python/pyspark/sql/tests/pandas/test_pandas_sqlmetrics.py - master - githubmirror/spark

python/pyspark/sql/tests/pandas/test_pandas_sqlmetrics.py

60 строк2 KB

Tian Gao

[SPARK-55474][PYTHON][TESTS] Remove test files from ignore list of ruff

18 фев 2026, 04:53

18 фев 2026, 04:53f74d3fb

#
# 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.
#

import unittest
from pyspark.sql.functions import pandas_udf
from pyspark.testing.sqlutils import ReusedSQLTestCase
from pyspark.testing.utils import (
    have_pandas,
    have_pyarrow,
    pandas_requirement_message,
    pyarrow_requirement_message,
)


@unittest.skipIf(
    not have_pandas or not have_pyarrow,
    pandas_requirement_message or pyarrow_requirement_message,
)
class PandasSQLMetrics(ReusedSQLTestCase):
    def test_pandas_sql_metrics_basic(self):
        # SPARK-34265: Instrument Python UDFs using SQL metrics

        python_sql_metrics = [
            "data sent to Python workers",
            "data returned from Python workers",
            "number of output rows",
        ]

        @pandas_udf("long")
        def test_pandas(col1):
            return col1 * col1

        self.spark.range(10).select(test_pandas("id")).collect()

        statusStore = self.spark._jsparkSession.sharedState().statusStore()
        lastExecId = statusStore.executionsList().last().executionId()
        executionMetrics = statusStore.execution(lastExecId).get().metrics().mkString()

        for metric in python_sql_metrics:
            self.assertIn(metric, executionMetrics)


if __name__ == "__main__":
    from pyspark.testing import main

    main()