Skip to content

BUG: Fix MultiIndex from_tuples on tuples with NaNs #60944

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.

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

Merged
merged 19 commits into from
Mar 7, 2025
Merged
Show file tree
Hide file tree
Changes from 5 commits
Commits
Show all changes
19 commits
Select commit Hold shift + click to select a range
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
2 changes: 1 addition & 1 deletion doc/source/whatsnew/v3.0.0.rst
Original file line number Diff line number Diff line change
Expand Up @@ -705,7 +705,7 @@ MultiIndex
- :meth:`MultiIndex.insert` would not insert NA value correctly at unified location of index -1 (:issue:`59003`)
- :func:`MultiIndex.get_level_values` accessing a :class:`DatetimeIndex` does not carry the frequency attribute along (:issue:`58327`, :issue:`57949`)
- Bug in :class:`DataFrame` arithmetic operations in case of unaligned MultiIndex columns (:issue:`60498`)
-
- Bug in :meth:`MultiIndex.from_tuples` causing wrong output with input of type tuples having NaN values (:issue:`60695`)

I/O
^^^
Expand Down
3 changes: 2 additions & 1 deletion pandas/core/indexes/multi.py
Original file line number Diff line number Diff line change
Expand Up @@ -9,6 +9,7 @@
Sequence,
)
from functools import wraps
from itertools import zip_longest
from sys import getsizeof
from typing import (
TYPE_CHECKING,
Expand Down Expand Up @@ -588,7 +589,7 @@ def from_tuples(
elif isinstance(tuples, list):
arrays = list(lib.to_object_array_tuples(tuples).T)
else:
arrs = zip(*tuples)
arrs = zip_longest(*tuples, fillvalue=np.nan)
arrays = cast(list[Sequence[Hashable]], arrs)

return cls.from_arrays(arrays, sortorder=sortorder, names=names)
Expand Down
22 changes: 22 additions & 0 deletions pandas/tests/indexes/multi/test_constructors.py
Original file line number Diff line number Diff line change
Expand Up @@ -410,6 +410,28 @@ def test_from_tuples_with_tuple_label():
tm.assert_frame_equal(expected, result)


@pytest.mark.parametrize(
"keys, expected",
(
((("l1",), ("l1", "l2")), (("l1", np.nan), ("l1", "l2"))),
(
(
(
"l1",
"l2",
),
("l1",),
),
(("l1", "l2"), ("l1", np.nan)),
),
),
)
def test_from_tuples_with_various_tuple_lengths(keys, expected):
# GH 60695
idx = MultiIndex.from_tuples(keys)
assert tuple(idx) == expected


# ----------------------------------------------------------------------------
# from_product
# ----------------------------------------------------------------------------
Expand Down
4 changes: 3 additions & 1 deletion pandas/tests/series/methods/test_map.py
Original file line number Diff line number Diff line change
Expand Up @@ -288,7 +288,9 @@ def test_map_dict_with_tuple_keys():
df = DataFrame({"a": [(1,), (2,), (3, 4), (5, 6)]})
label_mappings = {(1,): "A", (2,): "B", (3, 4): "A", (5, 6): "B"}

df["labels"] = df["a"].map(label_mappings)
# GH 60695
df["labels"] = df["a"].apply(lambda x: label_mappings.get(x, None))

df["expected_labels"] = Series(["A", "B", "A", "B"], index=df.index)
# All labels should be filled now
tm.assert_series_equal(df["labels"], df["expected_labels"], check_names=False)
Expand Down
15 changes: 15 additions & 0 deletions pandas/tests/series/test_constructors.py
Original file line number Diff line number Diff line change
Expand Up @@ -1447,6 +1447,12 @@ def test_constructor_dict_of_tuples(self):
expected = Series([3, 6], index=MultiIndex.from_tuples([(1, 2), (None, 5)]))
tm.assert_series_equal(result, expected)

# GH 60695
data = {(1,): 3, (4, 5): 6}
result = Series(data).sort_values()
expected = Series([3, 6], index=MultiIndex.from_tuples([(1, None), (4, 5)]))
tm.assert_series_equal(result, expected)

# https://github.com/pandas-dev/pandas/issues/22698
@pytest.mark.filterwarnings("ignore:elementwise comparison:FutureWarning")
def test_fromDict(self, using_infer_string):
Expand Down Expand Up @@ -1878,6 +1884,15 @@ def test_constructor_dict_multiindex(self):
result = result.reindex(index=expected.index)
tm.assert_series_equal(result, expected)

# GH 60695
d = {("a",): 0.0, ("a", "b"): 1.0}
_d = sorted(d.items())
result = Series(d)
expected = Series(
[x[1] for x in _d], index=MultiIndex.from_tuples([x[0] for x in _d])
)
tm.assert_series_equal(result, expected)

def test_constructor_dict_multiindex_reindex_flat(self):
# construction involves reindexing with a MultiIndex corner case
data = {("i", "i"): 0, ("i", "j"): 1, ("j", "i"): 2, "j": np.nan}
Expand Down
Loading