Skip to content

Navigation Menu

Sign in
Appearance settings

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly
Sign up
Appearance settings

Commit bcb99d5

Browse files
Zip Strict for pandas/core/computation and pandas/core/groupby #62469 (#62510)
1 parent 0557e16 commit bcb99d5

File tree

7 files changed

+25
-21
lines changed

7 files changed

+25
-21
lines changed

‎pandas/core/computation/align.py‎

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -93,7 +93,7 @@ def _align_core(terms):
9393

9494
from pandas import Series
9595

96-
ndims = Series(dict(zip(term_index, term_dims)))
96+
ndims = Series(dict(zip(term_index, term_dims, strict=True)))
9797

9898
# initial axes are the axes of the largest-axis'd term
9999
biggest = terms[ndims.idxmax()].value
@@ -116,7 +116,7 @@ def _align_core(terms):
116116
axes[ax] = axes[ax].union(itm)
117117

118118
for i, ndim in ndims.items():
119-
for axis, items in zip(range(ndim), axes):
119+
for axis, items in zip(range(ndim), axes, strict=False):
120120
ti = terms[i].value
121121

122122
if hasattr(ti, "reindex"):

‎pandas/core/computation/expr.py‎

Lines changed: 3 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -383,11 +383,11 @@ class BaseExprVisitor(ast.NodeVisitor):
383383
"FloorDiv",
384384
"Mod",
385385
)
386-
binary_op_nodes_map = dict(zip(binary_ops, binary_op_nodes))
386+
binary_op_nodes_map = dict(zip(binary_ops, binary_op_nodes, strict=True))
387387

388388
unary_ops = UNARY_OPS_SYMS
389389
unary_op_nodes = "UAdd", "USub", "Invert", "Not"
390-
unary_op_nodes_map = dict(zip(unary_ops, unary_op_nodes))
390+
unary_op_nodes_map = dict(zip(unary_ops, unary_op_nodes, strict=True))
391391

392392
rewrite_map = {
393393
ast.Eq: ast.In,
@@ -731,7 +731,7 @@ def visit_Compare(self, node, **kwargs):
731731
# recursive case: we have a chained comparison, a CMP b CMP c, etc.
732732
left = node.left
733733
values = []
734-
for op, comp in zip(ops, comps):
734+
for op, comp in zip(ops, comps, strict=True):
735735
new_node = self.visit(
736736
ast.Compare(comparators=[comp], left=left, ops=[self.translate_In(op)])
737737
)

‎pandas/core/computation/ops.py‎

Lines changed: 4 additions & 4 deletions
Original file line numberDiff line numberDiff line change
@@ -302,11 +302,11 @@ def _not_in(x, y):
302302
_in,
303303
_not_in,
304304
)
305-
_cmp_ops_dict = dict(zip(CMP_OPS_SYMS, _cmp_ops_funcs))
305+
_cmp_ops_dict = dict(zip(CMP_OPS_SYMS, _cmp_ops_funcs, strict=True))
306306

307307
BOOL_OPS_SYMS = ("&", "|", "and", "or")
308308
_bool_ops_funcs = (operator.and_, operator.or_, operator.and_, operator.or_)
309-
_bool_ops_dict = dict(zip(BOOL_OPS_SYMS, _bool_ops_funcs))
309+
_bool_ops_dict = dict(zip(BOOL_OPS_SYMS, _bool_ops_funcs, strict=True))
310310

311311
ARITH_OPS_SYMS = ("+", "-", "*", "/", "**", "//", "%")
312312
_arith_ops_funcs = (
@@ -318,7 +318,7 @@ def _not_in(x, y):
318318
operator.floordiv,
319319
operator.mod,
320320
)
321-
_arith_ops_dict = dict(zip(ARITH_OPS_SYMS, _arith_ops_funcs))
321+
_arith_ops_dict = dict(zip(ARITH_OPS_SYMS, _arith_ops_funcs, strict=True))
322322

323323
_binary_ops_dict = {}
324324

@@ -484,7 +484,7 @@ def _disallow_scalar_only_bool_ops(self) -> None:
484484

485485
UNARY_OPS_SYMS = ("+", "-", "~", "not")
486486
_unary_ops_funcs = (operator.pos, operator.neg, operator.invert, operator.invert)
487-
_unary_ops_dict = dict(zip(UNARY_OPS_SYMS, _unary_ops_funcs))
487+
_unary_ops_dict = dict(zip(UNARY_OPS_SYMS, _unary_ops_funcs, strict=True))
488488

489489

490490
class UnaryOp(Op):

‎pandas/core/groupby/generic.py‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -536,7 +536,7 @@ def _aggregate_multiple_funcs(self, arg, *args, **kwargs) -> DataFrame:
536536
else:
537537
# list of functions / function names
538538
columns = (com.get_callable_name(f) or f for f in arg)
539-
arg = zip(columns, arg)
539+
arg = zip(columns, arg, strict=True)
540540

541541
results: dict[base.OutputKey, DataFrame | Series] = {}
542542
with com.temp_setattr(self, "as_index", True):

‎pandas/core/groupby/groupby.py‎

Lines changed: 5 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -682,7 +682,10 @@ def get_converter(s):
682682
raise ValueError(msg) from err
683683

684684
converters = (get_converter(s) for s in index_sample)
685-
names = (tuple(f(n) for f, n in zip(converters, name)) for name in names)
685+
names = (
686+
tuple(f(n) for f, n in zip(converters, name, strict=True))
687+
for name in names
688+
)
686689

687690
else:
688691
converter = get_converter(index_sample)
@@ -1235,6 +1238,7 @@ def _insert_inaxis_grouper(
12351238
zip(
12361239
reversed(self._grouper.names),
12371240
self._grouper.get_group_levels(),
1241+
strict=True,
12381242
)
12391243
):
12401244
if name is None:

‎pandas/core/groupby/grouper.py‎

Lines changed: 3 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -684,9 +684,9 @@ def groups(self) -> dict[Hashable, Index]:
684684

685685
r, counts = libalgos.groupsort_indexer(ensure_platform_int(codes), len(uniques))
686686
counts = ensure_int64(counts).cumsum()
687-
_result = (r[start:end] for start, end in zip(counts, counts[1:]))
687+
_result = (r[start:end] for start, end in zip(counts, counts[1:], strict=False))
688688
# map to the label
689-
result = {k: self._index.take(v) for k, v in zip(uniques, _result)}
689+
result = {k: self._index.take(v) for k, v in zip(uniques, _result, strict=True)}
690690

691691
return PrettyDict(result)
692692

@@ -875,7 +875,7 @@ def is_in_obj(gpr) -> bool:
875875
return gpr._mgr.references_same_values(obj_gpr_column._mgr, 0)
876876
return False
877877

878-
for gpr, level in zip(keys, levels):
878+
for gpr, level in zip(keys, levels, strict=True):
879879
if is_in_obj(gpr): # df.groupby(df['name'])
880880
in_axis = True
881881
exclusions.add(gpr.name)

‎pandas/core/groupby/ops.py‎

Lines changed: 7 additions & 7 deletions
Original file line numberDiff line numberDiff line change
@@ -625,7 +625,7 @@ def get_iterator(self, data: NDFrameT) -> Iterator[tuple[Hashable, NDFrameT]]:
625625
splitter = self._get_splitter(data)
626626
# TODO: Would be more efficient to skip unobserved for transforms
627627
keys = self.result_index
628-
yield from zip(keys, splitter)
628+
yield from zip(keys, splitter, strict=True)
629629

630630
@final
631631
def _get_splitter(self, data: NDFrame) -> DataSplitter:
@@ -766,7 +766,7 @@ def result_index_and_ids(self) -> tuple[Index, npt.NDArray[np.intp]]:
766766
]
767767
sorts = [ping._sort for ping in self.groupings]
768768
# When passed a categorical grouping, keep all categories
769-
for k, (ping, level) in enumerate(zip(self.groupings, levels)):
769+
for k, (ping, level) in enumerate(zip(self.groupings, levels, strict=True)):
770770
if ping._passed_categorical:
771771
levels[k] = level.set_categories(ping._orig_cats)
772772

@@ -997,7 +997,7 @@ def apply_groupwise(
997997
result_values = []
998998

999999
# This calls DataSplitter.__iter__
1000-
zipped = zip(group_keys, splitter)
1000+
zipped = zip(group_keys, splitter, strict=True)
10011001

10021002
for key, group in zipped:
10031003
# Pinning name is needed for
@@ -1095,7 +1095,7 @@ def groups(self):
10951095
# GH 3881
10961096
result = {
10971097
key: value
1098-
for key, value in zip(self.binlabels, self.bins)
1098+
for key, value in zip(self.binlabels, self.bins, strict=True)
10991099
if key is not NaT
11001100
}
11011101
return result
@@ -1126,7 +1126,7 @@ def get_iterator(self, data: NDFrame):
11261126
slicer = lambda start, edge: data.iloc[start:edge]
11271127

11281128
start: np.int64 | int = 0
1129-
for edge, label in zip(self.bins, self.binlabels):
1129+
for edge, label in zip(self.bins, self.binlabels, strict=True):
11301130
if label is not NaT:
11311131
yield label, slicer(start, edge)
11321132
start = edge
@@ -1139,7 +1139,7 @@ def indices(self):
11391139
indices = collections.defaultdict(list)
11401140

11411141
i: np.int64 | int = 0
1142-
for label, bin in zip(self.binlabels, self.bins):
1142+
for label, bin in zip(self.binlabels, self.bins, strict=True):
11431143
if i < bin:
11441144
if label is not NaT:
11451145
indices[label] = list(range(i, bin))
@@ -1229,7 +1229,7 @@ def __iter__(self) -> Iterator:
12291229

12301230
starts, ends = lib.generate_slices(self._slabels, self.ngroups)
12311231
sdata = self._sorted_data
1232-
for start, end in zip(starts, ends):
1232+
for start, end in zip(starts, ends, strict=True):
12331233
yield self._chop(sdata, slice(start, end))
12341234

12351235
@cache_readonly

0 commit comments

Comments
(0)

AltStyle によって変換されたページ (->オリジナル) /