Skip to content

BUG: union_categoricals can't handle NaN #13759

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

Closed
wants to merge 1 commit into from
Closed

BUG: union_categoricals can't handle NaN #13759

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
53 changes: 53 additions & 0 deletions pandas/tools/tests/test_concat.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -889,6 +889,59 @@ def test_union_categorical(self):
with tm.assertRaises(ValueError):
union_categoricals([])

def test_union_categoricals_nan(self):
# GH 13759
res = union_categoricals([pd.Categorical([1, 2, np.nan]),
pd.Categorical([3, 2, np.nan])])
exp = Categorical([1, 2, np.nan, 3, 2, np.nan])
tm.assert_categorical_equal(res, exp)

res = union_categoricals([pd.Categorical(['A', 'B']),
pd.Categorical(['B', 'B', np.nan])])
exp = Categorical(['A', 'B', 'B', 'B', np.nan])
tm.assert_categorical_equal(res, exp)

val1 = [pd.Timestamp('2011-01-01'), pd.Timestamp('2011-03-01'),
pd.NaT]
val2 = [pd.NaT, pd.Timestamp('2011-01-01'),
pd.Timestamp('2011-02-01')]

res = union_categoricals([pd.Categorical(val1), pd.Categorical(val2)])
exp = Categorical(val1 + val2,
categories=[pd.Timestamp('2011-01-01'),
pd.Timestamp('2011-03-01'),
pd.Timestamp('2011-02-01')])
tm.assert_categorical_equal(res, exp)

# all NaN
res = union_categoricals([pd.Categorical([np.nan, np.nan]),
pd.Categorical(['X'])])
exp = Categorical([np.nan, np.nan, 'X'])
tm.assert_categorical_equal(res, exp)

res = union_categoricals([pd.Categorical([np.nan, np.nan]),
pd.Categorical([np.nan, np.nan])])
exp = Categorical([np.nan, np.nan, np.nan, np.nan])
tm.assert_categorical_equal(res, exp)

def test_union_categoricals_empty(self):
# GH 13759
res = union_categoricals([pd.Categorical([]),
pd.Categorical([])])
exp = Categorical([])
tm.assert_categorical_equal(res, exp)

res = union_categoricals([pd.Categorical([]),
pd.Categorical([1.0])])
exp = Categorical([1.0])
tm.assert_categorical_equal(res, exp)

# to make dtype equal
nanc = pd.Categorical(np.array([np.nan], dtype=np.float64))
res = union_categoricals([nanc,
pd.Categorical([])])
tm.assert_categorical_equal(res, nanc)

def test_concat_bug_1719(self):
ts1 = tm.makeTimeSeries()
ts2 = tm.makeTimeSeries()[::2]
Expand Down
14 changes: 10 additions & 4 deletions pandas/types/concat.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -6,6 +6,7 @@
import pandas.tslib as tslib
from pandas import compat
from pandas.compat import map
from pandas.core.algorithms import take_1d
from .common import (is_categorical_dtype,
is_sparse,
is_datetimetz,
Expand Down Expand Up @@ -254,10 +255,15 @@ def union_categoricals(to_union):

new_codes = []
for c in to_union:
indexer = categories.get_indexer(c.categories)
new_codes.append(indexer.take(c.codes))
codes = np.concatenate(new_codes)
return Categorical(codes, categories=categories, ordered=False,
if len(c.categories) > 0:
indexer = categories.get_indexer(c.categories)
new_codes.append(take_1d(indexer, c.codes, fill_value=-1))
else:
# must be all NaN
new_codes.append(c.codes)

new_codes = np.concatenate(new_codes)
return Categorical(new_codes, categories=categories, ordered=False,
fastpath=True)


Expand Down