Skip to content

REF: avoid result=None case in _python_agg_general #29499

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 6 commits into from
Nov 12, 2019
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
10 changes: 6 additions & 4 deletions pandas/core/groupby/groupby.py
Original file line number Diff line number Diff line change
Expand Up @@ -898,6 +898,10 @@ def _python_agg_general(self, func, *args, **kwargs):
# iterate through "columns" ex exclusions to populate output dict
output = {}
for name, obj in self._iterate_slices():
if self.grouper.ngroups == 0:
# agg_series below assumes ngroups > 0
continue

try:
# if this function is invalid for this dtype, we will ignore it.
func(obj[:0])
Expand All @@ -911,10 +915,8 @@ def _python_agg_general(self, func, *args, **kwargs):
pass

result, counts = self.grouper.agg_series(obj, f)
if result is not None:
# TODO: only 3 test cases get None here, do something
# in those cases
output[name] = self._try_cast(result, obj, numeric_only=True)
assert result is not None
output[name] = self._try_cast(result, obj, numeric_only=True)

if len(output) == 0:
return self._python_apply_general(f)
Expand Down
20 changes: 13 additions & 7 deletions pandas/core/groupby/ops.py
Original file line number Diff line number Diff line change
Expand Up @@ -583,6 +583,9 @@ def _transform(
return result

def agg_series(self, obj: Series, func):
# Caller is responsible for checking ngroups != 0
assert self.ngroups != 0

if is_extension_array_dtype(obj.dtype) and obj.dtype.kind != "M":
# _aggregate_series_fast would raise TypeError when
# calling libreduction.Slider
Expand All @@ -608,8 +611,10 @@ def agg_series(self, obj: Series, func):
return self._aggregate_series_pure_python(obj, func)

def _aggregate_series_fast(self, obj, func):
# At this point we have already checked that obj.index is not a MultiIndex
# and that obj is backed by an ndarray, not ExtensionArray
# At this point we have already checked that
# - obj.index is not a MultiIndex
# - obj is backed by an ndarray, not ExtensionArray
# - ngroups != 0
func = self._is_builtin_func(func)

group_index, _, ngroups = self.group_info
Expand Down Expand Up @@ -642,11 +647,9 @@ def _aggregate_series_pure_python(self, obj, func):
counts[label] = group.shape[0]
result[label] = res

if result is not None:
# if splitter is empty, result can be None, in which case
# maybe_convert_objects would raise TypeError
result = lib.maybe_convert_objects(result, try_float=0)
# TODO: try_cast back to EA?
assert result is not None
result = lib.maybe_convert_objects(result, try_float=0)
# TODO: try_cast back to EA?

return result, counts

Expand Down Expand Up @@ -797,6 +800,9 @@ def groupings(self):
]

def agg_series(self, obj: Series, func):
# Caller is responsible for checking ngroups != 0
assert self.ngroups != 0

if is_extension_array_dtype(obj.dtype):
# pre-empty SeriesBinGrouper from raising TypeError
# TODO: watch out, this can return None
Expand Down