Skip to content

CLN: _wrap_applied_output #35412

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.

Sign up for GitHub

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

Closed
wants to merge 5 commits into from
Closed

CLN: _wrap_applied_output #35412

Show file tree
Hide file tree
Changes from 3 commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
aa02b83
CLN: Clean/Simplify _wrap_applied_output
rhshadrach Jul 25, 2020
21e1fca
Refactored if-else.
rhshadrach Aug 4, 2020
0e16de3
Merge branch 'master' of https://github.com/pandas-dev/pandas into ap…
rhshadrach Aug 4, 2020
bb032ea
Merge remote-tracking branch 'upstream/master' into apply_output_cleanup
rhshadrach Aug 13, 2020
059405c
Reworked logic for non-NDFrame cases
rhshadrach Aug 14, 2020
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
235 changes: 88 additions & 147 deletions pandas/core/groupby/generic.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1213,171 +1213,112 @@ def _wrap_applied_output(self, keys, values, not_indexed_same=False):
if len(keys) == 0:
return self.obj._constructor(index=keys)

key_names = self.grouper.names

# GH12824
# GH12824 - If first value is None, can't assume all are None
first_not_none = next(com.not_none(*values), None)

if first_not_none is None:
# GH9684. If all values are None, then this will throw an error.
# We'd prefer it return an empty dataframe.
# GH9684 - All values are None, return an empty frame.
return self.obj._constructor()
elif isinstance(first_not_none, DataFrame):

if isinstance(first_not_none, DataFrame):
return self._concat_objects(keys, values, not_indexed_same=not_indexed_same)
else:
if len(self.grouper.groupings) > 1:
key_index = self.grouper.result_index

key_index = self.grouper.result_index if self.as_index else None

if isinstance(first_not_none, NDFrame):

# this is to silence a DeprecationWarning
# TODO: Remove when default dtype of empty Series is object
kwargs = first_not_none._construct_axes_dict()
if isinstance(first_not_none, Series):
backup = create_series_with_explicit_dtype(
**kwargs, dtype_if_empty=object
)
else:
ping = self.grouper.groupings[0]
if len(keys) == ping.ngroups:
key_index = ping.group_index
key_index.name = key_names[0]
backup = first_not_none._constructor(**kwargs)

key_lookup = Index(keys)
indexer = key_lookup.get_indexer(key_index)
values = [x if (x is not None) else backup for x in values]
else:
# values are not series or array-like but scalars
# self._selection_name not passed through to Series as the
# result should not take the name of original selection
# of columns
if self.as_index:
return self.obj._constructor_sliced(values, index=key_index)
else:
result = DataFrame(values, index=key_index, columns=[self._selection])
self._insert_inaxis_grouper_inplace(result)
return result

v = values[0]

if not isinstance(v, ABCSeries):
# GH1738: values is list of arrays of unequal lengths
# TODO: sure this is right? we used to do this
# after raising AttributeError above
return self.obj._constructor_sliced(
values, index=key_index, name=self._selection_name
)

# reorder the values
values = [values[i] for i in indexer]
all_indexed_same = all_indexes_same((x.index for x in values))

# GH3596 - provide a reduction (Frame -> Series) if groups are unique
if self.squeeze:
# assign the name to this series
applied_index = self._selected_obj._get_axis(self.axis)
if len(values) == 1 and applied_index.nlevels == 1:
values[0].name = keys[0]

# GH2893
# we have series in the values array, we want to
# produce a series:
# if any of the sub-series are not indexed the same
# OR we don't have a multi-index and we have only a
# single values
return self._concat_objects(
keys, values, not_indexed_same=not_indexed_same
)

# update due to the potential reorder
first_not_none = next(com.not_none(*values), None)
else:
# still a series
# path added as of GH 5545
elif all_indexed_same:
from pandas.core.reshape.concat import concat

key_index = Index(keys, name=key_names[0])
return concat(values)

# don't use the key indexer
if not self.as_index:
key_index = None
if not all_indexed_same:
# GH 8467
return self._concat_objects(keys, values, not_indexed_same=True)

# make Nones an empty object
if first_not_none is None:
return self.obj._constructor()
elif isinstance(first_not_none, NDFrame):
stacked_values = np.vstack([np.asarray(v) for v in values])

# this is to silence a DeprecationWarning
# TODO: Remove when default dtype of empty Series is object
kwargs = first_not_none._construct_axes_dict()
if isinstance(first_not_none, Series):
backup = create_series_with_explicit_dtype(
**kwargs, dtype_if_empty=object
)
else:
backup = first_not_none._constructor(**kwargs)

values = [x if (x is not None) else backup for x in values]

v = values[0]

if isinstance(v, (np.ndarray, Index, Series)) or not self.as_index:
if isinstance(v, Series):
applied_index = self._selected_obj._get_axis(self.axis)
all_indexed_same = all_indexes_same([x.index for x in values])
singular_series = len(values) == 1 and applied_index.nlevels == 1

# GH3596
# provide a reduction (Frame -> Series) if groups are
# unique
if self.squeeze:
# assign the name to this series
if singular_series:
values[0].name = keys[0]

# GH2893
# we have series in the values array, we want to
# produce a series:
# if any of the sub-series are not indexed the same
# OR we don't have a multi-index and we have only a
# single values
return self._concat_objects(
keys, values, not_indexed_same=not_indexed_same
)

# still a series
# path added as of GH 5545
elif all_indexed_same:
from pandas.core.reshape.concat import concat

return concat(values)

if not all_indexed_same:
# GH 8467
return self._concat_objects(keys, values, not_indexed_same=True)

if self.axis == 0 and isinstance(v, ABCSeries):
# GH6124 if the list of Series have a consistent name,
# then propagate that name to the result.
index = v.index.copy()
if index.name is None:
# Only propagate the series name to the result
# if all series have a consistent name. If the
# series do not have a consistent name, do
# nothing.
names = {v.name for v in values}
if len(names) == 1:
index.name = list(names)[0]

# normally use vstack as its faster than concat
# and if we have mi-columns
if (
isinstance(v.index, MultiIndex)
or key_index is None
or isinstance(key_index, MultiIndex)
):
stacked_values = np.vstack([np.asarray(v) for v in values])
result = self.obj._constructor(
stacked_values, index=key_index, columns=index
)
else:
# GH5788 instead of stacking; concat gets the
# dtypes correct
from pandas.core.reshape.concat import concat

result = concat(
values,
keys=key_index,
names=key_index.names,
axis=self.axis,
).unstack()
result.columns = index
elif isinstance(v, ABCSeries):
stacked_values = np.vstack([np.asarray(v) for v in values])
result = self.obj._constructor(
stacked_values.T, index=v.index, columns=key_index
)
elif not self.as_index:
# We add grouping column below, so create a frame here
result = DataFrame(
values, index=key_index, columns=[self._selection]
)
else:
# GH#1738: values is list of arrays of unequal lengths
# fall through to the outer else clause
# TODO: sure this is right? we used to do this
# after raising AttributeError above
return self.obj._constructor_sliced(
values, index=key_index, name=self._selection_name
)
if self.axis == 0:
index = key_index
columns = v.index.copy()
if columns.name is None:
# GH6124 - propagate name of Series when it's consistent
names = {v.name for v in values}
if len(names) == 1:
columns.name = list(names)[0]
else:
index = v.index
columns = key_index
stacked_values = stacked_values.T

# if we have date/time like in the original, then coerce dates
# as we are stacking can easily have object dtypes here
so = self._selected_obj
if so.ndim == 2 and so.dtypes.apply(needs_i8_conversion).any():
result = _recast_datetimelike_result(result)
else:
result = result._convert(datetime=True)
result = self.obj._constructor(stacked_values, index=index, columns=columns)

if not self.as_index:
self._insert_inaxis_grouper_inplace(result)
# if we have date/time like in the original, then coerce dates
# as we are stacking can easily have object dtypes here
so = self._selected_obj
if so.ndim == 2 and so.dtypes.apply(needs_i8_conversion).any():
result = _recast_datetimelike_result(result)
else:
result = result._convert(datetime=True)

return self._reindex_output(result)
if not self.as_index:
self._insert_inaxis_grouper_inplace(result)

# values are not series or array-like but scalars
else:
# self._selection_name not passed through to Series as the
# result should not take the name of original selection
# of columns
return self.obj._constructor_sliced(values, index=key_index)
return self._reindex_output(result)

def _transform_general(
self, func, *args, engine="cython", engine_kwargs=None, **kwargs
Expand Down
7 changes: 4 additions & 3 deletions pandas/core/indexes/api.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -298,15 +298,16 @@ def all_indexes_same(indexes):

Parameters
----------
indexes : list of Index objects
indexes : iterable of Index objects

Returns
-------
bool
True if all indexes contain the same elements, False otherwise.
"""
first = indexes[0]
for index in indexes[1:]:
itr = iter(indexes)
first = next(itr)
for index in itr:
if not first.equals(index):
return False
return True
8 changes: 5 additions & 3 deletions pandas/tests/groupby/test_apply.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -868,13 +868,15 @@ def test_apply_multi_level_name(category):
b = [1, 2] * 5
if category:
b = pd.Categorical(b, categories=[1, 2, 3])
expected_index = pd.CategoricalIndex([1, 2], categories=[1, 2, 3], name="B")
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Is there an open issue for this?

Copy link
Member Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I don't believe so. There is only one issue tagged with categorical, groupby, and apply which is not relevant. I also took a look through those tagged as categorical and groupby and didn't see anything either.

Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Can you add a whatsnew for this? Something along the lines of groupby apply will now maintain a CategoricalIndex (assuming that is now the case)

else:
expected_index = pd.Index([1, 2], name="B")
df = pd.DataFrame(
{"A": np.arange(10), "B": b, "C": list(range(10)), "D": list(range(10))}
).set_index(["A", "B"])
result = df.groupby("B").apply(lambda x: x.sum())
expected = pd.DataFrame(
{"C": [20, 25], "D": [20, 25]}, index=pd.Index([1, 2], name="B")
)

expected = pd.DataFrame({"C": [20, 25], "D": [20, 25]}, index=expected_index)
tm.assert_frame_equal(result, expected)
assert df.index.names == ["A", "B"]

Expand Down