def _create_run(uri, experiment_id, work_dir, entry_point):
"""
Create a ``Run`` against the current MLflow tracking server, logging metadata (e.g. the URI,
entry point, and parameters of the project) about the run. Return an ``ActiveRun`` that can be
used to report additional data about the run (metrics/params) to the tracking server.
"""
if _is_local_uri(uri):
source_name = tracking.utils._get_git_url_if_present(_expand_uri(uri))
else:
source_name = _expand_uri(uri)
source_version = _get_git_commit(work_dir)
existing_run = fluent.active_run()
if existing_run:
parent_run_id = existing_run.info.run_id
else:
parent_run_id = None
tags = {
MLFLOW_USER: _get_user(),
MLFLOW_SOURCE_NAME: source_name,
MLFLOW_SOURCE_TYPE: SourceType.to_string(SourceType.PROJECT),
MLFLOW_PROJECT_ENTRY_POINT: entry_point
}
if source_version is not None:
tags[MLFLOW_GIT_COMMIT] = source_version
if parent_run_id is not None:
tags[MLFLOW_PARENT_RUN_ID] = parent_run_id
active_run = tracking.MlflowClient().create_run(experiment_id=experiment_id, tags=tags)
return active_run
def _create_run(uri, experiment_id, work_dir, version, entry_point,
parameters):
"""
Create a ``Run`` against the current MLflow tracking server, logging metadata (e.g. the URI,
entry point, and parameters of the project) about the run. Return an ``ActiveRun`` that can be
used to report additional data about the run (metrics/params) to the tracking server.
"""
if _is_local_uri(uri):
source_name = tracking._tracking_service.utils._get_git_url_if_present(
_expand_uri(uri))
else:
source_name = _expand_uri(uri)
source_version = _get_git_commit(work_dir)
existing_run = fluent.active_run()
if existing_run:
parent_run_id = existing_run.info.run_id
else:
parent_run_id = None
tags = {
MLFLOW_USER: _get_user(),
MLFLOW_SOURCE_NAME: source_name,
MLFLOW_SOURCE_TYPE: SourceType.to_string(SourceType.PROJECT),
MLFLOW_PROJECT_ENTRY_POINT: entry_point,
}
if source_version is not None:
tags[MLFLOW_GIT_COMMIT] = source_version
if parent_run_id is not None:
tags[MLFLOW_PARENT_RUN_ID] = parent_run_id
repo_url = _get_git_repo_url(work_dir)
if repo_url is not None:
tags[MLFLOW_GIT_REPO_URL] = repo_url
tags[LEGACY_MLFLOW_GIT_REPO_URL] = repo_url
# Add branch name tag if a branch is specified through -version
if _is_valid_branch_name(work_dir, version):
tags[MLFLOW_GIT_BRANCH] = version
tags[LEGACY_MLFLOW_GIT_BRANCH_NAME] = version
active_run = tracking.MlflowClient().create_run(
experiment_id=experiment_id, tags=tags)
project = _project_spec.load_project(work_dir)
# Consolidate parameters for logging.
# `storage_dir` is `None` since we want to log actual path not downloaded local path
entry_point_obj = project.get_entry_point(entry_point)
final_params, extra_params = entry_point_obj.compute_parameters(
parameters, storage_dir=None)
params_list = [
Param(key, value) for key, value in list(final_params.items()) +
list(extra_params.items())
]
tracking.MlflowClient().log_batch(active_run.info.run_id,
params=params_list)
return active_run
def log_model(artifact_path, **kwargs):
"""
Export model in Python function form and log it with current MLflow tracking service.
Model is exported by calling ``@save_model`` and logging the result with
``@tracking.log_output_files``.
"""
with TempDir() as tmp:
local_path = tmp.path(artifact_path)
run_id = active_run().info.run_uuid
if 'model' in kwargs:
raise Exception("Unused argument 'model'. log_model creates a new model object")
save_model(dst_path=local_path, model=Model(artifact_path=artifact_path, run_id=run_id),
**kwargs)
log_artifacts(local_path, artifact_path)
def _create_run(uri, experiment_id, work_dir, entry_point):
"""
Create a ``Run`` against the current MLflow tracking server, logging metadata (e.g. the URI,
entry point, and parameters of the project) about the run. Return an ``ActiveRun`` that can be
used to report additional data about the run (metrics/params) to the tracking server.
"""
if _is_local_uri(uri):
source_name = tracking.utils._get_git_url_if_present(_expand_uri(uri))
else:
source_name = _expand_uri(uri)
existing_run = fluent.active_run()
if existing_run:
parent_run_id = existing_run.info.run_uuid
else:
parent_run_id = None
active_run = tracking.MlflowClient().create_run(
experiment_id=experiment_id,
source_name=source_name,
source_version=_get_git_commit(work_dir),
entry_point_name=entry_point,
source_type=SourceType.PROJECT,
parent_run_id=parent_run_id)
return active_run
def log_model(artifact_path,
loader_module=None,
data_path=None,
code_path=None,
conda_env=None,
python_model=None,
artifacts=None):
"""
Create a custom Pyfunc model, incorporating custom inference logic and data dependencies.
For information about the workflows that this method supports, see :ref:`Workflows for
creating custom pyfunc models <pyfunc-create-custom-workflows>` and
:ref:`Which workflow is right for my use case? <pyfunc-create-custom-selecting-workflow>`.
You cannot specify the parameters for the first workflow: ``loader_module``, ``data_path``
and the parameters for the second workflow: ``python_model``, ``artifacts`` together.
:param artifact_path: The run-relative artifact path to which to log the Python model.
:param loader_module: The name of the Python module that will be used to load the model
from ``data_path``. This module must define a method with the prototype
``_load_pyfunc(data_path)``. If not *None*, this module and its
dependencies must be included in one of the following locations:
- The MLflow library.
- Package(s) listed in the model's Conda environment, specified by
the ``conda_env`` parameter.
- One or more of the files specified by the ``code_path`` parameter.
:param data_path: Path to a file or directory containing model data.
:param code_path: A list of local filesystem paths to Python file dependencies (or directories
containing file dependencies). These files will be *prepended* to the system
path before the model is loaded.
:param conda_env: Either a dictionary representation of a Conda environment or the path to a
Conda environment yaml file. This decribes the environment this model should
be run in. If ``python_model`` is not *None*, the Conda environment must
at least specify the dependencies contained in
:data:`mlflow.pyfunc.DEFAULT_CONDA_ENV`. If `None`, the default
:data:`mlflow.pyfunc.DEFAULT_CONDA_ENV` environment will be added to the
model. The following is an *example* dictionary representation of a Conda
environment::
{
'name': 'mlflow-env',
'channels': ['defaults'],
'dependencies': [
'python=3.7.0',
'cloudpickle==0.5.8'
]
}
:param python_model: An instance of a subclass of :class:`~PythonModel`. This class will be
serialized using the CloudPickle library. Any dependencies of the class
should be included in one of the following locations:
- The MLflow library.
- Package(s) listed in the model's Conda environment, specified by
the ``conda_env`` parameter.
- One or more of the files specified by the ``code_path`` parameter.
Note: If the class is imported from another module, as opposed to being
defined in the ``__main__`` scope, the defining module should also be
included in one of the listed locations.
:param artifacts: A dictionary containing ``<name, artifact_uri>`` entries. Remote artifact URIs
will be resolved to absolute filesystem paths, producing a dictionary of
``<name, absolute_path>`` entries. ``python_model`` can reference these
resolved entries as the ``artifacts`` property of the ``context`` parameter
in :func:`PythonModel.load_context() <mlflow.pyfunc.PythonModel.load_context>`
and :func:`PythonModel.predict() <mlflow.pyfunc.PythonModel.predict>`.
For example, consider the following ``artifacts`` dictionary::
{
"my_file": "s3://my-bucket/path/to/my/file"
}
In this case, the ``"my_file"`` artifact will be downloaded from S3. The
``python_model`` can then refer to ``"my_file"`` as an absolute filesystem
path via ``context.artifacts["my_file"]``.
If *None*, no artifacts will be added to the model.
"""
with TempDir() as tmp:
local_path = tmp.path(artifact_path)
run_id = active_run().info.run_uuid
save_model(dst_path=local_path,
model=Model(artifact_path=artifact_path, run_id=run_id),
loader_module=loader_module,
data_path=data_path,
code_path=code_path,
conda_env=conda_env,
python_model=python_model,
artifacts=artifacts)
log_artifacts(local_path, artifact_path)
def get_current_run_id():
return active_run().info.run_uuid
