def test_agg_grouping_is_list_tuple(ts):
df = tm.makeTimeDataFrame()
grouped = df.groupby(lambda x: x.year)
grouper = grouped.grouper.groupings[0].grouper
grouped.grouper.groupings[0] = Grouping(ts.index, list(grouper))
result = grouped.agg(np.mean)
expected = grouped.mean()
tm.assert_frame_equal(result, expected)
grouped.grouper.groupings[0] = Grouping(ts.index, tuple(grouper))
result = grouped.agg(np.mean)
expected = grouped.mean()
tm.assert_frame_equal(result, expected)
def _get_grouper(obj, key=None, axis=0, level=None, sort=True):
"""
create and return a BaseGrouper, which is an internal
mapping of how to create the grouper indexers.
This may be composed of multiple Grouping objects, indicating
multiple groupers
Groupers are ultimately index mappings. They can originate as:
index mappings, keys to columns, functions, or Groupers
Groupers enable local references to axis,level,sort, while
the passed in axis, level, and sort are 'global'.
This routine tries to figure of what the passing in references
are and then creates a Grouping for each one, combined into
a BaseGrouper.
"""
# The implementation is essentially the same as pandas.core.groupby
group_axis = obj._get_axis(axis)
# validate thatthe passed level is compatible with the passed
# axis of the object
if level is not None:
if not isinstance(group_axis, MultiIndex):
if isinstance(level, compat.string_types):
if obj.index.name != level:
raise ValueError('level name %s is not the name of the '
'index' % level)
elif level > 0:
raise ValueError('level > 0 only valid with MultiIndex')
level = None
key = group_axis
# a passed in Grouper, directly convert
if isinstance(key, Grouper):
binner, grouper, obj = key._get_grouper(obj)
if key.key is None:
return grouper, [], obj
else:
return grouper, set([key.key]), obj
# already have a BaseGrouper, just return it
elif isinstance(key, BaseGrouper):
return key, [], obj
if not isinstance(key, (tuple, list)):
keys = [key]
else:
keys = key
# what are we after, exactly?
match_axis_length = len(keys) == len(group_axis)
any_callable = any(callable(g) or isinstance(g, dict) for g in keys)
any_arraylike = any(
isinstance(g, (list, tuple, Series, Index, np.ndarray)) for g in keys)
try:
if isinstance(obj, DataFrame):
all_in_columns = all(g in obj.columns for g in keys)
else:
all_in_columns = False
except Exception:
all_in_columns = False
if (not any_callable and not all_in_columns and not any_arraylike
and match_axis_length and level is None):
keys = [com._asarray_tuplesafe(keys)]
if isinstance(level, (tuple, list)):
if key is None:
keys = [None] * len(level)
levels = level
else:
levels = [level] * len(keys)
groupings = []
exclusions = []
# if the actual grouper should be obj[key]
def is_in_axis(key):
if not _is_label_like(key):
try:
obj._data.items.get_loc(key)
except Exception:
return False
return True
# if the the grouper is obj[name]
def is_in_obj(gpr):
try:
return id(gpr) == id(obj[gpr.name])
except Exception:
return False
for i, (gpr, level) in enumerate(zip(keys, levels)):
if is_in_obj(gpr): # df.groupby(df['name'])
in_axis, name = True, gpr.name
exclusions.append(name)
elif is_in_axis(gpr): # df.groupby('name')
in_axis, name, gpr = True, gpr, obj[gpr]
exclusions.append(name)
else:
in_axis, name = False, None
if com.is_categorical_dtype(gpr) and len(gpr) != len(obj):
raise ValueError(
"Categorical dtype grouper must have len(grouper) == len(data)"
)
ping = Grouping(group_axis,
gpr,
obj=obj,
name=name,
level=level,
sort=sort,
in_axis=in_axis)
groupings.append(ping)
if len(groupings) == 0:
raise ValueError('No group keys passed!')
# create the internals grouper
# Modified to insert CustomGrouper
grouper = CustomGrouper(group_axis, groupings, sort=sort)
return grouper, exclusions, obj