Skip to content

REF: Move agg helpers into apply #39498

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

Merged
merged 2 commits into from
Feb 3, 2021
Merged

REF: Move agg helpers into apply #39498

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
b221f45
REF: Move agg helpers into apply
rhshadrach Jan 31, 2021
39ee56e
Merge branch 'master' of https://github.com/pandas-dev/pandas into ag…
rhshadrach Feb 2, 2021
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
218 changes: 2 additions & 216 deletions pandas/core/aggregation.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -27,18 +27,16 @@
AggFuncType,
AggFuncTypeBase,
AggFuncTypeDict,
AggObjType,
Axis,
FrameOrSeries,
FrameOrSeriesUnion,
)

from pandas.core.dtypes.cast import is_nested_object
from pandas.core.dtypes.common import is_dict_like, is_list_like
from pandas.core.dtypes.generic import ABCDataFrame, ABCNDFrame, ABCSeries
from pandas.core.dtypes.generic import ABCDataFrame, ABCSeries

from pandas.core.algorithms import safe_sort
from pandas.core.base import DataError, SpecificationError
from pandas.core.base import SpecificationError
import pandas.core.common as com
from pandas.core.indexes.api import Index

Expand Down Expand Up @@ -532,215 +530,3 @@ def transform_str_or_callable(
return obj.apply(func, args=args, **kwargs)
except Exception:
return func(obj, *args, **kwargs)


def agg_list_like(
obj: AggObjType,
arg: List[AggFuncTypeBase],
_axis: int,
) -> FrameOrSeriesUnion:
"""
Compute aggregation in the case of a list-like argument.

Parameters
----------
obj : Pandas object to compute aggregation on.
arg : list
Aggregations to compute.
_axis : int, 0 or 1
Axis to compute aggregation on.

Returns
-------
Result of aggregation.
"""
from pandas.core.reshape.concat import concat

if _axis != 0:
raise NotImplementedError("axis other than 0 is not supported")

if obj._selected_obj.ndim == 1:
selected_obj = obj._selected_obj
else:
selected_obj = obj._obj_with_exclusions

results = []
keys = []

# degenerate case
if selected_obj.ndim == 1:
for a in arg:
colg = obj._gotitem(selected_obj.name, ndim=1, subset=selected_obj)
try:
new_res = colg.aggregate(a)

except TypeError:
pass
else:
results.append(new_res)

# make sure we find a good name
name = com.get_callable_name(a) or a
keys.append(name)

# multiples
else:
for index, col in enumerate(selected_obj):
colg = obj._gotitem(col, ndim=1, subset=selected_obj.iloc[:, index])
try:
new_res = colg.aggregate(arg)
except (TypeError, DataError):
pass
except ValueError as err:
# cannot aggregate
if "Must produce aggregated value" in str(err):
# raised directly in _aggregate_named
pass
elif "no results" in str(err):
# raised directly in _aggregate_multiple_funcs
pass
else:
raise
else:
results.append(new_res)
keys.append(col)

# if we are empty
if not len(results):
raise ValueError("no results")

try:
return concat(results, keys=keys, axis=1, sort=False)
except TypeError as err:

# we are concatting non-NDFrame objects,
# e.g. a list of scalars

from pandas import Series

result = Series(results, index=keys, name=obj.name)
if is_nested_object(result):
raise ValueError(
"cannot combine transform and aggregation operations"
) from err
return result


def agg_dict_like(
obj: AggObjType,
arg: AggFuncTypeDict,
_axis: int,
) -> FrameOrSeriesUnion:
"""
Compute aggregation in the case of a dict-like argument.

Parameters
----------
obj : Pandas object to compute aggregation on.
arg : dict
label-aggregation pairs to compute.
_axis : int, 0 or 1
Axis to compute aggregation on.

Returns
-------
Result of aggregation.
"""
is_aggregator = lambda x: isinstance(x, (list, tuple, dict))

if _axis != 0: # pragma: no cover
raise ValueError("Can only pass dict with axis=0")

selected_obj = obj._selected_obj

# if we have a dict of any non-scalars
# eg. {'A' : ['mean']}, normalize all to
# be list-likes
# Cannot use arg.values() because arg may be a Series
if any(is_aggregator(x) for _, x in arg.items()):
new_arg: AggFuncTypeDict = {}
for k, v in arg.items():
if not isinstance(v, (tuple, list, dict)):
new_arg[k] = [v]
else:
new_arg[k] = v

# the keys must be in the columns
# for ndim=2, or renamers for ndim=1

# ok for now, but deprecated
# {'A': { 'ra': 'mean' }}
# {'A': { 'ra': ['mean'] }}
# {'ra': ['mean']}

# not ok
# {'ra' : { 'A' : 'mean' }}
if isinstance(v, dict):
raise SpecificationError("nested renamer is not supported")
elif isinstance(selected_obj, ABCSeries):
raise SpecificationError("nested renamer is not supported")
elif (
isinstance(selected_obj, ABCDataFrame) and k not in selected_obj.columns
):
raise KeyError(f"Column '{k}' does not exist!")

arg = new_arg

else:
# deprecation of renaming keys
# GH 15931
keys = list(arg.keys())
if isinstance(selected_obj, ABCDataFrame) and len(
selected_obj.columns.intersection(keys)
) != len(keys):
cols = list(
safe_sort(
list(set(keys) - set(selected_obj.columns.intersection(keys))),
)
)
raise SpecificationError(f"Column(s) {cols} do not exist")

from pandas.core.reshape.concat import concat

if selected_obj.ndim == 1:
# key only used for output
colg = obj._gotitem(obj._selection, ndim=1)
results = {key: colg.agg(how) for key, how in arg.items()}
else:
# key used for column selection and output
results = {key: obj._gotitem(key, ndim=1).agg(how) for key, how in arg.items()}

# set the final keys
keys = list(arg.keys())

# Avoid making two isinstance calls in all and any below
is_ndframe = [isinstance(r, ABCNDFrame) for r in results.values()]

# combine results
if all(is_ndframe):
keys_to_use = [k for k in keys if not results[k].empty]
# Have to check, if at least one DataFrame is not empty.
keys_to_use = keys_to_use if keys_to_use != [] else keys
axis = 0 if isinstance(obj, ABCSeries) else 1
result = concat({k: results[k] for k in keys_to_use}, axis=axis)
elif any(is_ndframe):
# There is a mix of NDFrames and scalars
raise ValueError(
"cannot perform both aggregation "
"and transformation operations "
"simultaneously"
)
else:
from pandas import Series

# we have a dict of scalars
# GH 36212 use name only if obj is a series
if obj.ndim == 1:
obj = cast("Series", obj)
name = obj.name
else:
name = None

result = Series(results, name=name)

return result
Loading