def _compute_drop_idx(self):
"""Helper to compute indices to drop from category to drop"""
if self.drop is None:
return None
elif isinstance(self.drop, str) and self.drop == 'first':
return {feature: 0 for feature in self._encoders.keys()}
elif isinstance(self.drop, (dict, list)):
if isinstance(self.drop, list):
self.drop = dict(zip(range(len(self.drop)), self.drop))
if len(self.drop.keys()) != len(self._encoders):
msg = ("`drop` should have as many columns as the number "
"of features ({}), got {}")
raise ValueError(msg.format(len(self._encoders),
len(self.drop.keys())))
drop_idx = dict()
for feature in self.drop.keys():
self.drop[feature] = Series(self.drop[feature])
if len(self.drop[feature]) != 1:
msg = ("Trying to drop multiple values for feature {}, "
"this is not supported.").format(feature)
raise ValueError(msg)
cats = self._encoders[feature].classes_
if not self.drop[feature].isin(cats).all():
msg = ("Some categories for feature {} were supposed "
"to be dropped, but were not found in the encoder "
"categories.".format(feature))
raise ValueError(msg)
cats = Series(cats)
idx = cats.isin(self.drop[feature])
drop_idx[feature] = cp.asarray(cats[idx].index)
return drop_idx
else:
msg = ("Wrong input for parameter `drop`. Expected "
"'first', None or a dict, got {}")
raise ValueError(msg.format(type(self.drop)))
def remove_categories(self, removals, **kwargs):
from cudf import Series
cats = self.categories.to_series()
removals = Series(removals, dtype=cats.dtype)
removals_mask = removals.isin(cats)
# ensure all the removals are in the current categories
# list. If not, raise an error to match Pandas behavior
if not removals_mask.all():
vals = removals[~removals_mask].to_array()
msg = "removals must all be in old categories: {}".format(vals)
raise ValueError(msg)
return self.set_categories(cats[~cats.isin(removals)], **kwargs)
def remove_categories(self, removals, **kwargs):
"""
Remove the specified categories.
`removals` must be included in the
old categories. Values which were in the
removed categories will be set to null.
Parameters
----------
removals : category or list-like of category
The categories which should be removed.
inplace : bool, default False
Whether or not to remove the categories
inplace or return a copy of this categorical
with removed categories.
Returns
-------
cat
Categorical with removed categories or None
if inplace.
Examples
--------
>>> import cudf
>>> s = cudf.Series([10, 1, 1, 2, 10, 2, 10], dtype="category")
>>> s
0 10
1 1
2 1
3 2
4 10
5 2
6 10
dtype: category
Categories (3, int64): [1, 2, 10]
>>> s.cat.remove_categories([1])
0 10
1 null
2 null
3 2
4 10
5 2
6 10
dtype: category
Categories (2, int64): [2, 10]
>>> s
0 10
1 1
2 1
3 2
4 10
5 2
6 10
dtype: category
Categories (3, int64): [1, 2, 10]
>>> s.cat.remove_categories([10], inplace=True)
>>> s
0 null
1 1
2 1
3 2
4 null
5 2
6 null
dtype: category
Categories (2, int64): [1, 2]
"""
from cudf import Series
cats = self.categories.to_series()
removals = Series(removals, dtype=cats.dtype)
removals_mask = removals.isin(cats)
# ensure all the removals are in the current categories
# list. If not, raise an error to match Pandas behavior
if not removals_mask.all():
vals = removals[~removals_mask].to_array()
msg = "removals must all be in old categories: {}".format(vals)
raise ValueError(msg)
new_categories = cats[~cats.isin(removals)]._column
out_col = self._column
if not self._categories_equal(new_categories, **kwargs):
out_col = self._set_categories(new_categories, **kwargs)
return self._return_or_inplace(out_col, **kwargs)
