add strict param

Author: jsngn

pandas/core/reshape/concat.py

@@ -840,7 +840,7 @@ def _make_concat_multiindex(indexes, keys, levels=None, names=None) -> MultiInde
     if (levels is None and isinstance(keys[0], tuple)) or (
         levels is not None and len(levels) > 1
     ):
-        zipped = list(zip(*keys))
+        zipped = list(zip(*keys, strict=True))
         if names is None:
             names = [None] * len(zipped)
 
@@ -866,13 +866,13 @@ def _make_concat_multiindex(indexes, keys, levels=None, names=None) -> MultiInde
         # things are potentially different sizes, so compute the exact codes
         # for each level and pass those to MultiIndex.from_arrays
 
-        for hlevel, level in zip(zipped, levels):
+        for hlevel, level in zip(zipped, levels, strict=True):
             to_concat = []
             if isinstance(hlevel, Index) and hlevel.equals(level):
                 lens = [len(idx) for idx in indexes]
                 codes_list.append(np.repeat(np.arange(len(hlevel)), lens))
             else:
-                for key, index in zip(hlevel, indexes):
+                for key, index in zip(hlevel, indexes, strict=True):
                     # Find matching codes, include matching nan values as equal.
                     mask = (isna(level) & isna(key)) | (level == key)
                     if not mask.any():
@@ -922,7 +922,7 @@ def _make_concat_multiindex(indexes, keys, levels=None, names=None) -> MultiInde
 
     # do something a bit more speedy
 
-    for hlevel, level in zip(zipped, levels):
+    for hlevel, level in zip(zipped, levels, strict=True):
         hlevel_index = ensure_index(hlevel)
         mapped = level.get_indexer(hlevel_index)
 

pandas/core/reshape/encoding.py

@@ -209,7 +209,9 @@ def check_len(item, name: str) -> None:
             # columns to prepend to result.
             with_dummies = [data.select_dtypes(exclude=dtypes_to_encode)]
 
-        for col, pre, sep in zip(data_to_encode.items(), prefix, prefix_sep):
+        for col, pre, sep in zip(
+            data_to_encode.items(), prefix, prefix_sep, strict=False
+        ):
             # col is (column_name, column), use just column data here
             dummy = _get_dummies_1d(
                 col[1],
@@ -323,15 +325,15 @@ def get_empty_frame(data) -> DataFrame:
         codes = codes[mask]
         n_idx = np.arange(N)[mask]
 
-        for ndx, code in zip(n_idx, codes):
+        for ndx, code in zip(n_idx, codes, strict=True):
             sp_indices[code].append(ndx)
 
         if drop_first:
             # remove first categorical level to avoid perfect collinearity
             # GH12042
             sp_indices = sp_indices[1:]
             dummy_cols = dummy_cols[1:]
-        for col, ixs in zip(dummy_cols, sp_indices):
+        for col, ixs in zip(dummy_cols, sp_indices, strict=True):
             sarr = SparseArray(
                 np.ones(len(ixs), dtype=dtype),
                 sparse_index=IntIndex(N, ixs),
@@ -535,7 +537,11 @@ def from_dummies(
                 raise ValueError(len_msg)
         elif isinstance(default_category, Hashable):
             default_category = dict(
-                zip(variables_slice, [default_category] * len(variables_slice))
+                zip(
+                    variables_slice,
+                    [default_category] * len(variables_slice),
+                    strict=True,
+                )
             )
         else:
             raise TypeError(

pandas/core/reshape/melt.py

@@ -199,7 +199,7 @@ def melt(
         missing = idx == -1
         if missing.any():
             missing_labels = [
-                lab for lab, not_found in zip(labels, missing) if not_found
+                lab for lab, not_found in zip(labels, missing, strict=True) if not_found
             ]
             raise KeyError(
                 "The following id_vars or value_vars are not present in "

pandas/core/reshape/merge.py

@@ -1230,7 +1230,7 @@ def _maybe_restore_index_levels(self, result: DataFrame) -> None:
         """
         names_to_restore = []
         for name, left_key, right_key in zip(
-            self.join_names, self.left_on, self.right_on
+            self.join_names, self.left_on, self.right_on, strict=True
         ):
             if (
                 # Argument 1 to "_is_level_reference" of "NDFrame" has incompatible
@@ -1263,7 +1263,7 @@ def _maybe_add_join_keys(
 
         assert all(isinstance(x, _known) for x in self.left_join_keys)
 
-        keys = zip(self.join_names, self.left_on, self.right_on)
+        keys = zip(self.join_names, self.left_on, self.right_on, strict=True)
         for i, (name, lname, rname) in enumerate(keys):
             if not _should_fill(lname, rname):
                 continue
@@ -1572,7 +1572,7 @@ def _get_merge_keys(
 
         # ugh, spaghetti re #733
         if _any(self.left_on) and _any(self.right_on):
-            for lk, rk in zip(self.left_on, self.right_on):
+            for lk, rk in zip(self.left_on, self.right_on, strict=True):
                 lk = extract_array(lk, extract_numpy=True)
                 rk = extract_array(rk, extract_numpy=True)
                 if is_lkey(lk):
@@ -1635,7 +1635,7 @@ def _get_merge_keys(
                 right_keys = [
                     lev._values.take(lev_codes)
                     for lev, lev_codes in zip(
-                        self.right.index.levels, self.right.index.codes
+                        self.right.index.levels, self.right.index.codes, strict=True
                     )
                 ]
             else:
@@ -1657,7 +1657,7 @@ def _get_merge_keys(
                 left_keys = [
                     lev._values.take(lev_codes)
                     for lev, lev_codes in zip(
-                        self.left.index.levels, self.left.index.codes
+                        self.left.index.levels, self.left.index.codes, strict=True
                     )
                 ]
             else:
@@ -1674,7 +1674,7 @@ def _maybe_coerce_merge_keys(self) -> None:
         # or if we have object and integer dtypes
 
         for lk, rk, name in zip(
-            self.left_join_keys, self.right_join_keys, self.join_names
+            self.left_join_keys, self.right_join_keys, self.join_names, strict=True
         ):
             if (len(lk) and not len(rk)) or (not len(lk) and len(rk)):
                 continue
@@ -2042,7 +2042,7 @@ def get_join_indexers(
             _factorize_keys(left_keys[n], right_keys[n], sort=sort)
             for n in range(len(left_keys))
         )
-        zipped = zip(*mapped)
+        zipped = zip(*mapped, strict=True)
         llab, rlab, shape = (list(x) for x in zipped)
 
         # get flat i8 keys from label lists
@@ -2427,7 +2427,7 @@ def _check_dtype_match(left: ArrayLike, right: ArrayLike, i: int) -> None:
                 raise MergeError(msg)
 
         # validate index types are the same
-        for i, (lk, rk) in enumerate(zip(left_join_keys, right_join_keys)):
+        for i, (lk, rk) in enumerate(zip(left_join_keys, right_join_keys, strict=True)):
             _check_dtype_match(lk, rk, i)
 
         if self.left_index:
@@ -2612,7 +2612,7 @@ def _get_multiindex_indexer(
         _factorize_keys(index.levels[n]._values, join_keys[n], sort=sort)
         for n in range(index.nlevels)
     )
-    zipped = zip(*mapped)
+    zipped = zip(*mapped, strict=True)
     rcodes, lcodes, shape = (list(x) for x in zipped)
     if sort:
         rcodes = list(map(np.take, rcodes, index.codes))

pandas/core/reshape/pivot.py

@@ -1098,8 +1098,8 @@ def crosstab(
     from pandas import DataFrame
 
     data = {
-        **dict(zip(unique_rownames, index)),
-        **dict(zip(unique_colnames, columns)),
+        **dict(zip(unique_rownames, index, strict=True)),
+        **dict(zip(unique_colnames, columns, strict=True)),
     }
     df = DataFrame(data, index=common_idx)
 

pandas/core/reshape/reshape.py

@@ -696,7 +696,9 @@ def stack_factorize(index):
             levels=new_levels, codes=new_codes, names=new_names, verify_integrity=False
         )
     else:
-        levels, (ilab, clab) = zip(*map(stack_factorize, (frame.index, frame.columns)))
+        levels, (ilab, clab) = zip(
+            *map(stack_factorize, (frame.index, frame.columns)), strict=True
+        )
         codes = ilab.repeat(K), np.tile(clab, N).ravel()
         new_index = MultiIndex(
             levels=levels,
@@ -778,21 +780,21 @@ def _stack_multi_column_index(columns: MultiIndex) -> MultiIndex | Index:
 
     levs = (
         [lev[c] if c >= 0 else None for c in codes]
-        for lev, codes in zip(columns.levels[:-1], columns.codes[:-1])
+        for lev, codes in zip(columns.levels[:-1], columns.codes[:-1], strict=True)
     )
 
     # Remove duplicate tuples in the MultiIndex.
-    tuples = zip(*levs)
+    tuples = zip(*levs, strict=True)
     unique_tuples = (key for key, _ in itertools.groupby(tuples))
-    new_levs = zip(*unique_tuples)
+    new_levs = zip(*unique_tuples, strict=True)
 
     # The dtype of each level must be explicitly set to avoid inferring the wrong type.
     # See GH-36991.
     return MultiIndex.from_arrays(
         [
             # Not all indices can accept None values.
             Index(new_lev, dtype=lev.dtype) if None not in new_lev else new_lev
-            for new_lev, lev in zip(new_levs, columns.levels)
+            for new_lev, lev in zip(new_levs, columns.levels, strict=True)
         ],
         names=columns.names[:-1],
     )