def test_output_type_context_mgr(global_output_type, context_type):
dataset = get_small_dataset('numba')
test_type = 'cupy' if global_output_type != 'cupy' else 'numpy'
cuml.set_global_output_type(test_type)
# use cuml context manager
with cuml.using_output_type(context_type):
dbscan_float = cuml.DBSCAN(eps=1.0, min_samples=1)
dbscan_float.fit(dataset)
res = dbscan_float.labels_
if context_type == 'numba':
assert is_cuda_array(res)
else:
assert isinstance(res, test_output_types[context_type])
# use cuml again outside the context manager
dbscan_float = cuml.DBSCAN(eps=1.0, min_samples=1)
dbscan_float.fit(dataset)
res = dbscan_float.labels_
assert isinstance(res, test_output_types[test_type])
def global_output_type(request):
output_type = request.param
yield output_type
# Ensure we reset the type at the end of the test
cuml.set_global_output_type(None)
def check_correct_type(index):
output_type = test_output_types_str[index]
# Force a race condition
if index == 0:
sleep(0.1)
set_global_output_type(output_type)
sleep(0.5)
return cuml.global_settings.output_type == output_type
def test_dask_sql_sg_logistic_regression(
datatype,
nrows,
ncols,
n_parts,
wrap_predict
):
if wrap_predict:
cuml.set_global_output_type("input")
else:
cuml.set_global_output_type("cudf")
X, y = make_classification(
n_samples=nrows, n_features=ncols, n_informative=5, random_state=0
)
X_train, X_test, y_train, y_test = train_test_split(X, y)
train_df = cudf.DataFrame(
X_train, dtype=datatype, columns=[chr(i) for i in range(ncols)]
)
train_df["target"] = y_train
train_ddf = dask_cudf.from_cudf(train_df, npartitions=n_parts)
c = Context()
c.create_table("train_df", train_ddf)
train_query = f"""
CREATE MODEL model WITH (
model_class = 'cuml.linear_model.LogisticRegression',
wrap_predict = {wrap_predict},
target_column = 'target'
) AS (
SELECT * FROM train_df
)
"""
c.sql(train_query)
skmodel = LogisticRegression().fit(X_train, y_train)
test_df = cudf.DataFrame(
X_test, dtype=datatype, columns=[chr(i) for i in range(ncols)]
)
test_ddf = dask_cudf.from_cudf(test_df, npartitions=n_parts)
c.create_table("test_df", test_ddf)
inference_query = """
SELECT * FROM PREDICT(
MODEL model,
SELECT * FROM test_df
)
"""
preds = c.sql(inference_query).compute()
score = cuml.metrics.accuracy_score(y_test, preds["target"].to_numpy())
assert score >= skmodel.score(X_test, y_test) - 0.022
def test_global_output_type(global_output_type, input_type):
dataset = get_small_dataset(input_type)
cuml.set_global_output_type(global_output_type)
dbscan_float = cuml.DBSCAN(eps=1.0, min_samples=1)
dbscan_float.fit(dataset)
res = dbscan_float.labels_
if global_output_type == 'numba':
assert is_cuda_array(res)
else:
assert isinstance(res, test_output_types[global_output_type])
def __init__(self, operation_type: str, params: Optional[dict] = None):
super().__init__(operation_type, params)
self.operation_impl = self._convert_to_operation(operation_type)
self.operation_id = operation_type
cuml.set_global_output_type('numpy')