def test_getattr(client):
# Test getattr on local param
kmeans_model = KMeans(client=client)
# Test AttributeError
with pytest.raises(AttributeError):
kmeans_model.cluster_centers_
assert kmeans_model.client is not None
# Test getattr on local_model param with a non-distributed model
X, y = make_blobs(n_samples=5,
n_features=5,
centers=2,
n_parts=2,
cluster_std=0.01,
random_state=10)
kmeans_model.fit(X)
assert kmeans_model.cluster_centers_ is not None
assert isinstance(kmeans_model.cluster_centers_, cupy.core.ndarray)
# Test getattr on trained distributed model
X, y = load_text_corpus(client)
nb_model = MultinomialNB(client=client)
nb_model.fit(X, y)
assert nb_model.feature_count_ is not None
assert isinstance(nb_model.feature_count_, cupy.core.ndarray)
def test_basic_fit_predict(client):
X, y = load_text_corpus(client)
model = MultinomialNB()
model.fit(X, y)
y_hat = model.predict(X)
y_hat = y_hat.compute()
y = y.compute()
assert(accuracy_score(y_hat.get(), y) > .97)
def test_score(client):
X, y = load_text_corpus(client)
model = MultinomialNB()
model.fit(X, y)
y_hat = model.predict(X)
score = model.score(X, y)
y_hat_local = y_hat.compute()
y_local = y.compute()
assert(accuracy_score(y_hat_local.get(), y_local) == score)
def test_single_distributed_exact_results(client):
X, y = load_text_corpus(client)
sgX, sgy = (X.compute(), y.compute())
model = MultinomialNB()
model.fit(X, y)
sg_model = SGNB()
sg_model.fit(sgX, sgy)
y_hat = model.predict(X)
sg_y_hat = sg_model.predict(sgX).get()
y_hat = y_hat.compute().get()
assert(accuracy_score(y_hat, sg_y_hat) == 1.0)
def test_getattr(cluster):
client = Client(cluster)
try:
# Test getattr on local param
kmeans_model = KMeans(client=client)
assert kmeans_model.client is not None
# Test getattr on local_model param with a non-distributed model
X, y = make_blobs(n_samples=5,
n_features=5,
centers=2,
n_parts=2,
cluster_std=0.01,
random_state=10)
wait(X)
kmeans_model.fit(X)
assert kmeans_model.cluster_centers_ is not None
assert isinstance(kmeans_model.cluster_centers_, cupy.core.ndarray)
# Test getattr on trained distributed model
X, y = load_text_corpus(client)
print(str(X.compute()))
nb_model = MultinomialNB(client=client)
nb_model.fit(X, y)
assert nb_model.feature_count_ is not None
assert isinstance(nb_model.feature_count_, cupy.core.ndarray)
finally:
client.close()
def test_getattr(cluster):
client = Client(cluster)
# Test getattr on local param
kmeans_model = KMeans(client=client)
assert kmeans_model.client is not None
# Test getattr on local_model param with a non-distributed model
X_cudf, y = make_blobs(5,
5,
2,
2,
cluster_std=0.01,
verbose=False,
random_state=10)
wait(X_cudf)
kmeans_model.fit(X_cudf)
assert kmeans_model.cluster_centers_ is not None
assert isinstance(kmeans_model.cluster_centers_, cudf.DataFrame)
# Test getattr on trained distributed model
X, y = load_text_corpus(client)
print(str(X.compute()))
nb_model = MultinomialNB(client=client)
nb_model.fit(X, y)
assert nb_model.feature_count_ is not None
assert isinstance(nb_model.feature_count_, cupy.core.ndarray)
