From b1a226724190be4c6e80836b5fd7bd6bcf30d56e Mon Sep 17 00:00:00 2001
From: Lu Yibo <1478354316@qq.com>
Date: Wed, 5 Nov 2025 00:22:50 +0800
Subject: [PATCH 1/2] Enhance zip calls with strict parameter

Added 'strict=True' parameter to zip calls for better error handling.
---
 pandas/core/reshape/encoding.py | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/pandas/core/reshape/encoding.py b/pandas/core/reshape/encoding.py
index 5c5fed272b925..fad2cf4b3cd1e 100644
--- a/pandas/core/reshape/encoding.py
+++ b/pandas/core/reshape/encoding.py
@@ -211,7 +211,7 @@ 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=True):
             # col is (column_name, column), use just column data here
             dummy = _get_dummies_1d(
                 col[1],
@@ -325,7 +325,7 @@ 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:
@@ -333,7 +333,7 @@ def get_empty_frame(data) -> DataFrame:
             # 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),
@@ -538,7 +538,7 @@ 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(

From d43efb99758f4300e4a85b4ddd4fa240c7e76ea9 Mon Sep 17 00:00:00 2001
From: Lu Yibo <1478354316@qq.com>
Date: Wed, 5 Nov 2025 00:35:25 +0800
Subject: [PATCH 2/2] some changes to fix bugs

---
 pandas/core/reshape/encoding.py | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/pandas/core/reshape/encoding.py b/pandas/core/reshape/encoding.py
index fad2cf4b3cd1e..0dfd721dee312 100644
--- a/pandas/core/reshape/encoding.py
+++ b/pandas/core/reshape/encoding.py
@@ -211,7 +211,7 @@ 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, strict=True):
+        for col, pre, sep in zip(data_to_encode.items(), prefix, prefix_sep):
             # col is (column_name, column), use just column data here
             dummy = _get_dummies_1d(
                 col[1],
@@ -538,7 +538,7 @@ def from_dummies(
                 raise ValueError(len_msg)
         elif isinstance(default_category, Hashable):
             default_category = dict(
-                zip(variables_slice, [default_category] * len(variables_slice), strict=True)
+                zip(variables_slice, [default_category] * len(variables_slice))
             )
         else:
             raise TypeError(