STY: Use strict arg in zip() in pandas/core/arrays (#62596)

Author: GuruprashanthKrishnakumar

pandas/core/arrays/arrow/array.py

@@ -888,7 +888,7 @@ def _cmp_method(self, other, op) -> ArrowExtensionArray:
                 boxed = self._box_pa(other)
             except pa.lib.ArrowInvalid:
                 # e.g. GH#60228 [1, "b"] we have to operate pointwise
-                res_values = [op(x, y) for x, y in zip(self, other)]
+                res_values = [op(x, y) for x, y in zip(self, other, strict=True)]
                 result = pa.array(res_values, type=pa.bool_(), from_pandas=True)
             else:
                 rtype = boxed.type
@@ -2713,7 +2713,7 @@ def _str_extract(self, pat: str, flags: int = 0, expand: bool = True):
         if expand:
             return {
                 col: self._from_pyarrow_array(pc.struct_field(result, [i]))
-                for col, i in zip(groups, range(result.type.num_fields))
+                for col, i in zip(groups, range(result.type.num_fields), strict=True)
             }
         else:
             return type(self)(pc.struct_field(result, [0]))

pandas/core/arrays/base.py

@@ -2869,7 +2869,7 @@ def convert_values(param):
 
             # If the operator is not defined for the underlying objects,
             # a TypeError should be raised
-            res = [op(a, b) for (a, b) in zip(lvalues, rvalues)]
+            res = [op(a, b) for (a, b) in zip(lvalues, rvalues, strict=True)]
 
             def _maybe_convert(arr):
                 if coerce_to_dtype:
@@ -2885,7 +2885,7 @@ def _maybe_convert(arr):
                 return res
 
             if op.__name__ in {"divmod", "rdivmod"}:
-                a, b = zip(*res)
+                a, b = zip(*res, strict=True)
                 return _maybe_convert(a), _maybe_convert(b)
 
             return _maybe_convert(res)

pandas/core/arrays/categorical.py

@@ -2,6 +2,7 @@
 
 from csv import QUOTE_NONNUMERIC
 from functools import partial
+import itertools
 import operator
 from shutil import get_terminal_size
 from typing import (
@@ -2429,8 +2430,8 @@ def _reverse_indexer(self) -> dict[Hashable, npt.NDArray[np.intp]]:
             ensure_platform_int(self.codes), categories.size
         )
         counts = ensure_int64(counts).cumsum()
-        _result = (r[start:end] for start, end in zip(counts, counts[1:]))
-        return dict(zip(categories, _result))
+        _result = (r[start:end] for start, end in itertools.pairwise(counts))
+        return dict(zip(categories, _result, strict=True))
 
     # ------------------------------------------------------------------
     # Reductions
@@ -3165,5 +3166,8 @@ def factorize_from_iterables(iterables) -> tuple[list[np.ndarray], list[Index]]:
         # For consistency, it should return two empty lists.
         return [], []
 
-    codes, categories = zip(*(factorize_from_iterable(it) for it in iterables))
+    codes, categories = zip(
+        *(factorize_from_iterable(it) for it in iterables),
+        strict=True,
+    )
     return list(codes), list(categories)

pandas/core/arrays/datetimelike.py

@@ -2374,7 +2374,7 @@ def _concat_same_type(
             to_concat = [x for x in to_concat if len(x)]
 
             if obj.freq is not None and all(x.freq == obj.freq for x in to_concat):
-                pairs = zip(to_concat[:-1], to_concat[1:])
+                pairs = zip(to_concat[:-1], to_concat[1:], strict=True)
                 if all(pair[0][-1] + obj.freq == pair[1][0] for pair in pairs):
                     new_freq = obj.freq
                     new_obj._freq = new_freq

pandas/core/arrays/interval.py

@@ -1893,7 +1893,7 @@ def to_tuples(self, na_tuple: bool = True) -> np.ndarray:
         >>> idx.to_tuples()
         Index([(0, 1), (1, 2)], dtype='object')
         """
-        tuples = com.asarray_tuplesafe(zip(self._left, self._right))
+        tuples = com.asarray_tuplesafe(zip(self._left, self._right, strict=True))
         if not na_tuple:
             # GH 18756
             tuples = np.where(~self.isna(), tuples, np.nan)

pandas/core/arrays/masked.py

@@ -344,7 +344,7 @@ def __iter__(self) -> Iterator:
                     yield val
             else:
                 na_value = self.dtype.na_value
-                for isna_, val in zip(self._mask, self._data):
+                for isna_, val in zip(self._mask, self._data, strict=True):
                     if isna_:
                         yield na_value
                     else:

pandas/core/arrays/period.py

@@ -1445,7 +1445,7 @@ def _range_from_fields(
 
         freqstr = freq.freqstr
         year, quarter = _make_field_arrays(year, quarter)
-        for y, q in zip(year, quarter):
+        for y, q in zip(year, quarter, strict=True):
             calendar_year, calendar_month = parsing.quarter_to_myear(y, q, freqstr)
             val = libperiod.period_ordinal(
                 calendar_year, calendar_month, 1, 1, 1, 1, 0, 0, base
@@ -1455,7 +1455,7 @@ def _range_from_fields(
         freq = to_offset(freq, is_period=True)
         base = libperiod.freq_to_dtype_code(freq)
         arrays = _make_field_arrays(year, month, day, hour, minute, second)
-        for y, mth, d, h, mn, s in zip(*arrays):
+        for y, mth, d, h, mn, s in zip(*arrays, strict=True):
             ordinals.append(libperiod.period_ordinal(y, mth, d, h, mn, s, 0, 0, base))
 
     return np.array(ordinals, dtype=np.int64), freq

pandas/core/arrays/sparse/array.py

@@ -1753,7 +1753,7 @@ def __array_ufunc__(self, ufunc: np.ufunc, method: str, *inputs, **kwargs):
                     self._simple_new(
                         sp_value, self.sp_index, SparseDtype(sp_value.dtype, fv)
                     )
-                    for sp_value, fv in zip(sp_values, fill_value)
+                    for sp_value, fv in zip(sp_values, fill_value, strict=True)
                 )
                 return arrays
             elif method == "reduce":

pandas/core/arrays/timedeltas.py

@@ -621,7 +621,9 @@ def __truediv__(self, other):
         if is_object_dtype(other.dtype):
             other = np.asarray(other)
             if self.ndim > 1:
-                res_cols = [left / right for left, right in zip(self, other)]
+                res_cols = [
+                    left / right for left, right in zip(self, other, strict=True)
+                ]
                 res_cols2 = [x.reshape(1, -1) for x in res_cols]
                 result = np.concatenate(res_cols2, axis=0)
             else:
@@ -670,7 +672,9 @@ def __floordiv__(self, other):
         elif is_object_dtype(other.dtype):
             other = np.asarray(other)
             if self.ndim > 1:
-                res_cols = [left // right for left, right in zip(self, other)]
+                res_cols = [
+                    left // right for left, right in zip(self, other, strict=True)
+                ]
                 res_cols2 = [x.reshape(1, -1) for x in res_cols]
                 result = np.concatenate(res_cols2, axis=0)
             else:

pyproject.toml

@@ -445,15 +445,6 @@ exclude = [
 "pandas/_config/config.py" = ["B905"]
 "pandas/conftest.py" = ["B905"]
 "pandas/core/array_algos/quantile.py" = ["B905"]
-"pandas/core/arrays/arrow/array.py" = ["B905"]
-"pandas/core/arrays/base.py" = ["B905"]
-"pandas/core/arrays/categorical.py" = ["B905"]
-"pandas/core/arrays/datetimelike.py" = ["B905"]
-"pandas/core/arrays/interval.py" = ["B905"]
-"pandas/core/arrays/masked.py" = ["B905"]
-"pandas/core/arrays/period.py" = ["B905"]
-"pandas/core/arrays/sparse/array.py" = ["B905"]
-"pandas/core/arrays/timedeltas.py" = ["B905"]
 "pandas/core/computation/align.py" = ["B905"]
 "pandas/core/computation/expr.py" = ["B905"]
 "pandas/core/computation/ops.py" = ["B905"]