def _call(self,
*args,
_pypads_env: LoggerEnv,
_pypads_autologgers=None,
_logger_call,
_logger_output,
**kwargs):
if _pypads_autologgers is None:
_pypads_autologgers = [
"keras", "tensorflow", "xgboost", "gluon", "spark", "lightgbm",
"sklearn"
]
if 'tensorflow' in _pypads_autologgers and 'tensorflow' in sys.modules and 'tensorflow' not in added_auto_logs \
and is_package_available('tensorflow'):
added_auto_logs.add('tensorflow')
from mlflow import tensorflow
tensorflow.autolog()
if 'keras' in _pypads_autologgers and 'keras' in sys.modules and 'keras' not in added_auto_logs \
and is_package_available('keras'):
added_auto_logs.add('keras')
from mlflow import keras
keras.autolog()
if 'xgboost' in _pypads_autologgers and 'xgboost' in sys.modules and 'xgboost' not in added_auto_logs \
and is_package_available('xgboost'):
added_auto_logs.add('xgboost')
from mlflow import xgboost
xgboost.autolog()
if 'gluon' in _pypads_autologgers and 'gluon' in sys.modules and 'gluon' not in added_auto_logs \
and is_package_available('gluon'):
added_auto_logs.add('gluon')
from mlflow import gluon
gluon.autolog()
if 'spark' in _pypads_autologgers and 'spark' in sys.modules and 'spark' not in added_auto_logs \
and is_package_available('pyspark'):
added_auto_logs.add('spark')
from mlflow import spark
spark.autolog()
if 'lightgbm' in _pypads_autologgers and 'lightgbm' in sys.modules and 'lightgbm' not in added_auto_logs \
and is_package_available('lightgbm'):
added_auto_logs.add('lightgbm')
from mlflow import lightgbm
lightgbm.autolog()
if 'sklearn' in _pypads_autologgers and 'sklearn' in sys.modules and 'sklearn' not in added_auto_logs \
and is_package_available('sklearn'):
added_auto_logs.add('sklearn')
from mlflow import sklearn
sklearn.autolog()
def autolog(log_input_example=False, log_model_signature=True): # pylint: disable=unused-argument
locals_copy = locals().items()
# Mapping of library module name to specific autolog function
# eg: mxnet.gluon is the actual library, mlflow.gluon.autolog is our autolog function for it
LIBRARY_TO_AUTOLOG_FN = {
"tensorflow": tensorflow.autolog,
"keras": keras.autolog,
"mxnet.gluon": gluon.autolog,
"xgboost": xgboost.autolog,
"lightgbm": lightgbm.autolog,
"sklearn": sklearn.autolog,
"fastai": fastai.autolog,
"pyspark": spark.autolog,
}
def setup_autologging(module):
autolog_fn = LIBRARY_TO_AUTOLOG_FN[module.__name__]
try:
needed_params = list(inspect.signature(autolog_fn).parameters.keys())
filtered = {k: v for k, v in locals_copy if k in needed_params}
except ValueError:
filtered = {}
try:
autolog_fn(**filtered)
_logger.info("Autologging successfully enabled for %s.", module.__name__)
except Exception as e: # pylint: disable=broad-except
_logger.warning(
"Exception raised while enabling autologging for %s: %s", module.__name__, str(e)
)
# for each autolog library (except pyspark), register a post-import hook.
# this way, we do not send any errors to the user until we know they are using the library.
# the post-import hook also retroactively activates for previously-imported libraries.
for module in list(set(LIBRARY_TO_AUTOLOG_FN.keys()) - set(["pyspark"])):
register_post_import_hook(setup_autologging, module, overwrite=True)
# for pyspark, we activate autologging immediately, without waiting for a module import.
# this is because on Databricks a SparkSession already exists and the user can directly
# interact with it, and this activity should be logged.
try:
spark.autolog()
except ImportError as ie:
# if pyspark isn't installed, a user could potentially install it in the middle
# of their session so we want to enable autologging once they do
if "pyspark" in str(ie):
register_post_import_hook(setup_autologging, "pyspark", overwrite=True)
except Exception as e: # pylint: disable=broad-except
_logger.warning("Exception raised while enabling autologging for spark: %s", str(e))
def autolog(
log_input_examples=False,
log_model_signatures=True,
log_models=True,
disable=False,
exclusive=False,
): # pylint: disable=unused-argument
"""
Enables (or disables) and configures autologging for all supported integrations.
The parameters are passed to any autologging integrations that support them.
See the :ref:`tracking docs <automatic-logging>` for a list of supported autologging
integrations.
:param log_input_examples: If ``True``, input examples from training datasets are collected and
logged along with model artifacts during training. If ``False``,
input examples are not logged.
Note: Input examples are MLflow model attributes
and are only collected if ``log_models`` is also ``True``.
:param log_model_signatures: If ``True``,
:py:class:`ModelSignatures <mlflow.models.ModelSignature>`
describing model inputs and outputs are collected and logged along
with model artifacts during training. If ``False``, signatures are
not logged. Note: Model signatures are MLflow model attributes
and are only collected if ``log_models`` is also ``True``.
:param log_models: If ``True``, trained models are logged as MLflow model artifacts.
If ``False``, trained models are not logged.
Input examples and model signatures, which are attributes of MLflow models,
are also omitted when ``log_models`` is ``False``.
:param disable: If ``True``, disables all supported autologging integrations. If ``False``,
enables all supported autologging integrations.
:param exclusive: If ``True``, autologged content is not logged to user-created fluent runs.
If ``False``, autologged content is logged to the active fluent run,
which may be user-created.
.. code-block:: python
:caption: Example
import numpy as np
import mlflow.sklearn
from mlflow.tracking import MlflowClient
from sklearn.linear_model import LinearRegression
def print_auto_logged_info(r):
tags = {k: v for k, v in r.data.tags.items() if not k.startswith("mlflow.")}
artifacts = [f.path for f in MlflowClient().list_artifacts(r.info.run_id, "model")]
print("run_id: {}".format(r.info.run_id))
print("artifacts: {}".format(artifacts))
print("params: {}".format(r.data.params))
print("metrics: {}".format(r.data.metrics))
print("tags: {}".format(tags))
# prepare training data
X = np.array([[1, 1], [1, 2], [2, 2], [2, 3]])
y = np.dot(X, np.array([1, 2])) + 3
# Auto log all the parameters, metrics, and artifacts
mlflow.autolog()
model = LinearRegression()
with mlflow.start_run() as run:
model.fit(X, y)
# fetch the auto logged parameters and metrics for ended run
print_auto_logged_info(mlflow.get_run(run_id=run.info.run_id))
.. code-block:: text
:caption: Output
run_id: fd10a17d028c47399a55ab8741721ef7
artifacts: ['model/MLmodel', 'model/conda.yaml', 'model/model.pkl']
params: {'copy_X': 'True',
'normalize': 'False',
'fit_intercept': 'True',
'n_jobs': 'None'}
metrics: {'training_score': 1.0,
'training_rmse': 4.440892098500626e-16,
'training_r2_score': 1.0,
'training_mae': 2.220446049250313e-16,
'training_mse': 1.9721522630525295e-31}
tags: {'estimator_class': 'sklearn.linear_model._base.LinearRegression',
'estimator_name': 'LinearRegression'}
"""
locals_copy = locals().items()
# Mapping of library module name to specific autolog function
# eg: mxnet.gluon is the actual library, mlflow.gluon.autolog is our autolog function for it
LIBRARY_TO_AUTOLOG_FN = {
"tensorflow": tensorflow.autolog,
"keras": keras.autolog,
"mxnet.gluon": gluon.autolog,
"xgboost": xgboost.autolog,
"lightgbm": lightgbm.autolog,
"statsmodels": statsmodels.autolog,
"sklearn": sklearn.autolog,
"fastai": fastai.autolog,
"pyspark": spark.autolog,
# TODO: Broaden this beyond pytorch_lightning as we add autologging support for more
# Pytorch frameworks under mlflow.pytorch.autolog
"pytorch_lightning": pytorch.autolog,
}
def setup_autologging(module):
try:
autolog_fn = LIBRARY_TO_AUTOLOG_FN[module.__name__]
try:
needed_params = list(
inspect.signature(autolog_fn).parameters.keys())
filtered = {k: v for k, v in locals_copy if k in needed_params}
except Exception: # pylint: disable=broad-except
filtered = {}
autolog_fn(**filtered)
_logger.info("Autologging successfully enabled for %s.",
module.__name__)
except Exception as e: # pylint: disable=broad-except
if _is_testing():
# Raise unexpected exceptions in test mode in order to detect
# errors within dependent autologging integrations
raise
else:
_logger.warning(
"Exception raised while enabling autologging for %s: %s",
module.__name__,
str(e),
)
# for each autolog library (except pyspark), register a post-import hook.
# this way, we do not send any errors to the user until we know they are using the library.
# the post-import hook also retroactively activates for previously-imported libraries.
for module in list(set(LIBRARY_TO_AUTOLOG_FN.keys()) - set(["pyspark"])):
register_post_import_hook(setup_autologging, module, overwrite=True)
# for pyspark, we activate autologging immediately, without waiting for a module import.
# this is because on Databricks a SparkSession already exists and the user can directly
# interact with it, and this activity should be logged.
try:
spark.autolog()
except ImportError as ie:
# if pyspark isn't installed, a user could potentially install it in the middle
# of their session so we want to enable autologging once they do
if "pyspark" in str(ie):
register_post_import_hook(setup_autologging,
"pyspark",
overwrite=True)
except Exception as e: # pylint: disable=broad-except
if _is_testing():
# Raise unexpected exceptions in test mode in order to detect
# errors within dependent autologging integrations
raise
else:
_logger.warning(
"Exception raised while enabling autologging for spark: %s",
str(e))
def autolog(log_input_examples=False, log_model_signatures=True): # pylint: disable=unused-argument
"""
Enable autologging for all supported integrations.
The parameters are passed to any autologging integrations that support them.
See the :ref:`tracking docs <automatic-logging>` for a list of supported autologging
integrations.
:param log_input_examples: If ``True``, input examples from training datasets are collected and
logged along with model artifacts during training. If ``False``,
input examples are not logged.
:param log_model_signatures: If ``True``,
:py:class:`ModelSignatures <mlflow.models.ModelSignature>`
describing model inputs and outputs are collected and logged along
with model artifacts during training. If ``False``, signatures are
not logged.
"""
locals_copy = locals().items()
# Mapping of library module name to specific autolog function
# eg: mxnet.gluon is the actual library, mlflow.gluon.autolog is our autolog function for it
LIBRARY_TO_AUTOLOG_FN = {
"tensorflow": tensorflow.autolog,
"keras": keras.autolog,
"mxnet.gluon": gluon.autolog,
"xgboost": xgboost.autolog,
"lightgbm": lightgbm.autolog,
"sklearn": sklearn.autolog,
"fastai": fastai.autolog,
"pyspark": spark.autolog,
# TODO: Broaden this beyond pytorch_lightning as we add autologging support for more
# Pytorch frameworks under mlflow.pytorch.autolog
"pytorch_lightning": pytorch.autolog,
}
def setup_autologging(module):
autolog_fn = LIBRARY_TO_AUTOLOG_FN[module.__name__]
try:
needed_params = list(inspect.signature(autolog_fn).parameters.keys())
filtered = {k: v for k, v in locals_copy if k in needed_params}
except ValueError:
filtered = {}
try:
autolog_fn(**filtered)
_logger.info("Autologging successfully enabled for %s.", module.__name__)
except Exception as e: # pylint: disable=broad-except
_logger.warning(
"Exception raised while enabling autologging for %s: %s", module.__name__, str(e)
)
# for each autolog library (except pyspark), register a post-import hook.
# this way, we do not send any errors to the user until we know they are using the library.
# the post-import hook also retroactively activates for previously-imported libraries.
for module in list(set(LIBRARY_TO_AUTOLOG_FN.keys()) - set(["pyspark"])):
register_post_import_hook(setup_autologging, module, overwrite=True)
# for pyspark, we activate autologging immediately, without waiting for a module import.
# this is because on Databricks a SparkSession already exists and the user can directly
# interact with it, and this activity should be logged.
try:
spark.autolog()
except ImportError as ie:
# if pyspark isn't installed, a user could potentially install it in the middle
# of their session so we want to enable autologging once they do
if "pyspark" in str(ie):
register_post_import_hook(setup_autologging, "pyspark", overwrite=True)
except Exception as e: # pylint: disable=broad-except
_logger.warning("Exception raised while enabling autologging for spark: %s", str(e))