def load_model(model_uri, dfs_tmpdir=None):
"""
Load the Spark MLlib model from the path.
:param model_uri: The location, in URI format, of the MLflow model, for example:
- ``/Users/me/path/to/local/model``
- ``relative/path/to/local/model``
- ``s3://my_bucket/path/to/model``
- ``runs:/<mlflow_run_id>/run-relative/path/to/model``
- ``models:/<model_name>/<model_version>``
- ``models:/<model_name>/<stage>``
For more information about supported URI schemes, see
`Referencing Artifacts <https://www.mlflow.org/docs/latest/concepts.html#
artifact-locations>`_.
:param dfs_tmpdir: Temporary directory path on Distributed (Hadoop) File System (DFS) or local
filesystem if running in local mode. The model is loaded from this
destination. Defaults to ``/tmp/mlflow``.
:return: pyspark.ml.pipeline.PipelineModel
.. code-block:: python
:caption: Example
from mlflow import spark
model = mlflow.spark.load_model("spark-model")
# Prepare test documents, which are unlabeled (id, text) tuples.
test = spark.createDataFrame([
(4, "spark i j k"),
(5, "l m n"),
(6, "spark hadoop spark"),
(7, "apache hadoop")], ["id", "text"])
# Make predictions on test documents
prediction = model.transform(test)
"""
if RunsArtifactRepository.is_runs_uri(model_uri):
runs_uri = model_uri
model_uri = RunsArtifactRepository.get_underlying_uri(model_uri)
_logger.info("'%s' resolved as '%s'", runs_uri, model_uri)
elif ModelsArtifactRepository.is_models_uri(model_uri):
runs_uri = model_uri
model_uri = ModelsArtifactRepository.get_underlying_uri(model_uri)
_logger.info("'%s' resolved as '%s'", runs_uri, model_uri)
flavor_conf = _get_flavor_configuration_from_uri(model_uri, FLAVOR_NAME)
model_uri = append_to_uri_path(model_uri, flavor_conf["model_data"])
local_model_path = _download_artifact_from_uri(model_uri)
_add_code_from_conf_to_system_path(local_model_path, flavor_conf)
return _load_model(model_uri=model_uri, dfs_tmpdir_base=dfs_tmpdir)
def load_model(model_uri, dfs_tmpdir=None):
"""
Load the Spark MLlib model from the path.
:param model_uri: The location, in URI format, of the MLflow model, for example:
- ``/Users/me/path/to/local/model``
- ``relative/path/to/local/model``
- ``s3://my_bucket/path/to/model``
- ``runs:/<mlflow_run_id>/run-relative/path/to/model``
For more information about supported URI schemes, see
`Referencing Artifacts <https://www.mlflow.org/docs/latest/tracking.html#
artifact-locations>`_.
:param dfs_tmpdir: Temporary directory path on Distributed (Hadoop) File System (DFS) or local
filesystem if running in local mode. The model is loaded from this
destination. Defaults to ``/tmp/mlflow``.
:return: pyspark.ml.pipeline.PipelineModel
>>> from mlflow import spark
>>> model = mlflow.spark.load_model("spark-model")
>>> # Prepare test documents, which are unlabeled (id, text) tuples.
>>> test = spark.createDataFrame([
... (4, "spark i j k"),
... (5, "l m n"),
... (6, "spark hadoop spark"),
... (7, "apache hadoop")], ["id", "text"])
>>> # Make predictions on test documents.
>>> prediction = model.transform(test)
"""
if RunsArtifactRepository.is_runs_uri(model_uri):
runs_uri = model_uri
model_uri = RunsArtifactRepository.get_underlying_uri(model_uri)
_logger.info("'%s' resolved as '%s'", runs_uri, model_uri)
flavor_conf = _get_flavor_configuration_from_uri(model_uri, FLAVOR_NAME)
model_uri = posixpath.join(model_uri, flavor_conf["model_data"])
return _load_model(model_uri=model_uri, dfs_tmpdir=dfs_tmpdir)
