Spaces:
Sleeping
Sleeping
File size: 2,162 Bytes
d916065 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 |
# Natural Language Toolkit: Clusterer Interfaces
#
# Copyright (C) 2001-2023 NLTK Project
# Author: Trevor Cohn <[email protected]>
# Porting: Steven Bird <[email protected]>
# URL: <https://www.nltk.org/>
# For license information, see LICENSE.TXT
from abc import ABCMeta, abstractmethod
from nltk.probability import DictionaryProbDist
class ClusterI(metaclass=ABCMeta):
"""
Interface covering basic clustering functionality.
"""
@abstractmethod
def cluster(self, vectors, assign_clusters=False):
"""
Assigns the vectors to clusters, learning the clustering parameters
from the data. Returns a cluster identifier for each vector.
"""
@abstractmethod
def classify(self, token):
"""
Classifies the token into a cluster, setting the token's CLUSTER
parameter to that cluster identifier.
"""
def likelihood(self, vector, label):
"""
Returns the likelihood (a float) of the token having the
corresponding cluster.
"""
if self.classify(vector) == label:
return 1.0
else:
return 0.0
def classification_probdist(self, vector):
"""
Classifies the token into a cluster, returning
a probability distribution over the cluster identifiers.
"""
likelihoods = {}
sum = 0.0
for cluster in self.cluster_names():
likelihoods[cluster] = self.likelihood(vector, cluster)
sum += likelihoods[cluster]
for cluster in self.cluster_names():
likelihoods[cluster] /= sum
return DictionaryProbDist(likelihoods)
@abstractmethod
def num_clusters(self):
"""
Returns the number of clusters.
"""
def cluster_names(self):
"""
Returns the names of the clusters.
:rtype: list
"""
return list(range(self.num_clusters()))
def cluster_name(self, index):
"""
Returns the names of the cluster at index.
"""
return index
|