9fcf0ea718
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>
255 lines
8.6 KiB
Python
255 lines
8.6 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 unittest
|
|
|
|
from pyspark.sql.functions import array, explode, col, lit, udf, pandas_udf
|
|
from pyspark.sql.types import DoubleType, StructType, StructField, Row
|
|
from pyspark.testing.sqlutils import ReusedSQLTestCase, have_pandas, have_pyarrow, \
|
|
pandas_requirement_message, pyarrow_requirement_message
|
|
from pyspark.testing.utils import QuietTest
|
|
|
|
if have_pandas:
|
|
import pandas as pd
|
|
from pandas.util.testing import assert_frame_equal
|
|
|
|
if have_pyarrow:
|
|
import pyarrow as pa # noqa: F401
|
|
|
|
|
|
@unittest.skipIf(
|
|
not have_pandas or not have_pyarrow,
|
|
pandas_requirement_message or pyarrow_requirement_message)
|
|
class CogroupedMapInPandasTests(ReusedSQLTestCase):
|
|
|
|
@property
|
|
def data1(self):
|
|
return self.spark.range(10).toDF('id') \
|
|
.withColumn("ks", array([lit(i) for i in range(20, 30)])) \
|
|
.withColumn("k", explode(col('ks')))\
|
|
.withColumn("v", col('k') * 10)\
|
|
.drop('ks')
|
|
|
|
@property
|
|
def data2(self):
|
|
return self.spark.range(10).toDF('id') \
|
|
.withColumn("ks", array([lit(i) for i in range(20, 30)])) \
|
|
.withColumn("k", explode(col('ks'))) \
|
|
.withColumn("v2", col('k') * 100) \
|
|
.drop('ks')
|
|
|
|
def test_simple(self):
|
|
self._test_merge(self.data1, self.data2)
|
|
|
|
def test_left_group_empty(self):
|
|
left = self.data1.where(col("id") % 2 == 0)
|
|
self._test_merge(left, self.data2)
|
|
|
|
def test_right_group_empty(self):
|
|
right = self.data2.where(col("id") % 2 == 0)
|
|
self._test_merge(self.data1, right)
|
|
|
|
def test_different_schemas(self):
|
|
right = self.data2.withColumn('v3', lit('a'))
|
|
self._test_merge(self.data1, right, 'id long, k int, v int, v2 int, v3 string')
|
|
|
|
def test_complex_group_by(self):
|
|
left = pd.DataFrame.from_dict({
|
|
'id': [1, 2, 3],
|
|
'k': [5, 6, 7],
|
|
'v': [9, 10, 11]
|
|
})
|
|
|
|
right = pd.DataFrame.from_dict({
|
|
'id': [11, 12, 13],
|
|
'k': [5, 6, 7],
|
|
'v2': [90, 100, 110]
|
|
})
|
|
|
|
left_gdf = self.spark\
|
|
.createDataFrame(left)\
|
|
.groupby(col('id') % 2 == 0)
|
|
|
|
right_gdf = self.spark \
|
|
.createDataFrame(right) \
|
|
.groupby(col('id') % 2 == 0)
|
|
|
|
def merge_pandas(l, r):
|
|
return pd.merge(l[['k', 'v']], r[['k', 'v2']], on=['k'])
|
|
|
|
result = left_gdf \
|
|
.cogroup(right_gdf) \
|
|
.applyInPandas(merge_pandas, 'k long, v long, v2 long') \
|
|
.sort(['k']) \
|
|
.toPandas()
|
|
|
|
expected = pd.DataFrame.from_dict({
|
|
'k': [5, 6, 7],
|
|
'v': [9, 10, 11],
|
|
'v2': [90, 100, 110]
|
|
})
|
|
|
|
assert_frame_equal(expected, result)
|
|
|
|
def test_empty_group_by(self):
|
|
left = self.data1
|
|
right = self.data2
|
|
|
|
def merge_pandas(l, r):
|
|
return pd.merge(l, r, on=['id', 'k'])
|
|
|
|
result = left.groupby().cogroup(right.groupby())\
|
|
.applyInPandas(merge_pandas, 'id long, k int, v int, v2 int') \
|
|
.sort(['id', 'k']) \
|
|
.toPandas()
|
|
|
|
left = left.toPandas()
|
|
right = right.toPandas()
|
|
|
|
expected = pd \
|
|
.merge(left, right, on=['id', 'k']) \
|
|
.sort_values(by=['id', 'k'])
|
|
|
|
assert_frame_equal(expected, result)
|
|
|
|
def test_mixed_scalar_udfs_followed_by_cogrouby_apply(self):
|
|
df = self.spark.range(0, 10).toDF('v1')
|
|
df = df.withColumn('v2', udf(lambda x: x + 1, 'int')(df['v1'])) \
|
|
.withColumn('v3', pandas_udf(lambda x: x + 2, 'int')(df['v1']))
|
|
|
|
result = df.groupby().cogroup(df.groupby()) \
|
|
.applyInPandas(lambda x, y: pd.DataFrame([(x.sum().sum(), y.sum().sum())]),
|
|
'sum1 int, sum2 int').collect()
|
|
|
|
self.assertEquals(result[0]['sum1'], 165)
|
|
self.assertEquals(result[0]['sum2'], 165)
|
|
|
|
def test_with_key_left(self):
|
|
self._test_with_key(self.data1, self.data1, isLeft=True)
|
|
|
|
def test_with_key_right(self):
|
|
self._test_with_key(self.data1, self.data1, isLeft=False)
|
|
|
|
def test_with_key_left_group_empty(self):
|
|
left = self.data1.where(col("id") % 2 == 0)
|
|
self._test_with_key(left, self.data1, isLeft=True)
|
|
|
|
def test_with_key_right_group_empty(self):
|
|
right = self.data1.where(col("id") % 2 == 0)
|
|
self._test_with_key(self.data1, right, isLeft=False)
|
|
|
|
def test_with_key_complex(self):
|
|
|
|
def left_assign_key(key, l, _):
|
|
return l.assign(key=key[0])
|
|
|
|
result = self.data1 \
|
|
.groupby(col('id') % 2 == 0)\
|
|
.cogroup(self.data2.groupby(col('id') % 2 == 0)) \
|
|
.applyInPandas(left_assign_key, 'id long, k int, v int, key boolean') \
|
|
.sort(['id', 'k']) \
|
|
.toPandas()
|
|
|
|
expected = self.data1.toPandas()
|
|
expected = expected.assign(key=expected.id % 2 == 0)
|
|
|
|
assert_frame_equal(expected, result)
|
|
|
|
def test_wrong_return_type(self):
|
|
# Test that we get a sensible exception invalid values passed to apply
|
|
left = self.data1
|
|
right = self.data2
|
|
with QuietTest(self.sc):
|
|
with self.assertRaisesRegexp(
|
|
NotImplementedError,
|
|
'Invalid return type.*MapType'):
|
|
left.groupby('id').cogroup(right.groupby('id')).applyInPandas(
|
|
lambda l, r: l, 'id long, v map<int, int>')
|
|
|
|
def test_wrong_args(self):
|
|
left = self.data1
|
|
right = self.data2
|
|
with self.assertRaisesRegexp(ValueError, 'Invalid function'):
|
|
left.groupby('id').cogroup(right.groupby('id')) \
|
|
.applyInPandas(lambda: 1, StructType([StructField("d", DoubleType())]))
|
|
|
|
def test_case_insensitive_grouping_column(self):
|
|
# SPARK-31915: case-insensitive grouping column should work.
|
|
df1 = self.spark.createDataFrame([(1, 1)], ("column", "value"))
|
|
|
|
row = df1.groupby("ColUmn").cogroup(
|
|
df1.groupby("COLUMN")
|
|
).applyInPandas(lambda r, l: r + l, "column long, value long").first()
|
|
self.assertEquals(row.asDict(), Row(column=2, value=2).asDict())
|
|
|
|
df2 = self.spark.createDataFrame([(1, 1)], ("column", "value"))
|
|
|
|
row = df1.groupby("ColUmn").cogroup(
|
|
df2.groupby("COLUMN")
|
|
).applyInPandas(lambda r, l: r + l, "column long, value long").first()
|
|
self.assertEquals(row.asDict(), Row(column=2, value=2).asDict())
|
|
|
|
@staticmethod
|
|
def _test_with_key(left, right, isLeft):
|
|
|
|
def right_assign_key(key, l, r):
|
|
return l.assign(key=key[0]) if isLeft else r.assign(key=key[0])
|
|
|
|
result = left \
|
|
.groupby('id') \
|
|
.cogroup(right.groupby('id')) \
|
|
.applyInPandas(right_assign_key, 'id long, k int, v int, key long') \
|
|
.toPandas()
|
|
|
|
expected = left.toPandas() if isLeft else right.toPandas()
|
|
expected = expected.assign(key=expected.id)
|
|
|
|
assert_frame_equal(expected, result)
|
|
|
|
@staticmethod
|
|
def _test_merge(left, right, output_schema='id long, k int, v int, v2 int'):
|
|
|
|
def merge_pandas(l, r):
|
|
return pd.merge(l, r, on=['id', 'k'])
|
|
|
|
result = left \
|
|
.groupby('id') \
|
|
.cogroup(right.groupby('id')) \
|
|
.applyInPandas(merge_pandas, output_schema)\
|
|
.sort(['id', 'k']) \
|
|
.toPandas()
|
|
|
|
left = left.toPandas()
|
|
right = right.toPandas()
|
|
|
|
expected = pd \
|
|
.merge(left, right, on=['id', 'k']) \
|
|
.sort_values(by=['id', 'k'])
|
|
|
|
assert_frame_equal(expected, result)
|
|
|
|
|
|
if __name__ == "__main__":
|
|
from pyspark.sql.tests.test_pandas_cogrouped_map 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)
|