, single_dists)
Example #12
| Source File: sample_distortion_metric.py From AIF360 with Apache License 2.0 | 5 votes |
|
def manhattan_distance(self, privileged=None, returned=False):
"""Compute the average Manhattan distance between the samples from the
two datasets.
"""
condition = self._to_condition(privileged)
distance, mask = utils.compute_distance(self.dataset.features,
self.distorted_dataset.features, self.dataset.protected_attributes,
self.dataset.protected_attribute_names, dist_fun=scdist.cityblock,
condition=condition)
if returned:
return distance, self.dataset.instance_weights[mask]
return distance
Example #13
| Source File: SOMClustering.py From susi with BSD 3-Clause "New" or "Revised" License | 4 votes |
|
def get_node_distance_matrix(self, datapoint, som_array):
"""Get distance of datapoint and node using Euclidean distance.
Parameters
----------
datapoint : np.array, shape=(X.shape[1])
Datapoint = one row of the dataset `X`
som_array : np.array
Weight vectors of the SOM,
shape = (self.n_rows, self.n_columns, X.shape[1])
Returns
-------
distmat : np.array of float
Distance between datapoint and each SOM node
"""
# algorithms on the full matrix
if self.distance_metric == "euclidean":
return np.linalg.norm(som_array - datapoint, axis=2)
# node-by-node algorithms
distmat = np.zeros((self.n_rows, self.n_columns))
if self.distance_metric == "manhattan":
for node in self.node_list_:
distmat[node] = dist.cityblock(
som_array[node[0], node[1]], datapoint)
elif self.distance_metric == "mahalanobis":
for node in self.node_list_:
som_node = som_array[node[0], node[1]]
cov = np.cov(np.stack((datapoint, som_node), axis=0),
rowvar=False)
cov_pinv = np.linalg.pinv(cov) # pseudo-inverse
distmat[node] = dist.mahalanobis(
datapoint, som_node, cov_pinv)
elif self.distance_metric == "tanimoto":
# Note that this is a binary distance measure.
# Therefore, the vectors have to be converted.
# Source: Melssen 2006, Supervised Kohonen networks for
# classification problems
# VERY SLOW ALGORITHM!!!
threshold = 0.5
for node in self.node_list_:
som_node = som_array[node[0], node[1]]
distmat[node] = dist.rogerstanimoto(
binarize(datapoint.reshape(1, -1), threshold, copy=True),
binarize(som_node.reshape(1, -1), threshold, copy=True))
return distmat
Example #14
| Source File: sliced_wasserstein.py From persim with MIT License | 4 votes |
|
def sliced_wasserstein(PD1, PD2, M=50):
""" Implementation of Sliced Wasserstein distance as described in
Sliced Wasserstein Kernel for Persistence Diagrams by Mathieu Carriere, Marco Cuturi, Steve Oudot (https://arxiv.org/abs/1706.03358)
Parameters
-----------
PD1: np.array size (m,2)
Persistence diagram
PD2: np.array size (n,2)
Persistence diagram
M: int, default is 50
Iterations to run approximation.
Returns
--------
sw: float
Sliced Wasserstein distance between PD1 and PD2
"""
diag_theta = np.array(
[np.cos(0.25 * np.pi), np.sin(0.25 * np.pi)], dtype=np.float32
)
l_theta1 = [np.dot(diag_theta, x) for x in PD1]
l_theta2 = [np.dot(diag_theta, x) for x in PD2]
if (len(l_theta1) != PD1.shape[0]) or (len(l_theta2) != PD2.shape[0]):
raise ValueError("The projected points and origin do not match")
PD_delta1 = [[np.sqrt(x ** 2 / 2.0)] * 2 for x in l_theta1]
PD_delta2 = [[np.sqrt(x ** 2 / 2.0)] * 2 for x in l_theta2]
# i have the input now to compute the sw
sw = 0
theta = 0.5
step = 1.0 / M
for i in range(M):
l_theta = np.array(
[np.cos(theta * np.pi), np.sin(theta * np.pi)], dtype=np.float32
)
V1 = [np.dot(l_theta, x) for x in PD1] + [np.dot(l_theta, x) for x in PD_delta2]
V2 = [np.dot(l_theta, x) for x in PD2] + [np.dot(l_theta, x) for x in PD_delta1]
sw += step * cityblock(sorted(V1), sorted(V2))
theta += step
return sw
