[
https://issues.apache.org/jira/browse/SPARK-46148?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Hyukjin Kwon reassigned SPARK-46148:
------------------------------------
Assignee: Hyukjin Kwon
> Fix pyspark.pandas.mlflow.load_model test (Python 3.12)
> -------------------------------------------------------
>
> Key: SPARK-46148
> URL: https://issues.apache.org/jira/browse/SPARK-46148
> Project: Spark
> Issue Type: Sub-task
> Components: PySpark
> Affects Versions: 4.0.0
> Reporter: Hyukjin Kwon
> Assignee: Hyukjin Kwon
> Priority: Major
> Labels: pull-request-available
>
> {code}
> **********************************************************************
> File "/__w/spark/spark/python/pyspark/pandas/mlflow.py", line 172, in
> pyspark.pandas.mlflow.load_model
> Failed example:
> prediction_df
> Exception raised:
> Traceback (most recent call last):
> File "/usr/lib/python3.10/doctest.py", line 1350, in __run
> exec(compile(example.source, filename, "single",
> File "<doctest pyspark.pandas.mlflow.load_model[18]>", line 1, in
> <module>
> prediction_df
> File "/__w/spark/spark/python/pyspark/pandas/frame.py", line 13291, in
> __repr__
> pdf = cast("DataFrame",
> self._get_or_create_repr_pandas_cache(max_display_count))
> File "/__w/spark/spark/python/pyspark/pandas/frame.py", line 13282, in
> _get_or_create_repr_pandas_cache
> self, "_repr_pandas_cache", {n: self.head(n +
> 1)._to_internal_pandas()}
> File "/__w/spark/spark/python/pyspark/pandas/frame.py", line 13277, in
> _to_internal_pandas
> return self._internal.to_pandas_frame
> File "/__w/spark/spark/python/pyspark/pandas/utils.py", line 599, in
> wrapped_lazy_property
> setattr(self, attr_name, fn(self))
> File "/__w/spark/spark/python/pyspark/pandas/internal.py", line 1110,
> in to_pandas_frame
> pdf = sdf.toPandas()
> File "/__w/spark/spark/python/pyspark/sql/pandas/conversion.py", line
> 213, in toPandas
> rows = self.collect()
> File "/__w/spark/spark/python/pyspark/sql/dataframe.py", line 1369, in
> collect
> sock_info = self._jdf.collectToPython()
> File
> "/__w/spark/spark/python/lib/py4j-0.10.9.7-src.zip/py4j/java_gateway.py",
> line 1322, in __call__
> return_value = get_return_value(
> File "/__w/spark/spark/python/pyspark/errors/exceptions/captured.py",
> line 188, in deco
> raise converted from None
> pyspark.errors.exceptions.captured.PythonException:
> An exception was thrown from the Python worker. Please see the stack
> trace below.
> Traceback (most recent call last):
> File "/__w/spark/spark/python/lib/pyspark.zip/pyspark/worker.py", line
> 1523, in main
> process()
> File "/__w/spark/spark/python/lib/pyspark.zip/pyspark/worker.py", line
> 1515, in process
> serializer.dump_stream(out_iter, outfile)
> File
> "/__w/spark/spark/python/lib/pyspark.zip/pyspark/sql/pandas/serializers.py",
> line 485, in dump_stream
> return ArrowStreamSerializer.dump_stream(self,
> init_stream_yield_batches(), stream)
> File
> "/__w/spark/spark/python/lib/pyspark.zip/pyspark/sql/pandas/serializers.py",
> line 101, in dump_stream
> for batch in iterator:
> File
> "/__w/spark/spark/python/lib/pyspark.zip/pyspark/sql/pandas/serializers.py",
> line 478, in init_stream_yield_batches
> for series in iterator:
> File "/__w/spark/spark/python/lib/pyspark.zip/pyspark/worker.py", line
> 1284, in func
> for result_batch, result_type in result_iter:
> File
> "/usr/local/lib/python3.10/dist-packages/mlflow/pyfunc/__init__.py", line
> 1619, in udf
> yield _predict_row_batch(batch_predict_fn, row_batch_args)
> File
> "/usr/local/lib/python3.10/dist-packages/mlflow/pyfunc/__init__.py", line
> 1383, in _predict_row_batch
> result = predict_fn(pdf, params)
> File
> "/usr/local/lib/python3.10/dist-packages/mlflow/pyfunc/__init__.py", line
> 1601, in batch_predict_fn
> return loaded_model.predict(pdf, params=params)
> File
> "/usr/local/lib/python3.10/dist-packages/mlflow/pyfunc/__init__.py", line
> 491, in predict
> return _predict()
> File
> "/usr/local/lib/python3.10/dist-packages/mlflow/pyfunc/__init__.py", line
> 477, in _predict
> return self._predict_fn(data, params=params)
> File
> "/usr/local/lib/python3.10/dist-packages/mlflow/sklearn/__init__.py", line
> 517, in predict
> return self.sklearn_model.predict(data)
> File
> "/usr/local/lib/python3.10/dist-packages/sklearn/linear_model/_base.py", line
> 386, in predict
> return self._decision_function(X)
> File
> "/usr/local/lib/python3.10/dist-packages/sklearn/linear_model/_base.py", line
> 369, in _decision_function
> X = self._validate_data(X, accept_sparse=["csr", "csc", "coo"],
> reset=False)
> File "/usr/local/lib/python3.10/dist-packages/sklearn/base.py", line
> 580, in _validate_data
> self._check_feature_names(X, reset=reset)
> File "/usr/local/lib/python3.10/dist-packages/sklearn/base.py", line
> 507, in _check_feature_names
> raise ValueError(message)
> ValueError: The feature names should match those that were passed during
> fit.
> Feature names unseen at fit time:
> - 0
> - 1
> Feature names seen at fit time, yet now missing:
> - x1
> - x2
> JVM stacktrace:
> org.apache.spark.SparkException: Job aborted due to stage failure: Task 2
> in stage 1.0 failed 1 times, most recent failure: Lost task 2.0 in stage 1.0
> (TID 3) (localhost executor driver):
> org.apache.spark.api.python.PythonException: Traceback (most recent call
> last):
> File "/__w/spark/spark/python/lib/pyspark.zip/pyspark/worker.py", line
> 1523, in main
> process()
> File "/__w/spark/spark/python/lib/pyspark.zip/pyspark/worker.py", line
> 1515, in process
> serializer.dump_stream(out_iter, outfile)
> File
> "/__w/spark/spark/python/lib/pyspark.zip/pyspark/sql/pandas/serializers.py",
> line 485, in dump_stream
> return ArrowStreamSerializer.dump_stream(self,
> init_stream_yield_batches(), stream)
> File
> "/__w/spark/spark/python/lib/pyspark.zip/pyspark/sql/pandas/serializers.py",
> line 101, in dump_stream
> for batch in iterator:
> File
> "/__w/spark/spark/python/lib/pyspark.zip/pyspark/sql/pandas/serializers.py",
> line 478, in init_stream_yield_batches
> for series in iterator:
> File "/__w/spark/spark/python/lib/pyspark.zip/pyspark/worker.py", line
> 1284, in func
> for result_batch, result_type in result_iter:
> File
> "/usr/local/lib/python3.10/dist-packages/mlflow/pyfunc/__init__.py", line
> 1619, in udf
> yield _predict_row_batch(batch_predict_fn, row_batch_args)
> File
> "/usr/local/lib/python3.10/dist-packages/mlflow/pyfunc/__init__.py", line
> 1383, in _predict_row_batch
> at scala.collection.Iterator$$anon$9.hasNext(Iterator.scala:583)
> at
> org.apache.spark.shuffle.sort.BypassMergeSortShuffleWriter.write(BypassMergeSortShuffleWriter.java:140)
> at
> org.apache.spark.shuffle.ShuffleWriteProcessor.write(ShuffleWriteProcessor.scala:57)
> at
> org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:111)
> at
> org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:54)
> at
> org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
> at org.apache.spark.scheduler.Task.run(Task.scala:141)
> at
> org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:628)
> at
> org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
> at
> org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
> at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:96)
> at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:631)
> at
> java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1136)
> at
> java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635)
> at java.base/java.lang.Thread.run(Thread.java:840)
> **********************************************************************
> {code}
> See https://github.com/apache/spark/actions/runs/7020654429/job/19100965399
--
This message was sent by Atlassian Jira
(v8.20.10#820010)
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org
For additional commands, e-mail: issues-h...@spark.apache.org
