CLN: Dead version checking code post minimum version bump (#27063)

* Remove dateutil version check tests

* Remove more dead version checking code

* Flake8 and fix bs4 comparison

* Use import_optional_dependency again

* Remove unused import

* Change bs4 import test to check for ImportError and add whatsnew

* Some linting

* noqa necessary imports

Author: mroeschke

doc/source/whatsnew/v0.25.0.rst

@@ -538,6 +538,7 @@ Other API changes
 - Most Pandas classes had a ``__bytes__`` method, which was used for getting a python2-style bytestring representation of the object. This method has been removed as a part of dropping Python2 (:issue:`26447`)
 - The ``.str``-accessor has been disabled for 1-level :class:`MultiIndex`, use :meth:`MultiIndex.to_flat_index` if necessary (:issue:`23679`)
 - Removed support of gtk package for clipboards (:issue:`26563`)
+- Using an unsupported version of Beautiful Soup 4 will now raise an ``ImportError`` instead of a ``ValueError`` (:issue:`27063`)
 
 .. _whatsnew_0250.deprecations:
 

pandas/io/html.py

@@ -4,7 +4,6 @@
 """
 
 from collections import abc
-from distutils.version import LooseVersion
 import numbers
 import os
 import re
@@ -830,10 +829,8 @@ def _parser_dispatch(flavor):
         if not _HAS_BS4:
             raise ImportError(
                 "BeautifulSoup4 (bs4) not found, please install it")
-        import bs4
-        if LooseVersion(bs4.__version__) <= LooseVersion('4.2.0'):
-            raise ValueError("A minimum version of BeautifulSoup 4.2.1 "
-                             "is required")
+        # Although we call this above, we want to raise here right before use.
+        bs4 = import_optional_dependency('bs4')  # noqa:F841
 
     else:
         if not _HAS_LXML:

pandas/io/pytables.py

@@ -5,7 +5,6 @@
 
 import copy
 from datetime import date, datetime
-from distutils.version import LooseVersion
 import itertools
 import os
 import re
@@ -227,10 +226,6 @@ def _tables():
         import tables
         _table_mod = tables
 
-        # version requirements
-        if LooseVersion(tables.__version__) < LooseVersion('3.0.0'):
-            raise ImportError("PyTables version >= 3.0.0 is required")
-
         # set the file open policy
         # return the file open policy; this changes as of pytables 3.1
         # depending on the HDF5 version

pandas/tests/indexes/datetimes/test_timezones.py

@@ -2,7 +2,6 @@
 Tests for DatetimeIndex timezone-related methods
 """
 from datetime import date, datetime, time, timedelta, tzinfo
-from distutils.version import LooseVersion
 
 import dateutil
 from dateutil.tz import gettz, tzlocal
@@ -554,14 +553,10 @@ def test_dti_construction_ambiguous_endpoint(self, tz):
         assert times[0] == Timestamp('2013-10-26 23:00', tz=tz, freq="H")
 
         if str(tz).startswith('dateutil'):
-            if LooseVersion(dateutil.__version__) < LooseVersion('2.6.0'):
-                # see GH#14621
-                assert times[-1] == Timestamp('2013-10-27 01:00:00+0000',
-                                              tz=tz, freq="H")
-            elif LooseVersion(dateutil.__version__) > LooseVersion('2.6.0'):
-                # fixed ambiguous behavior
-                assert times[-1] == Timestamp('2013-10-27 01:00:00+0100',
-                                              tz=tz, freq="H")
+            # fixed ambiguous behavior
+            # see GH#14621
+            assert times[-1] == Timestamp('2013-10-27 01:00:00+0100',
+                                          tz=tz, freq="H")
         else:
             assert times[-1] == Timestamp('2013-10-27 01:00:00+0000',
                                           tz=tz, freq="H")

pandas/tests/indexes/datetimes/test_tools.py

@@ -2,10 +2,8 @@
 
 import calendar
 from datetime import datetime, time
-from distutils.version import LooseVersion
 import locale
 
-import dateutil
 from dateutil.parser import parse
 from dateutil.tz.tz import tzoffset
 import numpy as np
@@ -1739,8 +1737,6 @@ def test_parsers_dayfirst_yearfirst(self, cache):
         # 2.5.2 20/12/21   [dayfirst=1, yearfirst=0] -> 2021-12-20 00:00:00
         # 2.5.3 20/12/21   [dayfirst=1, yearfirst=0] -> 2021-12-20 00:00:00
 
-        is_lt_253 = LooseVersion(dateutil.__version__) < LooseVersion('2.5.3')
-
         # str : dayfirst, yearfirst, expected
         cases = {'10-11-12': [(False, False,
                                datetime(2012, 10, 11)),
@@ -1762,11 +1758,6 @@ def test_parsers_dayfirst_yearfirst(self, cache):
         for date_str, values in cases.items():
             for dayfirst, yearfirst, expected in values:
 
-                # odd comparisons across version
-                # let's just skip
-                if dayfirst and yearfirst and is_lt_253:
-                    continue
-
                 # compare with dateutil result
                 dateutil_result = parse(date_str, dayfirst=dayfirst,
                                         yearfirst=yearfirst)

pandas/tests/io/conftest.py

@@ -1,4 +1,3 @@
-from distutils.version import LooseVersion
 import os
 
 import pytest
@@ -43,12 +42,6 @@ def s3_resource(tips_file, jsonl_file):
     """
     pytest.importorskip('s3fs')
     boto3 = pytest.importorskip('boto3')
-    botocore = pytest.importorskip('botocore')
-
-    if LooseVersion(botocore.__version__) < LooseVersion("1.11.0"):
-        # botocore leaks an uncatchable ResourceWarning before 1.11.0;
-        # see GH 23731 and https://github.com/boto/botocore/issues/1464
-        pytest.skip("botocore is leaking resources before 1.11.0")
 
     with tm.ensure_safe_environment_variables():
         # temporary workaround as moto fails for botocore >= 1.11 otherwise,

pandas/tests/io/excel/test_style.py

@@ -1,5 +1,3 @@
-from distutils.version import LooseVersion
-
 import numpy as np
 import pytest
 
@@ -107,15 +105,8 @@ def custom_converter(css):
                     assert cell1.font.color.rgb != cell2.font.color.rgb
                     assert cell2.font.color.rgb == alpha + '0000FF'
                 elif ref == 'D4':
-                    # This fails with engine=xlsxwriter due to
-                    # https://bitbucket.org/openpyxl/openpyxl/issues/800
-                    if engine == 'xlsxwriter' \
-                       and (LooseVersion(openpyxl.__version__) <
-                            LooseVersion('2.4.6')):
-                        pass
-                    else:
-                        assert cell1.font.underline != cell2.font.underline
-                        assert cell2.font.underline == 'single'
+                    assert cell1.font.underline != cell2.font.underline
+                    assert cell2.font.underline == 'single'
                 elif ref == 'B5':
                     assert not cell1.border.left.style
                     assert (cell2.border.top.style ==

pandas/tests/io/pytables/test_pytables.py

@@ -43,8 +43,7 @@
             'release beyong 3.4.4 to support numpy 1.16x'))
 
 
-_default_compressor = ('blosc' if LooseVersion(tables.__version__) >=
-                       LooseVersion('2.2') else 'zlib')
+_default_compressor = 'blosc'
 
 
 ignore_natural_naming_warning = pytest.mark.filterwarnings(

pandas/tests/io/test_html.py

@@ -54,7 +54,7 @@ def assert_framelist_equal(list1, list2, *args, **kwargs):
 def test_bs4_version_fails(monkeypatch, datapath):
     import bs4
     monkeypatch.setattr(bs4, '__version__', '4.2')
-    with pytest.raises(ValueError, match="minimum version"):
+    with pytest.raises(ImportError, match="Pandas requires version"):
         read_html(datapath("io", "data", "spam.html"), flavor='bs4')
 
 

pandas/tests/io/test_parquet.py

@@ -1,6 +1,5 @@
 """ test parquet compat """
 import datetime
-from distutils.version import LooseVersion
 import os
 from warnings import catch_warnings
 
@@ -454,10 +453,8 @@ class TestParquetFastParquet(Base):
     def test_basic(self, fp, df_full):
         df = df_full
 
-        # additional supported types for fastparquet
-        if LooseVersion(fastparquet.__version__) >= LooseVersion('0.1.4'):
-            df['datetime_tz'] = pd.date_range('20130101', periods=3,
-                                              tz='US/Eastern')
+        df['datetime_tz'] = pd.date_range('20130101', periods=3,
+                                          tz='US/Eastern')
         df['timedelta'] = pd.timedelta_range('1 day', periods=3)
         check_round_trip(df, fp)
 
@@ -485,8 +482,6 @@ def test_unsupported(self, fp):
         self.check_error_on_write(df, fp, ValueError)
 
     def test_categorical(self, fp):
-        if LooseVersion(fastparquet.__version__) < LooseVersion("0.1.3"):
-            pytest.skip("CategoricalDtype not supported for older fp")
         df = pd.DataFrame({'a': pd.Categorical(list('abc'))})
         check_round_trip(df, fp)
 
@@ -512,7 +507,7 @@ def test_partition_cols_supported(self, fp, df_full):
             df.to_parquet(path, engine="fastparquet",
                           partition_cols=partition_cols, compression=None)
             assert os.path.exists(path)
-            import fastparquet
+            import fastparquet  # noqa: F811
             actual_partition_cols = fastparquet.ParquetFile(path, False).cats
             assert len(actual_partition_cols) == 2
 
@@ -524,7 +519,7 @@ def test_partition_on_supported(self, fp, df_full):
             df.to_parquet(path, engine="fastparquet", compression=None,
                           partition_on=partition_cols)
             assert os.path.exists(path)
-            import fastparquet
+            import fastparquet  # noqa: F811
             actual_partition_cols = fastparquet.ParquetFile(path, False).cats
             assert len(actual_partition_cols) == 2
 

pandas/tests/scalar/timestamp/test_rendering.py

@@ -1,7 +1,5 @@
-from distutils.version import LooseVersion
 import pprint
 
-import dateutil
 import pytest
 import pytz  # noqa  # a test below uses pytz but only inside a `eval` call
 
@@ -10,13 +8,8 @@
 
 class TestTimestampRendering:
 
-    # dateutil zone change (only matters for repr)
-    if LooseVersion(dateutil.__version__) >= LooseVersion('2.6.0'):
-        timezones = ['UTC', 'Asia/Tokyo', 'US/Eastern',
-                     'dateutil/US/Pacific']
-    else:
-        timezones = ['UTC', 'Asia/Tokyo', 'US/Eastern',
-                     'dateutil/America/Los_Angeles']
+    timezones = ['UTC', 'Asia/Tokyo', 'US/Eastern',
+                 'dateutil/US/Pacific']
 
     @pytest.mark.parametrize('tz', timezones)
     @pytest.mark.parametrize('freq', ['D', 'M', 'S', 'N'])

pandas/tests/scalar/timestamp/test_timezones.py

@@ -2,7 +2,6 @@
 Tests for Timestamp timezone-related methods
 """
 from datetime import date, datetime, timedelta
-from distutils.version import LooseVersion
 
 import dateutil
 from dateutil.tz import gettz, tzoffset
@@ -145,31 +144,22 @@ def test_tz_localize_ambiguous_compat(self):
         assert result_pytz.value == result_dateutil.value
         assert result_pytz.value == 1382835600000000000
 
-        if LooseVersion(dateutil.__version__) < LooseVersion('2.6.0'):
-            # dateutil 2.6 buggy w.r.t. ambiguous=0
-            # see gh-14621
-            # see https://github.com/dateutil/dateutil/issues/321
-            assert (result_pytz.to_pydatetime().tzname() ==
-                    result_dateutil.to_pydatetime().tzname())
-            assert str(result_pytz) == str(result_dateutil)
-        elif LooseVersion(dateutil.__version__) > LooseVersion('2.6.0'):
-            # fixed ambiguous behavior
-            assert result_pytz.to_pydatetime().tzname() == 'GMT'
-            assert result_dateutil.to_pydatetime().tzname() == 'BST'
-            assert str(result_pytz) != str(result_dateutil)
+        # fixed ambiguous behavior
+        # see gh-14621
+        assert result_pytz.to_pydatetime().tzname() == 'GMT'
+        assert result_dateutil.to_pydatetime().tzname() == 'BST'
+        assert str(result_pytz) != str(result_dateutil)
 
         # 1 hour difference
         result_pytz = naive.tz_localize(pytz_zone, ambiguous=1)
         result_dateutil = naive.tz_localize(dateutil_zone, ambiguous=1)
         assert result_pytz.value == result_dateutil.value
         assert result_pytz.value == 1382832000000000000
 
-        # dateutil < 2.6 is buggy w.r.t. ambiguous timezones
-        if LooseVersion(dateutil.__version__) > LooseVersion('2.5.3'):
-            # see gh-14621
-            assert str(result_pytz) == str(result_dateutil)
-            assert (result_pytz.to_pydatetime().tzname() ==
-                    result_dateutil.to_pydatetime().tzname())
+        # see gh-14621
+        assert str(result_pytz) == str(result_dateutil)
+        assert (result_pytz.to_pydatetime().tzname() ==
+                result_dateutil.to_pydatetime().tzname())
 
     @pytest.mark.parametrize('tz', [pytz.timezone('US/Eastern'),
                                     gettz('US/Eastern'),

pandas/tests/tseries/offsets/test_offsets.py

@@ -1,5 +1,4 @@
 from datetime import date, datetime, timedelta
-from distutils.version import LooseVersion
 
 import numpy as np
 import pytest
@@ -2998,25 +2997,6 @@ def _make_timestamp(self, string, hrs_offset, tz):
             offset_string = '-{hrs:02d}00'.format(hrs=-1 * hrs_offset)
         return Timestamp(string + offset_string).tz_convert(tz)
 
-    def test_fallback_plural(self):
-        # test moving from daylight savings to standard time
-        import dateutil
-        for tz, utc_offsets in self.timezone_utc_offsets.items():
-            hrs_pre = utc_offsets['utc_offset_daylight']
-            hrs_post = utc_offsets['utc_offset_standard']
-
-            if LooseVersion(dateutil.__version__) < LooseVersion('2.6.0'):
-                # buggy ambiguous behavior in 2.6.0
-                # GH 14621
-                # https://github.com/dateutil/dateutil/issues/321
-                self._test_all_offsets(
-                    n=3, tstart=self._make_timestamp(self.ts_pre_fallback,
-                                                     hrs_pre, tz),
-                    expected_utc_offset=hrs_post)
-            elif LooseVersion(dateutil.__version__) > LooseVersion('2.6.0'):
-                # fixed, but skip the test
-                continue
-
     def test_springforward_plural(self):
         # test moving from standard to daylight savings
         for tz, utc_offsets in self.timezone_utc_offsets.items():