parsimony.algorithms.cluster.KMeans

Class KMeans

object --+ | bases.BaseAlgorithm --+ | bases.ImplicitAlgorithm --+ | KMeans

The K-means clustering algorithm. Performs clustering using the K-means clustering algorithm, also known as Lloyd's algorithm. Parameters ---------- K : Positive integer. The number of clusters to find. init : KMeans.INIT or numpy array with shape (K, p). The initialisation method to use for the centres. If init is a numpy array, it contains the actual centres to use. repeat : Positive integer. Default is 10. The number of times to repeat the initialisation and run the algorithm. The set of centre points that give the lowest within-cluster sum of squares is returned. max_iter : Non-negative integer. Maximum allowed number of iterations. Default is 100. eps : Positive float. The tolerance used by the stopping criterion. Returns ------- centers : Numpy array. The mean cluster centres. Examples -------- >>> import numpy as np

Instance Methods

[hide private]

__init__(self, K, init='random', repeat=10, max_iter=100, eps=5e-08)
x.__init__(...) initializes x; see help(type(x)) for signature source code

run(self, X)
Runs the K-means clustering algorithm on the given data matrix.

source code

_init_mus(self, X, K)

source code

_closest_centers(self, X, mus, K)
Given a set of points and a set of centres, compute the closest centre to each point.

source code

_new_centers(self, X, closest, K)
Given a set of points, X, and their previously closest centre, encoded in closest, computes their new centres.

source code

_wcss(self, X, mus, closest, K)
Within-cluster sum of squares loss function.

source code

Inherited from bases.BaseAlgorithm: get_params, set_params

Inherited from object: __delattr__, __format__, __getattribute__, __hash__, __new__, __reduce__, __reduce_ex__, __repr__, __setattr__, __sizeof__, __str__, __subclasshook__

Inherited from bases.BaseAlgorithm (private): _abc_cache, _abc_negative_cache, _abc_negative_cache_version, _abc_registry

Properties

[hide private]

Inherited from object: __class__

init(self, K, init=`'random'`, repeat=10, max_iter=100, eps=5e-08)
(Constructor)

source code

x.__init__(...) initializes x; see help(type(x)) for signature

Overrides: object.__init__: (inherited documentation)

run(self, X)

source code

Runs the K-means clustering algorithm on the given data matrix.

Parameters
----------
X : Numpy array of shape (n, p). The matrix of points to cluster.

Overrides: bases.ImplicitAlgorithm.run

Class KMeans

__init__(self, K, init='random', repeat=10, max_iter=100, eps=5e-08) (Constructor)

run(self, X)

init(self, K, init=`'random'`, repeat=10, max_iter=100, eps=5e-08)
(Constructor)