[SPARK-45635][PYTHON][TESTS] Cleanup unused import for PySpark testing

itholic · HyukjinKwon · commit 25c74d0d4e28 · 2023-10-26T11:17:18.000+09:00
### What changes were proposed in this pull request? This PR proposes to cleanup unused import for PySpark testing. ### Why are the changes needed? To optimize PySpark testing. ### Does this PR introduce _any_ user-facing change? No, it's test-only. ### How was this patch tested? The existing CI should pass. ### Was this patch authored or co-authored using generative AI tooling? No. Closes #43489 from itholic/SPARK-45635. Authored-by: Haejoon Lee <haejoon.lee@databricks.com> Signed-off-by: Hyukjin Kwon <gurwls223@apache.org>
diff --git a/python/pyspark/pandas/tests/computation/test_corrwith.py b/python/pyspark/pandas/tests/computation/test_corrwith.py
@@ -17,7 +17,6 @@
 import unittest
 
 import numpy as np
-import pandas as pd
 
 from pyspark import pandas as ps
 from pyspark.testing.pandasutils import ComparisonTestBase
diff --git a/python/pyspark/pandas/tests/data_type_ops/test_num_arithmetic.py b/python/pyspark/pandas/tests/data_type_ops/test_num_arithmetic.py
@@ -15,7 +15,6 @@
 # limitations under the License.
 #
 
-import datetime
 import unittest
 
 import pandas as pd
diff --git a/python/pyspark/pandas/tests/data_type_ops/testing_utils.py b/python/pyspark/pandas/tests/data_type_ops/testing_utils.py
@@ -22,7 +22,6 @@
 import pandas as pd
 
 import pyspark.pandas as ps
-from pyspark.pandas.typedef import extension_dtypes
 from pyspark.pandas.typedef.typehints import (
     extension_dtypes_available,
     extension_float_dtypes_available,
diff --git a/python/pyspark/pandas/tests/frame/test_constructor.py b/python/pyspark/pandas/tests/frame/test_constructor.py
@@ -22,7 +22,6 @@
 
 from pyspark import pandas as ps
 from pyspark.pandas.typedef.typehints import (
-    extension_dtypes,
     extension_dtypes_available,
     extension_float_dtypes_available,
     extension_object_dtypes_available,
diff --git a/python/pyspark/pandas/tests/groupby/test_groupby.py b/python/pyspark/pandas/tests/groupby/test_groupby.py
@@ -22,7 +22,7 @@
 import pandas as pd
 
 from pyspark import pandas as ps
-from pyspark.pandas.exceptions import PandasNotImplementedError, DataError
+from pyspark.pandas.exceptions import PandasNotImplementedError
 from pyspark.pandas.missing.groupby import (
     MissingPandasLikeDataFrameGroupBy,
     MissingPandasLikeSeriesGroupBy,
diff --git a/python/pyspark/pandas/tests/indexes/test_base_slow.py b/python/pyspark/pandas/tests/indexes/test_base_slow.py
@@ -20,7 +20,7 @@
 import pandas as pd
 
 import pyspark.pandas as ps
-from pyspark.testing.pandasutils import ComparisonTestBase, TestUtils, SPARK_CONF_ARROW_ENABLED
+from pyspark.testing.pandasutils import ComparisonTestBase, TestUtils
 
 
 class IndexesSlowTestsMixin:
diff --git a/python/pyspark/pandas/tests/indexes/test_datetime_property.py b/python/pyspark/pandas/tests/indexes/test_datetime_property.py
@@ -15,7 +15,6 @@
 # limitations under the License.
 #
 
-import datetime
 import unittest
 
 import numpy as np
diff --git a/python/pyspark/pandas/tests/series/test_as_type.py b/python/pyspark/pandas/tests/series/test_as_type.py
@@ -23,7 +23,6 @@
 from pyspark.testing.pandasutils import ComparisonTestBase
 from pyspark.testing.sqlutils import SQLTestUtils
 from pyspark.pandas.typedef.typehints import (
-    extension_dtypes,
     extension_dtypes_available,
     extension_float_dtypes_available,
     extension_object_dtypes_available,
diff --git a/python/pyspark/pandas/tests/series/test_cumulative.py b/python/pyspark/pandas/tests/series/test_cumulative.py
@@ -16,7 +16,6 @@
 #
 import unittest
 
-import numpy as np
 import pandas as pd
 
 from pyspark import pandas as ps
diff --git a/python/pyspark/pandas/tests/series/test_series.py b/python/pyspark/pandas/tests/series/test_series.py
@@ -26,20 +26,13 @@
 
 from pyspark import pandas as ps
 from pyspark.testing.pandasutils import (
-    have_tabulate,
     PandasOnSparkTestCase,
     SPARK_CONF_ARROW_ENABLED,
-    tabulate_requirement_message,
 )
 from pyspark.testing.sqlutils import SQLTestUtils
 from pyspark.pandas.exceptions import PandasNotImplementedError
 from pyspark.pandas.missing.series import MissingPandasLikeSeries
-from pyspark.pandas.typedef.typehints import (
-    extension_dtypes,
-    extension_dtypes_available,
-    extension_float_dtypes_available,
-    extension_object_dtypes_available,
-)
+from pyspark.pandas.typedef.typehints import extension_object_dtypes_available
 
 
 class SeriesTestsMixin:
diff --git a/python/pyspark/pandas/tests/test_dataframe_spark_io.py b/python/pyspark/pandas/tests/test_dataframe_spark_io.py
@@ -16,8 +16,6 @@
 #
 
 import unittest
-import glob
-import os
 
 import numpy as np
 import pandas as pd
diff --git a/python/pyspark/pandas/tests/test_frame_resample.py b/python/pyspark/pandas/tests/test_frame_resample.py
@@ -17,19 +17,12 @@
 
 
 import unittest
-import inspect
 import datetime
-import os
 
 import numpy as np
 import pandas as pd
 
 from pyspark import pandas as ps
-from pyspark.pandas.exceptions import PandasNotImplementedError, DataError
-from pyspark.pandas.missing.resample import (
-    MissingPandasLikeDataFrameResampler,
-    MissingPandasLikeSeriesResampler,
-)
 from pyspark.testing.pandasutils import PandasOnSparkTestCase, TestUtils
 
 
diff --git a/python/pyspark/pandas/tests/test_ops_on_diff_frames.py b/python/pyspark/pandas/tests/test_ops_on_diff_frames.py
@@ -23,11 +23,9 @@
 
 from pyspark import pandas as ps
 from pyspark.pandas.config import set_option, reset_option
-from pyspark.pandas.frame import DataFrame
 from pyspark.testing.pandasutils import PandasOnSparkTestCase
 from pyspark.testing.sqlutils import SQLTestUtils
 from pyspark.pandas.typedef.typehints import (
-    extension_dtypes,
     extension_dtypes_available,
     extension_float_dtypes_available,
     extension_object_dtypes_available,
diff --git a/python/pyspark/pandas/tests/test_resample.py b/python/pyspark/pandas/tests/test_resample.py
@@ -25,7 +25,7 @@
 import pandas as pd
 
 from pyspark import pandas as ps
-from pyspark.pandas.exceptions import PandasNotImplementedError, DataError
+from pyspark.pandas.exceptions import PandasNotImplementedError
 from pyspark.pandas.missing.resample import (
     MissingPandasLikeDataFrameResampler,
     MissingPandasLikeSeriesResampler,
diff --git a/python/pyspark/pandas/tests/test_series_resample.py b/python/pyspark/pandas/tests/test_series_resample.py
@@ -17,19 +17,12 @@
 
 
 import unittest
-import inspect
 import datetime
-import os
 
 import numpy as np
 import pandas as pd
 
 from pyspark import pandas as ps
-from pyspark.pandas.exceptions import PandasNotImplementedError, DataError
-from pyspark.pandas.missing.resample import (
-    MissingPandasLikeDataFrameResampler,
-    MissingPandasLikeSeriesResampler,
-)
 from pyspark.testing.pandasutils import PandasOnSparkTestCase, TestUtils
 
 
diff --git a/python/pyspark/pandas/tests/test_spark_functions.py b/python/pyspark/pandas/tests/test_spark_functions.py
@@ -15,11 +15,6 @@
 # limitations under the License.
 #
 
-import numpy as np
-
-from pyspark.pandas.spark import functions as SF
-from pyspark.pandas.utils import spark_column_equals
-from pyspark.sql import functions as F
 from pyspark.testing.pandasutils import PandasOnSparkTestCase
 
 
diff --git a/python/pyspark/testing/connectutils.py b/python/pyspark/testing/connectutils.py
@@ -16,7 +16,6 @@
 #
 import shutil
 import tempfile
-import types
 import typing
 import os
 import functools
diff --git a/python/pyspark/testing/utils.py b/python/pyspark/testing/utils.py
@@ -56,7 +56,7 @@
 from pyspark.find_spark_home import _find_spark_home
 from pyspark.sql.dataframe import DataFrame
 from pyspark.sql import Row
-from pyspark.sql.types import StructType, AtomicType, StructField
+from pyspark.sql.types import StructType, StructField
 
 
 __all__ = ["assertDataFrameEqual", "assertSchemaEqual"]

Original file line number	Diff line number	Diff line change
`@@ -15,7 +15,6 @@`
`15`	`15`	`# limitations under the License.`
`16`	`16`	`#`
`17`	`17`
`18`		`-import datetime`
`19`	`18`	`import unittest`
`20`	`19`
`21`	`20`	`import pandas as pd`
Original file line number	Diff line number	Diff line change
`@@ -16,7 +16,6 @@`
`16`	`16`	`#`
`17`	`17`	`import unittest`
`18`	`18`
`19`		`-import numpy as np`
`20`	`19`	`import pandas as pd`
`21`	`20`
`22`	`21`	`from pyspark import pandas as ps`