def test_works_with_simplified_dunn(self, _, n_clusters):
X, y = data(n_clusters)
single_kmeans = KMeans(n_clusters=2, init="kdtree")
kmeans = DunnSearch(single_kmeans, max_clusters=10).fit(X)
rand = adjusted_rand_score(y, kmeans.labels_)
assert n_clusters == kmeans.n_clusters_
assert rand > 0.75
def test_works_with_simplified_dunn(self, _, n_clusters):
X, y = data(n_clusters)
single_kmeans = KMeans(n_clusters=2, init='kdtree')
kmeans = DunnSearch(single_kmeans, max_clusters=10).fit(X)
rand = adjusted_rand_score(y, kmeans.labels_)
self.assertEqual(n_clusters, kmeans.n_clusters_)
self.assertGreater(rand, 0.75)
def test_works_with_sampled_gap(self, _, n_clusters):
X, y = data(n_clusters)
single_kmeans = KMeans(n_clusters=2)
kmeans = GAPSearch(single_kmeans, max_clusters=10).fit(X)
rand = adjusted_rand_score(y, kmeans.labels_)
# allow for misidentification of 1 cluster
self.assertGreaterEqual(kmeans.n_clusters_ + 1, n_clusters)
self.assertLessEqual(kmeans.n_clusters_ - 1, n_clusters)
self.assertGreater(rand, 0.75)
def test_works_with_sampled_gap(self, _, n_clusters):
X, y = data(n_clusters)
single_kmeans = KMeans(n_clusters=2)
kmeans = GAPSearch(single_kmeans, max_clusters=10).fit(X)
rand = adjusted_rand_score(y, kmeans.labels_)
# allow for misidentification of 1 cluster
assert kmeans.n_clusters_ + 1 >= n_clusters
assert kmeans.n_clusters_ - 1 <= n_clusters
assert rand > 0.75
def test_works_with_unfit_removal(self):
n_clusters = 3
X, y = data(n_clusters)
single_kmeans = KMeans(n_clusters=2)
kmeans = DunnSearch(single_kmeans, max_clusters=10,
drop_unfit=True).fit(X)
rand = adjusted_rand_score(y, kmeans.labels_)
assert n_clusters == kmeans.n_clusters_
assert rand > 0.75
assert kmeans.estimators_ is None
def test_works_with_unfit_removal(self):
n_clusters = 3
X, y = data(n_clusters)
single_kmeans = KMeans(n_clusters=2)
kmeans = DunnSearch(single_kmeans, max_clusters=10,
drop_unfit=True).fit(X)
rand = adjusted_rand_score(y, kmeans.labels_)
self.assertEqual(n_clusters, kmeans.n_clusters_)
self.assertGreater(rand, 0.75)
self.assertIsNone(kmeans.estimators_)
def test_works_with_unfit_removal(self):
n_clusters = 3
X, y = data(n_clusters)
single_kmeans = KMeans(n_clusters=2)
kmeans = GAPSearch(
single_kmeans, max_clusters=10, drop_unfit=True).fit(X)
rand = adjusted_rand_score(y, kmeans.labels_)
# allow for misidentification of 1 cluster
self.assertGreaterEqual(kmeans.n_clusters_ + 1, n_clusters)
self.assertLessEqual(kmeans.n_clusters_ - 1, n_clusters)
self.assertGreater(rand, 0.75)
self.assertIsNone(kmeans.estimators_)
def test_works_with_unfit_removal(self):
n_clusters = 3
X, y = data(n_clusters)
single_kmeans = KMeans(n_clusters=2)
kmeans = GAPSearch(single_kmeans, max_clusters=10,
drop_unfit=True).fit(X)
rand = adjusted_rand_score(y, kmeans.labels_)
# allow for misidentification of 1 cluster
assert kmeans.n_clusters_ + 1 >= n_clusters
assert kmeans.n_clusters_ - 1 <= n_clusters
assert rand > 0.75
assert kmeans.estimators_ is None
def test_works_with_full_exact_dunn(self, _, n_clusters):
X, y = data(n_clusters)
single_kmeans = KMeans(n_clusters=2, init="kdtree")
kmeans = DunnSearch(
single_kmeans,
max_clusters=15,
inter="closest",
intra="furthest",
).fit(X)
rand = adjusted_rand_score(y, kmeans.labels_)
assert n_clusters == kmeans.n_clusters_
assert rand > 0.75
def test_works_with_full_exact_dunn(self, _, n_clusters):
X, y = data(n_clusters)
single_kmeans = KMeans(n_clusters=2, init='kdtree')
kmeans = DunnSearch(
single_kmeans,
max_clusters=15,
inter='closest',
intra='furthest',
).fit(X)
rand = adjusted_rand_score(y, kmeans.labels_)
self.assertEqual(n_clusters, kmeans.n_clusters_)
self.assertGreater(rand, 0.75)