batuhan-basoglu/Vehicle-Anti-Theft-Face-Recognition-System
1
1
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Fixed database typo and removed unnecessary class identifier.

Browse source
This commit is contained in:
Batuhan Berk Başoğlu 2020-10-14 10:10:37 -04:00
parent 00ad49a143
commit 45fb349a7d
5098 changed files with 952558 additions and 85 deletions
Download patch file Download diff file Expand all files Collapse all files

29
venv/Lib/site-packages/scipy/cluster/__init__.py Normal file
View file

@ -0,0 +1,29 @@
"""
=========================================
Clustering package (:mod:`scipy.cluster`)
=========================================
.. currentmodule:: scipy.cluster
:mod:`scipy.cluster.vq`
Clustering algorithms are useful in information theory, target detection,
communications, compression, and other areas. The `vq` module only
supports vector quantization and the k-means algorithms.
:mod:`scipy.cluster.hierarchy`
The `hierarchy` module provides functions for hierarchical and
agglomerative clustering. Its features include generating hierarchical
clusters from distance matrices,
calculating statistics on clusters, cutting linkages
to generate flat clusters, and visualizing clusters with dendrograms.
"""
__all__ = ['vq', 'hierarchy']
from . import vq, hierarchy
from scipy._lib._testutils import PytestTester
test = PytestTester(__name__)
del PytestTester

BIN
venv/Lib/site-packages/scipy/cluster/__pycache__/__init__.cpython-36.pyc Normal file
View file

Binary file not shown.

BIN
venv/Lib/site-packages/scipy/cluster/__pycache__/hierarchy.cpython-36.pyc Normal file
View file

Binary file not shown.

BIN
venv/Lib/site-packages/scipy/cluster/__pycache__/setup.cpython-36.pyc Normal file
View file

Binary file not shown.

BIN
venv/Lib/site-packages/scipy/cluster/__pycache__/vq.cpython-36.pyc Normal file
View file

Binary file not shown.

BIN
venv/Lib/site-packages/scipy/cluster/_hierarchy.cp36-win32.pyd Normal file
View file

Binary file not shown.

BIN
venv/Lib/site-packages/scipy/cluster/_optimal_leaf_ordering.cp36-win32.pyd Normal file
View file

Binary file not shown.

BIN
venv/Lib/site-packages/scipy/cluster/_vq.cp36-win32.pyd Normal file
View file

Binary file not shown.

4140
venv/Lib/site-packages/scipy/cluster/hierarchy.py Normal file
View file

File diff suppressed because it is too large Load diff

27
venv/Lib/site-packages/scipy/cluster/setup.py Normal file
View file

@ -0,0 +1,27 @@
DEFINE_MACROS = [("SCIPY_PY3K", None)]
def configuration(parent_package='', top_path=None):
from numpy.distutils.misc_util import Configuration, get_numpy_include_dirs
config = Configuration('cluster', parent_package, top_path)
config.add_data_dir('tests')
config.add_extension('_vq',
sources=[('_vq.c')],
include_dirs=[get_numpy_include_dirs()])
config.add_extension('_hierarchy',
sources=[('_hierarchy.c')],
include_dirs=[get_numpy_include_dirs()])
config.add_extension('_optimal_leaf_ordering',
sources=[('_optimal_leaf_ordering.c')],
include_dirs=[get_numpy_include_dirs()])
return config
if __name__ == '__main__':
from numpy.distutils.core import setup
setup(**configuration(top_path='').todict())

0
venv/Lib/site-packages/scipy/cluster/tests/__init__.py Normal file
View file

BIN
venv/Lib/site-packages/scipy/cluster/tests/__pycache__/__init__.cpython-36.pyc Normal file
View file

Binary file not shown.

BIN
venv/Lib/site-packages/scipy/cluster/tests/__pycache__/hierarchy_test_data.cpython-36.pyc Normal file
View file

Binary file not shown.

BIN
venv/Lib/site-packages/scipy/cluster/tests/__pycache__/test_hierarchy.cpython-36.pyc Normal file
View file

Binary file not shown.

BIN
venv/Lib/site-packages/scipy/cluster/tests/__pycache__/test_vq.cpython-36.pyc Normal file
View file

Binary file not shown.

145
venv/Lib/site-packages/scipy/cluster/tests/hierarchy_test_data.py Normal file
View file

@ -0,0 +1,145 @@
from numpy import array
Q_X = array([[5.26563660e-01, 3.14160190e-01, 8.00656370e-02],
[7.50205180e-01, 4.60299830e-01, 8.98696460e-01],
[6.65461230e-01, 6.94011420e-01, 9.10465700e-01],
[9.64047590e-01, 1.43082200e-03, 7.39874220e-01],
[1.08159060e-01, 5.53028790e-01, 6.63804780e-02],
[9.31359130e-01, 8.25424910e-01, 9.52315440e-01],
[6.78086960e-01, 3.41903970e-01, 5.61481950e-01],
[9.82730940e-01, 7.04605210e-01, 8.70978630e-02],
[6.14691610e-01, 4.69989230e-02, 6.02406450e-01],
[5.80161260e-01, 9.17354970e-01, 5.88163850e-01],
[1.38246310e+00, 1.96358160e+00, 1.94437880e+00],
[2.10675860e+00, 1.67148730e+00, 1.34854480e+00],
[1.39880070e+00, 1.66142050e+00, 1.32224550e+00],
[1.71410460e+00, 1.49176380e+00, 1.45432170e+00],
[1.54102340e+00, 1.84374950e+00, 1.64658950e+00],
[2.08512480e+00, 1.84524350e+00, 2.17340850e+00],
[1.30748740e+00, 1.53801650e+00, 2.16007740e+00],
[1.41447700e+00, 1.99329070e+00, 1.99107420e+00],
[1.61943490e+00, 1.47703280e+00, 1.89788160e+00],
[1.59880600e+00, 1.54988980e+00, 1.57563350e+00],
[3.37247380e+00, 2.69635310e+00, 3.39981700e+00],
[3.13705120e+00, 3.36528090e+00, 3.06089070e+00],
[3.29413250e+00, 3.19619500e+00, 2.90700170e+00],
[2.65510510e+00, 3.06785900e+00, 2.97198540e+00],
[3.30941040e+00, 2.59283970e+00, 2.57714110e+00],
[2.59557220e+00, 3.33477370e+00, 3.08793190e+00],
[2.58206180e+00, 3.41615670e+00, 3.26441990e+00],
[2.71127000e+00, 2.77032450e+00, 2.63466500e+00],
[2.79617850e+00, 3.25473720e+00, 3.41801560e+00],
[2.64741750e+00, 2.54538040e+00, 3.25354110e+00]])
ytdist = array([662., 877., 255., 412., 996., 295., 468., 268., 400., 754.,
564., 138., 219., 869., 669.])
linkage_ytdist_single = array([[2., 5., 138., 2.],
[3., 4., 219., 2.],
[0., 7., 255., 3.],
[1., 8., 268., 4.],
[6., 9., 295., 6.]])
linkage_ytdist_complete = array([[2., 5., 138., 2.],
[3., 4., 219., 2.],
[1., 6., 400., 3.],
[0., 7., 412., 3.],
[8., 9., 996., 6.]])
linkage_ytdist_average = array([[2., 5., 138., 2.],
[3., 4., 219., 2.],
[0., 7., 333.5, 3.],
[1., 6., 347.5, 3.],
[8., 9., 680.77777778, 6.]])
linkage_ytdist_weighted = array([[2., 5., 138., 2.],
[3., 4., 219., 2.],
[0., 7., 333.5, 3.],
[1., 6., 347.5, 3.],
[8., 9., 670.125, 6.]])
# the optimal leaf ordering of linkage_ytdist_single
linkage_ytdist_single_olo = array([[5., 2., 138., 2.],
[4., 3., 219., 2.],
[7., 0., 255., 3.],
[1., 8., 268., 4.],
[6., 9., 295., 6.]])
X = array([[1.43054825, -7.5693489],
[6.95887839, 6.82293382],
[2.87137846, -9.68248579],
[7.87974764, -6.05485803],
[8.24018364, -6.09495602],
[7.39020262, 8.54004355]])
linkage_X_centroid = array([[3., 4., 0.36265956, 2.],
[1., 5., 1.77045373, 2.],
[0., 2., 2.55760419, 2.],
[6., 8., 6.43614494, 4.],
[7., 9., 15.17363237, 6.]])
linkage_X_median = array([[3., 4., 0.36265956, 2.],
[1., 5., 1.77045373, 2.],
[0., 2., 2.55760419, 2.],
[6., 8., 6.43614494, 4.],
[7., 9., 15.17363237, 6.]])
linkage_X_ward = array([[3., 4., 0.36265956, 2.],
[1., 5., 1.77045373, 2.],
[0., 2., 2.55760419, 2.],
[6., 8., 9.10208346, 4.],
[7., 9., 24.7784379, 6.]])
# the optimal leaf ordering of linkage_X_ward
linkage_X_ward_olo = array([[4., 3., 0.36265956, 2.],
[5., 1., 1.77045373, 2.],
[2., 0., 2.55760419, 2.],
[6., 8., 9.10208346, 4.],
[7., 9., 24.7784379, 6.]])
inconsistent_ytdist = {
1: array([[138., 0., 1., 0.],
[219., 0., 1., 0.],
[255., 0., 1., 0.],
[268., 0., 1., 0.],
[295., 0., 1., 0.]]),
2: array([[138., 0., 1., 0.],
[219., 0., 1., 0.],
[237., 25.45584412, 2., 0.70710678],
[261.5, 9.19238816, 2., 0.70710678],
[233.66666667, 83.9424406, 3., 0.7306594]]),
3: array([[138., 0., 1., 0.],
[219., 0., 1., 0.],
[237., 25.45584412, 2., 0.70710678],
[247.33333333, 25.38372182, 3., 0.81417007],
[239., 69.36377537, 4., 0.80733783]]),
4: array([[138., 0., 1., 0.],
[219., 0., 1., 0.],
[237., 25.45584412, 2., 0.70710678],
[247.33333333, 25.38372182, 3., 0.81417007],
[235., 60.73302232, 5., 0.98793042]])}
fcluster_inconsistent = {
0.8: array([6, 2, 2, 4, 6, 2, 3, 7, 3, 5, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 1,
1, 1, 1, 1, 1, 1, 1, 1, 1]),
1.0: array([6, 2, 2, 4, 6, 2, 3, 7, 3, 5, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 1,
1, 1, 1, 1, 1, 1, 1, 1, 1]),
2.0: array([1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 1, 1, 1, 1])}
fcluster_distance = {
0.6: array([4, 4, 4, 4, 4, 4, 4, 5, 4, 4, 6, 6, 6, 6, 6, 7, 6, 6, 6, 6, 3,
1, 1, 1, 2, 1, 1, 1, 1, 1]),
1.0: array([2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 1,
1, 1, 1, 1, 1, 1, 1, 1, 1]),
2.0: array([1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 1, 1, 1, 1])}
fcluster_maxclust = {
8.0: array([5, 5, 5, 5, 5, 5, 5, 6, 5, 5, 7, 7, 7, 7, 7, 8, 7, 7, 7, 7, 4,
1, 1, 1, 3, 1, 1, 1, 1, 2]),
4.0: array([3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 2,
1, 1, 1, 1, 1, 1, 1, 1, 1]),
1.0: array([1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 1, 1, 1, 1])}

1085
venv/Lib/site-packages/scipy/cluster/tests/test_hierarchy.py Normal file
View file

File diff suppressed because it is too large Load diff

311
venv/Lib/site-packages/scipy/cluster/tests/test_vq.py Normal file
View file

@ -0,0 +1,311 @@
import warnings
import sys
import numpy as np
from numpy.testing import (assert_array_equal, assert_array_almost_equal,
assert_allclose, assert_equal, assert_,
suppress_warnings)
import pytest
from pytest import raises as assert_raises
from scipy.cluster.vq import (kmeans, kmeans2, py_vq, vq, whiten,
ClusterError, _krandinit)
from scipy.cluster import _vq
from scipy.sparse.sputils import matrix
TESTDATA_2D = np.array([
-2.2, 1.17, -1.63, 1.69, -2.04, 4.38, -3.09, 0.95, -1.7, 4.79, -1.68, 0.68,
-2.26, 3.34, -2.29, 2.55, -1.72, -0.72, -1.99, 2.34, -2.75, 3.43, -2.45,
2.41, -4.26, 3.65, -1.57, 1.87, -1.96, 4.03, -3.01, 3.86, -2.53, 1.28,
-4.0, 3.95, -1.62, 1.25, -3.42, 3.17, -1.17, 0.12, -3.03, -0.27, -2.07,
-0.55, -1.17, 1.34, -2.82, 3.08, -2.44, 0.24, -1.71, 2.48, -5.23, 4.29,
-2.08, 3.69, -1.89, 3.62, -2.09, 0.26, -0.92, 1.07, -2.25, 0.88, -2.25,
2.02, -4.31, 3.86, -2.03, 3.42, -2.76, 0.3, -2.48, -0.29, -3.42, 3.21,
-2.3, 1.73, -2.84, 0.69, -1.81, 2.48, -5.24, 4.52, -2.8, 1.31, -1.67,
-2.34, -1.18, 2.17, -2.17, 2.82, -1.85, 2.25, -2.45, 1.86, -6.79, 3.94,
-2.33, 1.89, -1.55, 2.08, -1.36, 0.93, -2.51, 2.74, -2.39, 3.92, -3.33,
2.99, -2.06, -0.9, -2.83, 3.35, -2.59, 3.05, -2.36, 1.85, -1.69, 1.8,
-1.39, 0.66, -2.06, 0.38, -1.47, 0.44, -4.68, 3.77, -5.58, 3.44, -2.29,
2.24, -1.04, -0.38, -1.85, 4.23, -2.88, 0.73, -2.59, 1.39, -1.34, 1.75,
-1.95, 1.3, -2.45, 3.09, -1.99, 3.41, -5.55, 5.21, -1.73, 2.52, -2.17,
0.85, -2.06, 0.49, -2.54, 2.07, -2.03, 1.3, -3.23, 3.09, -1.55, 1.44,
-0.81, 1.1, -2.99, 2.92, -1.59, 2.18, -2.45, -0.73, -3.12, -1.3, -2.83,
0.2, -2.77, 3.24, -1.98, 1.6, -4.59, 3.39, -4.85, 3.75, -2.25, 1.71, -3.28,
3.38, -1.74, 0.88, -2.41, 1.92, -2.24, 1.19, -2.48, 1.06, -1.68, -0.62,
-1.3, 0.39, -1.78, 2.35, -3.54, 2.44, -1.32, 0.66, -2.38, 2.76, -2.35,
3.95, -1.86, 4.32, -2.01, -1.23, -1.79, 2.76, -2.13, -0.13, -5.25, 3.84,
-2.24, 1.59, -4.85, 2.96, -2.41, 0.01, -0.43, 0.13, -3.92, 2.91, -1.75,
-0.53, -1.69, 1.69, -1.09, 0.15, -2.11, 2.17, -1.53, 1.22, -2.1, -0.86,
-2.56, 2.28, -3.02, 3.33, -1.12, 3.86, -2.18, -1.19, -3.03, 0.79, -0.83,
0.97, -3.19, 1.45, -1.34, 1.28, -2.52, 4.22, -4.53, 3.22, -1.97, 1.75,
-2.36, 3.19, -0.83, 1.53, -1.59, 1.86, -2.17, 2.3, -1.63, 2.71, -2.03,
3.75, -2.57, -0.6, -1.47, 1.33, -1.95, 0.7, -1.65, 1.27, -1.42, 1.09, -3.0,
3.87, -2.51, 3.06, -2.6, 0.74, -1.08, -0.03, -2.44, 1.31, -2.65, 2.99,
-1.84, 1.65, -4.76, 3.75, -2.07, 3.98, -2.4, 2.67, -2.21, 1.49, -1.21,
1.22, -5.29, 2.38, -2.85, 2.28, -5.6, 3.78, -2.7, 0.8, -1.81, 3.5, -3.75,
4.17, -1.29, 2.99, -5.92, 3.43, -1.83, 1.23, -1.24, -1.04, -2.56, 2.37,
-3.26, 0.39, -4.63, 2.51, -4.52, 3.04, -1.7, 0.36, -1.41, 0.04, -2.1, 1.0,
-1.87, 3.78, -4.32, 3.59, -2.24, 1.38, -1.99, -0.22, -1.87, 1.95, -0.84,
2.17, -5.38, 3.56, -1.27, 2.9, -1.79, 3.31, -5.47, 3.85, -1.44, 3.69,
-2.02, 0.37, -1.29, 0.33, -2.34, 2.56, -1.74, -1.27, -1.97, 1.22, -2.51,
-0.16, -1.64, -0.96, -2.99, 1.4, -1.53, 3.31, -2.24, 0.45, -2.46, 1.71,
-2.88, 1.56, -1.63, 1.46, -1.41, 0.68, -1.96, 2.76, -1.61,
2.11]).reshape((200, 2))
# Global data
X = np.array([[3.0, 3], [4, 3], [4, 2],
[9, 2], [5, 1], [6, 2], [9, 4],
[5, 2], [5, 4], [7, 4], [6, 5]])
CODET1 = np.array([[3.0000, 3.0000],
[6.2000, 4.0000],
[5.8000, 1.8000]])
CODET2 = np.array([[11.0/3, 8.0/3],
[6.7500, 4.2500],
[6.2500, 1.7500]])
LABEL1 = np.array([0, 1, 2, 2, 2, 2, 1, 2, 1, 1, 1])
class TestWhiten(object):
def test_whiten(self):
desired = np.array([[5.08738849, 2.97091878],
[3.19909255, 0.69660580],
[4.51041982, 0.02640918],
[4.38567074, 0.95120889],
[2.32191480, 1.63195503]])
for tp in np.array, matrix:
obs = tp([[0.98744510, 0.82766775],
[0.62093317, 0.19406729],
[0.87545741, 0.00735733],
[0.85124403, 0.26499712],
[0.45067590, 0.45464607]])
assert_allclose(whiten(obs), desired, rtol=1e-5)
def test_whiten_zero_std(self):
desired = np.array([[0., 1.0, 2.86666544],
[0., 1.0, 1.32460034],
[0., 1.0, 3.74382172]])
for tp in np.array, matrix:
obs = tp([[0., 1., 0.74109533],
[0., 1., 0.34243798],
[0., 1., 0.96785929]])
with warnings.catch_warnings(record=True) as w:
warnings.simplefilter('always')
assert_allclose(whiten(obs), desired, rtol=1e-5)
assert_equal(len(w), 1)
assert_(issubclass(w[-1].category, RuntimeWarning))
def test_whiten_not_finite(self):
for tp in np.array, matrix:
for bad_value in np.nan, np.inf, -np.inf:
obs = tp([[0.98744510, bad_value],
[0.62093317, 0.19406729],
[0.87545741, 0.00735733],
[0.85124403, 0.26499712],
[0.45067590, 0.45464607]])
assert_raises(ValueError, whiten, obs)
class TestVq(object):
def test_py_vq(self):
initc = np.concatenate(([[X[0]], [X[1]], [X[2]]]))
for tp in np.array, matrix:
label1 = py_vq(tp(X), tp(initc))[0]
assert_array_equal(label1, LABEL1)
def test_vq(self):
initc = np.concatenate(([[X[0]], [X[1]], [X[2]]]))
for tp in np.array, matrix:
label1, dist = _vq.vq(tp(X), tp(initc))
assert_array_equal(label1, LABEL1)
tlabel1, tdist = vq(tp(X), tp(initc))
def test_vq_1d(self):
# Test special rank 1 vq algo, python implementation.
data = X[:, 0]
initc = data[:3]
a, b = _vq.vq(data, initc)
ta, tb = py_vq(data[:, np.newaxis], initc[:, np.newaxis])
assert_array_equal(a, ta)
assert_array_equal(b, tb)
def test__vq_sametype(self):
a = np.array([1.0, 2.0], dtype=np.float64)
b = a.astype(np.float32)
assert_raises(TypeError, _vq.vq, a, b)
def test__vq_invalid_type(self):
a = np.array([1, 2], dtype=int)
assert_raises(TypeError, _vq.vq, a, a)
def test_vq_large_nfeat(self):
X = np.random.rand(20, 20)
code_book = np.random.rand(3, 20)
codes0, dis0 = _vq.vq(X, code_book)
codes1, dis1 = py_vq(X, code_book)
assert_allclose(dis0, dis1, 1e-5)
assert_array_equal(codes0, codes1)
X = X.astype(np.float32)
code_book = code_book.astype(np.float32)
codes0, dis0 = _vq.vq(X, code_book)
codes1, dis1 = py_vq(X, code_book)
assert_allclose(dis0, dis1, 1e-5)
assert_array_equal(codes0, codes1)
def test_vq_large_features(self):
X = np.random.rand(10, 5) * 1000000
code_book = np.random.rand(2, 5) * 1000000
codes0, dis0 = _vq.vq(X, code_book)
codes1, dis1 = py_vq(X, code_book)
assert_allclose(dis0, dis1, 1e-5)
assert_array_equal(codes0, codes1)
class TestKMean(object):
def test_large_features(self):
# Generate a data set with large values, and run kmeans on it to
# (regression for 1077).
d = 300
n = 100
m1 = np.random.randn(d)
m2 = np.random.randn(d)
x = 10000 * np.random.randn(n, d) - 20000 * m1
y = 10000 * np.random.randn(n, d) + 20000 * m2
data = np.empty((x.shape[0] + y.shape[0], d), np.double)
data[:x.shape[0]] = x
data[x.shape[0]:] = y
kmeans(data, 2)
def test_kmeans_simple(self):
np.random.seed(54321)
initc = np.concatenate(([[X[0]], [X[1]], [X[2]]]))
for tp in np.array, matrix:
code1 = kmeans(tp(X), tp(initc), iter=1)[0]
assert_array_almost_equal(code1, CODET2)
def test_kmeans_lost_cluster(self):
# This will cause kmeans to have a cluster with no points.
data = TESTDATA_2D
initk = np.array([[-1.8127404, -0.67128041],
[2.04621601, 0.07401111],
[-2.31149087, -0.05160469]])
kmeans(data, initk)
with suppress_warnings() as sup:
sup.filter(UserWarning,
"One of the clusters is empty. Re-run kmeans with a "
"different initialization")
kmeans2(data, initk, missing='warn')
assert_raises(ClusterError, kmeans2, data, initk, missing='raise')
def test_kmeans2_simple(self):
np.random.seed(12345678)
initc = np.concatenate(([[X[0]], [X[1]], [X[2]]]))
for tp in np.array, matrix:
code1 = kmeans2(tp(X), tp(initc), iter=1)[0]
code2 = kmeans2(tp(X), tp(initc), iter=2)[0]
assert_array_almost_equal(code1, CODET1)
assert_array_almost_equal(code2, CODET2)
def test_kmeans2_rank1(self):
data = TESTDATA_2D
data1 = data[:, 0]
initc = data1[:3]
code = initc.copy()
kmeans2(data1, code, iter=1)[0]
kmeans2(data1, code, iter=2)[0]
def test_kmeans2_rank1_2(self):
data = TESTDATA_2D
data1 = data[:, 0]
kmeans2(data1, 2, iter=1)
def test_kmeans2_high_dim(self):
# test kmeans2 when the number of dimensions exceeds the number
# of input points
data = TESTDATA_2D
data = data.reshape((20, 20))[:10]
kmeans2(data, 2)
def test_kmeans2_init(self):
np.random.seed(12345)
data = TESTDATA_2D
kmeans2(data, 3, minit='points')
kmeans2(data[:, :1], 3, minit='points') # special case (1-D)
kmeans2(data, 3, minit='++')
kmeans2(data[:, :1], 3, minit='++') # special case (1-D)
# minit='random' can give warnings, filter those
with suppress_warnings() as sup:
sup.filter(message="One of the clusters is empty. Re-run.")
kmeans2(data, 3, minit='random')
kmeans2(data[:, :1], 3, minit='random') # special case (1-D)
@pytest.mark.skipif(sys.platform == 'win32',
reason='Fails with MemoryError in Wine.')
def test_krandinit(self):
data = TESTDATA_2D
datas = [data.reshape((200, 2)), data.reshape((20, 20))[:10]]
k = int(1e6)
for data in datas:
np.random.seed(1234)
init = _krandinit(data, k)
orig_cov = np.cov(data, rowvar=0)
init_cov = np.cov(init, rowvar=0)
assert_allclose(orig_cov, init_cov, atol=1e-2)
def test_kmeans2_empty(self):
# Regression test for gh-1032.
assert_raises(ValueError, kmeans2, [], 2)
def test_kmeans_0k(self):
# Regression test for gh-1073: fail when k arg is 0.
assert_raises(ValueError, kmeans, X, 0)
assert_raises(ValueError, kmeans2, X, 0)
assert_raises(ValueError, kmeans2, X, np.array([]))
def test_kmeans_large_thres(self):
# Regression test for gh-1774
x = np.array([1, 2, 3, 4, 10], dtype=float)
res = kmeans(x, 1, thresh=1e16)
assert_allclose(res[0], np.array([4.]))
assert_allclose(res[1], 2.3999999999999999)
def test_kmeans2_kpp_low_dim(self):
# Regression test for gh-11462
prev_res = np.array([[-1.95266667, 0.898],
[-3.153375, 3.3945]])
np.random.seed(42)
res, _ = kmeans2(TESTDATA_2D, 2, minit='++')
assert_allclose(res, prev_res)
def test_kmeans2_kpp_high_dim(self):
# Regression test for gh-11462
n_dim = 100
size = 10
centers = np.vstack([5 * np.ones(n_dim),
-5 * np.ones(n_dim)])
np.random.seed(42)
data = np.vstack([
np.random.multivariate_normal(centers[0], np.eye(n_dim), size=size),
np.random.multivariate_normal(centers[1], np.eye(n_dim), size=size)
])
res, _ = kmeans2(data, 2, minit='++')
assert_array_almost_equal(res, centers, decimal=0)

756
venv/Lib/site-packages/scipy/cluster/vq.py Normal file
View file

@ -0,0 +1,756 @@
"""
K-means clustering and vector quantization (:mod:`scipy.cluster.vq`)
====================================================================
Provides routines for k-means clustering, generating code books
from k-means models and quantizing vectors by comparing them with
centroids in a code book.
.. autosummary::
:toctree: generated/
whiten -- Normalize a group of observations so each feature has unit variance
vq -- Calculate code book membership of a set of observation vectors
kmeans -- Perform k-means on a set of observation vectors forming k clusters
kmeans2 -- A different implementation of k-means with more methods
-- for initializing centroids
Background information
----------------------
The k-means algorithm takes as input the number of clusters to
generate, k, and a set of observation vectors to cluster. It
returns a set of centroids, one for each of the k clusters. An
observation vector is classified with the cluster number or
centroid index of the centroid closest to it.
A vector v belongs to cluster i if it is closer to centroid i than
any other centroid. If v belongs to i, we say centroid i is the
dominating centroid of v. The k-means algorithm tries to
minimize distortion, which is defined as the sum of the squared distances
between each observation vector and its dominating centroid.
The minimization is achieved by iteratively reclassifying
the observations into clusters and recalculating the centroids until
a configuration is reached in which the centroids are stable. One can
also define a maximum number of iterations.
Since vector quantization is a natural application for k-means,
information theory terminology is often used. The centroid index
or cluster index is also referred to as a "code" and the table
mapping codes to centroids and, vice versa, is often referred to as a
"code book". The result of k-means, a set of centroids, can be
used to quantize vectors. Quantization aims to find an encoding of
vectors that reduces the expected distortion.
All routines expect obs to be an M by N array, where the rows are
the observation vectors. The codebook is a k by N array, where the
ith row is the centroid of code word i. The observation vectors
and centroids have the same feature dimension.
As an example, suppose we wish to compress a 24-bit color image
(each pixel is represented by one byte for red, one for blue, and
one for green) before sending it over the web. By using a smaller
8-bit encoding, we can reduce the amount of data by two
thirds. Ideally, the colors for each of the 256 possible 8-bit
encoding values should be chosen to minimize distortion of the
color. Running k-means with k=256 generates a code book of 256
codes, which fills up all possible 8-bit sequences. Instead of
sending a 3-byte value for each pixel, the 8-bit centroid index
(or code word) of the dominating centroid is transmitted. The code
book is also sent over the wire so each 8-bit code can be
translated back to a 24-bit pixel value representation. If the
image of interest was of an ocean, we would expect many 24-bit
blues to be represented by 8-bit codes. If it was an image of a
human face, more flesh-tone colors would be represented in the
code book.
"""
import warnings
import numpy as np
from collections import deque
from scipy._lib._util import _asarray_validated
from scipy.spatial.distance import cdist
from . import _vq
__docformat__ = 'restructuredtext'
__all__ = ['whiten', 'vq', 'kmeans', 'kmeans2']
class ClusterError(Exception):
pass
def whiten(obs, check_finite=True):
"""
Normalize a group of observations on a per feature basis.
Before running k-means, it is beneficial to rescale each feature
dimension of the observation set with whitening. Each feature is
divided by its standard deviation across all observations to give
it unit variance.
Parameters
----------
obs : ndarray
Each row of the array is an observation. The
columns are the features seen during each observation.
>>> # f0 f1 f2
>>> obs = [[ 1., 1., 1.], #o0
... [ 2., 2., 2.], #o1
... [ 3., 3., 3.], #o2
... [ 4., 4., 4.]] #o3
check_finite : bool, optional
Whether to check that the input matrices contain only finite numbers.
Disabling may give a performance gain, but may result in problems
(crashes, non-termination) if the inputs do contain infinities or NaNs.
Default: True
Returns
-------
result : ndarray
Contains the values in `obs` scaled by the standard deviation
of each column.
Examples
--------
>>> from scipy.cluster.vq import whiten
>>> features = np.array([[1.9, 2.3, 1.7],
... [1.5, 2.5, 2.2],
... [0.8, 0.6, 1.7,]])
>>> whiten(features)
array([[ 4.17944278, 2.69811351, 7.21248917],
[ 3.29956009, 2.93273208, 9.33380951],
[ 1.75976538, 0.7038557 , 7.21248917]])
"""
obs = _asarray_validated(obs, check_finite=check_finite)
std_dev = obs.std(axis=0)
zero_std_mask = std_dev == 0
if zero_std_mask.any():
std_dev[zero_std_mask] = 1.0
warnings.warn("Some columns have standard deviation zero. "
"The values of these columns will not change.",
RuntimeWarning)
return obs / std_dev
def vq(obs, code_book, check_finite=True):
"""
Assign codes from a code book to observations.
Assigns a code from a code book to each observation. Each
observation vector in the 'M' by 'N' `obs` array is compared with the
centroids in the code book and assigned the code of the closest
centroid.
The features in `obs` should have unit variance, which can be
achieved by passing them through the whiten function. The code
book can be created with the k-means algorithm or a different
encoding algorithm.
Parameters
----------
obs : ndarray
Each row of the 'M' x 'N' array is an observation. The columns are
the "features" seen during each observation. The features must be
whitened first using the whiten function or something equivalent.
code_book : ndarray
The code book is usually generated using the k-means algorithm.
Each row of the array holds a different code, and the columns are
the features of the code.
>>> # f0 f1 f2 f3
>>> code_book = [
... [ 1., 2., 3., 4.], #c0
... [ 1., 2., 3., 4.], #c1
... [ 1., 2., 3., 4.]] #c2
check_finite : bool, optional
Whether to check that the input matrices contain only finite numbers.
Disabling may give a performance gain, but may result in problems
(crashes, non-termination) if the inputs do contain infinities or NaNs.
Default: True
Returns
-------
code : ndarray
A length M array holding the code book index for each observation.
dist : ndarray
The distortion (distance) between the observation and its nearest
code.
Examples
--------
>>> from numpy import array
>>> from scipy.cluster.vq import vq
>>> code_book = array([[1.,1.,1.],
... [2.,2.,2.]])
>>> features = array([[ 1.9,2.3,1.7],
... [ 1.5,2.5,2.2],
... [ 0.8,0.6,1.7]])
>>> vq(features,code_book)
(array([1, 1, 0],'i'), array([ 0.43588989, 0.73484692, 0.83066239]))
"""
obs = _asarray_validated(obs, check_finite=check_finite)
code_book = _asarray_validated(code_book, check_finite=check_finite)
ct = np.common_type(obs, code_book)
c_obs = obs.astype(ct, copy=False)
c_code_book = code_book.astype(ct, copy=False)
if np.issubdtype(ct, np.float64) or np.issubdtype(ct, np.float32):
return _vq.vq(c_obs, c_code_book)
return py_vq(obs, code_book, check_finite=False)
def py_vq(obs, code_book, check_finite=True):
""" Python version of vq algorithm.
The algorithm computes the Euclidean distance between each
observation and every frame in the code_book.
Parameters
----------
obs : ndarray
Expects a rank 2 array. Each row is one observation.
code_book : ndarray
Code book to use. Same format than obs. Should have same number of
features (e.g., columns) than obs.
check_finite : bool, optional
Whether to check that the input matrices contain only finite numbers.
Disabling may give a performance gain, but may result in problems
(crashes, non-termination) if the inputs do contain infinities or NaNs.
Default: True
Returns
-------
code : ndarray
code[i] gives the label of the ith obversation; its code is
code_book[code[i]].
mind_dist : ndarray
min_dist[i] gives the distance between the ith observation and its
corresponding code.
Notes
-----
This function is slower than the C version but works for
all input types. If the inputs have the wrong types for the
C versions of the function, this one is called as a last resort.
It is about 20 times slower than the C version.
"""
obs = _asarray_validated(obs, check_finite=check_finite)
code_book = _asarray_validated(code_book, check_finite=check_finite)
if obs.ndim != code_book.ndim:
raise ValueError("Observation and code_book should have the same rank")
if obs.ndim == 1:
obs = obs[:, np.newaxis]
code_book = code_book[:, np.newaxis]
dist = cdist(obs, code_book)
code = dist.argmin(axis=1)
min_dist = dist[np.arange(len(code)), code]
return code, min_dist
# py_vq2 was equivalent to py_vq
py_vq2 = np.deprecate(py_vq, old_name='py_vq2', new_name='py_vq')
def _kmeans(obs, guess, thresh=1e-5):
""" "raw" version of k-means.
Returns
-------
code_book
The lowest distortion codebook found.
avg_dist
The average distance a observation is from a code in the book.
Lower means the code_book matches the data better.
See Also
--------
kmeans : wrapper around k-means
Examples
--------
Note: not whitened in this example.
>>> from numpy import array
>>> from scipy.cluster.vq import _kmeans
>>> features = array([[ 1.9,2.3],
... [ 1.5,2.5],
... [ 0.8,0.6],
... [ 0.4,1.8],
... [ 1.0,1.0]])
>>> book = array((features[0],features[2]))
>>> _kmeans(features,book)
(array([[ 1.7 , 2.4 ],
[ 0.73333333, 1.13333333]]), 0.40563916697728591)
"""
code_book = np.asarray(guess)
diff = np.inf
prev_avg_dists = deque([diff], maxlen=2)
while diff > thresh:
# compute membership and distances between obs and code_book
obs_code, distort = vq(obs, code_book, check_finite=False)
prev_avg_dists.append(distort.mean(axis=-1))
# recalc code_book as centroids of associated obs
code_book, has_members = _vq.update_cluster_means(obs, obs_code,
code_book.shape[0])
code_book = code_book[has_members]
diff = prev_avg_dists[0] - prev_avg_dists[1]
return code_book, prev_avg_dists[1]
def kmeans(obs, k_or_guess, iter=20, thresh=1e-5, check_finite=True):
"""
Performs k-means on a set of observation vectors forming k clusters.
The k-means algorithm adjusts the classification of the observations
into clusters and updates the cluster centroids until the position of
the centroids is stable over successive iterations. In this
implementation of the algorithm, the stability of the centroids is
determined by comparing the absolute value of the change in the average
Euclidean distance between the observations and their corresponding
centroids against a threshold. This yields
a code book mapping centroids to codes and vice versa.
Parameters
----------
obs : ndarray
Each row of the M by N array is an observation vector. The
columns are the features seen during each observation.
The features must be whitened first with the `whiten` function.
k_or_guess : int or ndarray
The number of centroids to generate. A code is assigned to
each centroid, which is also the row index of the centroid
in the code_book matrix generated.
The initial k centroids are chosen by randomly selecting
observations from the observation matrix. Alternatively,
passing a k by N array specifies the initial k centroids.
iter : int, optional
The number of times to run k-means, returning the codebook
with the lowest distortion. This argument is ignored if
initial centroids are specified with an array for the
``k_or_guess`` parameter. This parameter does not represent the
number of iterations of the k-means algorithm.
thresh : float, optional
Terminates the k-means algorithm if the change in
distortion since the last k-means iteration is less than
or equal to threshold.
check_finite : bool, optional
Whether to check that the input matrices contain only finite numbers.
Disabling may give a performance gain, but may result in problems
(crashes, non-termination) if the inputs do contain infinities or NaNs.
Default: True
Returns
-------
codebook : ndarray
A k by N array of k centroids. The ith centroid
codebook[i] is represented with the code i. The centroids
and codes generated represent the lowest distortion seen,
not necessarily the globally minimal distortion.
distortion : float
The mean (non-squared) Euclidean distance between the observations
passed and the centroids generated. Note the difference to the standard
definition of distortion in the context of the k-means algorithm, which
is the sum of the squared distances.
See Also
--------
kmeans2 : a different implementation of k-means clustering
with more methods for generating initial centroids but without
using a distortion change threshold as a stopping criterion.
whiten : must be called prior to passing an observation matrix
to kmeans.
Examples
--------
>>> from numpy import array
>>> from scipy.cluster.vq import vq, kmeans, whiten
>>> import matplotlib.pyplot as plt
>>> features = array([[ 1.9,2.3],
... [ 1.5,2.5],
... [ 0.8,0.6],
... [ 0.4,1.8],
... [ 0.1,0.1],
... [ 0.2,1.8],
... [ 2.0,0.5],
... [ 0.3,1.5],
... [ 1.0,1.0]])
>>> whitened = whiten(features)
>>> book = np.array((whitened[0],whitened[2]))
>>> kmeans(whitened,book)
(array([[ 2.3110306 , 2.86287398], # random
[ 0.93218041, 1.24398691]]), 0.85684700941625547)
>>> from numpy import random
>>> random.seed((1000,2000))
>>> codes = 3
>>> kmeans(whitened,codes)
(array([[ 2.3110306 , 2.86287398], # random
[ 1.32544402, 0.65607529],
[ 0.40782893, 2.02786907]]), 0.5196582527686241)
>>> # Create 50 datapoints in two clusters a and b
>>> pts = 50
>>> a = np.random.multivariate_normal([0, 0], [[4, 1], [1, 4]], size=pts)
>>> b = np.random.multivariate_normal([30, 10],
... [[10, 2], [2, 1]],
... size=pts)
>>> features = np.concatenate((a, b))
>>> # Whiten data
>>> whitened = whiten(features)
>>> # Find 2 clusters in the data
>>> codebook, distortion = kmeans(whitened, 2)
>>> # Plot whitened data and cluster centers in red
>>> plt.scatter(whitened[:, 0], whitened[:, 1])
>>> plt.scatter(codebook[:, 0], codebook[:, 1], c='r')
>>> plt.show()
"""
obs = _asarray_validated(obs, check_finite=check_finite)
if iter < 1:
raise ValueError("iter must be at least 1, got %s" % iter)
# Determine whether a count (scalar) or an initial guess (array) was passed.
if not np.isscalar(k_or_guess):
guess = _asarray_validated(k_or_guess, check_finite=check_finite)
if guess.size < 1:
raise ValueError("Asked for 0 clusters. Initial book was %s" %
guess)
return _kmeans(obs, guess, thresh=thresh)
# k_or_guess is a scalar, now verify that it's an integer
k = int(k_or_guess)
if k != k_or_guess:
raise ValueError("If k_or_guess is a scalar, it must be an integer.")
if k < 1:
raise ValueError("Asked for %d clusters." % k)
# initialize best distance value to a large value
best_dist = np.inf
for i in range(iter):
# the initial code book is randomly selected from observations
guess = _kpoints(obs, k)
book, dist = _kmeans(obs, guess, thresh=thresh)
if dist < best_dist:
best_book = book
best_dist = dist
return best_book, best_dist
def _kpoints(data, k):
"""Pick k points at random in data (one row = one observation).
Parameters
----------
data : ndarray
Expect a rank 1 or 2 array. Rank 1 are assumed to describe one
dimensional data, rank 2 multidimensional data, in which case one
row is one observation.
k : int
Number of samples to generate.
Returns
-------
x : ndarray
A 'k' by 'N' containing the initial centroids
"""
idx = np.random.choice(data.shape[0], size=k, replace=False)
return data[idx]
def _krandinit(data, k):
"""Returns k samples of a random variable whose parameters depend on data.
More precisely, it returns k observations sampled from a Gaussian random
variable whose mean and covariances are the ones estimated from the data.
Parameters
----------
data : ndarray
Expect a rank 1 or 2 array. Rank 1 is assumed to describe 1-D
data, rank 2 multidimensional data, in which case one
row is one observation.
k : int
Number of samples to generate.
Returns
-------
x : ndarray
A 'k' by 'N' containing the initial centroids
"""
mu = data.mean(axis=0)
if data.ndim == 1:
cov = np.cov(data)
x = np.random.randn(k)
x *= np.sqrt(cov)
elif data.shape[1] > data.shape[0]:
# initialize when the covariance matrix is rank deficient
_, s, vh = np.linalg.svd(data - mu, full_matrices=False)
x = np.random.randn(k, s.size)
sVh = s[:, None] * vh / np.sqrt(data.shape[0] - 1)
x = x.dot(sVh)
else:
cov = np.atleast_2d(np.cov(data, rowvar=False))
# k rows, d cols (one row = one obs)
# Generate k sample of a random variable ~ Gaussian(mu, cov)
x = np.random.randn(k, mu.size)
x = x.dot(np.linalg.cholesky(cov).T)
x += mu
return x
def _kpp(data, k):
""" Picks k points in the data based on the kmeans++ method.
Parameters
----------
data : ndarray
Expect a rank 1 or 2 array. Rank 1 is assumed to describe 1-D
data, rank 2 multidimensional data, in which case one
row is one observation.
k : int
Number of samples to generate.
Returns
-------
init : ndarray
A 'k' by 'N' containing the initial centroids.
References
----------
.. [1] D. Arthur and S. Vassilvitskii, "k-means++: the advantages of
careful seeding", Proceedings of the Eighteenth Annual ACM-SIAM Symposium
on Discrete Algorithms, 2007.
"""
dims = data.shape[1] if len(data.shape) > 1 else 1
init = np.ndarray((k, dims))
for i in range(k):
if i == 0:
init[i, :] = data[np.random.randint(data.shape[0])]
else:
D2 = cdist(init[:i,:], data, metric='sqeuclidean').min(axis=0)
probs = D2/D2.sum()
cumprobs = probs.cumsum()
r = np.random.rand()
init[i, :] = data[np.searchsorted(cumprobs, r)]
return init
_valid_init_meth = {'random': _krandinit, 'points': _kpoints, '++': _kpp}
def _missing_warn():
"""Print a warning when called."""
warnings.warn("One of the clusters is empty. "
"Re-run kmeans with a different initialization.")
def _missing_raise():
"""Raise a ClusterError when called."""
raise ClusterError("One of the clusters is empty. "
"Re-run kmeans with a different initialization.")
_valid_miss_meth = {'warn': _missing_warn, 'raise': _missing_raise}
def kmeans2(data, k, iter=10, thresh=1e-5, minit='random',
missing='warn', check_finite=True):
"""
Classify a set of observations into k clusters using the k-means algorithm.
The algorithm attempts to minimize the Euclidean distance between
observations and centroids. Several initialization methods are
included.
Parameters
----------
data : ndarray
A 'M' by 'N' array of 'M' observations in 'N' dimensions or a length
'M' array of 'M' 1-D observations.
k : int or ndarray
The number of clusters to form as well as the number of
centroids to generate. If `minit` initialization string is
'matrix', or if a ndarray is given instead, it is
interpreted as initial cluster to use instead.
iter : int, optional
Number of iterations of the k-means algorithm to run. Note
that this differs in meaning from the iters parameter to
the kmeans function.
thresh : float, optional
(not used yet)
minit : str, optional
Method for initialization. Available methods are 'random',
'points', '++' and 'matrix':
'random': generate k centroids from a Gaussian with mean and
variance estimated from the data.
'points': choose k observations (rows) at random from data for
the initial centroids.
'++': choose k observations accordingly to the kmeans++ method
(careful seeding)
'matrix': interpret the k parameter as a k by M (or length k
array for 1-D data) array of initial centroids.
missing : str, optional
Method to deal with empty clusters. Available methods are
'warn' and 'raise':
'warn': give a warning and continue.
'raise': raise an ClusterError and terminate the algorithm.
check_finite : bool, optional
Whether to check that the input matrices contain only finite numbers.
Disabling may give a performance gain, but may result in problems
(crashes, non-termination) if the inputs do contain infinities or NaNs.
Default: True
Returns
-------
centroid : ndarray
A 'k' by 'N' array of centroids found at the last iteration of
k-means.
label : ndarray
label[i] is the code or index of the centroid the
ith observation is closest to.
See Also
--------
kmeans
References
----------
.. [1] D. Arthur and S. Vassilvitskii, "k-means++: the advantages of
careful seeding", Proceedings of the Eighteenth Annual ACM-SIAM Symposium
on Discrete Algorithms, 2007.
Examples
--------
>>> from scipy.cluster.vq import kmeans2
>>> import matplotlib.pyplot as plt
Create z, an array with shape (100, 2) containing a mixture of samples
from three multivariate normal distributions.
>>> np.random.seed(12345678)
>>> a = np.random.multivariate_normal([0, 6], [[2, 1], [1, 1.5]], size=45)
>>> b = np.random.multivariate_normal([2, 0], [[1, -1], [-1, 3]], size=30)
>>> c = np.random.multivariate_normal([6, 4], [[5, 0], [0, 1.2]], size=25)
>>> z = np.concatenate((a, b, c))
>>> np.random.shuffle(z)
Compute three clusters.
>>> centroid, label = kmeans2(z, 3, minit='points')
>>> centroid
array([[-0.35770296, 5.31342524],
[ 2.32210289, -0.50551972],
[ 6.17653859, 4.16719247]])
How many points are in each cluster?
>>> counts = np.bincount(label)
>>> counts
array([52, 27, 21])
Plot the clusters.
>>> w0 = z[label == 0]
>>> w1 = z[label == 1]
>>> w2 = z[label == 2]
>>> plt.plot(w0[:, 0], w0[:, 1], 'o', alpha=0.5, label='cluster 0')
>>> plt.plot(w1[:, 0], w1[:, 1], 'd', alpha=0.5, label='cluster 1')
>>> plt.plot(w2[:, 0], w2[:, 1], 's', alpha=0.5, label='cluster 2')
>>> plt.plot(centroid[:, 0], centroid[:, 1], 'k*', label='centroids')
>>> plt.axis('equal')
>>> plt.legend(shadow=True)
>>> plt.show()
"""
if int(iter) < 1:
raise ValueError("Invalid iter (%s), "
"must be a positive integer." % iter)
try:
miss_meth = _valid_miss_meth[missing]
except KeyError:
raise ValueError("Unknown missing method %r" % (missing,))
data = _asarray_validated(data, check_finite=check_finite)
if data.ndim == 1:
d = 1
elif data.ndim == 2:
d = data.shape[1]
else:
raise ValueError("Input of rank > 2 is not supported.")
if data.size < 1:
raise ValueError("Empty input is not supported.")
# If k is not a single value, it should be compatible with data's shape
if minit == 'matrix' or not np.isscalar(k):
code_book = np.array(k, copy=True)
if data.ndim != code_book.ndim:
raise ValueError("k array doesn't match data rank")
nc = len(code_book)
if data.ndim > 1 and code_book.shape[1] != d:
raise ValueError("k array doesn't match data dimension")
else:
nc = int(k)
if nc < 1:
raise ValueError("Cannot ask kmeans2 for %d clusters"
" (k was %s)" % (nc, k))
elif nc != k:
warnings.warn("k was not an integer, was converted.")
try:
init_meth = _valid_init_meth[minit]
except KeyError:
raise ValueError("Unknown init method %r" % (minit,))
else:
code_book = init_meth(data, k)
for i in range(iter):
# Compute the nearest neighbor for each obs using the current code book
label = vq(data, code_book)[0]
# Update the code book by computing centroids
new_code_book, has_members = _vq.update_cluster_means(data, label, nc)
if not has_members.all():
miss_meth()
# Set the empty clusters to their previous positions
new_code_book[~has_members] = code_book[~has_members]
code_book = new_code_book
return code_book, label