def test_sklearn_v2(self, namespace):
deploy_model(
"sklearn",
namespace=namespace,
protocol="kfserving",
model_implementation="SKLEARN_SERVER",
model_uri="gs://seldon-models/sklearn/iris",
)
wait_for_status("sklearn", namespace)
wait_for_rollout("sklearn", namespace)
time.sleep(1)
logging.warning("Initial request")
r = v2_protocol.inference_request(
model_name="sklearn",
namespace=namespace,
payload={
"inputs": [{
"name": "input-0",
"shape": [1, 4],
"datatype": "FP32",
"data": [[0.1, 0.2, 0.3, 0.4]],
}]
},
)
assert r.status_code == 200
def test_xgboost_v2(self, namespace):
deploy_model(
"xgboost",
namespace=namespace,
protocol="kfserving",
model_implementation="XGBOOST_SERVER",
model_uri="gs://seldon-models/xgboost/iris",
)
wait_for_status("xgboost", namespace)
wait_for_rollout("xgboost", namespace)
time.sleep(1)
logging.warning("Initial request")
r = v2_protocol.inference_request(
deployment_name="xgboost",
model_name="model",
namespace=namespace,
payload={
"inputs": [
{
"name": "input-0",
"shape": [1, 4],
"datatype": "FP32",
"data": [[0.1, 0.2, 0.3, 0.4]],
}
]
},
)
assert len(r["outputs"]) > 0
def test_sklearn_v2(self, namespace):
spec = "../resources/iris-sklearn-v2.yaml"
retry_run(f"kubectl apply -f {spec} -n {namespace}")
wait_for_status("sklearn", namespace)
wait_for_rollout("sklearn", namespace)
time.sleep(1)
logging.warning("Initial request")
r = v2_protocol.inference_request(
model_name="sklearn",
namespace=namespace,
payload={
"inputs": [{
"name": "input-0",
"shape": [4],
"datatype": "FP32",
"data": [[0.1, 0.2, 0.3, 0.4]],
}],
},
)
assert r.status_code == 200
run(f"kubectl delete -f {spec} -n {namespace}", shell=True)
def test_mlflow_v2(self, namespace):
tag = "mlflow"
deploy_model(
tag,
namespace=namespace,
protocol="kfserving",
model_implementation="MLFLOW_SERVER",
model_uri="gs://seldon-models/v1.10.0-dev/mlflow/elasticnet_wine",
)
wait_for_status(tag, namespace)
wait_for_rollout(tag, namespace)
time.sleep(1)
logging.warning("Initial request")
r = v2_protocol.inference_request(
deployment_name=tag,
model_name="model",
namespace=namespace,
payload={
"parameters": {
"content_type": "pd"
},
"inputs": [
{
"name": "fixed acidity",
"shape": [1],
"datatype": "FP32",
"data": [7.4],
"parameters": {
"content_type": "np"
},
},
{
"name": "volatile acidity",
"shape": [1],
"datatype": "FP32",
"data": [0.7000],
"parameters": {
"content_type": "np"
},
},
{
"name": "citric acidity",
"shape": [1],
"datatype": "FP32",
"data": [0],
"parameters": {
"content_type": "np"
},
},
{
"name": "residual sugar",
"shape": [1],
"datatype": "FP32",
"data": [1.9],
"parameters": {
"content_type": "np"
},
},
{
"name": "chlorides",
"shape": [1],
"datatype": "FP32",
"data": [0.076],
"parameters": {
"content_type": "np"
},
},
{
"name": "free sulfur dioxide",
"shape": [1],
"datatype": "FP32",
"data": [11],
"parameters": {
"content_type": "np"
},
},
{
"name": "total sulfur dioxide",
"shape": [1],
"datatype": "FP32",
"data": [34],
"parameters": {
"content_type": "np"
},
},
{
"name": "density",
"shape": [1],
"datatype": "FP32",
"data": [0.9978],
"parameters": {
"content_type": "np"
},
},
{
"name": "pH",
"shape": [1],
"datatype": "FP32",
"data": [3.51],
"parameters": {
"content_type": "np"
},
},
{
"name": "sulphates",
"shape": [1],
"datatype": "FP32",
"data": [0.56],
"parameters": {
"content_type": "np"
},
},
{
"name": "alcohol",
"shape": [1],
"datatype": "FP32",
"data": [9.4],
"parameters": {
"content_type": "np"
},
},
],
},
)
assert r.status_code == 200
