From ab9ee88dd5f00864ca670359abf125562f56bfdb Mon Sep 17 00:00:00 2001
From: Shashwati <shashwatibhattacaharya21.2@gmail.com>
Date: Fri, 13 Feb 2026 12:19:25 +0530
Subject: [PATCH] PYTHON: Fix pandas Categorical deprecation warnings in tests
 (GH-49255)

Replace pd.Categorical() calls that specify categories containing
values not in the categories list with the recommended pattern:
create the Categorical first, then use .set_categories() to restrict.

Fixes deprecation warnings:
- test_category: cat_strings_with_na
- test_category_implicit_from_pandas: two Categorical instances

Fixes #49255
---
 python/pyarrow/tests/test_pandas.py | 22 +++++++++++++---------
 1 file changed, 13 insertions(+), 9 deletions(-)

diff --git a/python/pyarrow/tests/test_pandas.py b/python/pyarrow/tests/test_pandas.py
index cecf10f2165..dde607d756f 100644
--- a/python/pyarrow/tests/test_pandas.py
+++ b/python/pyarrow/tests/test_pandas.py
@@ -3069,15 +3069,19 @@ def test_category(self):
         v2 = [4, 5, 6, 7, 8]
         v3 = [b'foo', None, b'bar', b'qux', np.nan]
 
+        cat_strings = pd.Categorical(v1 * repeats)
+        cat_strings_with_na = cat_strings.set_categories(['foo', 'bar'])
+
+        cat_strings_ordered = pd.Categorical(
+            v1 * repeats, categories=['bar', 'qux', 'foo'], ordered=True
+        )
+
         arrays = {
-            'cat_strings': pd.Categorical(v1 * repeats),
-            'cat_strings_with_na': pd.Categorical(v1 * repeats,
-                                                  categories=['foo', 'bar']),
+            'cat_strings': cat_strings,
+            'cat_strings_with_na': cat_strings_with_na,
             'cat_ints': pd.Categorical(v2 * repeats),
             'cat_binary': pd.Categorical(v3 * repeats),
-            'cat_strings_ordered': pd.Categorical(
-                v1 * repeats, categories=['bar', 'qux', 'foo'],
-                ordered=True),
+            'cat_strings_ordered': cat_strings_ordered,
             'ints': v2 * repeats,
             'ints2': v2 * repeats,
             'strings': v1 * repeats,
@@ -3096,10 +3100,10 @@ def _check(v):
             result = arr.to_pandas()
             tm.assert_series_equal(pd.Series(result), pd.Series(v))
 
+        base = pd.Categorical(['a', 'b', 'c'])
         arrays = [
-            pd.Categorical(['a', 'b', 'c'], categories=['a', 'b']),
-            pd.Categorical(['a', 'b', 'c'], categories=['a', 'b'],
-                           ordered=True)
+            base.set_categories(['a', 'b']),
+            base.set_categories(['a', 'b']).as_ordered(),
         ]
         for arr in arrays:
             _check(arr)