spark-instrumented-optimizer/python/pyspark/sql/tests/test_session.py

369 lines
14 KiB
Python
Raw Normal View History

[SPARK-26032][PYTHON] Break large sql/tests.py files into smaller files ## What changes were proposed in this pull request? This is the official first attempt to break huge single `tests.py` file - I did it locally before few times and gave up for some reasons. Now, currently it really makes the unittests super hard to read and difficult to check. To me, it even bothers me to to scroll down the big file. It's one single 7000 lines file! This is not only readability issue. Since one big test takes most of tests time, the tests don't run in parallel fully - although it will costs to start and stop the context. We could pick up one example and follow. Given my investigation, the current style looks closer to NumPy structure and looks easier to follow. Please see https://github.com/numpy/numpy/tree/master/numpy. Basically this PR proposes to break down `pyspark/sql/tests.py` into ...: ```bash pyspark ... ├── sql ... │   ├── tests # Includes all tests broken down from 'pyspark/sql/tests.py' │ │  │ # Each matchs to module in 'pyspark/sql'. Additionally, some logical group can │ │  │ # be added. For instance, 'test_arrow.py', 'test_datasources.py' ... │   │   ├── __init__.py │   │   ├── test_appsubmit.py │   │   ├── test_arrow.py │   │   ├── test_catalog.py │   │   ├── test_column.py │   │   ├── test_conf.py │   │   ├── test_context.py │   │   ├── test_dataframe.py │   │   ├── test_datasources.py │   │   ├── test_functions.py │   │   ├── test_group.py │   │   ├── test_pandas_udf.py │   │   ├── test_pandas_udf_grouped_agg.py │   │   ├── test_pandas_udf_grouped_map.py │   │   ├── test_pandas_udf_scalar.py │   │   ├── test_pandas_udf_window.py │   │   ├── test_readwriter.py │   │   ├── test_serde.py │   │   ├── test_session.py │   │   ├── test_streaming.py │   │   ├── test_types.py │   │   ├── test_udf.py │   │   └── test_utils.py ... ├── testing # Includes testing utils that can be used in unittests. │   ├── __init__.py │   └── sqlutils.py ... ``` ## How was this patch tested? Existing tests should cover. `cd python` and `./run-tests-with-coverage`. Manually checked they are actually being ran. Each test (not officially) can be ran via: ``` SPARK_TESTING=1 ./bin/pyspark pyspark.sql.tests.test_pandas_udf_scalar ``` Note that if you're using Mac and Python 3, you might have to `OBJC_DISABLE_INITIALIZE_FORK_SAFETY=YES`. Closes #23021 from HyukjinKwon/SPARK-25344. Authored-by: hyukjinkwon <gurwls223@apache.org> Signed-off-by: hyukjinkwon <gurwls223@apache.org>
2018-11-14 01:51:11 -05:00
#
# 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 os
import unittest
from pyspark import SparkConf, SparkContext
from pyspark.sql import SparkSession, SQLContext, Row
from pyspark.testing.sqlutils import ReusedSQLTestCase
2018-11-14 23:30:52 -05:00
from pyspark.testing.utils import PySparkTestCase
[SPARK-26032][PYTHON] Break large sql/tests.py files into smaller files ## What changes were proposed in this pull request? This is the official first attempt to break huge single `tests.py` file - I did it locally before few times and gave up for some reasons. Now, currently it really makes the unittests super hard to read and difficult to check. To me, it even bothers me to to scroll down the big file. It's one single 7000 lines file! This is not only readability issue. Since one big test takes most of tests time, the tests don't run in parallel fully - although it will costs to start and stop the context. We could pick up one example and follow. Given my investigation, the current style looks closer to NumPy structure and looks easier to follow. Please see https://github.com/numpy/numpy/tree/master/numpy. Basically this PR proposes to break down `pyspark/sql/tests.py` into ...: ```bash pyspark ... ├── sql ... │   ├── tests # Includes all tests broken down from 'pyspark/sql/tests.py' │ │  │ # Each matchs to module in 'pyspark/sql'. Additionally, some logical group can │ │  │ # be added. For instance, 'test_arrow.py', 'test_datasources.py' ... │   │   ├── __init__.py │   │   ├── test_appsubmit.py │   │   ├── test_arrow.py │   │   ├── test_catalog.py │   │   ├── test_column.py │   │   ├── test_conf.py │   │   ├── test_context.py │   │   ├── test_dataframe.py │   │   ├── test_datasources.py │   │   ├── test_functions.py │   │   ├── test_group.py │   │   ├── test_pandas_udf.py │   │   ├── test_pandas_udf_grouped_agg.py │   │   ├── test_pandas_udf_grouped_map.py │   │   ├── test_pandas_udf_scalar.py │   │   ├── test_pandas_udf_window.py │   │   ├── test_readwriter.py │   │   ├── test_serde.py │   │   ├── test_session.py │   │   ├── test_streaming.py │   │   ├── test_types.py │   │   ├── test_udf.py │   │   └── test_utils.py ... ├── testing # Includes testing utils that can be used in unittests. │   ├── __init__.py │   └── sqlutils.py ... ``` ## How was this patch tested? Existing tests should cover. `cd python` and `./run-tests-with-coverage`. Manually checked they are actually being ran. Each test (not officially) can be ran via: ``` SPARK_TESTING=1 ./bin/pyspark pyspark.sql.tests.test_pandas_udf_scalar ``` Note that if you're using Mac and Python 3, you might have to `OBJC_DISABLE_INITIALIZE_FORK_SAFETY=YES`. Closes #23021 from HyukjinKwon/SPARK-25344. Authored-by: hyukjinkwon <gurwls223@apache.org> Signed-off-by: hyukjinkwon <gurwls223@apache.org>
2018-11-14 01:51:11 -05:00
class SparkSessionTests(ReusedSQLTestCase):
def test_sqlcontext_reuses_sparksession(self):
sqlContext1 = SQLContext(self.sc)
sqlContext2 = SQLContext(self.sc)
self.assertTrue(sqlContext1.sparkSession is sqlContext2.sparkSession)
class SparkSessionTests1(ReusedSQLTestCase):
# We can't include this test into SQLTests because we will stop class's SparkContext and cause
# other tests failed.
def test_sparksession_with_stopped_sparkcontext(self):
self.sc.stop()
sc = SparkContext('local[4]', self.sc.appName)
spark = SparkSession.builder.getOrCreate()
try:
df = spark.createDataFrame([(1, 2)], ["c", "c"])
df.collect()
finally:
spark.stop()
sc.stop()
class SparkSessionTests2(PySparkTestCase):
# This test is separate because it's closely related with session's start and stop.
# See SPARK-23228.
def test_set_jvm_default_session(self):
spark = SparkSession.builder.getOrCreate()
try:
self.assertTrue(spark._jvm.SparkSession.getDefaultSession().isDefined())
finally:
spark.stop()
self.assertTrue(spark._jvm.SparkSession.getDefaultSession().isEmpty())
def test_jvm_default_session_already_set(self):
# Here, we assume there is the default session already set in JVM.
jsession = self.sc._jvm.SparkSession(self.sc._jsc.sc())
self.sc._jvm.SparkSession.setDefaultSession(jsession)
spark = SparkSession.builder.getOrCreate()
try:
self.assertTrue(spark._jvm.SparkSession.getDefaultSession().isDefined())
# The session should be the same with the exiting one.
self.assertTrue(jsession.equals(spark._jvm.SparkSession.getDefaultSession().get()))
finally:
spark.stop()
class SparkSessionTests3(unittest.TestCase):
def test_active_session(self):
spark = SparkSession.builder \
.master("local") \
.getOrCreate()
try:
activeSession = SparkSession.getActiveSession()
df = activeSession.createDataFrame([(1, 'Alice')], ['age', 'name'])
self.assertEqual(df.collect(), [Row(age=1, name=u'Alice')])
finally:
spark.stop()
def test_get_active_session_when_no_active_session(self):
active = SparkSession.getActiveSession()
self.assertEqual(active, None)
spark = SparkSession.builder \
.master("local") \
.getOrCreate()
active = SparkSession.getActiveSession()
self.assertEqual(active, spark)
spark.stop()
active = SparkSession.getActiveSession()
self.assertEqual(active, None)
def test_SparkSession(self):
spark = SparkSession.builder \
.master("local") \
.config("some-config", "v2") \
.getOrCreate()
try:
self.assertEqual(spark.conf.get("some-config"), "v2")
self.assertEqual(spark.sparkContext._conf.get("some-config"), "v2")
self.assertEqual(spark.version, spark.sparkContext.version)
spark.sql("CREATE DATABASE test_db")
spark.catalog.setCurrentDatabase("test_db")
self.assertEqual(spark.catalog.currentDatabase(), "test_db")
spark.sql("CREATE TABLE table1 (name STRING, age INT) USING parquet")
self.assertEqual(spark.table("table1").columns, ['name', 'age'])
self.assertEqual(spark.range(3).count(), 3)
finally:
spark.sql("DROP DATABASE test_db CASCADE")
[SPARK-26032][PYTHON] Break large sql/tests.py files into smaller files ## What changes were proposed in this pull request? This is the official first attempt to break huge single `tests.py` file - I did it locally before few times and gave up for some reasons. Now, currently it really makes the unittests super hard to read and difficult to check. To me, it even bothers me to to scroll down the big file. It's one single 7000 lines file! This is not only readability issue. Since one big test takes most of tests time, the tests don't run in parallel fully - although it will costs to start and stop the context. We could pick up one example and follow. Given my investigation, the current style looks closer to NumPy structure and looks easier to follow. Please see https://github.com/numpy/numpy/tree/master/numpy. Basically this PR proposes to break down `pyspark/sql/tests.py` into ...: ```bash pyspark ... ├── sql ... │   ├── tests # Includes all tests broken down from 'pyspark/sql/tests.py' │ │  │ # Each matchs to module in 'pyspark/sql'. Additionally, some logical group can │ │  │ # be added. For instance, 'test_arrow.py', 'test_datasources.py' ... │   │   ├── __init__.py │   │   ├── test_appsubmit.py │   │   ├── test_arrow.py │   │   ├── test_catalog.py │   │   ├── test_column.py │   │   ├── test_conf.py │   │   ├── test_context.py │   │   ├── test_dataframe.py │   │   ├── test_datasources.py │   │   ├── test_functions.py │   │   ├── test_group.py │   │   ├── test_pandas_udf.py │   │   ├── test_pandas_udf_grouped_agg.py │   │   ├── test_pandas_udf_grouped_map.py │   │   ├── test_pandas_udf_scalar.py │   │   ├── test_pandas_udf_window.py │   │   ├── test_readwriter.py │   │   ├── test_serde.py │   │   ├── test_session.py │   │   ├── test_streaming.py │   │   ├── test_types.py │   │   ├── test_udf.py │   │   └── test_utils.py ... ├── testing # Includes testing utils that can be used in unittests. │   ├── __init__.py │   └── sqlutils.py ... ``` ## How was this patch tested? Existing tests should cover. `cd python` and `./run-tests-with-coverage`. Manually checked they are actually being ran. Each test (not officially) can be ran via: ``` SPARK_TESTING=1 ./bin/pyspark pyspark.sql.tests.test_pandas_udf_scalar ``` Note that if you're using Mac and Python 3, you might have to `OBJC_DISABLE_INITIALIZE_FORK_SAFETY=YES`. Closes #23021 from HyukjinKwon/SPARK-25344. Authored-by: hyukjinkwon <gurwls223@apache.org> Signed-off-by: hyukjinkwon <gurwls223@apache.org>
2018-11-14 01:51:11 -05:00
spark.stop()
def test_global_default_session(self):
spark = SparkSession.builder \
.master("local") \
.getOrCreate()
try:
self.assertEqual(SparkSession.builder.getOrCreate(), spark)
finally:
spark.stop()
def test_default_and_active_session(self):
spark = SparkSession.builder \
.master("local") \
.getOrCreate()
activeSession = spark._jvm.SparkSession.getActiveSession()
defaultSession = spark._jvm.SparkSession.getDefaultSession()
try:
self.assertEqual(activeSession, defaultSession)
finally:
spark.stop()
def test_config_option_propagated_to_existing_session(self):
session1 = SparkSession.builder \
.master("local") \
.config("spark-config1", "a") \
.getOrCreate()
self.assertEqual(session1.conf.get("spark-config1"), "a")
session2 = SparkSession.builder \
.config("spark-config1", "b") \
.getOrCreate()
try:
self.assertEqual(session1, session2)
self.assertEqual(session1.conf.get("spark-config1"), "b")
finally:
session1.stop()
def test_new_session(self):
session = SparkSession.builder \
.master("local") \
.getOrCreate()
newSession = session.newSession()
try:
self.assertNotEqual(session, newSession)
finally:
session.stop()
newSession.stop()
def test_create_new_session_if_old_session_stopped(self):
session = SparkSession.builder \
.master("local") \
.getOrCreate()
session.stop()
newSession = SparkSession.builder \
.master("local") \
.getOrCreate()
try:
self.assertNotEqual(session, newSession)
finally:
newSession.stop()
def test_active_session_with_None_and_not_None_context(self):
from pyspark.context import SparkContext
from pyspark.conf import SparkConf
sc = None
session = None
try:
sc = SparkContext._active_spark_context
self.assertEqual(sc, None)
activeSession = SparkSession.getActiveSession()
self.assertEqual(activeSession, None)
sparkConf = SparkConf()
sc = SparkContext.getOrCreate(sparkConf)
activeSession = sc._jvm.SparkSession.getActiveSession()
self.assertFalse(activeSession.isDefined())
session = SparkSession(sc)
activeSession = sc._jvm.SparkSession.getActiveSession()
self.assertTrue(activeSession.isDefined())
activeSession2 = SparkSession.getActiveSession()
self.assertNotEqual(activeSession2, None)
finally:
if session is not None:
session.stop()
if sc is not None:
sc.stop()
class SparkSessionTests4(ReusedSQLTestCase):
def test_get_active_session_after_create_dataframe(self):
session2 = None
try:
activeSession1 = SparkSession.getActiveSession()
session1 = self.spark
self.assertEqual(session1, activeSession1)
session2 = self.spark.newSession()
activeSession2 = SparkSession.getActiveSession()
self.assertEqual(session1, activeSession2)
self.assertNotEqual(session2, activeSession2)
session2.createDataFrame([(1, 'Alice')], ['age', 'name'])
activeSession3 = SparkSession.getActiveSession()
self.assertEqual(session2, activeSession3)
session1.createDataFrame([(1, 'Alice')], ['age', 'name'])
activeSession4 = SparkSession.getActiveSession()
self.assertEqual(session1, activeSession4)
finally:
if session2 is not None:
session2.stop()
class SparkSessionTests5(unittest.TestCase):
def setUp(self):
# These tests require restarting the Spark context so we set up a new one for each test
# rather than at the class level.
self.sc = SparkContext('local[4]', self.__class__.__name__, conf=SparkConf())
self.spark = SparkSession(self.sc)
def tearDown(self):
self.sc.stop()
self.spark.stop()
def test_sqlcontext_with_stopped_sparksession(self):
# SPARK-30856: test that SQLContext.getOrCreate() returns a usable instance after
# the SparkSession is restarted.
sql_context = self.spark._wrapped
self.spark.stop()
sc = SparkContext('local[4]', self.sc.appName)
spark = SparkSession(sc) # Instantiate the underlying SQLContext
new_sql_context = spark._wrapped
self.assertIsNot(new_sql_context, sql_context)
self.assertIs(SQLContext.getOrCreate(sc).sparkSession, spark)
try:
df = spark.createDataFrame([(1, 2)], ['c', 'c'])
df.collect()
finally:
spark.stop()
self.assertIsNone(SQLContext._instantiatedContext)
sc.stop()
def test_sqlcontext_with_stopped_sparkcontext(self):
# SPARK-30856: test initialization via SparkSession when only the SparkContext is stopped
self.sc.stop()
self.sc = SparkContext('local[4]', self.sc.appName)
self.spark = SparkSession(self.sc)
self.assertIs(SQLContext.getOrCreate(self.sc).sparkSession, self.spark)
def test_get_sqlcontext_with_stopped_sparkcontext(self):
# SPARK-30856: test initialization via SQLContext.getOrCreate() when only the SparkContext
# is stopped
self.sc.stop()
self.sc = SparkContext('local[4]', self.sc.appName)
self.assertIs(SQLContext.getOrCreate(self.sc)._sc, self.sc)
[SPARK-26032][PYTHON] Break large sql/tests.py files into smaller files ## What changes were proposed in this pull request? This is the official first attempt to break huge single `tests.py` file - I did it locally before few times and gave up for some reasons. Now, currently it really makes the unittests super hard to read and difficult to check. To me, it even bothers me to to scroll down the big file. It's one single 7000 lines file! This is not only readability issue. Since one big test takes most of tests time, the tests don't run in parallel fully - although it will costs to start and stop the context. We could pick up one example and follow. Given my investigation, the current style looks closer to NumPy structure and looks easier to follow. Please see https://github.com/numpy/numpy/tree/master/numpy. Basically this PR proposes to break down `pyspark/sql/tests.py` into ...: ```bash pyspark ... ├── sql ... │   ├── tests # Includes all tests broken down from 'pyspark/sql/tests.py' │ │  │ # Each matchs to module in 'pyspark/sql'. Additionally, some logical group can │ │  │ # be added. For instance, 'test_arrow.py', 'test_datasources.py' ... │   │   ├── __init__.py │   │   ├── test_appsubmit.py │   │   ├── test_arrow.py │   │   ├── test_catalog.py │   │   ├── test_column.py │   │   ├── test_conf.py │   │   ├── test_context.py │   │   ├── test_dataframe.py │   │   ├── test_datasources.py │   │   ├── test_functions.py │   │   ├── test_group.py │   │   ├── test_pandas_udf.py │   │   ├── test_pandas_udf_grouped_agg.py │   │   ├── test_pandas_udf_grouped_map.py │   │   ├── test_pandas_udf_scalar.py │   │   ├── test_pandas_udf_window.py │   │   ├── test_readwriter.py │   │   ├── test_serde.py │   │   ├── test_session.py │   │   ├── test_streaming.py │   │   ├── test_types.py │   │   ├── test_udf.py │   │   └── test_utils.py ... ├── testing # Includes testing utils that can be used in unittests. │   ├── __init__.py │   └── sqlutils.py ... ``` ## How was this patch tested? Existing tests should cover. `cd python` and `./run-tests-with-coverage`. Manually checked they are actually being ran. Each test (not officially) can be ran via: ``` SPARK_TESTING=1 ./bin/pyspark pyspark.sql.tests.test_pandas_udf_scalar ``` Note that if you're using Mac and Python 3, you might have to `OBJC_DISABLE_INITIALIZE_FORK_SAFETY=YES`. Closes #23021 from HyukjinKwon/SPARK-25344. Authored-by: hyukjinkwon <gurwls223@apache.org> Signed-off-by: hyukjinkwon <gurwls223@apache.org>
2018-11-14 01:51:11 -05:00
class SparkSessionBuilderTests(unittest.TestCase):
def test_create_spark_context_first_then_spark_session(self):
sc = None
session = None
try:
conf = SparkConf().set("key1", "value1")
sc = SparkContext('local[4]', "SessionBuilderTests", conf=conf)
session = SparkSession.builder.config("key2", "value2").getOrCreate()
self.assertEqual(session.conf.get("key1"), "value1")
self.assertEqual(session.conf.get("key2"), "value2")
self.assertEqual(session.sparkContext, sc)
self.assertFalse(sc.getConf().contains("key2"))
self.assertEqual(sc.getConf().get("key1"), "value1")
finally:
if session is not None:
session.stop()
if sc is not None:
sc.stop()
def test_another_spark_session(self):
session1 = None
session2 = None
try:
session1 = SparkSession.builder.config("key1", "value1").getOrCreate()
session2 = SparkSession.builder.config("key2", "value2").getOrCreate()
self.assertEqual(session1.conf.get("key1"), "value1")
self.assertEqual(session2.conf.get("key1"), "value1")
self.assertEqual(session1.conf.get("key2"), "value2")
self.assertEqual(session2.conf.get("key2"), "value2")
self.assertEqual(session1.sparkContext, session2.sparkContext)
self.assertEqual(session1.sparkContext.getConf().get("key1"), "value1")
self.assertFalse(session1.sparkContext.getConf().contains("key2"))
finally:
if session1 is not None:
session1.stop()
if session2 is not None:
session2.stop()
class SparkExtensionsTest(unittest.TestCase):
# These tests are separate because it uses 'spark.sql.extensions' which is
# static and immutable. This can't be set or unset, for example, via `spark.conf`.
@classmethod
def setUpClass(cls):
import glob
from pyspark.find_spark_home import _find_spark_home
SPARK_HOME = _find_spark_home()
filename_pattern = (
"sql/core/target/scala-*/test-classes/org/apache/spark/sql/"
"SparkSessionExtensionSuite.class")
if not glob.glob(os.path.join(SPARK_HOME, filename_pattern)):
raise unittest.SkipTest(
"'org.apache.spark.sql.SparkSessionExtensionSuite' is not "
"available. Will skip the related tests.")
# Note that 'spark.sql.extensions' is a static immutable configuration.
cls.spark = SparkSession.builder \
.master("local[4]") \
.appName(cls.__name__) \
.config(
"spark.sql.extensions",
"org.apache.spark.sql.MyExtensions") \
.getOrCreate()
@classmethod
def tearDownClass(cls):
cls.spark.stop()
def test_use_custom_class_for_extensions(self):
self.assertTrue(
self.spark._jsparkSession.sessionState().planner().strategies().contains(
self.spark._jvm.org.apache.spark.sql.MySparkStrategy(self.spark._jsparkSession)),
"MySparkStrategy not found in active planner strategies")
self.assertTrue(
self.spark._jsparkSession.sessionState().analyzer().extendedResolutionRules().contains(
self.spark._jvm.org.apache.spark.sql.MyRule(self.spark._jsparkSession)),
"MyRule not found in extended resolution rules")
if __name__ == "__main__":
[SPARK-32319][PYSPARK] Disallow the use of unused imports Disallow the use of unused imports: - Unnecessary increases the memory footprint of the application - Removes the imports that are required for the examples in the docstring from the file-scope to the example itself. This keeps the files itself clean, and gives a more complete example as it also includes the imports :) ``` fokkodriesprongFan spark % flake8 python | grep -i "imported but unused" python/pyspark/cloudpickle.py:46:1: F401 'functools.partial' imported but unused python/pyspark/cloudpickle.py:55:1: F401 'traceback' imported but unused python/pyspark/heapq3.py:868:5: F401 '_heapq.*' imported but unused python/pyspark/__init__.py:61:1: F401 'pyspark.version.__version__' imported but unused python/pyspark/__init__.py:62:1: F401 'pyspark._globals._NoValue' imported but unused python/pyspark/__init__.py:115:1: F401 'pyspark.sql.SQLContext' imported but unused python/pyspark/__init__.py:115:1: F401 'pyspark.sql.HiveContext' imported but unused python/pyspark/__init__.py:115:1: F401 'pyspark.sql.Row' imported but unused python/pyspark/rdd.py:21:1: F401 're' imported but unused python/pyspark/rdd.py:29:1: F401 'tempfile.NamedTemporaryFile' imported but unused python/pyspark/mllib/regression.py:26:1: F401 'pyspark.mllib.linalg.SparseVector' imported but unused python/pyspark/mllib/clustering.py:28:1: F401 'pyspark.mllib.linalg.SparseVector' imported but unused python/pyspark/mllib/clustering.py:28:1: F401 'pyspark.mllib.linalg.DenseVector' imported but unused python/pyspark/mllib/classification.py:26:1: F401 'pyspark.mllib.linalg.SparseVector' imported but unused python/pyspark/mllib/feature.py:28:1: F401 'pyspark.mllib.linalg.DenseVector' imported but unused python/pyspark/mllib/feature.py:28:1: F401 'pyspark.mllib.linalg.SparseVector' imported but unused python/pyspark/mllib/feature.py:30:1: F401 'pyspark.mllib.regression.LabeledPoint' imported but unused python/pyspark/mllib/tests/test_linalg.py:18:1: F401 'sys' imported but unused python/pyspark/mllib/tests/test_linalg.py:642:5: F401 'pyspark.mllib.tests.test_linalg.*' imported but unused python/pyspark/mllib/tests/test_feature.py:21:1: F401 'numpy.random' imported but unused python/pyspark/mllib/tests/test_feature.py:21:1: F401 'numpy.exp' imported but unused python/pyspark/mllib/tests/test_feature.py:23:1: F401 'pyspark.mllib.linalg.Vector' imported but unused python/pyspark/mllib/tests/test_feature.py:23:1: F401 'pyspark.mllib.linalg.VectorUDT' imported but unused python/pyspark/mllib/tests/test_feature.py:185:5: F401 'pyspark.mllib.tests.test_feature.*' imported but unused python/pyspark/mllib/tests/test_util.py:97:5: F401 'pyspark.mllib.tests.test_util.*' imported but unused python/pyspark/mllib/tests/test_stat.py:23:1: F401 'pyspark.mllib.linalg.Vector' imported but unused python/pyspark/mllib/tests/test_stat.py:23:1: F401 'pyspark.mllib.linalg.SparseVector' imported but unused python/pyspark/mllib/tests/test_stat.py:23:1: F401 'pyspark.mllib.linalg.DenseVector' imported but unused python/pyspark/mllib/tests/test_stat.py:23:1: F401 'pyspark.mllib.linalg.VectorUDT' imported but unused python/pyspark/mllib/tests/test_stat.py:23:1: F401 'pyspark.mllib.linalg._convert_to_vector' imported but unused python/pyspark/mllib/tests/test_stat.py:23:1: F401 'pyspark.mllib.linalg.DenseMatrix' imported but unused python/pyspark/mllib/tests/test_stat.py:23:1: F401 'pyspark.mllib.linalg.SparseMatrix' imported but unused python/pyspark/mllib/tests/test_stat.py:23:1: F401 'pyspark.mllib.linalg.MatrixUDT' imported but unused python/pyspark/mllib/tests/test_stat.py:181:5: F401 'pyspark.mllib.tests.test_stat.*' imported but unused python/pyspark/mllib/tests/test_streaming_algorithms.py:18:1: F401 'time.time' imported but unused python/pyspark/mllib/tests/test_streaming_algorithms.py:18:1: F401 'time.sleep' imported but unused python/pyspark/mllib/tests/test_streaming_algorithms.py:470:5: F401 'pyspark.mllib.tests.test_streaming_algorithms.*' imported but unused python/pyspark/mllib/tests/test_algorithms.py:295:5: F401 'pyspark.mllib.tests.test_algorithms.*' imported but unused python/pyspark/tests/test_serializers.py:90:13: F401 'xmlrunner' imported but unused python/pyspark/tests/test_rdd.py:21:1: F401 'sys' imported but unused python/pyspark/tests/test_rdd.py:29:1: F401 'pyspark.resource.ResourceProfile' imported but unused python/pyspark/tests/test_rdd.py:885:5: F401 'pyspark.tests.test_rdd.*' imported but unused python/pyspark/tests/test_readwrite.py:19:1: F401 'sys' imported but unused python/pyspark/tests/test_readwrite.py:22:1: F401 'array.array' imported but unused python/pyspark/tests/test_readwrite.py:309:5: F401 'pyspark.tests.test_readwrite.*' imported but unused python/pyspark/tests/test_join.py:62:5: F401 'pyspark.tests.test_join.*' imported but unused python/pyspark/tests/test_taskcontext.py:19:1: F401 'shutil' imported but unused python/pyspark/tests/test_taskcontext.py:325:5: F401 'pyspark.tests.test_taskcontext.*' imported but unused python/pyspark/tests/test_conf.py:36:5: F401 'pyspark.tests.test_conf.*' imported but unused python/pyspark/tests/test_broadcast.py:148:5: F401 'pyspark.tests.test_broadcast.*' imported but unused python/pyspark/tests/test_daemon.py:76:5: F401 'pyspark.tests.test_daemon.*' imported but unused python/pyspark/tests/test_util.py:77:5: F401 'pyspark.tests.test_util.*' imported but unused python/pyspark/tests/test_pin_thread.py:19:1: F401 'random' imported but unused python/pyspark/tests/test_pin_thread.py:149:5: F401 'pyspark.tests.test_pin_thread.*' imported but unused python/pyspark/tests/test_worker.py:19:1: F401 'sys' imported but unused python/pyspark/tests/test_worker.py:26:5: F401 'resource' imported but unused python/pyspark/tests/test_worker.py:203:5: F401 'pyspark.tests.test_worker.*' imported but unused python/pyspark/tests/test_profiler.py:101:5: F401 'pyspark.tests.test_profiler.*' imported but unused python/pyspark/tests/test_shuffle.py:18:1: F401 'sys' imported but unused python/pyspark/tests/test_shuffle.py:171:5: F401 'pyspark.tests.test_shuffle.*' imported but unused python/pyspark/tests/test_rddbarrier.py:43:5: F401 'pyspark.tests.test_rddbarrier.*' imported but unused python/pyspark/tests/test_context.py:129:13: F401 'userlibrary.UserClass' imported but unused python/pyspark/tests/test_context.py:140:13: F401 'userlib.UserClass' imported but unused python/pyspark/tests/test_context.py:310:5: F401 'pyspark.tests.test_context.*' imported but unused python/pyspark/tests/test_appsubmit.py:241:5: F401 'pyspark.tests.test_appsubmit.*' imported but unused python/pyspark/streaming/dstream.py:18:1: F401 'sys' imported but unused python/pyspark/streaming/tests/test_dstream.py:27:1: F401 'pyspark.RDD' imported but unused python/pyspark/streaming/tests/test_dstream.py:647:5: F401 'pyspark.streaming.tests.test_dstream.*' imported but unused python/pyspark/streaming/tests/test_kinesis.py:83:5: F401 'pyspark.streaming.tests.test_kinesis.*' imported but unused python/pyspark/streaming/tests/test_listener.py:152:5: F401 'pyspark.streaming.tests.test_listener.*' imported but unused python/pyspark/streaming/tests/test_context.py:178:5: F401 'pyspark.streaming.tests.test_context.*' imported but unused python/pyspark/testing/utils.py:30:5: F401 'scipy.sparse' imported but unused python/pyspark/testing/utils.py:36:5: F401 'numpy as np' imported but unused python/pyspark/ml/regression.py:25:1: F401 'pyspark.ml.tree._TreeEnsembleParams' imported but unused python/pyspark/ml/regression.py:25:1: F401 'pyspark.ml.tree._HasVarianceImpurity' imported but unused python/pyspark/ml/regression.py:29:1: F401 'pyspark.ml.wrapper.JavaParams' imported but unused python/pyspark/ml/util.py:19:1: F401 'sys' imported but unused python/pyspark/ml/__init__.py:25:1: F401 'pyspark.ml.pipeline' imported but unused python/pyspark/ml/pipeline.py:18:1: F401 'sys' imported but unused python/pyspark/ml/stat.py:22:1: F401 'pyspark.ml.linalg.DenseMatrix' imported but unused python/pyspark/ml/stat.py:22:1: F401 'pyspark.ml.linalg.Vectors' imported but unused python/pyspark/ml/tests/test_training_summary.py:18:1: F401 'sys' imported but unused python/pyspark/ml/tests/test_training_summary.py:364:5: F401 'pyspark.ml.tests.test_training_summary.*' imported but unused python/pyspark/ml/tests/test_linalg.py:381:5: F401 'pyspark.ml.tests.test_linalg.*' imported but unused python/pyspark/ml/tests/test_tuning.py:427:9: F401 'pyspark.sql.functions as F' imported but unused python/pyspark/ml/tests/test_tuning.py:757:5: F401 'pyspark.ml.tests.test_tuning.*' imported but unused python/pyspark/ml/tests/test_wrapper.py:120:5: F401 'pyspark.ml.tests.test_wrapper.*' imported but unused python/pyspark/ml/tests/test_feature.py:19:1: F401 'sys' imported but unused python/pyspark/ml/tests/test_feature.py:304:5: F401 'pyspark.ml.tests.test_feature.*' imported but unused python/pyspark/ml/tests/test_image.py:19:1: F401 'py4j' imported but unused python/pyspark/ml/tests/test_image.py:22:1: F401 'pyspark.testing.mlutils.PySparkTestCase' imported but unused python/pyspark/ml/tests/test_image.py:71:5: F401 'pyspark.ml.tests.test_image.*' imported but unused python/pyspark/ml/tests/test_persistence.py:456:5: F401 'pyspark.ml.tests.test_persistence.*' imported but unused python/pyspark/ml/tests/test_evaluation.py:56:5: F401 'pyspark.ml.tests.test_evaluation.*' imported but unused python/pyspark/ml/tests/test_stat.py:43:5: F401 'pyspark.ml.tests.test_stat.*' imported but unused python/pyspark/ml/tests/test_base.py:70:5: F401 'pyspark.ml.tests.test_base.*' imported but unused python/pyspark/ml/tests/test_param.py:20:1: F401 'sys' imported but unused python/pyspark/ml/tests/test_param.py:375:5: F401 'pyspark.ml.tests.test_param.*' imported but unused python/pyspark/ml/tests/test_pipeline.py:62:5: F401 'pyspark.ml.tests.test_pipeline.*' imported but unused python/pyspark/ml/tests/test_algorithms.py:333:5: F401 'pyspark.ml.tests.test_algorithms.*' imported but unused python/pyspark/ml/param/__init__.py:18:1: F401 'sys' imported but unused python/pyspark/resource/tests/test_resources.py:17:1: F401 'random' imported but unused python/pyspark/resource/tests/test_resources.py:20:1: F401 'pyspark.resource.ResourceProfile' imported but unused python/pyspark/resource/tests/test_resources.py:75:5: F401 'pyspark.resource.tests.test_resources.*' imported but unused python/pyspark/sql/functions.py:32:1: F401 'pyspark.sql.udf.UserDefinedFunction' imported but unused python/pyspark/sql/functions.py:34:1: F401 'pyspark.sql.pandas.functions.pandas_udf' imported but unused python/pyspark/sql/session.py:30:1: F401 'pyspark.sql.types.Row' imported but unused python/pyspark/sql/session.py:30:1: F401 'pyspark.sql.types.StringType' imported but unused python/pyspark/sql/readwriter.py:1084:5: F401 'pyspark.sql.Row' imported but unused python/pyspark/sql/context.py:26:1: F401 'pyspark.sql.types.IntegerType' imported but unused python/pyspark/sql/context.py:26:1: F401 'pyspark.sql.types.Row' imported but unused python/pyspark/sql/context.py:26:1: F401 'pyspark.sql.types.StringType' imported but unused python/pyspark/sql/context.py:27:1: F401 'pyspark.sql.udf.UDFRegistration' imported but unused python/pyspark/sql/streaming.py:1212:5: F401 'pyspark.sql.Row' imported but unused python/pyspark/sql/tests/test_utils.py:55:5: F401 'pyspark.sql.tests.test_utils.*' imported but unused python/pyspark/sql/tests/test_pandas_map.py:18:1: F401 'sys' imported but unused python/pyspark/sql/tests/test_pandas_map.py:22:1: F401 'pyspark.sql.functions.pandas_udf' imported but unused python/pyspark/sql/tests/test_pandas_map.py:22:1: F401 'pyspark.sql.functions.PandasUDFType' imported but unused python/pyspark/sql/tests/test_pandas_map.py:119:5: F401 'pyspark.sql.tests.test_pandas_map.*' imported but unused python/pyspark/sql/tests/test_catalog.py:193:5: F401 'pyspark.sql.tests.test_catalog.*' imported but unused python/pyspark/sql/tests/test_group.py:39:5: F401 'pyspark.sql.tests.test_group.*' imported but unused python/pyspark/sql/tests/test_session.py:361:5: F401 'pyspark.sql.tests.test_session.*' imported but unused python/pyspark/sql/tests/test_conf.py:49:5: F401 'pyspark.sql.tests.test_conf.*' imported but unused python/pyspark/sql/tests/test_pandas_cogrouped_map.py:19:1: F401 'sys' imported but unused python/pyspark/sql/tests/test_pandas_cogrouped_map.py:21:1: F401 'pyspark.sql.functions.sum' imported but unused python/pyspark/sql/tests/test_pandas_cogrouped_map.py:21:1: F401 'pyspark.sql.functions.PandasUDFType' imported but unused python/pyspark/sql/tests/test_pandas_cogrouped_map.py:29:5: F401 'pandas.util.testing.assert_series_equal' imported but unused python/pyspark/sql/tests/test_pandas_cogrouped_map.py:32:5: F401 'pyarrow as pa' imported but unused python/pyspark/sql/tests/test_pandas_cogrouped_map.py:248:5: F401 'pyspark.sql.tests.test_pandas_cogrouped_map.*' imported but unused python/pyspark/sql/tests/test_udf.py:24:1: F401 'py4j' imported but unused python/pyspark/sql/tests/test_pandas_udf_typehints.py:246:5: F401 'pyspark.sql.tests.test_pandas_udf_typehints.*' imported but unused python/pyspark/sql/tests/test_functions.py:19:1: F401 'sys' imported but unused python/pyspark/sql/tests/test_functions.py:362:9: F401 'pyspark.sql.functions.exists' imported but unused python/pyspark/sql/tests/test_functions.py:387:5: F401 'pyspark.sql.tests.test_functions.*' imported but unused python/pyspark/sql/tests/test_pandas_udf_scalar.py:21:1: F401 'sys' imported but unused python/pyspark/sql/tests/test_pandas_udf_scalar.py:45:5: F401 'pyarrow as pa' imported but unused python/pyspark/sql/tests/test_pandas_udf_window.py:355:5: F401 'pyspark.sql.tests.test_pandas_udf_window.*' imported but unused python/pyspark/sql/tests/test_arrow.py:38:5: F401 'pyarrow as pa' imported but unused python/pyspark/sql/tests/test_pandas_grouped_map.py:20:1: F401 'sys' imported but unused python/pyspark/sql/tests/test_pandas_grouped_map.py:38:5: F401 'pyarrow as pa' imported but unused python/pyspark/sql/tests/test_dataframe.py:382:9: F401 'pyspark.sql.DataFrame' imported but unused python/pyspark/sql/avro/functions.py:125:5: F401 'pyspark.sql.Row' imported but unused python/pyspark/sql/pandas/functions.py:19:1: F401 'sys' imported but unused ``` After: ``` fokkodriesprongFan spark % flake8 python | grep -i "imported but unused" fokkodriesprongFan spark % ``` ### What changes were proposed in this pull request? Removing unused imports from the Python files to keep everything nice and tidy. ### Why are the changes needed? Cleaning up of the imports that aren't used, and suppressing the imports that are used as references to other modules, preserving backward compatibility. ### Does this PR introduce _any_ user-facing change? No. ### How was this patch tested? Adding the rule to the existing Flake8 checks. Closes #29121 from Fokko/SPARK-32319. Authored-by: Fokko Driesprong <fokko@apache.org> Signed-off-by: Dongjoon Hyun <dongjoon@apache.org>
2020-08-08 11:51:57 -04:00
from pyspark.sql.tests.test_session import * # noqa: F401
[SPARK-26032][PYTHON] Break large sql/tests.py files into smaller files ## What changes were proposed in this pull request? This is the official first attempt to break huge single `tests.py` file - I did it locally before few times and gave up for some reasons. Now, currently it really makes the unittests super hard to read and difficult to check. To me, it even bothers me to to scroll down the big file. It's one single 7000 lines file! This is not only readability issue. Since one big test takes most of tests time, the tests don't run in parallel fully - although it will costs to start and stop the context. We could pick up one example and follow. Given my investigation, the current style looks closer to NumPy structure and looks easier to follow. Please see https://github.com/numpy/numpy/tree/master/numpy. Basically this PR proposes to break down `pyspark/sql/tests.py` into ...: ```bash pyspark ... ├── sql ... │   ├── tests # Includes all tests broken down from 'pyspark/sql/tests.py' │ │  │ # Each matchs to module in 'pyspark/sql'. Additionally, some logical group can │ │  │ # be added. For instance, 'test_arrow.py', 'test_datasources.py' ... │   │   ├── __init__.py │   │   ├── test_appsubmit.py │   │   ├── test_arrow.py │   │   ├── test_catalog.py │   │   ├── test_column.py │   │   ├── test_conf.py │   │   ├── test_context.py │   │   ├── test_dataframe.py │   │   ├── test_datasources.py │   │   ├── test_functions.py │   │   ├── test_group.py │   │   ├── test_pandas_udf.py │   │   ├── test_pandas_udf_grouped_agg.py │   │   ├── test_pandas_udf_grouped_map.py │   │   ├── test_pandas_udf_scalar.py │   │   ├── test_pandas_udf_window.py │   │   ├── test_readwriter.py │   │   ├── test_serde.py │   │   ├── test_session.py │   │   ├── test_streaming.py │   │   ├── test_types.py │   │   ├── test_udf.py │   │   └── test_utils.py ... ├── testing # Includes testing utils that can be used in unittests. │   ├── __init__.py │   └── sqlutils.py ... ``` ## How was this patch tested? Existing tests should cover. `cd python` and `./run-tests-with-coverage`. Manually checked they are actually being ran. Each test (not officially) can be ran via: ``` SPARK_TESTING=1 ./bin/pyspark pyspark.sql.tests.test_pandas_udf_scalar ``` Note that if you're using Mac and Python 3, you might have to `OBJC_DISABLE_INITIALIZE_FORK_SAFETY=YES`. Closes #23021 from HyukjinKwon/SPARK-25344. Authored-by: hyukjinkwon <gurwls223@apache.org> Signed-off-by: hyukjinkwon <gurwls223@apache.org>
2018-11-14 01:51:11 -05:00
try:
import xmlrunner # type: ignore[import]
[SPARK-28130][PYTHON] Print pretty messages for skipped tests when xmlrunner is available in PySpark ## What changes were proposed in this pull request? Currently, pretty skipped message added by https://github.com/apache/spark/commit/f7435bec6a9348cfbbe26b13c230c08545d16067 mechanism seems not working when xmlrunner is installed apparently. This PR fixes two things: 1. When `xmlrunner` is installed, seems `xmlrunner` does not respect `vervosity` level in unittests (default is level 1). So the output looks as below ``` Running tests... ---------------------------------------------------------------------- SSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSS ---------------------------------------------------------------------- ``` So it is not caught by our message detection mechanism. 2. If we manually set the `vervocity` level to `xmlrunner`, it prints messages as below: ``` test_mixed_udf (pyspark.sql.tests.test_pandas_udf_scalar.ScalarPandasUDFTests) ... SKIP (0.000s) test_mixed_udf_and_sql (pyspark.sql.tests.test_pandas_udf_scalar.ScalarPandasUDFTests) ... SKIP (0.000s) ... ``` This is different in our Jenkins machine: ``` test_createDataFrame_column_name_encoding (pyspark.sql.tests.test_arrow.ArrowTests) ... skipped 'Pandas >= 0.23.2 must be installed; however, it was not found.' test_createDataFrame_does_not_modify_input (pyspark.sql.tests.test_arrow.ArrowTests) ... skipped 'Pandas >= 0.23.2 must be installed; however, it was not found.' ... ``` Note that last `SKIP` is different. This PR fixes the regular expression to catch `SKIP` case as well. ## How was this patch tested? Manually tested. **Before:** ``` Starting test(python2.7): pyspark.... Finished test(python2.7): pyspark.... (0s) ... Tests passed in 562 seconds ======================================================================== ... ``` **After:** ``` Starting test(python2.7): pyspark.... Finished test(python2.7): pyspark.... (48s) ... 93 tests were skipped ... Tests passed in 560 seconds Skipped tests pyspark.... with python2.7: pyspark...(...) ... SKIP (0.000s) ... ======================================================================== ... ``` Closes #24927 from HyukjinKwon/SPARK-28130. Authored-by: HyukjinKwon <gurwls223@apache.org> Signed-off-by: HyukjinKwon <gurwls223@apache.org>
2019-06-23 20:58:17 -04:00
testRunner = xmlrunner.XMLTestRunner(output='target/test-reports', verbosity=2)
[SPARK-26032][PYTHON] Break large sql/tests.py files into smaller files ## What changes were proposed in this pull request? This is the official first attempt to break huge single `tests.py` file - I did it locally before few times and gave up for some reasons. Now, currently it really makes the unittests super hard to read and difficult to check. To me, it even bothers me to to scroll down the big file. It's one single 7000 lines file! This is not only readability issue. Since one big test takes most of tests time, the tests don't run in parallel fully - although it will costs to start and stop the context. We could pick up one example and follow. Given my investigation, the current style looks closer to NumPy structure and looks easier to follow. Please see https://github.com/numpy/numpy/tree/master/numpy. Basically this PR proposes to break down `pyspark/sql/tests.py` into ...: ```bash pyspark ... ├── sql ... │   ├── tests # Includes all tests broken down from 'pyspark/sql/tests.py' │ │  │ # Each matchs to module in 'pyspark/sql'. Additionally, some logical group can │ │  │ # be added. For instance, 'test_arrow.py', 'test_datasources.py' ... │   │   ├── __init__.py │   │   ├── test_appsubmit.py │   │   ├── test_arrow.py │   │   ├── test_catalog.py │   │   ├── test_column.py │   │   ├── test_conf.py │   │   ├── test_context.py │   │   ├── test_dataframe.py │   │   ├── test_datasources.py │   │   ├── test_functions.py │   │   ├── test_group.py │   │   ├── test_pandas_udf.py │   │   ├── test_pandas_udf_grouped_agg.py │   │   ├── test_pandas_udf_grouped_map.py │   │   ├── test_pandas_udf_scalar.py │   │   ├── test_pandas_udf_window.py │   │   ├── test_readwriter.py │   │   ├── test_serde.py │   │   ├── test_session.py │   │   ├── test_streaming.py │   │   ├── test_types.py │   │   ├── test_udf.py │   │   └── test_utils.py ... ├── testing # Includes testing utils that can be used in unittests. │   ├── __init__.py │   └── sqlutils.py ... ``` ## How was this patch tested? Existing tests should cover. `cd python` and `./run-tests-with-coverage`. Manually checked they are actually being ran. Each test (not officially) can be ran via: ``` SPARK_TESTING=1 ./bin/pyspark pyspark.sql.tests.test_pandas_udf_scalar ``` Note that if you're using Mac and Python 3, you might have to `OBJC_DISABLE_INITIALIZE_FORK_SAFETY=YES`. Closes #23021 from HyukjinKwon/SPARK-25344. Authored-by: hyukjinkwon <gurwls223@apache.org> Signed-off-by: hyukjinkwon <gurwls223@apache.org>
2018-11-14 01:51:11 -05:00
except ImportError:
2018-11-14 23:30:52 -05:00
testRunner = None
unittest.main(testRunner=testRunner, verbosity=2)