def _make_labels(self):
if self._was_factor: # pragma: no cover
raise Exception('Should not call this method grouping by level')
else:
values = self.grouper
if values.dtype != np.object_:
values = values.astype('O')
# khash
rizer = lib.Factorizer(len(values))
labels, counts = rizer.factorize(values, sort=False)
uniques = Index(rizer.uniques, name=self.name)
if self.sort and len(counts) > 0:
sorter = uniques.argsort()
reverse_indexer = np.empty(len(sorter), dtype=np.int32)
reverse_indexer.put(sorter, np.arange(len(sorter)))
mask = labels < 0
labels = reverse_indexer.take(labels)
np.putmask(labels, mask, -1)
uniques = uniques.take(sorter)
counts = counts.take(sorter)
self._labels = labels
self._group_index = uniques
self._counts = counts
def _set_grouper(self, obj, sort=False):
"""
given an object and the specifications, setup the internal grouper
for this particular specification
Parameters
----------
obj : the subject object
sort : bool, default False
whether the resulting grouper should be sorted
"""
if self.key is not None and self.level is not None:
raise ValueError(
"The Grouper cannot specify both a key and a level!")
# Keep self.grouper value before overriding
if self._grouper is None:
self._grouper = self.grouper
# the key must be a valid info item
if self.key is not None:
key = self.key
# The 'on' is already defined
if getattr(self.grouper, "name", None) == key and isinstance(
obj, ABCSeries):
ax = self._grouper.take(obj.index)
else:
if key not in obj._info_axis:
raise KeyError(
"The grouper name {0} is not found".format(key))
ax = Index(obj[key], name=key)
else:
ax = obj._get_axis(self.axis)
if self.level is not None:
level = self.level
# if a level is given it must be a mi level or
# equivalent to the axis name
if isinstance(ax, MultiIndex):
level = ax._get_level_number(level)
ax = Index(ax._get_level_values(level),
name=ax.names[level])
else:
if level not in (0, ax.name):
raise ValueError(
"The level {0} is not valid".format(level))
# possibly sort
if (self.sort or sort) and not ax.is_monotonic:
# use stable sort to support first, last, nth
indexer = self.indexer = ax.argsort(kind="mergesort")
ax = ax.take(indexer)
obj = obj.take(indexer, axis=self.axis, is_copy=False)
self.obj = obj
self.grouper = ax
return self.grouper
def _set_grouper(self, obj, sort=False):
"""
given an object and the specifications, setup the internal grouper
for this particular specification
Parameters
----------
obj : the subject object
sort : bool, default False
whether the resulting grouper should be sorted
"""
if self.key is not None and self.level is not None:
raise ValueError(
"The Grouper cannot specify both a key and a level!")
# Keep self.grouper value before overriding
if self._grouper is None:
self._grouper = self.grouper
# the key must be a valid info item
if self.key is not None:
key = self.key
# The 'on' is already defined
if (getattr(self.grouper, 'name', None) == key and
isinstance(obj, ABCSeries)):
ax = self._grouper.take(obj.index)
else:
if key not in obj._info_axis:
raise KeyError(
"The grouper name {0} is not found".format(key))
ax = Index(obj[key], name=key)
else:
ax = obj._get_axis(self.axis)
if self.level is not None:
level = self.level
# if a level is given it must be a mi level or
# equivalent to the axis name
if isinstance(ax, MultiIndex):
level = ax._get_level_number(level)
ax = Index(ax._get_level_values(level),
name=ax.names[level])
else:
if level not in (0, ax.name):
raise ValueError(
"The level {0} is not valid".format(level))
# possibly sort
if (self.sort or sort) and not ax.is_monotonic:
# use stable sort to support first, last, nth
indexer = self.indexer = ax.argsort(kind='mergesort')
ax = ax.take(indexer)
obj = obj._take(indexer, axis=self.axis, is_copy=False)
self.obj = obj
self.grouper = ax
return self.grouper
def _sort_labels(uniques, left, right):
if not isinstance(uniques, np.ndarray):
# tuplesafe
uniques = Index(uniques).values
sorter = uniques.argsort()
reverse_indexer = np.empty(len(sorter), dtype=np.int32)
reverse_indexer.put(sorter, np.arange(len(sorter)))
return reverse_indexer.take(left), reverse_indexer.take(right)
def _sort_labels(uniques, left, right):
if not isinstance(uniques, np.ndarray):
# tuplesafe
uniques = Index(uniques).values
sorter = uniques.argsort()
reverse_indexer = np.empty(len(sorter), dtype=np.int32)
reverse_indexer.put(sorter, np.arange(len(sorter)))
return reverse_indexer.take(left), reverse_indexer.take(right)
def unique_with_labels(values):
from pandas.core.index import Index
rizer = lib.Factorizer(len(values))
labels, _ = rizer.factorize(values, sort=False)
uniques = Index(rizer.uniques)
try:
sorter = uniques.argsort()
reverse_indexer = np.empty(len(sorter), dtype='i4')
reverse_indexer.put(sorter, np.arange(len(sorter)))
labels = reverse_indexer.take(labels)
uniques = uniques.take(sorter)
except TypeError:
pass
return uniques, labels
def _sort_labels(uniques, left, right):
if not isinstance(uniques, np.ndarray):
# tuplesafe
uniques = Index(uniques).values
sorter = uniques.argsort()
reverse_indexer = np.empty(len(sorter), dtype=np.int64)
reverse_indexer.put(sorter, np.arange(len(sorter)))
new_left = reverse_indexer.take(com._ensure_platform_int(left))
np.putmask(new_left, left == -1, -1)
new_right = reverse_indexer.take(com._ensure_platform_int(right))
np.putmask(new_right, right == -1, -1)
return new_left, new_right