STY: enable subset of flake8-bugbear (#40743)

Author: twoertwein

.pre-commit-config.yaml

@@ -36,7 +36,7 @@ repos:
     rev: 3.9.0
     hooks:
     -   id: flake8
-        additional_dependencies: [flake8-comprehensions>=3.1.0]
+        additional_dependencies: [flake8-comprehensions>=3.1.0, flake8-bugbear>=21.3.2]
     -   id: flake8
         name: flake8 (cython)
         types: [cython]

environment.yml

@@ -21,6 +21,7 @@ dependencies:
   - black=20.8b1
   - cpplint
   - flake8
+  - flake8-bugbear>=21.3.2  # used by flake8, find likely bugs
   - flake8-comprehensions>=3.1.0  # used by flake8, linting of unnecessary comprehensions
   - isort>=5.2.1  # check that imports are in the right order
   - mypy=0.812

pandas/core/common.py

@@ -336,7 +336,7 @@ def get_callable_name(obj):
     if isinstance(obj, partial):
         return get_callable_name(obj.func)
     # fall back to class name
-    if hasattr(obj, "__call__"):
+    if callable(obj):
         return type(obj).__name__
     # everything failed (probably because the argument
     # wasn't actually callable); we return None

pandas/core/dtypes/common.py

@@ -1576,7 +1576,7 @@ def _is_dtype(arr_or_dtype, condition) -> bool:
         return False
     try:
         dtype = get_dtype(arr_or_dtype)
-    except (TypeError, ValueError, UnicodeEncodeError):
+    except (TypeError, ValueError):
         return False
     return condition(dtype)
 
@@ -1651,7 +1651,7 @@ def _is_dtype_type(arr_or_dtype, condition) -> bool:
 
     try:
         tipo = pandas_dtype(arr_or_dtype).type
-    except (TypeError, ValueError, UnicodeEncodeError):
+    except (TypeError, ValueError):
         if is_scalar(arr_or_dtype):
             return condition(type(None))
 

pandas/core/reshape/pivot.py

@@ -458,7 +458,7 @@ def _convert_by(by):
     elif (
         is_scalar(by)
         or isinstance(by, (np.ndarray, Index, ABCSeries, Grouper))
-        or hasattr(by, "__call__")
+        or callable(by)
     ):
         by = [by]
     else:

pandas/tests/frame/methods/test_to_csv.py

@@ -773,10 +773,7 @@ def test_to_csv_dups_cols(self):
             [df_float, df_int, df_bool, df_object, df_dt], axis=1, ignore_index=True
         )
 
-        cols = []
-        for i in range(5):
-            cols.extend([0, 1, 2])
-        df.columns = cols
+        df.columns = [0, 1, 2] * 5
 
         with tm.ensure_clean() as filename:
             df.to_csv(filename)

pandas/tests/indexes/categorical/test_indexing.py

@@ -244,9 +244,9 @@ def test_get_indexer_non_unique(self):
         for indexer in [idx2, list("abf"), Index(list("abf"))]:
             msg = "Reindexing only valid with uniquely valued Index objects"
             with pytest.raises(InvalidIndexError, match=msg):
-                idx1.get_indexer(idx2)
+                idx1.get_indexer(indexer)
 
-            r1, _ = idx1.get_indexer_non_unique(idx2)
+            r1, _ = idx1.get_indexer_non_unique(indexer)
             expected = np.array([0, 1, 2, -1], dtype=np.intp)
             tm.assert_almost_equal(r1, expected)
 

pandas/tests/indexes/datetimes/test_indexing.py

@@ -173,7 +173,7 @@ def test_where_other(self):
         i = date_range("20130101", periods=3, tz="US/Eastern")
 
         for arr in [np.nan, pd.NaT]:
-            result = i.where(notna(i), other=np.nan)
+            result = i.where(notna(i), other=arr)
             expected = i
             tm.assert_index_equal(result, expected)
 

pandas/tests/io/sas/test_sas7bdat.py

@@ -95,9 +95,11 @@ def test_iterator_loop(self):
         # github #13654
         for j in 0, 1:
             for k in self.test_ix[j]:
-                for chunksize in 3, 5, 10, 11:
+                for chunksize in (3, 5, 10, 11):
                     fname = os.path.join(self.dirpath, f"test{k}.sas7bdat")
-                    with pd.read_sas(fname, chunksize=10, encoding="utf-8") as rdr:
+                    with pd.read_sas(
+                        fname, chunksize=chunksize, encoding="utf-8"
+                    ) as rdr:
                         y = 0
                         for x in rdr:
                             y += x.shape[0]

pandas/tests/resample/test_datetime_index.py

@@ -1342,7 +1342,7 @@ def test_resample_nunique():
     assert expected.name == "ID"
 
     for t in [r, g]:
-        result = r.ID.nunique()
+        result = t.ID.nunique()
         tm.assert_series_equal(result, expected)
 
     result = df.ID.resample("D").nunique()

requirements-dev.txt

@@ -9,6 +9,7 @@ cython>=0.29.21
 black==20.8b1
 cpplint
 flake8
+flake8-bugbear>=21.3.2
 flake8-comprehensions>=3.1.0
 isort>=5.2.1
 mypy==0.812

setup.cfg

@@ -76,7 +76,16 @@ ignore =
     W504,  # line break after binary operator
     E402,  # module level import not at top of file
     E731,  # do not assign a lambda expression, use a def
-    S001   # found modulo formatter (incorrect picks up mod operations)
+    S001,  # found modulo formatter (incorrect picks up mod operations)
+    B005,  # controversial
+    B006,  # controversial
+    B007,  # controversial
+    B008,  # controversial
+    B009,  # setattr is used to side-step mypy
+    B010,  # getattr is used to side-step mypy
+    B011,  # tests use assert False
+    B015,  # tests use comparisons but not their returned value
+    B301   # false positives
 exclude =
     doc/sphinxext/*.py,
     doc/build/*.py,