tree 8b9eea2780e30dfab7d538783c11376c74262bb8
parent eb74d55fb541cdb10c1772d58d0105e3d4bc38b3
author Fokko Driesprong <fokko@apache.org> 1596901917 -0700
committer Dongjoon Hyun <dongjoon@apache.org> 1596901917 -0700

[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>