[backport 2.3.x] TST (string dtype): un-xfail string tests specific to object dtype (#59433) (#60180)

Co-authored-by: jbrockmendel <[email protected]>

Author: jorisvandenbossche

pandas/tests/copy_view/test_interp_fillna.py

@@ -1,8 +1,6 @@
 import numpy as np
 import pytest
 
-from pandas._config import using_string_dtype
-
 from pandas import (
     NA,
     ArrowDtype,
@@ -137,10 +135,9 @@ def test_interp_fill_functions_inplace(
         assert np.shares_memory(arr, get_array(df, "a")) is (dtype == "float64")
 
 
-@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
-def test_interpolate_cleaned_fill_method(using_copy_on_write):
-    # Check that "method is set to None" case works correctly
+def test_interpolate_cannot_with_object_dtype(using_copy_on_write):
     df = DataFrame({"a": ["a", np.nan, "c"], "b": 1})
+    df["a"] = df["a"].astype(object)
     df_orig = df.copy()
 
     msg = "DataFrame.interpolate with object dtype"
@@ -159,16 +156,16 @@ def test_interpolate_cleaned_fill_method(using_copy_on_write):
     tm.assert_frame_equal(df, df_orig)
 
 
-@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
-def test_interpolate_object_convert_no_op(using_copy_on_write):
+def test_interpolate_object_convert_no_op(using_copy_on_write, using_infer_string):
     df = DataFrame({"a": ["a", "b", "c"], "b": 1})
+    df["a"] = df["a"].astype(object)
     arr_a = get_array(df, "a")
     msg = "DataFrame.interpolate with method=pad is deprecated"
     with tm.assert_produces_warning(FutureWarning, match=msg):
         df.interpolate(method="pad", inplace=True)
 
     # Now CoW makes a copy, it should not!
-    if using_copy_on_write:
+    if using_copy_on_write and not using_infer_string:
         assert df._mgr._has_no_reference(0)
         assert np.shares_memory(arr_a, get_array(df, "a"))
 

pandas/tests/copy_view/test_replace.py

@@ -356,10 +356,9 @@ def test_replace_empty_list(using_copy_on_write):
         assert not df2._mgr._has_no_reference(0)
 
 
-@pytest.mark.xfail(using_string_dtype() and HAS_PYARROW, reason="TODO(infer_string)")
 @pytest.mark.parametrize("value", ["d", None])
 def test_replace_object_list_inplace(using_copy_on_write, value):
-    df = DataFrame({"a": ["a", "b", "c"]})
+    df = DataFrame({"a": ["a", "b", "c"]}, dtype=object)
     arr = get_array(df, "a")
     df.replace(["c"], value, inplace=True)
     if using_copy_on_write or value is None:

pandas/tests/test_algos.py

@@ -1704,20 +1704,25 @@ def test_unique_complex_numbers(self, array, expected):
 
 
 class TestHashTable:
-    @pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)", strict=False)
     @pytest.mark.parametrize(
         "htable, data",
         [
-            (ht.PyObjectHashTable, [f"foo_{i}" for i in range(1000)]),
-            (ht.StringHashTable, [f"foo_{i}" for i in range(1000)]),
+            (
+                ht.PyObjectHashTable,
+                np.array([f"foo_{i}" for i in range(1000)], dtype=object),
+            ),
+            (
+                ht.StringHashTable,
+                np.array([f"foo_{i}" for i in range(1000)], dtype=object),
+            ),
             (ht.Float64HashTable, np.arange(1000, dtype=np.float64)),
             (ht.Int64HashTable, np.arange(1000, dtype=np.int64)),
             (ht.UInt64HashTable, np.arange(1000, dtype=np.uint64)),
         ],
     )
     def test_hashtable_unique(self, htable, data, writable):
         # output of maker has guaranteed unique elements
-        s = Series(data)
+        s = Series(data, dtype=data.dtype)
         if htable == ht.Float64HashTable:
             # add NaN for float column
             s.loc[500] = np.nan
@@ -1744,20 +1749,25 @@ def test_hashtable_unique(self, htable, data, writable):
         reconstr = result_unique[result_inverse]
         tm.assert_numpy_array_equal(reconstr, s_duplicated.values)
 
-    @pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)", strict=False)
     @pytest.mark.parametrize(
         "htable, data",
         [
-            (ht.PyObjectHashTable, [f"foo_{i}" for i in range(1000)]),
-            (ht.StringHashTable, [f"foo_{i}" for i in range(1000)]),
+            (
+                ht.PyObjectHashTable,
+                np.array([f"foo_{i}" for i in range(1000)], dtype=object),
+            ),
+            (
+                ht.StringHashTable,
+                np.array([f"foo_{i}" for i in range(1000)], dtype=object),
+            ),
             (ht.Float64HashTable, np.arange(1000, dtype=np.float64)),
             (ht.Int64HashTable, np.arange(1000, dtype=np.int64)),
             (ht.UInt64HashTable, np.arange(1000, dtype=np.uint64)),
         ],
     )
     def test_hashtable_factorize(self, htable, writable, data):
         # output of maker has guaranteed unique elements
-        s = Series(data)
+        s = Series(data, dtype=data.dtype)
         if htable == ht.Float64HashTable:
             # add NaN for float column
             s.loc[500] = np.nan