Skip to content

Zip Strict specification for pandas/core/indexes #62533

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

Merged
merged 7 commits into from
Oct 13, 2025
+28 −27
Merged

Zip Strict specification for pandas/core/indexes #62533

Show file tree
Hide file tree
Changes from 4 commits
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
f6f1210
add strict arg to interval.py
krishna-datta Oct 1, 2025
7b352dc
expect to fail; removed check
krishna-datta Oct 1, 2025
a57bea0
revert acc chng
krishna-datta Oct 10, 2025
418f19f
some more strict added
krishna-datta Oct 10, 2025
6dd8988
comments
krishna-datta Oct 13, 2025
998a26b
set all to True
krishna-datta Oct 13, 2025
f302b33
mypy
krishna-datta Oct 13, 2025
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
4 changes: 2 additions & 2 deletions pandas/core/indexes/interval.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1056,8 +1056,8 @@ def _intersection_non_unique(self, other: IntervalIndex) -> IntervalIndex:
first_nan_loc = np.arange(len(self))[self.isna()][0]
mask[first_nan_loc] = True

other_tups = set(zip(other.left, other.right))
for i, tup in enumerate(zip(self.left, self.right)):
other_tups = set(zip(other.left, other.right, strict=True))
for i, tup in enumerate(zip(self.left, self.right, strict=True)):
if tup in other_tups:
mask[i] = True

Expand Down
47 changes: 25 additions & 22 deletions pandas/core/indexes/multi.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -720,7 +720,7 @@ def from_frame(
if not isinstance(df, ABCDataFrame):
raise TypeError("Input must be a DataFrame")

column_names, columns = zip(*df.items())
column_names, columns = zip(*df.items(), strict=True)
names = column_names if names is None else names
return cls.from_arrays(columns, sortorder=sortorder, names=names)

Expand Down Expand Up @@ -878,7 +878,10 @@ def levels(self) -> FrozenList:
# Use cache_readonly to ensure that self.get_locs doesn't repeatedly
# create new IndexEngine
# https://github.com/pandas-dev/pandas/issues/31648
result = [x._rename(name=name) for x, name in zip(self._levels, self._names)]
result = [
x._rename(name=name)
for x, name in zip(self._levels, self._names, strict=True)
]
for level in result:
# disallow midx.levels[0].name = "foo"
level._no_setting_name = True
Expand Down Expand Up @@ -912,7 +915,7 @@ def _set_levels(
else:
level_numbers = [self._get_level_number(lev) for lev in level]
new_levels_list = list(self._levels)
for lev_num, lev in zip(level_numbers, levels):
for lev_num, lev in zip(level_numbers, levels, strict=False):
new_levels_list[lev_num] = ensure_index(lev, copy=copy)._view()
new_levels = FrozenList(new_levels_list)

Expand Down Expand Up @@ -1148,13 +1151,13 @@ def _set_codes(
if level is None:
new_codes = FrozenList(
_coerce_indexer_frozen(level_codes, lev, copy=copy).view()
for lev, level_codes in zip(self._levels, codes)
for lev, level_codes in zip(self._levels, codes, strict=False)
)
level_numbers = range(len(new_codes))
else:
level_numbers = [self._get_level_number(lev) for lev in level]
new_codes_list = list(self._codes)
for lev_num, level_codes in zip(level_numbers, codes):
for lev_num, level_codes in zip(level_numbers, codes, strict=False):
lev = self.levels[lev_num]
new_codes_list[lev_num] = _coerce_indexer_frozen(
level_codes, lev, copy=copy
Expand Down Expand Up @@ -1478,7 +1481,7 @@ def _formatter_func(self, tup):
Formats each item in tup according to its level's formatter function.
"""
formatter_funcs = (level._formatter_func for level in self.levels)
return tuple(func(val) for func, val in zip(formatter_funcs, tup))
return tuple(func(val) for func, val in zip(formatter_funcs, tup, strict=False))

def _get_values_for_csv(
self, *, na_rep: str = "nan", **kwargs
Expand All @@ -1487,7 +1490,7 @@ def _get_values_for_csv(
new_codes = []

# go through the levels and format them
for level, level_codes in zip(self.levels, self.codes):
for level, level_codes in zip(self.levels, self.codes, strict=False):
level_strs = level._get_values_for_csv(na_rep=na_rep, **kwargs)
# add nan values, if there are any
mask = level_codes == -1
Expand Down Expand Up @@ -1527,7 +1530,7 @@ def _format_multi(
return []

stringified_levels = []
for lev, level_codes in zip(self.levels, self.codes):
for lev, level_codes in zip(self.levels, self.codes, strict=False):
na = _get_na_rep(lev.dtype)

if len(lev) > 0:
Expand All @@ -1550,7 +1553,7 @@ def _format_multi(
stringified_levels.append(formatted)

result_levels = []
for lev, lev_name in zip(stringified_levels, self.names):
for lev, lev_name in zip(stringified_levels, self.names, strict=False):
level = []

if include_names:
Expand Down Expand Up @@ -1627,7 +1630,7 @@ def _set_names(self, names, *, level=None) -> None:
level = (self._get_level_number(lev) for lev in level)

# set the name
for lev, name in zip(level, names):
for lev, name in zip(level, names, strict=False):
if name is not None:
# GH 20527
# All items in 'names' need to be hashable:
Expand Down Expand Up @@ -2094,7 +2097,7 @@ def _sort_levels_monotonic(self, raise_if_incomparable: bool = False) -> MultiIn
new_levels = []
new_codes = []

for lev, level_codes in zip(self.levels, self.codes):
for lev, level_codes in zip(self.levels, self.codes, strict=False):
Copy link
Member

@mroeschke mroeschke Oct 10, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

What fails when this is True?

Copy link
Contributor Author

@krishna-datta krishna-datta Oct 13, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

None of the tests are failing for any of the cases flagged. I originally set this to False, but after some more digging, and I see the MultiIndex constructor enforces the same length for the levels and codes. Setting these to True

if not lev.is_monotonic_increasing:
try:
# indexer to reorder the levels
Expand Down Expand Up @@ -2173,7 +2176,7 @@ def remove_unused_levels(self) -> MultiIndex:
new_codes = []

changed = False
for lev, level_codes in zip(self.levels, self.codes):
for lev, level_codes in zip(self.levels, self.codes, strict=False):
Copy link
Member

@mroeschke mroeschke Oct 10, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

What fails when this is True?

Copy link
Contributor Author

@krishna-datta krishna-datta Oct 13, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Same as above

# Since few levels are typically unused, bincount() is more
# efficient than unique() - however it only accepts positive values
# (and drops order):
Expand Down Expand Up @@ -2240,7 +2243,7 @@ def __getitem__(self, key):
key = com.cast_scalar_indexer(key)

retval = []
for lev, level_codes in zip(self.levels, self.codes):
for lev, level_codes in zip(self.levels, self.codes, strict=False):
Copy link
Member

@mroeschke mroeschke Oct 10, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

What fails when this is True?

Copy link
Contributor Author

@krishna-datta krishna-datta Oct 13, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Same as above

if level_codes[key] == -1:
retval.append(np.nan)
else:
Expand Down Expand Up @@ -3078,7 +3081,7 @@ def _partial_tup_index(self, tup: tuple, side: Literal["left", "right"] = "left"

n = len(tup)
start, end = 0, len(self)
zipped = zip(tup, self.levels, self.codes)
zipped = zip(tup, self.levels, self.codes, strict=False)
for k, (lab, lev, level_codes) in enumerate(zipped):
section = level_codes[start:end]

Expand Down Expand Up @@ -3362,7 +3365,7 @@ def maybe_mi_droplevels(indexer, levels):
"Key for location must have same length as number of levels"
)
result = None
for lev, k in zip(level, key):
for lev, k in zip(level, key, strict=False):
loc, new_index = self._get_loc_level(k, level=lev)
if isinstance(loc, slice):
mask = np.zeros(len(self), dtype=bool)
Expand Down Expand Up @@ -3948,7 +3951,7 @@ def _union(self, other, sort) -> MultiIndex:
if isinstance(result, MultiIndex):
return result
return MultiIndex.from_arrays(
zip(*result), sortorder=None, names=result_names
zip(*result, strict=False), sortorder=None, names=result_names
)

else:
Expand Down Expand Up @@ -3995,7 +3998,7 @@ def _maybe_match_names(self, other):
if len(self.names) != len(other.names):
return [None] * len(self.names)
names = []
for a_name, b_name in zip(self.names, other.names):
for a_name, b_name in zip(self.names, other.names, strict=False):
if a_name == b_name:
names.append(a_name)
else:
Expand Down Expand Up @@ -4092,7 +4095,7 @@ def putmask(self, mask, value: MultiIndex) -> MultiIndex:
new_codes = []

for i, (value_level, level, level_codes) in enumerate(
zip(subset.levels, self.levels, self.codes)
zip(subset.levels, self.levels, self.codes, strict=False)
):
new_level = level.union(value_level, sort=False)
value_codes = new_level.get_indexer_for(subset.get_level_values(i))
Expand Down Expand Up @@ -4123,7 +4126,7 @@ def insert(self, loc: int, item) -> MultiIndex:

new_levels = []
new_codes = []
for k, level, level_codes in zip(item, self.levels, self.codes):
for k, level, level_codes in zip(item, self.levels, self.codes, strict=True):
if k not in level:
# have to insert into level
# must insert at end otherwise you have to recompute all the
Expand Down Expand Up @@ -4219,7 +4222,7 @@ def _lexsort_depth(codes: list[np.ndarray], nlevels: int) -> int:


def sparsify_labels(label_list, start: int = 0, sentinel: object = ""):
pivoted = list(zip(*label_list))
pivoted = list(zip(*label_list, strict=True))
k = len(label_list)

result = pivoted[: start + 1]
Expand All @@ -4228,7 +4231,7 @@ def sparsify_labels(label_list, start: int = 0, sentinel: object = ""):
for cur in pivoted[start + 1 :]:
sparse_cur = []

for i, (p, t) in enumerate(zip(prev, cur)):
for i, (p, t) in enumerate(zip(prev, cur, strict=True)):
if i == k - 1:
sparse_cur.append(t)
result.append(sparse_cur) # type: ignore[arg-type]
Expand All @@ -4243,7 +4246,7 @@ def sparsify_labels(label_list, start: int = 0, sentinel: object = ""):

prev = cur

return list(zip(*result))
return list(zip(*result, strict=True))


def _get_na_rep(dtype: DtypeObj) -> str:
Expand Down
2 changes: 0 additions & 2 deletions pyproject.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -452,8 +452,6 @@ exclude = [
"pandas/core/groupby/groupby.py" = ["B905"]
"pandas/core/groupby/grouper.py" = ["B905"]
"pandas/core/groupby/ops.py" = ["B905"]
"pandas/core/indexes/interval.py" = ["B905"]
"pandas/core/indexes/multi.py" = ["B905"]
"pandas/core/methods/to_dict.py" = ["B905"]
"pandas/core/reshape/concat.py" = ["B905"]
"pandas/core/reshape/encoding.py" = ["B905"]
Expand Down
Loading