def _log_pretraining_metadata(estimator, *args, **kwargs): # pylint: disable=unused-argument
"""
Records metadata (e.g., params and tags) for a scikit-learn estimator prior to training.
This is intended to be invoked within a patched scikit-learn training routine
(e.g., `fit()`, `fit_transform()`, ...) and assumes the existence of an active
MLflow run that can be referenced via the fluent Tracking API.
:param estimator: The scikit-learn estimator for which to log metadata.
:param args: The arguments passed to the scikit-learn training routine (e.g.,
`fit()`, `fit_transform()`, ...).
:param kwargs: The keyword arguments passed to the scikit-learn training routine.
"""
# Deep parameter logging includes parameters from children of a given
# estimator. For some meta estimators (e.g., pipelines), recording
# these parameters is desirable. For parameter search estimators,
# however, child estimators act as seeds for the parameter search
# process; accordingly, we avoid logging initial, untuned parameters
# for these seed estimators.
should_log_params_deeply = not _is_parameter_search_estimator(
estimator)
# Chunk model parameters to avoid hitting the log_batch API limit
for chunk in _chunk_dict(
estimator.get_params(deep=should_log_params_deeply),
chunk_size=MAX_PARAMS_TAGS_PER_BATCH,
):
truncated = _truncate_dict(chunk, MAX_ENTITY_KEY_LENGTH,
MAX_PARAM_VAL_LENGTH)
try_mlflow_log(mlflow.log_params, truncated)
try_mlflow_log(mlflow.set_tags, _get_estimator_info_tags(estimator))
def _log_pretraining_metadata(autologging_client, estimator, *args,
**kwargs): # pylint: disable=unused-argument
"""
Records metadata (e.g., params and tags) for a scikit-learn estimator prior to training.
This is intended to be invoked within a patched scikit-learn training routine
(e.g., `fit()`, `fit_transform()`, ...) and assumes the existence of an active
MLflow run that can be referenced via the fluent Tracking API.
:param autologging_client: An instance of `MlflowAutologgingQueueingClient` used for
efficiently logging run data to MLflow Tracking.
:param estimator: The scikit-learn estimator for which to log metadata.
:param args: The arguments passed to the scikit-learn training routine (e.g.,
`fit()`, `fit_transform()`, ...).
:param kwargs: The keyword arguments passed to the scikit-learn training routine.
"""
# Deep parameter logging includes parameters from children of a given
# estimator. For some meta estimators (e.g., pipelines), recording
# these parameters is desirable. For parameter search estimators,
# however, child estimators act as seeds for the parameter search
# process; accordingly, we avoid logging initial, untuned parameters
# for these seed estimators.
should_log_params_deeply = not _is_parameter_search_estimator(
estimator)
run_id = mlflow.active_run().info.run_id
autologging_client.log_params(
run_id=mlflow.active_run().info.run_id,
params=estimator.get_params(deep=should_log_params_deeply),
)
autologging_client.set_tags(
run_id=run_id,
tags=_get_estimator_info_tags(estimator),
)
