def test_custom_transforms_with_drum_nginx_prediction_server(
self,
resources,
framework,
problem,
language,
docker,
tmp_path,
):
custom_model_dir = _create_custom_model_dir(
resources,
tmp_path,
framework,
problem,
language,
)
with DrumServerRun(
resources.target_types(problem),
resources.class_labels(framework, problem),
custom_model_dir,
docker,
nginx=True,
) as run:
input_dataset = resources.datasets(framework, problem)
# do predictions
response = requests.post(run.url_server_address + "/transform/",
files={"X": open(input_dataset)})
assert response.ok
in_data = pd.read_csv(input_dataset)
parsed_response = parse_multi_part_response(response)
transformed_mat = read_mtx_payload(parsed_response,
X_TRANSFORM_KEY)
actual_num_predictions = transformed_mat.shape[0]
assert in_data.shape[0] == actual_num_predictions
def test_custom_transform_server(
self,
resources,
framework,
problem,
language,
docker,
tmp_path,
use_arrow,
pass_target,
):
custom_model_dir = _create_custom_model_dir(
resources,
tmp_path,
framework,
problem,
language,
)
with DrumServerRun(
resources.target_types(problem),
resources.class_labels(framework, problem),
custom_model_dir,
docker,
) as run:
input_dataset = resources.datasets(framework, problem)
in_data = pd.read_csv(input_dataset)
files = {"X": open(input_dataset)}
if pass_target:
target_dataset = resources.targets(problem)
files["y"] = open(target_dataset)
if use_arrow:
files["arrow_version"] = ".2"
response = requests.post(run.url_server_address + "/transform/",
files=files)
assert response.ok
parsed_response = parse_multi_part_response(response)
if framework == SKLEARN_TRANSFORM_DENSE:
if use_arrow:
transformed_out = read_arrow_payload(
parsed_response, X_TRANSFORM_KEY)
if pass_target:
target_out = read_arrow_payload(
parsed_response, Y_TRANSFORM_KEY)
assert parsed_response["X.format"] == "arrow"
if pass_target:
assert parsed_response["y.format"] == "arrow"
else:
transformed_out = read_csv_payload(parsed_response,
X_TRANSFORM_KEY)
if pass_target:
target_out = read_csv_payload(parsed_response,
Y_TRANSFORM_KEY)
assert parsed_response["X.format"] == "csv"
if pass_target:
assert parsed_response["y.format"] == "csv"
actual_num_predictions = transformed_out.shape[0]
else:
transformed_out = read_mtx_payload(parsed_response,
X_TRANSFORM_KEY)
colnames = parsed_response["X.colnames"].decode("utf-8").split(
"\n")
assert len(colnames) == transformed_out.shape[1]
if pass_target:
# this shouldn't be sparse even though features are
if use_arrow:
target_out = read_arrow_payload(
parsed_response, Y_TRANSFORM_KEY)
if pass_target:
assert parsed_response["y.format"] == "arrow"
else:
target_out = read_csv_payload(parsed_response,
Y_TRANSFORM_KEY)
if pass_target:
assert parsed_response["y.format"] == "csv"
actual_num_predictions = transformed_out.shape[0]
assert parsed_response["X.format"] == "sparse"
validate_transformed_output(
transformed_out,
should_be_sparse=framework == SKLEARN_TRANSFORM)
if pass_target:
assert all(pd.read_csv(target_dataset) == target_out)
assert in_data.shape[0] == actual_num_predictions
def load_transform_output(response, is_sparse, request_key):
parsed_response = parse_multi_part_response(response)
if is_sparse:
return pd.DataFrame(read_mtx_payload(parsed_response, request_key))
else:
return pd.DataFrame(read_csv_payload(parsed_response, request_key))