CLN: catch Exception in fewer places, assorted cleanups (#28276)

Author: jbrockmendel

ci/code_checks.sh

@@ -203,7 +203,7 @@ if [[ -z "$CHECK" || "$CHECK" == "code" ]]; then
 import sys
 import pandas
 
-blacklist = {'bs4', 'gcsfs', 'html5lib', 'ipython', 'jinja2' 'hypothesis',
+blacklist = {'bs4', 'gcsfs', 'html5lib', 'ipython', 'jinja2', 'hypothesis',
              'lxml', 'numexpr', 'openpyxl', 'py', 'pytest', 's3fs', 'scipy',
              'tables', 'xlrd', 'xlsxwriter', 'xlwt'}
 mods = blacklist & set(m.split('.')[0] for m in sys.modules)

pandas/_libs/lib.pyx

@@ -235,7 +235,7 @@ def fast_unique_multiple(list arrays, sort: bool=True):
     if sort is None:
         try:
             uniques.sort()
-        except Exception:
+        except TypeError:
             # TODO: RuntimeWarning?
             pass
 
@@ -264,7 +264,7 @@ def fast_unique_multiple_list(lists: list, sort: bool=True) -> list:
     if sort:
         try:
             uniques.sort()
-        except Exception:
+        except TypeError:
             pass
 
     return uniques
@@ -304,7 +304,7 @@ def fast_unique_multiple_list_gen(object gen, bint sort=True):
     if sort:
         try:
             uniques.sort()
-        except Exception:
+        except TypeError:
             pass
 
     return uniques
@@ -1410,7 +1410,7 @@ def infer_datetimelike_array(arr: object) -> object:
         try:
             array_to_datetime(objs, errors='raise')
             return 'datetime'
-        except:
+        except (ValueError, TypeError):
             pass
 
         # we are *not* going to infer from strings

pandas/core/common.py

@@ -211,7 +211,7 @@ def try_sort(iterable):
     listed = list(iterable)
     try:
         return sorted(listed)
-    except Exception:
+    except TypeError:
         return listed
 
 

pandas/core/groupby/grouper.py

@@ -583,9 +583,11 @@ def _get_grouper(
     # if the actual grouper should be obj[key]
     def is_in_axis(key):
         if not _is_label_like(key):
+            items = obj._data.items
             try:
-                obj._data.items.get_loc(key)
-            except Exception:
+                items.get_loc(key)
+            except (KeyError, TypeError):
+                # TypeError shows up here if we pass e.g. Int64Index
                 return False
 
         return True

pandas/core/groupby/ops.py

@@ -615,14 +615,9 @@ def _aggregate(
         is_datetimelike,
         min_count=-1,
     ):
-        if values.ndim > 3:
+        if values.ndim > 2:
             # punting for now
-            raise NotImplementedError("number of dimensions is currently limited to 3")
-        elif values.ndim > 2:
-            for i, chunk in enumerate(values.transpose(2, 0, 1)):
-
-                chunk = chunk.squeeze()
-                agg_func(result[:, :, i], counts, chunk, comp_ids, min_count)
+            raise NotImplementedError("number of dimensions is currently limited to 2")
         else:
             agg_func(result, counts, values, comp_ids, min_count)
 
@@ -640,20 +635,9 @@ def _transform(
     ):
 
         comp_ids, _, ngroups = self.group_info
-        if values.ndim > 3:
+        if values.ndim > 2:
             # punting for now
-            raise NotImplementedError("number of dimensions is currently limited to 3")
-        elif values.ndim > 2:
-            for i, chunk in enumerate(values.transpose(2, 0, 1)):
-
-                transform_func(
-                    result[:, :, i],
-                    values,
-                    comp_ids,
-                    ngroups,
-                    is_datetimelike,
-                    **kwargs
-                )
+            raise NotImplementedError("number of dimensions is currently limited to 2")
         else:
             transform_func(result, values, comp_ids, ngroups, is_datetimelike, **kwargs)
 
@@ -932,11 +916,7 @@ def _chop(self, sdata, slice_obj):
 class FrameSplitter(DataSplitter):
     def fast_apply(self, f, names):
         # must return keys::list, values::list, mutated::bool
-        try:
-            starts, ends = lib.generate_slices(self.slabels, self.ngroups)
-        except Exception:
-            # fails when all -1
-            return [], True
+        starts, ends = lib.generate_slices(self.slabels, self.ngroups)
 
         sdata = self._get_sorted_data()
         return libreduction.apply_frame_axis0(sdata, f, names, starts, ends)

pandas/core/ops/__init__.py

@@ -698,10 +698,7 @@ def na_op(x, y):
 
         return result
 
-    def wrapper(self, other, axis=None):
-        # Validate the axis parameter
-        if axis is not None:
-            self._get_axis_number(axis)
+    def wrapper(self, other):
 
         res_name = get_op_result_name(self, other)
         other = lib.item_from_zerodim(other)
@@ -1104,7 +1101,7 @@ def f(self, other):
             # straight boolean comparisons we want to allow all columns
             # (regardless of dtype to pass thru) See #4537 for discussion.
             res = self._combine_const(other, func)
-            return res.fillna(True).astype(bool)
+            return res
 
     f.__name__ = op_name
 

pandas/tests/test_downstream.py

@@ -145,6 +145,7 @@ def _getitem_tuple(self, tup):
 
 # Cython import warning
 @pytest.mark.filterwarnings("ignore:can't resolve:ImportWarning")
+@pytest.mark.filterwarnings("ignore:RangeIndex.* is deprecated:DeprecationWarning")
 def test_pyarrow(df):
 
     pyarrow = import_module("pyarrow")  # noqa