fix more tests + remove some xfails

Author: jorisvandenbossche

pandas/tests/arrays/interval/test_interval_pyarrow.py

@@ -1,8 +1,6 @@
 import numpy as np
 import pytest
 
-from pandas._config import using_string_dtype
-
 import pandas as pd
 import pandas._testing as tm
 from pandas.core.arrays import IntervalArray
@@ -82,7 +80,6 @@ def test_arrow_array_missing():
     assert result.storage.equals(expected)
 
 
-@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
 @pytest.mark.filterwarnings(
     "ignore:Passing a BlockManager to DataFrame:DeprecationWarning"
 )

pandas/tests/arrays/period/test_arrow_compat.py

@@ -1,7 +1,5 @@
 import pytest
 
-from pandas._config import using_string_dtype
-
 from pandas.compat.pyarrow import pa_version_under10p1
 
 from pandas.core.dtypes.dtypes import PeriodDtype
@@ -79,7 +77,6 @@ def test_arrow_array_missing():
     assert result.storage.equals(expected)
 
 
-@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
 def test_arrow_table_roundtrip():
     from pandas.core.arrays.arrow.extension_types import ArrowPeriodType
 
@@ -99,7 +96,6 @@ def test_arrow_table_roundtrip():
     tm.assert_frame_equal(result, expected)
 
 
-@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
 def test_arrow_load_from_zero_chunks():
     # GH-41040
 

pandas/tests/frame/methods/test_reset_index.py

@@ -662,7 +662,7 @@ def test_reset_index_dtypes_on_empty_frame_with_multiindex(
     idx = MultiIndex.from_product([[0, 1], [0.5, 1.0], array])
     result = DataFrame(index=idx)[:0].reset_index().dtypes
     if using_infer_string and dtype == object:
-        dtype = "string"
+        dtype = "str"
     expected = Series({"level_0": np.int64, "level_1": np.float64, "level_2": dtype})
     tm.assert_series_equal(result, expected)
 

pandas/tests/frame/methods/test_select_dtypes.py

@@ -1,6 +1,8 @@
 import numpy as np
 import pytest
 
+from pandas._config import using_string_dtype
+
 from pandas.core.dtypes.dtypes import ExtensionDtype
 
 import pandas as pd
@@ -345,6 +347,7 @@ def test_select_dtypes_datetime_with_tz(self):
         expected = df3.reindex(columns=[])
         tm.assert_frame_equal(result, expected)
 
+    @pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)", strict=False)
     @pytest.mark.parametrize("dtype", [str, "str", np.bytes_, "S1", np.str_, "U1"])
     @pytest.mark.parametrize("arg", ["include", "exclude"])
     def test_select_dtypes_str_raises(self, dtype, arg):

pandas/tests/frame/test_constructors.py

@@ -256,7 +256,7 @@ def test_emptylike_constructor(self, emptylike, expected_index, expected_columns
         tm.assert_frame_equal(result, expected)
 
     def test_constructor_mixed(self, float_string_frame, using_infer_string):
-        dtype = "string" if using_infer_string else np.object_
+        dtype = "str" if using_infer_string else np.object_
         assert float_string_frame["foo"].dtype == dtype
 
     def test_constructor_cast_failure(self):

pandas/tests/frame/test_stack_unstack.py

@@ -658,7 +658,7 @@ def test_unstack_dtypes(self, using_infer_string):
         df2["D"] = "foo"
         df3 = df2.unstack("B")
         result = df3.dtypes
-        dtype = "string" if using_infer_string else np.dtype("object")
+        dtype = "str" if using_infer_string else np.dtype("object")
         expected = Series(
             [np.dtype("float64")] * 2 + [dtype] * 2,
             index=MultiIndex.from_arrays(

pandas/tests/groupby/test_apply.py

@@ -1017,7 +1017,7 @@ def test_groupby_apply_datetime_result_dtypes(using_infer_string):
     msg = "DataFrameGroupBy.apply operated on the grouping columns"
     with tm.assert_produces_warning(DeprecationWarning, match=msg):
         result = data.groupby("color").apply(lambda g: g.iloc[0]).dtypes
-    dtype = "string" if using_infer_string else object
+    dtype = "str" if using_infer_string else object
     expected = Series(
         [np.dtype("datetime64[us]"), dtype, dtype, np.int64, dtype],
         index=["observation", "color", "mood", "intensity", "score"],

pandas/tests/indexes/base_class/test_formats.py

@@ -9,7 +9,6 @@
 
 
 class TestIndexRendering:
-    @pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
     def test_repr_is_valid_construction_code(self):
         # for the case of Index, where the repr is traditional rather than
         # stylized

pandas/tests/indexing/test_indexing.py

@@ -259,7 +259,7 @@ def test_dups_fancy_indexing_only_missing_label(self, using_infer_string):
             with pytest.raises(
                 KeyError,
                 match=re.escape(
-                    "\"None of [Index(['E'], dtype='string')] are in the [index]\""
+                    "\"None of [Index(['E'], dtype='str')] are in the [index]\""
                 ),
             ):
                 dfnu.loc[["E"]]

pandas/tests/indexing/test_loc.py

@@ -62,12 +62,17 @@ def test_not_change_nan_loc(series, new_series, expected_ser):
 
 
 class TestLoc:
-    def test_none_values_on_string_columns(self):
+    def test_none_values_on_string_columns(self, using_infer_string):
         # Issue #32218
-        df = DataFrame(["1", "2", None], columns=["a"], dtype="str")
-
+        df = DataFrame(["1", "2", None], columns=["a"], dtype=object)
         assert df.loc[2, "a"] is None
 
+        df = DataFrame(["1", "2", None], columns=["a"], dtype="str")
+        if using_infer_string:
+            assert np.isnan(df.loc[2, "a"])
+        else:
+            assert df.loc[2, "a"] is None
+
     def test_loc_getitem_int(self, frame_or_series):
         # int label
         obj = frame_or_series(range(3), index=Index(list("abc"), dtype=object))