Skip to content

[SPARK-21552][SQL] Add DecimalType support to ArrowWriter. #18754

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
ueshin wants to merge 6 commits into from
Closed

[SPARK-21552][SQL] Add DecimalType support to ArrowWriter. #18754

Changes from 1 commit
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
9e60762
Add DecimalType support to ArrowWriter.
ueshin Jul 26, 2017
1fccaf8
Merge branch 'master' into issues/SPARK-21552
ueshin Dec 22, 2017
4a697b3
Use Arrow 0.8 APIs and fix a test.
ueshin Dec 12, 2017
bcadac8
Fix Python side.
ueshin Dec 18, 2017
e29f833
Modify tests for unsupported types.
ueshin Dec 18, 2017
025f298
Check the return value of `changePrecision()` for the case of overflow.
ueshin Dec 25, 2017
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Prev Previous commit
Next Next commit
Modify tests for unsupported types.
  • Loading branch information
@ueshin
ueshin committed Dec 22, 2017
commit e29f8330e455e6bf66d2c69f2875a70ae2c71cdb
14 changes: 8 additions & 6 deletions python/pyspark/sql/tests.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3194,10 +3194,11 @@ def create_pandas_data_frame(self):
return pd.DataFrame(data=data_dict)

def test_unsupported_datatype(self):
schema = StructType([StructField("decimal", DecimalType(), True)])
schema = StructType([StructField("map", MapType(StringType(), IntegerType()), True)])
df = self.spark.createDataFrame([(None,)], schema=schema)
with QuietTest(self.sc):
self.assertRaises(Exception, lambda: df.toPandas())
with self.assertRaisesRegexp(Exception, 'Unsupported data type'):
df.toPandas()

def test_null_conversion(self):
df_null = self.spark.createDataFrame([tuple([None for _ in range(len(self.data[0]))])] +
Expand Down Expand Up @@ -3733,12 +3734,12 @@ def test_vectorized_udf_varargs(self):

def test_vectorized_udf_unsupported_types(self):
from pyspark.sql.functions import pandas_udf, col
schema = StructType([StructField("dt", DecimalType(), True)])
schema = StructType([StructField("map", MapType(StringType(), IntegerType()), True)])
df = self.spark.createDataFrame([(None,)], schema=schema)
f = pandas_udf(lambda x: x, DecimalType())
f = pandas_udf(lambda x: x, MapType(StringType(), IntegerType()))
with QuietTest(self.sc):
with self.assertRaisesRegexp(Exception, 'Unsupported data type'):
df.select(f(col('dt'))).collect()
df.select(f(col('map'))).collect()

def test_vectorized_udf_null_date(self):
from pyspark.sql.functions import pandas_udf, col
Expand Down Expand Up @@ -4032,7 +4033,8 @@ def test_wrong_args(self):
def test_unsupported_types(self):
from pyspark.sql.functions import pandas_udf, col, PandasUDFType
schema = StructType(
[StructField("id", LongType(), True), StructField("dt", DecimalType(), True)])
[StructField("id", LongType(), True),
StructField("map", MapType(StringType(), IntegerType()), True)])
df = self.spark.createDataFrame([(1, None,)], schema=schema)
f = pandas_udf(lambda x: x, df.schema, PandasUDFType.GROUP_MAP)
with QuietTest(self.sc):
Expand Down