def __init__(original, self, *args, **kwargs):
original(self, *args, **kwargs)
_listen_for_spark_activity(self._sc)
def autolog(disable=False, silent=False): # pylint: disable=unused-argument
"""
Enables (or disables) and configures logging of Spark datasource paths, versions
(if applicable), and formats when they are read. This method is not threadsafe and assumes a
`SparkSession
<https://spark.apache.org/docs/latest/api/python/pyspark.sql.html#pyspark.sql.SparkSession>`_
already exists with the
`mlflow-spark JAR
<http://mlflow.org/docs/latest/tracking.html#automatic-logging-from-spark-experimental>`_
attached. It should be called on the Spark driver, not on the executors (i.e. do not call
this method within a function parallelized by Spark). This API requires Spark 3.0 or above.
Datasource information is cached in memory and logged to all subsequent MLflow runs,
including the active MLflow run (if one exists when the data is read). Note that autologging of
Spark ML (MLlib) models is not currently supported via this API. Datasource autologging is
best-effort, meaning that if Spark is under heavy load or MLflow logging fails for any reason
(e.g., if the MLflow server is unavailable), logging may be dropped.
For any unexpected issues with autologging, check Spark driver and executor logs in addition
to stderr & stdout generated from your MLflow code - datasource information is pulled from
Spark, so logs relevant to debugging may show up amongst the Spark logs.
.. code-block:: python
:caption: Example
import mlflow.spark
import os
import shutil
from pyspark.sql import SparkSession
# Create and persist some dummy data
# Note: On environments like Databricks with pre-created SparkSessions,
# ensure the org.mlflow:mlflow-spark:1.11.0 is attached as a library to
# your cluster
spark = (SparkSession.builder
.config("spark.jars.packages", "org.mlflow:mlflow-spark:1.11.0")
.master("local[*]")
.getOrCreate())
df = spark.createDataFrame([
(4, "spark i j k"),
(5, "l m n"),
(6, "spark hadoop spark"),
(7, "apache hadoop")], ["id", "text"])
import tempfile
tempdir = tempfile.mkdtemp()
df.write.csv(os.path.join(tempdir, "my-data-path"), header=True)
# Enable Spark datasource autologging.
mlflow.spark.autolog()
loaded_df = spark.read.csv(os.path.join(tempdir, "my-data-path"),
header=True, inferSchema=True)
# Call toPandas() to trigger a read of the Spark datasource. Datasource info
# (path and format) is logged to the current active run, or the
# next-created MLflow run if no run is currently active
with mlflow.start_run() as active_run:
pandas_df = loaded_df.toPandas()
:param disable: If ``True``, disables the Spark datasource autologging integration.
If ``False``, enables the Spark datasource autologging integration.
:param silent: If ``True``, suppress all event logs and warnings from MLflow during Spark
datasource autologging. If ``False``, show all events and warnings during Spark
datasource autologging.
"""
from mlflow.utils._spark_utils import _get_active_spark_session
from mlflow._spark_autologging import _listen_for_spark_activity
from pyspark.sql import SparkSession
from pyspark import SparkContext
def __init__(original, self, *args, **kwargs):
original(self, *args, **kwargs)
_listen_for_spark_activity(self._sc)
safe_patch(FLAVOR_NAME,
SparkSession,
"__init__",
__init__,
manage_run=False)
active_session = _get_active_spark_session()
if active_session is not None:
# We know SparkContext exists here already, so get it
sc = SparkContext.getOrCreate()
_listen_for_spark_activity(sc)
