[
https://issues.apache.org/jira/browse/SPARK-48249?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Hyukjin Kwon updated SPARK-48249:
---------------------------------
Description:
{code}
>>> spark.conf.set("spark.sql.pyspark.legacy.inferArrayTypeFromFirstElement.enabled",
>>> True)
>>> spark.createDataFrame([[[None, 1]]])
Traceback (most recent call last):
File "<stdin>", line 1, in <module>
File "/.../spark/python/pyspark/sql/session.py", line 1538, in createDataFrame
return self._create_dataframe(
^^^^^^^^^^^^^^^^^^^^^^^
File "/.../spark/python/pyspark/sql/session.py", line 1582, in
_create_dataframe
rdd, struct = self._createFromLocal(
^^^^^^^^^^^^^^^^^^^^^^
File "/.../spark/python/pyspark/sql/session.py", line 1184, in
_createFromLocal
struct = self._inferSchemaFromList(data, names=schema)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/.../spark/python/pyspark/sql/session.py", line 1060, in
_inferSchemaFromList
raise PySparkValueError(
pyspark.errors.exceptions.base.PySparkValueError: [CANNOT_DETERMINE_TYPE] Some
of types cannot be determined after inferring.
{code}
was:
{code}
>>> spark.conf.set("spark.sql.pyspark.legacy.inferArrayTypeFromFirstElement.enabled",
>>> True)
>>> spark.createDataFrame([None, 1])
Traceback (most recent call last):
File "<stdin>", line 1, in <module>
File "/.../spark/python/pyspark/sql/session.py", line 1538, in createDataFrame
return self._create_dataframe(
^^^^^^^^^^^^^^^^^^^^^^^
File "/.../spark/python/pyspark/sql/session.py", line 1582, in
_create_dataframe
rdd, struct = self._createFromLocal(
^^^^^^^^^^^^^^^^^^^^^^
File "/.../spark/python/pyspark/sql/session.py", line 1184, in
_createFromLocal
struct = self._inferSchemaFromList(data, names=schema)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/.../spark/python/pyspark/sql/session.py", line 1046, in
_inferSchemaFromList
schema = reduce(
^^^^^^^
File "/.../spark/python/pyspark/sql/session.py", line 1049, in <genexpr>
_infer_schema(
File "/.../spark/python/pyspark/sql/types.py", line 2015, in _infer_schema
raise PySparkTypeError(
pyspark.errors.exceptions.base.PySparkTypeError: [CANNOT_INFER_SCHEMA_FOR_TYPE]
Can not infer schema for type: `NoneType`.
{code}
> Use non-null value for legacy conf of inferArrayTypeFromFirstElement
> --------------------------------------------------------------------
>
> Key: SPARK-48249
> URL: https://issues.apache.org/jira/browse/SPARK-48249
> Project: Spark
> Issue Type: Bug
> Components: PySpark
> Affects Versions: 4.0.0
> Reporter: Hyukjin Kwon
> Priority: Major
>
> {code}
> >>> spark.conf.set("spark.sql.pyspark.legacy.inferArrayTypeFromFirstElement.enabled",
> >>> True)
> >>> spark.createDataFrame([[[None, 1]]])
> Traceback (most recent call last):
> File "<stdin>", line 1, in <module>
> File "/.../spark/python/pyspark/sql/session.py", line 1538, in
> createDataFrame
> return self._create_dataframe(
> ^^^^^^^^^^^^^^^^^^^^^^^
> File "/.../spark/python/pyspark/sql/session.py", line 1582, in
> _create_dataframe
> rdd, struct = self._createFromLocal(
> ^^^^^^^^^^^^^^^^^^^^^^
> File "/.../spark/python/pyspark/sql/session.py", line 1184, in
> _createFromLocal
> struct = self._inferSchemaFromList(data, names=schema)
> ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
> File "/.../spark/python/pyspark/sql/session.py", line 1060, in
> _inferSchemaFromList
> raise PySparkValueError(
> pyspark.errors.exceptions.base.PySparkValueError: [CANNOT_DETERMINE_TYPE]
> Some of types cannot be determined after inferring.
> {code}
--
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
