Skip to content

N clusters medoids fix #129

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 3 commits into from
Oct 19, 2021
Merged

N clusters medoids fix #129

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
dbb26dd
Don't sample with replacement for random placement
stefanhannie Sep 17, 2021
a0c2069
Add test to ensure n_clusters
stefanhannie Sep 17, 2021
11ed752
The initial medoids changed for determinism
stefanhannie Sep 17, 2021
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion sklearn_extra/cluster/_k_medoids.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -412,7 +412,7 @@ def _initialize_medoids(self, D, n_clusters, random_state_):

if self.init == "random": # Random initialization
# Pick random k medoids as the initial ones.
medoids = random_state_.choice(len(D), n_clusters)
medoids = random_state_.choice(len(D), n_clusters, replace=False)
elif self.init == "k-medoids++":
medoids = self._kpp_init(D, n_clusters, random_state_)
elif self.init == "heuristic": # Initialization by heuristic
Expand Down
20 changes: 19 additions & 1 deletion sklearn_extra/cluster/tests/test_k_medoids.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -48,6 +48,24 @@ def test_kmedoid_results(method, init, dtype):
assert dtype is np.dtype(km.transform(X_cc.astype(dtype)).dtype).type


@pytest.mark.parametrize("method", ["alternate", "pam"])
@pytest.mark.parametrize(
"init", ["random", "heuristic", "build", "k-medoids++"]
)
def test_kmedoid_nclusters(method, init):
n_clusters = 50

km = KMedoids(
n_clusters=n_clusters,
init=init,
method=method,
max_iter=1,
random_state=rng,
)
km.fit(X_cc)
assert len(np.unique(km.medoid_indices_)) == n_clusters


def test_clara_results():
expected = np.hstack([np.zeros(50), np.ones(50)])
km = CLARA(n_clusters=2)
Expand Down Expand Up @@ -113,7 +131,7 @@ def test_random_deterministic():
D = euclidean_distances(X)

medoids = KMedoids(init="random")._initialize_medoids(D, 4, rng)
assert_array_equal(medoids, [47, 117, 67, 103])
assert_array_equal(medoids, [114, 62, 33, 107])


def test_heuristic_deterministic():
Expand Down