def test_model_feedback_ok():
user_object = UserObject()
app = get_rest_microservice(user_object, debug=True)
client = app.test_client()
rv = client.get('/send-feedback?json={"request":{"data":{"ndarray":[]}},"reward":1.0}')
j = json.loads(rv.data)
print(j)
assert rv.status_code == 200
def test_model_bad_metrics():
user_object = UserObject(metrics_ok=False)
app = get_rest_microservice(user_object, debug=True)
client = app.test_client()
rv = client.get('/predict?json={"data":{"ndarray":[]}}')
j = json.loads(rv.data)
print(j)
assert rv.status_code == 400
def rest_prediction_server():
app = seldon_microservice.get_rest_microservice(
user_object, debug=DEBUG)
if args.tracing:
from flask_opentracing import FlaskTracer
tracing = FlaskTracer(tracer,True, app)
app.run(host='0.0.0.0', port=port)
def test_model_lowlevel_ok():
user_object = UserObjectLowLevel()
app = get_rest_microservice(user_object, debug=True)
client = app.test_client()
rv = client.get('/predict?json={"data":{"ndarray":[1,2]}}')
j = json.loads(rv.data)
print(j)
assert rv.status_code == 200
assert j["data"]["ndarray"] == [9, 9]
def test_model_no_json():
user_object = UserObject()
app = get_rest_microservice(user_object, debug=True)
client = app.test_client()
uo = UserObject()
rv = client.get('/predict?')
j = json.loads(rv.data)
print(j)
assert rv.status_code == 400
def test_model_ok():
user_object = UserObject()
app = get_rest_microservice(user_object, debug=True)
client = app.test_client()
rv = client.get('/predict?json={"data":{"ndarray":[]}}')
j = json.loads(rv.data)
print(j)
assert rv.status_code == 200
assert j["meta"]["tags"] == {"mytag": 1}
assert j["meta"]["metrics"] == user_object.metrics()
def test_model_bin_data_nparray():
user_object = UserObject(ret_nparray=True)
app = get_rest_microservice(user_object, debug=True)
client = app.test_client()
rv = client.get('/predict?json={"binData":"123"}')
j = json.loads(rv.data)
print(j)
assert rv.status_code == 200
assert j["data"]["ndarray"] == [1, 2, 3]
assert j["meta"]["tags"] == {"mytag": 1}
assert j["meta"]["metrics"] == user_object.metrics()
def test_model_bin_data():
user_object = UserObject()
app = get_rest_microservice(user_object, debug=True)
client = app.test_client()
bdata = b"123"
bdata_base64 = base64.b64encode(bdata).decode('utf-8')
rv = client.get('/predict?json={"binData":"' + bdata_base64 + '"}')
j = json.loads(rv.data)
sm = prediction_pb2.SeldonMessage()
# Check we can parse response
assert sm == json_format.Parse(rv.data, sm, ignore_unknown_fields=False)
print(j)
assert rv.status_code == 200
assert j["binData"] == bdata_base64
assert j["meta"]["tags"] == {"mytag": 1}
assert j["meta"]["metrics"] == user_object.metrics()
def test_model_tftensor_ok():
user_object = UserObject()
app = get_rest_microservice(user_object, debug=True)
client = app.test_client()
arr = np.array([1, 2])
datadef = prediction_pb2.DefaultData(
tftensor=tf.make_tensor_proto(arr)
)
request = prediction_pb2.SeldonMessage(data=datadef)
jStr = json_format.MessageToJson(request)
rv = client.get('/predict?json=' + jStr)
j = json.loads(rv.data)
print(j)
assert rv.status_code == 200
assert j["meta"]["tags"] == {"mytag": 1}
assert j["meta"]["metrics"] == user_object.metrics()
assert 'tftensor' in j['data']
tfp = TensorProto()
json_format.ParseDict(j['data'].get("tftensor"),
tfp, ignore_unknown_fields=False)
arr2 = tf.make_ndarray(tfp)
assert np.array_equal(arr, arr2)
def rest_prediction_server():
app = seldon_microservice.get_rest_microservice(user_object,
debug=DEBUG)
app.run(host='0.0.0.0', port=port)
