Zip Strict for pandas/util and pandas/_libs #62469 (#62540)

Author: shivamvishal

pandas/_libs/index.pyx

@@ -838,7 +838,7 @@ cdef class BaseMultiIndexCodesEngine:
             raise KeyError(key)
         try:
             indices = [1 if checknull(v) else lev.get_loc(v) + multiindex_nulls_shift
-                       for lev, v in zip(self.levels, key)]
+                       for lev, v in zip(self.levels, key, strict=True)]
         except KeyError:
             raise KeyError(key)
 

pandas/_libs/missing.pyx

@@ -72,7 +72,7 @@ cpdef bint check_na_tuples_nonequal(object left, object right):
     if len(left) != len(right):
         return False
 
-    for left_element, right_element in zip(left, right):
+    for left_element, right_element in zip(left, right, strict=True):
         if left_element is C_NA and right_element is not C_NA:
             return True
         elif right_element is C_NA and left_element is not C_NA:

pandas/_libs/tslibs/fields.pyx

@@ -109,7 +109,7 @@ def month_position_check(fields, weekdays) -> str | None:
         int32_t[:] months = fields["M"]
         int32_t[:] days = fields["D"]
 
-    for y, m, d, wd in zip(years, months, days, weekdays):
+    for y, m, d, wd in zip(years, months, days, weekdays, strict=True):
         if calendar_start:
             calendar_start &= d == 1
         if business_start:

pandas/_libs/tslibs/offsets.pyx

@@ -2217,7 +2217,7 @@ cdef class BusinessHour(BusinessMixin):
         # Use python string formatting to be faster than strftime
         hours = ",".join(
             f"{st.hour:02d}:{st.minute:02d}-{en.hour:02d}:{en.minute:02d}"
-            for st, en in zip(self.start, self.end)
+            for st, en in zip(self.start, self.end, strict=True)
         )
         attrs = [f"{self._prefix}={hours}"]
         out += ": " + ", ".join(attrs)
@@ -2414,7 +2414,7 @@ cdef class BusinessHour(BusinessMixin):
         # get total business hours by sec in one business day
         businesshours = sum(
             self._get_business_hours_by_sec(st, en)
-            for st, en in zip(self.start, self.end)
+            for st, en in zip(self.start, self.end, strict=True)
         )
 
         bd, r = divmod(abs(n * 60), businesshours // 60)
@@ -5357,7 +5357,7 @@ cpdef to_offset(freq, bint is_period=False):
                 # the last element must be blank
                 raise ValueError("last element must be blank")
 
-            tups = zip(split[0::4], split[1::4], split[2::4])
+            tups = zip(split[0::4], split[1::4], split[2::4], strict=False)
             for n, (sep, stride, name) in enumerate(tups):
                 name = _warn_about_deprecated_aliases(name, is_period)
                 _validate_to_offset_alias(name, is_period)

pandas/_libs/tslibs/timezones.pyx

@@ -252,7 +252,7 @@ cdef object _get_utc_trans_times_from_dateutil_tz(tzinfo tz):
     """
     new_trans = list(tz._trans_list)
     last_std_offset = 0
-    for i, (trans, tti) in enumerate(zip(tz._trans_list, tz._trans_idx)):
+    for i, (trans, tti) in enumerate(zip(tz._trans_list, tz._trans_idx, strict=True)):
         if not tti.isdst:
             last_std_offset = tti.offset
         new_trans[i] = trans - last_std_offset

pandas/util/_doctools.py

@@ -84,7 +84,7 @@ def plot(
             # left
             max_left_cols = max(self._shape(df)[1] for df in left)
             max_left_rows = max(self._shape(df)[0] for df in left)
-            for i, (_left, _label) in enumerate(zip(left, labels)):
+            for i, (_left, _label) in enumerate(zip(left, labels, strict=True)):
                 ax = fig.add_subplot(gs[i, 0:max_left_cols])
                 self._make_table(ax, _left, title=_label, height=1.0 / max_left_rows)
             # right
@@ -97,7 +97,7 @@ def plot(
             gs = gridspec.GridSpec(1, hcells)
             # left
             i = 0
-            for df, _label in zip(left, labels):
+            for df, _label in zip(left, labels, strict=True):
                 sp = self._shape(df)
                 ax = fig.add_subplot(gs[0, i : i + sp[1]])
                 self._make_table(ax, df, title=_label, height=height)

pandas/util/_validators.py

@@ -122,7 +122,7 @@ def validate_args(fname, args, max_fname_arg_count, compat_args) -> None:
     # We do this so that we can provide a more informative
     # error message about the parameters that we are not
     # supporting in the pandas implementation of 'fname'
-    kwargs = dict(zip(compat_args, args))
+    kwargs = dict(zip(compat_args, args, strict=False))
     _check_for_default_values(fname, kwargs, compat_args)
 
 
@@ -212,7 +212,7 @@ def validate_args_and_kwargs(
 
     # Check there is no overlap with the positional and keyword
     # arguments, similar to what is done in actual Python functions
-    args_dict = dict(zip(compat_args, args))
+    args_dict = dict(zip(compat_args, args, strict=False))
 
     for key in args_dict:
         if key in kwargs: