def test_bin_data():
a = np.array([1, 2, 3])
serialized = pickle.dumps(a)
data = {"binData": serialized}
arr = get_data_from_json(data)
assert not isinstance(arr, np.ndarray)
assert arr == serialized
def test_normal_data():
data = {"data": {"tensor": {"shape": [1, 1], "values": [1]}}}
arr = get_data_from_json(data)
assert isinstance(arr, np.ndarray)
assert arr.shape[0] == 1
assert arr.shape[1] == 1
assert arr[0][0] == 1
def TransformOutput():
request = extract_message()
logger.debug("Request: %s", request)
sanity_check_request(request)
if hasattr(user_model, "transform_output_rest"):
return jsonify(user_model.transform_output_rest(request))
else:
features = get_data_from_json(request)
names = request.get("data", {}).get("names")
meta = get_meta_from_json(request)
transformed = transform_output(user_model,
features,
names,
meta=meta)
logger.debug("Transformed: %s", transformed)
if isinstance(transformed, np.ndarray) or "data" in request:
new_class_names = get_class_names(user_model, names)
data = array_to_rest_datadef(transformed, new_class_names,
request.get("data", {}))
response = {"data": data, "meta": {}}
else:
response = {"binData": transformed, "meta": {}}
tags = get_custom_tags(user_model)
if tags:
response["meta"]["tags"] = tags
metrics = get_custom_metrics(user_model)
if metrics:
response["meta"]["metrics"] = metrics
return jsonify(response)
def TransformInput():
request = extract_message()
logger.debug("Request: %s", request)
sanity_check_request(request)
if hasattr(user_model, "transform_input_rest"):
return jsonify(user_model.transform_input_rest(request))
else:
features = get_data_from_json(request)
names = request.get("data", {}).get("names")
transformed = transform_input(user_model, features, names)
logger.debug("Transformed: %s", transformed)
# If predictions is an numpy array or we used the default data then return as numpy array
if isinstance(transformed, np.ndarray) or "data" in request:
new_feature_names = get_feature_names(user_model, names)
transformed = np.array(transformed)
data = array_to_rest_datadef(transformed, new_feature_names,
request.get("data", {}))
response = {"data": data, "meta": {}}
else:
response = {"binData": transformed, "meta": {}}
tags = get_custom_tags(user_model)
if tags:
response["meta"]["tags"] = tags
metrics = get_custom_metrics(user_model)
if metrics:
response["meta"]["metrics"] = metrics
return jsonify(response)
def Aggregate():
request = extract_message()
logger.debug("Request: %s", request)
sanity_check_seldon_message_list(request)
if hasattr(user_model, "aggregate_rest"):
return jsonify(user_model.aggregate_rest(request))
else:
features_list = []
names_list = []
for msg in request["seldonMessages"]:
features = get_data_from_json(msg)
names = msg.get("data", {}).get("names")
features_list.append(features)
names_list.append(names)
aggregated = aggregate(user_model, features_list, names_list)
logger.debug("Aggregated: %s", aggregated)
# If predictions is a numpy array or we used the default data then return as numpy array
if isinstance(
aggregated,
np.ndarray) or "data" in request["seldonMessages"][0]:
new_feature_names = get_feature_names(user_model,
names_list[0])
aggregated = np.array(aggregated)
data = array_to_rest_datadef(
aggregated, new_feature_names,
request["seldonMessages"][0].get("data", {}))
response = {"data": data, "meta": {}}
else:
response = {"binData": aggregated, "meta": {}}
tags = get_custom_tags(user_model)
if tags:
response["meta"]["tags"] = tags
metrics = get_custom_metrics(user_model)
if metrics:
response["meta"]["metrics"] = metrics
return jsonify(response)
def Predict():
request = extract_message()
logger.debug("Request: %s", request)
sanity_check_request(request)
if hasattr(user_model, "predict_rest"):
return jsonify(user_model.predict_rest(request))
else:
features = get_data_from_json(request)
names = request.get("data", {}).get("names")
meta = get_meta_from_json(request)
predictions = predict(user_model, features, names, meta=meta)
logger.debug("Predictions: %s", predictions)
# If predictions is an numpy array or we used the default data then return as numpy array
if isinstance(predictions, np.ndarray) or "data" in request:
predictions = np.array(predictions)
if len(predictions.shape) > 1:
class_names = get_class_names(user_model,
predictions.shape[1])
else:
class_names = []
data = array_to_rest_datadef(predictions, class_names,
request.get("data", {}))
response = {"data": data, "meta": {}}
else:
response = {"binData": predictions, "meta": {}}
tags = get_custom_tags(user_model)
if tags:
response["meta"]["tags"] = tags
metrics = get_custom_metrics(user_model)
if metrics:
response["meta"]["metrics"] = metrics
return jsonify(response)
def test_bad_data():
with pytest.raises(SeldonMicroserviceException):
data = {"foo": "bar"}
arr = get_data_from_json(data)
def test_str_data():
data = {"strData": "my string data"}
arr = get_data_from_json(data)
assert not isinstance(arr, np.ndarray)
assert arr == "my string data"
