python/pyspark/sql/tests/test_group.py

#
# 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 GroupTestsMixin:
    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, "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])


class GroupTests(GroupTestsMixin, ReusedSQLTestCase):
    pass


if __name__ == "__main__":
    import unittest
    from pyspark.sql.tests.test_group import *  # noqa: F401

    try:
        import xmlrunner

        testRunner = xmlrunner.XMLTestRunner(output="target/test-reports", verbosity=2)
    except ImportError:
        testRunner = None
    unittest.main(testRunner=testRunner, verbosity=2)