def test_speed_vs_sk(self):
from h2o4gpu.cluster import KMeansSklearn as skKMeans
n_samples = 100000
centers = 10
X, true_labels = make_blobs(n_samples=n_samples,
centers=centers,
cluster_std=1.,
random_state=42)
kmeans_h2o = KMeans(n_gpus=1, n_clusters=centers, random_state=42)
# Warmup - during first call CUDA kernels take ~2sec to load
kmeans_h2o.fit(X)
start_h2o = time.time()
kmeans_h2o.fit(X)
end_h2o = time.time()
if os.getenv("CHECKPERFORMANCE") is not None:
kmeans_sk = skKMeans(n_init=1,
n_clusters=centers,
algorithm='full',
n_jobs=-1)
start_sk = time.time()
kmeans_sk.fit(X)
end_sk = time.time()
assert end_h2o - start_h2o <= end_sk - start_sk
def _test_accuracy(self,
order,
n_samples=500000,
centers=10,
n_features=2):
from h2o4gpu.cluster import KMeansSklearn as skKMeans
X, true_labels = make_blobs(n_samples=n_samples,
centers=centers,
n_features=n_features,
cluster_std=2.,
random_state=42)
X = np.asanyarray(X, order=order)
kmeans_h2o = KMeans(n_gpus=1,
n_clusters=centers,
random_state=42,
verbose=1000)
kmeans_h2o.fit(X)
kmeans_sk = skKMeans(n_init=1, n_clusters=centers, random_state=42)
kmeans_sk.fit(X)
accuracy_h2o = v_measure_score(kmeans_h2o.labels_, true_labels)
accuracy_sk = v_measure_score(kmeans_sk.labels_, true_labels)
# We also want to be either better or at most 10% worse than SKLearn
# Everything else is horrible and we probably should fix something
# TODO: it's failing with lower rtol, find out why it's so inaccurate
assert np.allclose(accuracy_h2o, accuracy_sk, rtol=0.1, atol=0.05), \
'Accuracy error {0} {1} n_samples={2}, centers={3}, n_features={4}, order={5}'.format(
accuracy_h2o, accuracy_sk, n_samples, centers, n_features, order)
def test_accuracy(self):
from h2o4gpu.cluster import KMeansSklearn as skKMeans
n_samples = 500000
centers = 10
X, true_labels = make_blobs(n_samples=n_samples,
centers=centers,
cluster_std=1.,
random_state=42)
kmeans_h2o = KMeans(n_gpus=1, n_clusters=centers, random_state=42)
kmeans_h2o.fit(X)
kmeans_sk = skKMeans(n_init=1, n_clusters=centers, random_state=42)
kmeans_sk.fit(X)
accuracy_h2o = v_measure_score(kmeans_h2o.labels_, true_labels)
accuracy_sk = v_measure_score(kmeans_sk.labels_, true_labels)
# We also want to be either better or at most 10% worse than SKLearn
# Everything else is horrible and we probably should fix something
assert accuracy_h2o - accuracy_sk >= -0.1