def test_intra_similarity_of_cluster(self):
"""
Test that the intra-similarity of a cluster with several vectors is equivalent to the average similarity.
"""
v = [
Document("", ['a', 'b'], scheme=TF()),
Document("", ['a', 'a'], scheme=TF()),
]
c = Cluster(v)
self.assertEqual((c.similarity(v[0]) + c.similarity(v[1])) / 2.,
c.get_intra_similarity())
def test_empty_cluster_similarity(self):
"""
Test that when calculating the similarity between a vector and an empty cluster, the similarity is 0.
"""
c = Cluster()
v = Document("", ["a", "c"], scheme=TF())
self.assertEqual(0, c.similarity(v))
def test_intra_similarity_of_cluster_with_single_vector(self):
"""
Test that the intra-similarity of a cluster with a single vector is equivalent to that vector's similarity with the cluster.
"""
v = Document("", ['a', 'b'], scheme=TF())
c = Cluster(v)
self.assertEqual(c.similarity(v), c.get_intra_similarity())
def test_cluster_similarity(self):
"""
Test calculating the similarity between a cluster and a new vector.
"""
v = [
Document("", ["a", "b", "a", "c"], scheme=TF()),
Document("", ["a", "c"], scheme=TF())
]
c = Cluster(v)
n = Document("", ["a", "b"], scheme=TF())
self.assertEqual(
round(
(1.5 + 0.5) / (math.sqrt(2) * math.sqrt(1.5**2 + 0.5**2 + 1)),
5), round(c.similarity(n), 5))
c.vectors.remove(v[1])
self.assertEqual(
round(3 / (math.sqrt(2) * math.sqrt(2**2 + 1 + 1)), 5),
round(c.similarity(n), 5))
