def predict(self, model_uri, input_path, output_path, content_type,
json_format):
"""
Generate predictions using generic python model saved with MLflow.
Return the prediction results as a JSON.
"""
with TempDir() as tmp:
local_path = _download_artifact_from_uri(model_uri,
output_path=tmp.path())
if not self._no_conda and ENV in self._config:
conda_env_path = os.path.join(local_path, self._config[ENV])
# NOTE: We're calling main in the pyfunc scoring server belonging to the current
# conda environment. The model environment may contain mlflow with different version
# than the one in the current active environment. This is the intended behavior.
# We need to make sure the scoring server is consistent with the outside mlflow
# while the model that is being loaded may depend on a different version of mlflow.
# The hope is that the scoring server is self contained enough and does not have
# external mlflow dependencies that would be incompatible between mlflow versions.
if input_path is None:
input_path = "__stdin__"
if output_path is None:
output_path = "__stdout__"
command = "python {0} predict {1} {2} {3} {4} {5}".format(
scoring_server.__file__, shlex_quote(local_path),
shlex_quote(input_path), shlex_quote(output_path),
content_type, json_format)
return scoring_server._execute_in_conda_env(
conda_env_path, command)
else:
scoring_server._predict(local_path, input_path, output_path,
content_type, json_format)
def predict(
self,
model_uri,
input_path,
output_path,
content_type,
json_format,
):
"""
Generate predictions using generic python model saved with MLflow.
Return the prediction results as a JSON.
"""
local_path = _download_artifact_from_uri(model_uri)
# NB: Absolute windows paths do not work with mlflow apis, use file uri to ensure
# platform compatibility.
local_uri = path_to_local_file_uri(local_path)
if not self._no_conda and ENV in self._config:
conda_env_path = os.path.join(local_path, self._config[ENV])
command = (
'python -c "from mlflow.pyfunc.scoring_server import _predict; _predict('
'model_uri={model_uri}, '
'input_path={input_path}, '
'output_path={output_path}, '
'content_type={content_type}, '
'json_format={json_format})"').format(
model_uri=repr(local_uri),
input_path=repr(input_path),
output_path=repr(output_path),
content_type=repr(content_type),
json_format=repr(json_format))
return _execute_in_conda_env(conda_env_path, command,
self._install_mlflow)
else:
scoring_server._predict(local_uri, input_path, output_path,
content_type, json_format)
def predict(self, model_uri, input_path, output_path, content_type,
json_format):
"""
Generate predictions using generic python model saved with MLflow.
Return the prediction results as a JSON.
"""
local_path = _download_artifact_from_uri(model_uri)
# NB: Absolute windows paths do not work with mlflow apis, use file uri to ensure
# platform compatibility.
local_uri = path_to_local_file_uri(local_path)
command = (
'python -c "from mlflow.pyfunc.scoring_server import _predict; _predict('
"model_uri={model_uri}, "
"input_path={input_path}, "
"output_path={output_path}, "
"content_type={content_type}, "
'json_format={json_format})"').format(
model_uri=repr(local_uri),
input_path=repr(input_path),
output_path=repr(output_path),
content_type=repr(content_type),
json_format=repr(json_format),
)
if self._env_manager == _EnvManager.CONDA and ENV in self._config:
conda_env_path = os.path.join(local_path, self._config[ENV])
conda_env_name = get_or_create_conda_env(
conda_env_path,
env_id=self._env_id,
capture_output=False,
env_root_dir=self._env_root_dir,
)
return _execute_in_conda_env(conda_env_name,
command,
self._install_mlflow,
env_root_dir=self._env_root_dir)
elif self._env_manager == _EnvManager.VIRTUALENV:
activate_cmd = _get_or_create_virtualenv(
local_path, self._env_id, env_root_dir=self._env_root_dir)
return _execute_in_virtualenv(activate_cmd,
command,
self._install_mlflow,
env_root_dir=self._env_root_dir)
else:
scoring_server._predict(local_uri, input_path, output_path,
content_type, json_format)
