spark-instrumented-optimizer/python/pyspark/sql/tests/test_context.py
Sean Owen 6378d4bc06 [SPARK-28980][CORE][SQL][STREAMING][MLLIB] Remove most items deprecated in Spark 2.2.0 or earlier, for Spark 3
### What changes were proposed in this pull request?

- Remove SQLContext.createExternalTable and Catalog.createExternalTable, deprecated in favor of createTable since 2.2.0, plus tests of deprecated methods
- Remove HiveContext, deprecated in 2.0.0, in favor of `SparkSession.builder.enableHiveSupport`
- Remove deprecated KinesisUtils.createStream methods, plus tests of deprecated methods, deprecate in 2.2.0
- Remove deprecated MLlib (not Spark ML) linear method support, mostly utility constructors and 'train' methods, and associated docs. This includes methods in LinearRegression, LogisticRegression, Lasso, RidgeRegression. These have been deprecated since 2.0.0
- Remove deprecated Pyspark MLlib linear method support, including LogisticRegressionWithSGD, LinearRegressionWithSGD, LassoWithSGD
- Remove 'runs' argument in KMeans.train() method, which has been a no-op since 2.0.0
- Remove deprecated ChiSqSelector isSorted protected method
- Remove deprecated 'yarn-cluster' and 'yarn-client' master argument in favor of 'yarn' and deploy mode 'cluster', etc

Notes:

- I was not able to remove deprecated DataFrameReader.json(RDD) in favor of DataFrameReader.json(Dataset); the former was deprecated in 2.2.0, but, it is still needed to support Pyspark's .json() method, which can't use a Dataset.
- Looks like SQLContext.createExternalTable was not actually deprecated in Pyspark, but, almost certainly was meant to be? Catalog.createExternalTable was.
- I afterwards noted that the toDegrees, toRadians functions were almost removed fully in SPARK-25908, but Felix suggested keeping just the R version as they hadn't been technically deprecated. I'd like to revisit that. Do we really want the inconsistency? I'm not against reverting it again, but then that implies leaving SQLContext.createExternalTable just in Pyspark too, which seems weird.
- I *kept* LogisticRegressionWithSGD, LinearRegressionWithSGD, LassoWithSGD, RidgeRegressionWithSGD in Pyspark, though deprecated, as it is hard to remove them (still used by StreamingLogisticRegressionWithSGD?) and they are not fully removed in Scala. Maybe should not have been deprecated.

### Why are the changes needed?

Deprecated items are easiest to remove in a major release, so we should do so as much as possible for Spark 3. This does not target items deprecated 'recently' as of Spark 2.3, which is still 18 months old.

### Does this PR introduce any user-facing change?

Yes, in that deprecated items are removed from some public APIs.

### How was this patch tested?

Existing tests.

Closes #25684 from srowen/SPARK-28980.

Lead-authored-by: Sean Owen <sean.owen@databricks.com>
Co-authored-by: HyukjinKwon <gurwls223@apache.org>
Signed-off-by: Sean Owen <sean.owen@databricks.com>
2019-09-09 10:19:40 -05:00

271 lines
12 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.
#
import os
import shutil
import sys
import tempfile
import unittest
try:
from importlib import reload # Python 3.4+ only.
except ImportError:
# Otherwise, we will stick to Python 2's built-in reload.
pass
import py4j
from pyspark.sql import Row, SparkSession
from pyspark.sql.types import *
from pyspark.sql.window import Window
from pyspark.testing.utils import ReusedPySparkTestCase
class HiveContextSQLTests(ReusedPySparkTestCase):
@classmethod
def setUpClass(cls):
ReusedPySparkTestCase.setUpClass()
cls.tempdir = tempfile.NamedTemporaryFile(delete=False)
cls.hive_available = True
cls.spark = None
try:
cls.sc._jvm.org.apache.hadoop.hive.conf.HiveConf()
except py4j.protocol.Py4JError:
cls.tearDownClass()
cls.hive_available = False
except TypeError:
cls.tearDownClass()
cls.hive_available = False
if cls.hive_available:
cls.spark = SparkSession.builder.enableHiveSupport().getOrCreate()
os.unlink(cls.tempdir.name)
if cls.hive_available:
cls.testData = [Row(key=i, value=str(i)) for i in range(100)]
cls.df = cls.sc.parallelize(cls.testData).toDF()
def setUp(self):
if not self.hive_available:
self.skipTest("Hive is not available.")
@classmethod
def tearDownClass(cls):
ReusedPySparkTestCase.tearDownClass()
shutil.rmtree(cls.tempdir.name, ignore_errors=True)
if cls.spark is not None:
cls.spark.stop()
cls.spark = None
def test_save_and_load_table(self):
df = self.df
tmpPath = tempfile.mkdtemp()
shutil.rmtree(tmpPath)
df.write.saveAsTable("savedJsonTable", "json", "append", path=tmpPath)
actual = self.spark.catalog.createTable("externalJsonTable", tmpPath, "json")
self.assertEqual(sorted(df.collect()),
sorted(self.spark.sql("SELECT * FROM savedJsonTable").collect()))
self.assertEqual(sorted(df.collect()),
sorted(self.spark.sql("SELECT * FROM externalJsonTable").collect()))
self.assertEqual(sorted(df.collect()), sorted(actual.collect()))
self.spark.sql("DROP TABLE externalJsonTable")
df.write.saveAsTable("savedJsonTable", "json", "overwrite", path=tmpPath)
schema = StructType([StructField("value", StringType(), True)])
actual = self.spark.catalog.createTable("externalJsonTable", source="json",
schema=schema, path=tmpPath,
noUse="this options will not be used")
self.assertEqual(sorted(df.collect()),
sorted(self.spark.sql("SELECT * FROM savedJsonTable").collect()))
self.assertEqual(sorted(df.select("value").collect()),
sorted(self.spark.sql("SELECT * FROM externalJsonTable").collect()))
self.assertEqual(sorted(df.select("value").collect()), sorted(actual.collect()))
self.spark.sql("DROP TABLE savedJsonTable")
self.spark.sql("DROP TABLE externalJsonTable")
defaultDataSourceName = self.spark.conf.get("spark.sql.sources.default",
"org.apache.spark.sql.parquet")
self.spark.sql("SET spark.sql.sources.default=org.apache.spark.sql.json")
df.write.saveAsTable("savedJsonTable", path=tmpPath, mode="overwrite")
actual = self.spark.catalog.createTable("externalJsonTable", path=tmpPath)
self.assertEqual(sorted(df.collect()),
sorted(self.spark.sql("SELECT * FROM savedJsonTable").collect()))
self.assertEqual(sorted(df.collect()),
sorted(self.spark.sql("SELECT * FROM externalJsonTable").collect()))
self.assertEqual(sorted(df.collect()), sorted(actual.collect()))
self.spark.sql("DROP TABLE savedJsonTable")
self.spark.sql("DROP TABLE externalJsonTable")
self.spark.sql("SET spark.sql.sources.default=" + defaultDataSourceName)
shutil.rmtree(tmpPath)
def test_window_functions(self):
df = self.spark.createDataFrame([(1, "1"), (2, "2"), (1, "2"), (1, "2")], ["key", "value"])
w = Window.partitionBy("value").orderBy("key")
from pyspark.sql import functions as F
sel = df.select(df.value, df.key,
F.max("key").over(w.rowsBetween(0, 1)),
F.min("key").over(w.rowsBetween(0, 1)),
F.count("key").over(w.rowsBetween(float('-inf'), float('inf'))),
F.row_number().over(w),
F.rank().over(w),
F.dense_rank().over(w),
F.ntile(2).over(w))
rs = sorted(sel.collect())
expected = [
("1", 1, 1, 1, 1, 1, 1, 1, 1),
("2", 1, 1, 1, 3, 1, 1, 1, 1),
("2", 1, 2, 1, 3, 2, 1, 1, 1),
("2", 2, 2, 2, 3, 3, 3, 2, 2)
]
for r, ex in zip(rs, expected):
self.assertEqual(tuple(r), ex[:len(r)])
def test_window_functions_without_partitionBy(self):
df = self.spark.createDataFrame([(1, "1"), (2, "2"), (1, "2"), (1, "2")], ["key", "value"])
w = Window.orderBy("key", df.value)
from pyspark.sql import functions as F
sel = df.select(df.value, df.key,
F.max("key").over(w.rowsBetween(0, 1)),
F.min("key").over(w.rowsBetween(0, 1)),
F.count("key").over(w.rowsBetween(float('-inf'), float('inf'))),
F.row_number().over(w),
F.rank().over(w),
F.dense_rank().over(w),
F.ntile(2).over(w))
rs = sorted(sel.collect())
expected = [
("1", 1, 1, 1, 4, 1, 1, 1, 1),
("2", 1, 1, 1, 4, 2, 2, 2, 1),
("2", 1, 2, 1, 4, 3, 2, 2, 2),
("2", 2, 2, 2, 4, 4, 4, 3, 2)
]
for r, ex in zip(rs, expected):
self.assertEqual(tuple(r), ex[:len(r)])
def test_window_functions_cumulative_sum(self):
df = self.spark.createDataFrame([("one", 1), ("two", 2)], ["key", "value"])
from pyspark.sql import functions as F
# Test cumulative sum
sel = df.select(
df.key,
F.sum(df.value).over(Window.rowsBetween(Window.unboundedPreceding, 0)))
rs = sorted(sel.collect())
expected = [("one", 1), ("two", 3)]
for r, ex in zip(rs, expected):
self.assertEqual(tuple(r), ex[:len(r)])
# Test boundary values less than JVM's Long.MinValue and make sure we don't overflow
sel = df.select(
df.key,
F.sum(df.value).over(Window.rowsBetween(Window.unboundedPreceding - 1, 0)))
rs = sorted(sel.collect())
expected = [("one", 1), ("two", 3)]
for r, ex in zip(rs, expected):
self.assertEqual(tuple(r), ex[:len(r)])
# Test boundary values greater than JVM's Long.MaxValue and make sure we don't overflow
frame_end = Window.unboundedFollowing + 1
sel = df.select(
df.key,
F.sum(df.value).over(Window.rowsBetween(Window.currentRow, frame_end)))
rs = sorted(sel.collect())
expected = [("one", 3), ("two", 2)]
for r, ex in zip(rs, expected):
self.assertEqual(tuple(r), ex[:len(r)])
def test_collect_functions(self):
df = self.spark.createDataFrame([(1, "1"), (2, "2"), (1, "2"), (1, "2")], ["key", "value"])
from pyspark.sql import functions
self.assertEqual(
sorted(df.select(functions.collect_set(df.key).alias('r')).collect()[0].r),
[1, 2])
self.assertEqual(
sorted(df.select(functions.collect_list(df.key).alias('r')).collect()[0].r),
[1, 1, 1, 2])
self.assertEqual(
sorted(df.select(functions.collect_set(df.value).alias('r')).collect()[0].r),
["1", "2"])
self.assertEqual(
sorted(df.select(functions.collect_list(df.value).alias('r')).collect()[0].r),
["1", "2", "2", "2"])
def test_limit_and_take(self):
df = self.spark.range(1, 1000, numPartitions=10)
def assert_runs_only_one_job_stage_and_task(job_group_name, f):
tracker = self.sc.statusTracker()
self.sc.setJobGroup(job_group_name, description="")
f()
jobs = tracker.getJobIdsForGroup(job_group_name)
self.assertEqual(1, len(jobs))
stages = tracker.getJobInfo(jobs[0]).stageIds
self.assertEqual(1, len(stages))
self.assertEqual(1, tracker.getStageInfo(stages[0]).numTasks)
# Regression test for SPARK-10731: take should delegate to Scala implementation
assert_runs_only_one_job_stage_and_task("take", lambda: df.take(1))
# Regression test for SPARK-17514: limit(n).collect() should the perform same as take(n)
assert_runs_only_one_job_stage_and_task("collect_limit", lambda: df.limit(1).collect())
def test_datetime_functions(self):
from pyspark.sql import functions
from datetime import date
df = self.spark.range(1).selectExpr("'2017-01-22' as dateCol")
parse_result = df.select(functions.to_date(functions.col("dateCol"))).first()
self.assertEquals(date(2017, 1, 22), parse_result['to_date(`dateCol`)'])
def test_unbounded_frames(self):
from pyspark.sql import functions as F
from pyspark.sql import window
df = self.spark.range(0, 3)
def rows_frame_match():
return "ROWS BETWEEN UNBOUNDED PRECEDING AND UNBOUNDED FOLLOWING" in df.select(
F.count("*").over(window.Window.rowsBetween(-sys.maxsize, sys.maxsize))
).columns[0]
def range_frame_match():
return "RANGE BETWEEN UNBOUNDED PRECEDING AND UNBOUNDED FOLLOWING" in df.select(
F.count("*").over(window.Window.rangeBetween(-sys.maxsize, sys.maxsize))
).columns[0]
for new_maxsize in [2 ** 31 - 1, 2 ** 63 - 1, 2 ** 127 - 1]:
old_maxsize = sys.maxsize
sys.maxsize = new_maxsize
try:
# Manually reload window module to use monkey-patched sys.maxsize.
reload(window)
self.assertTrue(rows_frame_match())
self.assertTrue(range_frame_match())
finally:
sys.maxsize = old_maxsize
reload(window)
if __name__ == "__main__":
from pyspark.sql.tests.test_context import *
try:
import xmlrunner
testRunner = xmlrunner.XMLTestRunner(output='target/test-reports', verbosity=2)
except ImportError:
testRunner = None
unittest.main(testRunner=testRunner, verbosity=2)