class BirchImpl():
def __init__(self,
threshold=0.5,
branching_factor=50,
n_clusters=3,
compute_labels=True,
copy=True):
self._hyperparams = {
'threshold': threshold,
'branching_factor': branching_factor,
'n_clusters': n_clusters,
'compute_labels': compute_labels,
'copy': copy
}
def fit(self, X, y=None):
self._sklearn_model = SKLModel(**self._hyperparams)
if (y is not None):
self._sklearn_model.fit(X, y)
else:
self._sklearn_model.fit(X)
return self
def transform(self, X):
return self._sklearn_model.transform(X)
def predict(self, X):
return self._sklearn_model.predict(X)
def test_birch_predict():
"""Test the predict method predicts the nearest centroid."""
rng = np.random.RandomState(0)
X = generate_clustered_data(n_clusters=3, n_features=3, n_samples_per_cluster=10)
# n_samples * n_samples_per_cluster
shuffle_indices = np.arange(30)
rng.shuffle(shuffle_indices)
X_shuffle = X[shuffle_indices, :]
brc = Birch(n_clusters=4, threshold=1.0)
brc.fit(X_shuffle)
centroids = brc.subcluster_centers_
assert_array_equal(brc.labels_, brc.predict(X_shuffle))
nearest_centroid = pairwise_distances_argmin(X_shuffle, centroids)
assert_almost_equal(v_measure_score(nearest_centroid, brc.labels_), 1.0)
def test_birch_predict():
"""Test the predict method predicts the nearest centroid."""
rng = np.random.RandomState(0)
X = generate_clustered_data(n_clusters=3, n_features=3,
n_samples_per_cluster=10)
# n_samples * n_samples_per_cluster
shuffle_indices = np.arange(30)
rng.shuffle(shuffle_indices)
X_shuffle = X[shuffle_indices, :]
brc = Birch(n_clusters=4, threshold=1.)
brc.fit(X_shuffle)
centroids = brc.subcluster_centers_
assert_array_equal(brc.labels_, brc.predict(X_shuffle))
nearest_centroid = pairwise_distances_argmin(X_shuffle, centroids)
assert_almost_equal(v_measure_score(nearest_centroid, brc.labels_), 1.0)
