def __init__(
self,
index: Index,
grouper=None,
obj: FrameOrSeries | None = None,
name: Hashable = None,
level=None,
sort: bool = True,
observed: bool = False,
in_axis: bool = False,
dropna: bool = True,
):
self.name = name
self.level = level
self.grouper = _convert_grouper(index, grouper)
self.all_grouper = None
self.index = index
self.sort = sort
self.obj = obj
self.observed = observed
self.in_axis = in_axis
self.dropna = dropna
# right place for this?
if isinstance(grouper, (Series, Index)) and name is None:
self.name = grouper.name
if isinstance(grouper, MultiIndex):
self.grouper = grouper._values
# we have a single grouper which may be a myriad of things,
# some of which are dependent on the passing in level
if level is not None:
if not isinstance(level, int):
if level not in index.names:
raise AssertionError(f"Level {level} not in index")
level = index.names.index(level)
if self.name is None:
self.name = index.names[level]
(
self.grouper,
self._codes,
self._group_index,
) = index._get_grouper_for_level(self.grouper, level)
# a passed Grouper like, directly get the grouper in the same way
# as single grouper groupby, use the group_info to get codes
elif isinstance(self.grouper, Grouper):
# get the new grouper; we already have disambiguated
# what key/level refer to exactly, don't need to
# check again as we have by this point converted these
# to an actual value (rather than a pd.Grouper)
_, grouper, _ = self.grouper._get_grouper(
# error: Value of type variable "FrameOrSeries" of "_get_grouper"
# of "Grouper" cannot be "Optional[FrameOrSeries]"
self.obj, # type: ignore[type-var]
validate=False,
)
if self.name is None:
self.name = grouper.result_index.name
self.obj = self.grouper.obj
self.grouper = grouper._get_grouper()
else:
if self.grouper is None and self.name is not None and self.obj is not None:
self.grouper = self.obj[self.name]
elif isinstance(self.grouper, (list, tuple)):
self.grouper = com.asarray_tuplesafe(self.grouper)
# a passed Categorical
elif is_categorical_dtype(self.grouper):
self.grouper, self.all_grouper = recode_for_groupby(
self.grouper, self.sort, observed)
categories = self.grouper.categories
# we make a CategoricalIndex out of the cat grouper
# preserving the categories / ordered attributes
self._codes = self.grouper.codes
if observed:
codes = algorithms.unique1d(self.grouper.codes)
codes = codes[codes != -1]
if sort or self.grouper.ordered:
codes = np.sort(codes)
else:
codes = np.arange(len(categories))
self._group_index = CategoricalIndex(
Categorical.from_codes(codes=codes,
categories=categories,
ordered=self.grouper.ordered),
name=self.name,
)
# we are done
if isinstance(self.grouper, Grouping):
self.grouper = self.grouper.grouper
# no level passed
elif not isinstance(self.grouper,
(Series, Index, ExtensionArray, np.ndarray)):
if getattr(self.grouper, "ndim", 1) != 1:
t = self.name or str(type(self.grouper))
raise ValueError(f"Grouper for '{t}' not 1-dimensional")
self.grouper = self.index.map(self.grouper)
if not (hasattr(self.grouper, "__len__")
and len(self.grouper) == len(self.index)):
grper = pprint_thing(self.grouper)
errmsg = ("Grouper result violates len(labels) == "
f"len(data)\nresult: {grper}")
self.grouper = None # Try for sanity
raise AssertionError(errmsg)
# if we have a date/time-like grouper, make sure that we have
# Timestamps like
if getattr(self.grouper, "dtype", None) is not None:
if is_datetime64_dtype(self.grouper):
self.grouper = self.grouper.astype("datetime64[ns]")
elif is_timedelta64_dtype(self.grouper):
self.grouper = self.grouper.astype("timedelta64[ns]")
def __init__(
self,
index: Index,
grouper=None,
obj: FrameOrSeries | None = None,
level=None,
sort: bool = True,
observed: bool = False,
in_axis: bool = False,
dropna: bool = True,
):
self.level = level
self._orig_grouper = grouper
self.grouper = _convert_grouper(index, grouper)
self.all_grouper = None
self.index = index
self.sort = sort
self.obj = obj
self.observed = observed
self.in_axis = in_axis
self.dropna = dropna
self._passed_categorical = False
# we have a single grouper which may be a myriad of things,
# some of which are dependent on the passing in level
ilevel = self._ilevel
if ilevel is not None:
(
self.grouper, # Index
self._codes,
self._group_index,
) = index._get_grouper_for_level(self.grouper, ilevel)
# a passed Grouper like, directly get the grouper in the same way
# as single grouper groupby, use the group_info to get codes
elif isinstance(self.grouper, Grouper):
# get the new grouper; we already have disambiguated
# what key/level refer to exactly, don't need to
# check again as we have by this point converted these
# to an actual value (rather than a pd.Grouper)
_, newgrouper, newobj = self.grouper._get_grouper(
# error: Value of type variable "FrameOrSeries" of "_get_grouper"
# of "Grouper" cannot be "Optional[FrameOrSeries]"
self.obj, # type: ignore[type-var]
validate=False,
)
self.obj = newobj
ng = newgrouper._get_grouper()
if isinstance(newgrouper, ops.BinGrouper):
# in this case we have `ng is newgrouper`
self.grouper = ng
else:
# ops.BaseGrouper
# use Index instead of ndarray so we can recover the name
self.grouper = Index(ng, name=newgrouper.result_index.name)
elif is_categorical_dtype(self.grouper):
# a passed Categorical
self._passed_categorical = True
self.grouper, self.all_grouper = recode_for_groupby(
self.grouper, self.sort, observed
)
elif not isinstance(self.grouper, (Series, Index, ExtensionArray, np.ndarray)):
# no level passed
if getattr(self.grouper, "ndim", 1) != 1:
t = self.name or str(type(self.grouper))
raise ValueError(f"Grouper for '{t}' not 1-dimensional")
self.grouper = self.index.map(self.grouper)
if not (
hasattr(self.grouper, "__len__")
and len(self.grouper) == len(self.index)
):
grper = pprint_thing(self.grouper)
errmsg = (
"Grouper result violates len(labels) == "
f"len(data)\nresult: {grper}"
)
self.grouper = None # Try for sanity
raise AssertionError(errmsg)
if isinstance(self.grouper, np.ndarray):
# if we have a date/time-like grouper, make sure that we have
# Timestamps like
self.grouper = sanitize_to_nanoseconds(self.grouper)
