30468a9015
### What changes were proposed in this pull request? This PR completes snake_case rule at functions APIs across the languages, see also SPARK-10621. In more details, this PR: - Adds `count_distinct` in Scala Python, and R, and document that `count_distinct` is encouraged. This was not deprecated because `countDistinct` is pretty commonly used. We could deprecate in the future releases. - (Scala-specific) adds `typedlit` but doesn't deprecate `typedLit` which is arguably commonly used. Likewise, we could deprecate in the future releases. - Deprecates and renames: - `sumDistinct` -> `sum_distinct` - `bitwiseNOT` -> `bitwise_not` - `shiftLeft` -> `shiftleft` (matched with SQL name in `FunctionRegistry`) - `shiftRight` -> `shiftright` (matched with SQL name in `FunctionRegistry`) - `shiftRightUnsigned` -> `shiftrightunsigned` (matched with SQL name in `FunctionRegistry`) - (Scala-specific) `callUDF` -> `call_udf` ### Why are the changes needed? To keep the consistent naming in APIs. ### Does this PR introduce _any_ user-facing change? Yes, it deprecates some APIs and add new renamed APIs as described above. ### How was this patch tested? Unittests were added. Closes #31408 from HyukjinKwon/SPARK-34306. Authored-by: HyukjinKwon <gurwls223@apache.org> Signed-off-by: HyukjinKwon <gurwls223@apache.org>
48 lines
1.9 KiB
Python
48 lines
1.9 KiB
Python
#
|
|
# Licensed to the Apache Software Foundation (ASF) under one or more
|
|
# contributor license agreements. See the NOTICE file distributed with
|
|
# this work for additional information regarding copyright ownership.
|
|
# The ASF licenses this file to You under the Apache License, Version 2.0
|
|
# (the "License"); you may not use this file except in compliance with
|
|
# the License. You may obtain a copy of the License at
|
|
#
|
|
# http://www.apache.org/licenses/LICENSE-2.0
|
|
#
|
|
# Unless required by applicable law or agreed to in writing, software
|
|
# distributed under the License is distributed on an "AS IS" BASIS,
|
|
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
# See the License for the specific language governing permissions and
|
|
# limitations under the License.
|
|
#
|
|
|
|
from pyspark.sql import Row
|
|
from pyspark.testing.sqlutils import ReusedSQLTestCase
|
|
|
|
|
|
class GroupTests(ReusedSQLTestCase):
|
|
|
|
def test_aggregator(self):
|
|
df = self.df
|
|
g = df.groupBy()
|
|
self.assertEqual([99, 100], sorted(g.agg({'key': 'max', 'value': 'count'}).collect()[0]))
|
|
self.assertEqual([Row(**{"AVG(key#0)": 49.5})], g.mean().collect())
|
|
|
|
from pyspark.sql import functions
|
|
self.assertEqual((0, u'99'),
|
|
tuple(g.agg(functions.first(df.key), functions.last(df.value)).first()))
|
|
self.assertTrue(95 < g.agg(functions.approx_count_distinct(df.key)).first()[0])
|
|
# test deprecated countDistinct
|
|
self.assertEqual(100, g.agg(functions.countDistinct(df.value)).first()[0])
|
|
|
|
|
|
if __name__ == "__main__":
|
|
import unittest
|
|
from pyspark.sql.tests.test_group import * # noqa: F401
|
|
|
|
try:
|
|
import xmlrunner # type: ignore[import]
|
|
testRunner = xmlrunner.XMLTestRunner(output='target/test-reports', verbosity=2)
|
|
except ImportError:
|
|
testRunner = None
|
|
unittest.main(testRunner=testRunner, verbosity=2)
|