CLN core.groupby (#29389)

Author: jbrockmendel

pandas/core/base.py

@@ -586,9 +586,16 @@ def _aggregate_multiple_funcs(self, arg, _level, _axis):
                     new_res = colg.aggregate(arg)
                 except (TypeError, DataError):
                     pass
-                except ValueError:
+                except ValueError as err:
                     # cannot aggregate
-                    continue
+                    if "Must produce aggregated value" in str(err):
+                        # raised directly in _aggregate_named
+                        pass
+                    elif "no results" in str(err):
+                        # raised direcly in _aggregate_multiple_funcs
+                        pass
+                    else:
+                        raise
                 else:
                     results.append(new_res)
                     keys.append(col)

pandas/core/groupby/generic.py

@@ -244,7 +244,7 @@ def aggregate(self, func=None, *args, **kwargs):
         if isinstance(func, str):
             return getattr(self, func)(*args, **kwargs)
 
-        if isinstance(func, abc.Iterable):
+        elif isinstance(func, abc.Iterable):
             # Catch instances of lists / tuples
             # but not the class list / tuple itself.
             func = _maybe_mangle_lambdas(func)
@@ -261,8 +261,6 @@ def aggregate(self, func=None, *args, **kwargs):
 
             try:
                 return self._python_agg_general(func, *args, **kwargs)
-            except (AssertionError, TypeError):
-                raise
             except (ValueError, KeyError, AttributeError, IndexError):
                 # TODO: IndexError can be removed here following GH#29106
                 # TODO: AttributeError is caused by _index_data hijinx in
@@ -325,7 +323,7 @@ def _aggregate_multiple_funcs(self, arg, _level):
             if name in results:
                 raise SpecificationError(
                     "Function names must be unique, found multiple named "
-                    "{}".format(name)
+                    "{name}".format(name=name)
                 )
 
             # reset the cache so that we
@@ -1464,8 +1462,6 @@ def _transform_item_by_item(self, obj, wrapper):
         for i, col in enumerate(obj):
             try:
                 output[col] = self[col].transform(wrapper)
-            except AssertionError:
-                raise
             except TypeError:
                 # e.g. trying to call nanmean with string values
                 pass
@@ -1538,8 +1534,8 @@ def filter(self, func, dropna=True, *args, **kwargs):
             else:
                 # non scalars aren't allowed
                 raise TypeError(
-                    "filter function returned a %s, "
-                    "but expected a scalar bool" % type(res).__name__
+                    "filter function returned a {typ}, "
+                    "but expected a scalar bool".format(typ=type(res).__name__)
                 )
 
         return self._apply_filter(indices, dropna)

pandas/core/groupby/groupby.py

@@ -344,7 +344,7 @@ def __init__(
         self,
         obj: NDFrame,
         keys=None,
-        axis=0,
+        axis: int = 0,
         level=None,
         grouper=None,
         exclusions=None,
@@ -561,7 +561,9 @@ def __getattr__(self, attr):
             return self[attr]
 
         raise AttributeError(
-            "%r object has no attribute %r" % (type(self).__name__, attr)
+            "'{typ}' object has no attribute '{attr}'".format(
+                typ=type(self).__name__, attr=attr
+            )
         )
 
     @Substitution(
@@ -2486,6 +2488,6 @@ def groupby(obj, by, **kwds):
 
         klass = DataFrameGroupBy
     else:
-        raise TypeError("invalid type: {}".format(obj))
+        raise TypeError("invalid type: {obj}".format(obj=obj))
 
     return klass(obj, by, **kwds)

pandas/core/groupby/grouper.py

@@ -172,7 +172,9 @@ def _set_grouper(self, obj, sort=False):
                 ax = self._grouper.take(obj.index)
             else:
                 if key not in obj._info_axis:
-                    raise KeyError("The grouper name {0} is not found".format(key))
+                    raise KeyError(
+                        "The grouper name {key} is not found".format(key=key)
+                    )
                 ax = Index(obj[key], name=key)
 
         else:
@@ -188,7 +190,9 @@ def _set_grouper(self, obj, sort=False):
 
                 else:
                     if level not in (0, ax.name):
-                        raise ValueError("The level {0} is not valid".format(level))
+                        raise ValueError(
+                            "The level {level} is not valid".format(level=level)
+                        )
 
         # possibly sort
         if (self.sort or sort) and not ax.is_monotonic:
@@ -278,7 +282,9 @@ def __init__(
         if level is not None:
             if not isinstance(level, int):
                 if level not in index.names:
-                    raise AssertionError("Level {} not in index".format(level))
+                    raise AssertionError(
+                        "Level {level} not in index".format(level=level)
+                    )
                 level = index.names.index(level)
 
             if self.name is None:
@@ -344,15 +350,17 @@ def __init__(
             ):
                 if getattr(self.grouper, "ndim", 1) != 1:
                     t = self.name or str(type(self.grouper))
-                    raise ValueError("Grouper for '{}' not 1-dimensional".format(t))
+                    raise ValueError("Grouper for '{t}' not 1-dimensional".format(t=t))
                 self.grouper = self.index.map(self.grouper)
                 if not (
                     hasattr(self.grouper, "__len__")
                     and len(self.grouper) == len(self.index)
                 ):
                     errmsg = (
                         "Grouper result violates len(labels) == "
-                        "len(data)\nresult: %s" % pprint_thing(self.grouper)
+                        "len(data)\nresult: {grper}".format(
+                            grper=pprint_thing(self.grouper)
+                        )
                     )
                     self.grouper = None  # Try for sanity
                     raise AssertionError(errmsg)
@@ -426,7 +434,7 @@ def groups(self):
 def _get_grouper(
     obj: NDFrame,
     key=None,
-    axis=0,
+    axis: int = 0,
     level=None,
     sort=True,
     observed=False,
@@ -493,7 +501,9 @@ def _get_grouper(
             if isinstance(level, str):
                 if obj.index.name != level:
                     raise ValueError(
-                        "level name {} is not the name of the index".format(level)
+                        "level name {level} is not the name of the index".format(
+                            level=level
+                        )
                     )
             elif level > 0 or level < -1:
                 raise ValueError("level > 0 or level < -1 only valid with MultiIndex")
@@ -582,7 +592,7 @@ def _get_grouper(
     exclusions = []
 
     # if the actual grouper should be obj[key]
-    def is_in_axis(key):
+    def is_in_axis(key) -> bool:
         if not _is_label_like(key):
             items = obj._data.items
             try:
@@ -594,7 +604,7 @@ def is_in_axis(key):
         return True
 
     # if the grouper is obj[name]
-    def is_in_obj(gpr):
+    def is_in_obj(gpr) -> bool:
         if not hasattr(gpr, "name"):
             return False
         try:

pandas/core/groupby/ops.py

@@ -7,6 +7,7 @@
 """
 
 import collections
+from typing import List, Optional
 
 import numpy as np
 
@@ -385,7 +386,7 @@ def get_func(fname):
 
         return func
 
-    def _cython_operation(self, kind, values, how, axis, min_count=-1, **kwargs):
+    def _cython_operation(self, kind: str, values, how, axis, min_count=-1, **kwargs):
         assert kind in ["transform", "aggregate"]
         orig_values = values
 
@@ -398,16 +399,18 @@ def _cython_operation(self, kind, values, how, axis, min_count=-1, **kwargs):
         # categoricals are only 1d, so we
         # are not setup for dim transforming
         if is_categorical_dtype(values) or is_sparse(values):
-            raise NotImplementedError("{} dtype not supported".format(values.dtype))
+            raise NotImplementedError(
+                "{dtype} dtype not supported".format(dtype=values.dtype)
+            )
         elif is_datetime64_any_dtype(values):
             if how in ["add", "prod", "cumsum", "cumprod"]:
                 raise NotImplementedError(
-                    "datetime64 type does not support {} operations".format(how)
+                    "datetime64 type does not support {how} operations".format(how=how)
                 )
         elif is_timedelta64_dtype(values):
             if how in ["prod", "cumprod"]:
                 raise NotImplementedError(
-                    "timedelta64 type does not support {} operations".format(how)
+                    "timedelta64 type does not support {how} operations".format(how=how)
                 )
 
         if is_datetime64tz_dtype(values.dtype):
@@ -513,7 +516,7 @@ def _cython_operation(self, kind, values, how, axis, min_count=-1, **kwargs):
             result = result[:, 0]
 
         if how in self._name_functions:
-            names = self._name_functions[how]()
+            names = self._name_functions[how]()  # type: Optional[List[str]]
         else:
             names = None
 

pandas/core/resample.py

@@ -361,8 +361,6 @@ def _groupby_and_aggregate(self, how, grouper=None, *args, **kwargs):
                 result = grouped._aggregate_item_by_item(how, *args, **kwargs)
             else:
                 result = grouped.aggregate(how, *args, **kwargs)
-        except AssertionError:
-            raise
         except DataError:
             # we have a non-reducing function; try to evaluate
             result = grouped.apply(how, *args, **kwargs)
@@ -1450,7 +1448,7 @@ def _get_resampler(self, obj, kind=None):
         raise TypeError(
             "Only valid with DatetimeIndex, "
             "TimedeltaIndex or PeriodIndex, "
-            "but got an instance of %r" % type(ax).__name__
+            "but got an instance of '{typ}'".format(typ=type(ax).__name__)
         )
 
     def _get_grouper(self, obj, validate=True):
@@ -1463,7 +1461,7 @@ def _get_time_bins(self, ax):
         if not isinstance(ax, DatetimeIndex):
             raise TypeError(
                 "axis must be a DatetimeIndex, but got "
-                "an instance of %r" % type(ax).__name__
+                "an instance of {typ}".format(typ=type(ax).__name__)
             )
 
         if len(ax) == 0:
@@ -1539,7 +1537,7 @@ def _get_time_delta_bins(self, ax):
         if not isinstance(ax, TimedeltaIndex):
             raise TypeError(
                 "axis must be a TimedeltaIndex, but got "
-                "an instance of %r" % type(ax).__name__
+                "an instance of {typ}".format(typ=type(ax).__name__)
             )
 
         if not len(ax):
@@ -1564,7 +1562,7 @@ def _get_time_period_bins(self, ax):
         if not isinstance(ax, DatetimeIndex):
             raise TypeError(
                 "axis must be a DatetimeIndex, but got "
-                "an instance of %r" % type(ax).__name__
+                "an instance of {typ}".format(typ=type(ax).__name__)
             )
 
         freq = self.freq
@@ -1586,7 +1584,7 @@ def _get_period_bins(self, ax):
         if not isinstance(ax, PeriodIndex):
             raise TypeError(
                 "axis must be a PeriodIndex, but got "
-                "an instance of %r" % type(ax).__name__
+                "an instance of {typ}".format(typ=type(ax).__name__)
             )
 
         memb = ax.asfreq(self.freq, how=self.convention)