def setup_method(self, method):
self._logger = logger
self._logger.info(
f"Setting up test {self.__class__.__name__}::{method.__name__}")
self._test_env = {}
self._old_env = {}
self._setup_env(self._get_env_from_file())
self._run_db = get_run_db()
# the dbpath is already configured on the test startup before this stage
# so even though we set the env var, we still need to directly configure
# it in mlconf.
mlconf.dbpath = self._test_env["MLRUN_DBPATH"]
set_environment(
artifact_path="/User/data",
project=self.project_name,
)
self.custom_setup()
self._logger.info(
f"Finished setting up test {self.__class__.__name__}::{method.__name__}"
)
def _generate_runtime(self):
# This is following the steps in
# https://docs.mlrun.org/en/latest/runtimes/dask-mlrun.html#set-up-the-environment
mlconf.remote_host = "http://remote_host"
os.environ["V3IO_USERNAME"] = self.v3io_user
mlrun.set_environment(
project=self.project,
access_key=self.v3io_access_key,
artifact_path=self.artifact_path,
)
dask_cluster = mlrun.new_function(self.name,
project=self.project,
kind="dask",
image=self.image_name)
dask_cluster.apply(auto_mount())
dask_cluster.spec.min_replicas = 1
dask_cluster.spec.max_replicas = 4
dask_cluster.spec.remote = True
dask_cluster.spec.service_type = "NodePort"
return dask_cluster
def main():
# Load environment variables
load_dotenv()
# Setup project
project_name, artifact_path = set_environment(
project="remote-model-deployment",
artifact_path=os.getenv("MLRUN_ARTIFACT_PATH"),
api_path=os.getenv("MLRUN_DBPATH"),
access_key=os.getenv("V3IO_ACCESS_KEY"),
)
print(f"Creating project '{project_name}'")
# Push assets to V3IO
v3io_client = v3io.dataplane.Client()
push_to_v3io(v3io_client, "assets/model.pkl", "nick/tmp/model.pkl")
# Create MLRun function
serving_fn = code_to_function(
name="serving",
kind="serving",
image="mlrun/mlrun",
filename="assets/model_server.py",
).apply(mount_v3io())
print(f"Creating function '{serving_fn.metadata.name}'")
# Configure MLRun function
serving_fn.spec.default_class = "ClassifierModel"
serving_fn.add_model("my_model", model_path="/User/tmp/model.pkl")
# Deploy
addr = serving_fn.deploy()
# Test model inference
test_inference(addr)
def main():
# Load config
with open("config.yaml") as f:
config = yaml.safe_load(f)
# Set remote credentials
os.environ["MLRUN_DBPATH"] = config["MLRUN_DBPATH"]
os.environ["MLRUN_ARTIFACT_PATH"] = config["MLRUN_ARTIFACT_PATH"]
os.environ["V3IO_USERNAME"] = config["V3IO_USERNAME"]
os.environ["V3IO_API"] = config["V3IO_API"]
os.environ["V3IO_ACCESS_KEY"] = config["V3IO_ACCESS_KEY"]
# Setup project
project_name, artifact_path = set_environment(
project="remote-model-deployment",
artifact_path=os.getenv("MLRUN_ARTIFACT_PATH"),
api_path=os.getenv("MLRUN_DBPATH"),
access_key=os.getenv("V3IO_ACCESS_KEY"),
)
print(f"Setting project environment for '{project_name}'")
print(
fs.get_offline_features(
"level-3-demo/heart-disease-train").to_dataframe().head())
