HyukjinKwon commented on a change in pull request #22807:
[SPARK-25811][PySpark] Raise a proper error when unsafe cast is detected by
PyArrow
URL: https://github.com/apache/spark/pull/22807#discussion_r249626768
##########
File path: python/pyspark/sql/tests/test_pandas_udf.py
##########
@@ -197,6 +197,64 @@ def foofoo(x, y):
).collect
)
+ def test_pandas_udf_detect_unsafe_type_conversion(self):
+ from distutils.version import LooseVersion
+ import pandas as pd
+ import numpy as np
+ import pyarrow as pa
+
+ values = [1.0] * 3
+ pdf = pd.DataFrame({'A': values})
+ df = self.spark.createDataFrame(pdf).repartition(1)
+
+ @pandas_udf(returnType="int")
+ def udf(column):
+ return pd.Series(np.linspace(0, 1, 3))
+
+ # Since 0.11.0, PyArrow supports the feature to raise an error for
unsafe cast.
+ if LooseVersion(pa.__version__) >= LooseVersion("0.11.0"):
+ with self.sql_conf({
+ "spark.sql.execution.pandas.arrowSafeTypeConversion":
True}):
+ with self.assertRaisesRegexp(Exception,
+ "Exception thrown when converting
pandas.Series"):
+ df.select(['A']).withColumn('udf', udf('A')).collect()
+
+ # Disabling Arrow safe type check.
+ with self.sql_conf({
+ "spark.sql.execution.pandas.arrowSafeTypeConversion": False}):
+ df.select(['A']).withColumn('udf', udf('A')).collect()
+
+ def test_pandas_udf_arrow_overflow(self):
+ from distutils.version import LooseVersion
+ import pandas as pd
+ import pyarrow as pa
+
+ df = self.spark.range(0, 1)
+
+ @pandas_udf(returnType="byte")
+ def udf(column):
+ return pd.Series([128])
+
+ # Arrow 0.11.0+ allows enabling or disabling safe type check.
+ if LooseVersion(pa.__version__) >= LooseVersion("0.11.0"):
+ # When enabling safe type check, Arrow 0.11.0+ disallows overflow
cast.
+ with self.sql_conf({
+ "spark.sql.execution.pandas.arrowSafeTypeConversion":
True}):
+ with self.assertRaisesRegexp(Exception,
+ "Exception thrown when converting
pandas.Series"):
+ df.withColumn('udf', udf('id')).collect()
+
+ # Disabling safe type check, let Arrow do the cast anyway.
+ with
self.sql_conf({"spark.sql.execution.pandas.arrowSafeTypeConversion": False}):
+ df.withColumn('udf', udf('id')).collect()
+ else:
+ # SQL config `arrowSafeTypeConversion` no matters for older Arrow.
+ # Overflow cast causes an error.
+ with
self.sql_conf({"spark.sql.execution.pandas.arrowSafeTypeConversion": False}):
+ with self.assertRaisesRegexp(Exception,
+ "Integer value out of bounds"):
Review comment:
looks it can be inlined
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
[email protected]
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
