nltk.cluster.kmeans.KMeans

Class KMeans

The K-means clusterer starts with k arbitrary chosen means then allocates each vector to the cluster with the closest mean. It then recalculates the means of each cluster as the centroid of the vectors in the cluster. This process repeats until the cluster memberships stabilise. This is a hill-climbing algorithm which may converge to a local maximum. Hence the clustering is often repeated with random initial means and the most commonly occuring output means are chosen.

Instance Methods

[hide private]

__init__(self, num_means, distance, repeats=1, conv_test=1e-06, initial_means=None, normalise=False, svd_dimensions=None, rng=None)

source code

cluster_vectorspace(self, vectors, trace=False)
Finds the clusters using the given set of vectors.

source code

_cluster_vectorspace(self, vectors, trace=False)

source code

classify_vectorspace(self, vector)
Returns the index of the appropriate cluster for the vector.

source code

num_clusters(self)
Returns the number of clusters.

source code

means(self)
The means used for clustering.

source code

_sum_distances(self, vectors1, vectors2)

source code

_centroid(self, cluster)

source code

__repr__(self)

source code

Inherited from util.VectorSpace: classify, cluster, likelihood, likelihood_vectorspace, vector

Inherited from util.VectorSpace (private): _normalise

Inherited from api.ClusterI: classification_probdist, cluster_name, cluster_names

init(self, num_means, distance, repeats=1, conv_test=1e-06, initial_means=None, normalise=False, svd_dimensions=None, rng=None)
(Constructor)

source code

Parameters:

num_means (int) - the number of means to use (may use fewer)
distance (function taking two vectors and returing a float) - measure of distance between two vectors
repeats (int) - number of randomised clustering trials to use
conv_test (number) - maximum variation in mean differences before deemed convergent
initial_means (sequence of vectors) - set of k initial means
normalise (boolean) - should vectors be normalised to length 1
svd_dimensions (int) - number of dimensions to use in reducing vector dimensionsionality with SVD
rng (Random) - random number generator (or None)

Overrides: util.VectorSpace.__init__

cluster_vectorspace(self, vectors, trace=False)

source code

Finds the clusters using the given set of vectors.

Overrides: util.VectorSpace.cluster_vectorspace: (inherited documentation)

classify_vectorspace(self, vector)

source code

Returns the index of the appropriate cluster for the vector.

Overrides: util.VectorSpace.classify_vectorspace: (inherited documentation)

num_clusters(self)

source code

Returns the number of clusters.

Overrides: api.ClusterI.num_clusters: (inherited documentation)

Class KMeans

__init__(self, num_means, distance, repeats=1, conv_test=1e-06, initial_means=None, normalise=False, svd_dimensions=None, rng=None) (Constructor)

cluster_vectorspace(self, vectors, trace=False)

classify_vectorspace(self, vector)

num_clusters(self)

init(self, num_means, distance, repeats=1, conv_test=1e-06, initial_means=None, normalise=False, svd_dimensions=None, rng=None)
(Constructor)