TST (string dtype): un-xfail string tests specific to object dtype (pandas-dev#59433)

Co-authored-by: Joris Van den Bossche <jorisvandenbossche@gmail.com>

Author: jbrockmendel

pandas/tests/copy_view/test_interp_fillna.py

@@ -1,10 +1,6 @@
 import numpy as np
 import pytest
 
-from pandas._config import using_string_dtype
-
-from pandas.compat import HAS_PYARROW
-
 from pandas import (
  NA,
  DataFrame,
@@ -114,18 +110,18 @@ def test_interp_fill_functions_inplace(func, dtype):
  assert view._mgr._has_no_reference(0)
 
 
-@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
 def test_interpolate_cannot_with_object_dtype():
  df = DataFrame({"a": ["a", np.nan, "c"], "b": 1})
+ df["a"] = df["a"].astype(object)
 
  msg = "DataFrame cannot interpolate with object dtype"
  with pytest.raises(TypeError, match=msg):
  df.interpolate()
 
 
-@pytest.mark.xfail(using_string_dtype() and HAS_PYARROW, reason="TODO(infer_string)")
 def test_interpolate_object_convert_no_op():
  df = DataFrame({"a": ["a", "b", "c"], "b": 1})
+ df["a"] = df["a"].astype(object)
  arr_a = get_array(df, "a")
 
  # Now CoW makes a copy, it should not!

pandas/tests/copy_view/test_replace.py

@@ -259,10 +259,9 @@ def test_replace_empty_list():
  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(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)
  assert np.shares_memory(arr, get_array(df, "a"))

pandas/tests/test_algos.py

@@ -4,8 +4,6 @@
 import numpy as np
 import pytest
 
-from pandas._config import using_string_dtype
-
 from pandas._libs import (
  algos as libalgos,
  hashtable as ht,
@@ -1684,20 +1682,25 @@ 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
@@ -1724,20 +1727,25 @@ 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