TST (string dtype): resolve xfails in pandas/tests/series

Author: jorisvandenbossche

pandas/tests/series/accessors/test_dt_accessor.py

@@ -556,7 +556,6 @@ def test_strftime(self):
         )
         tm.assert_series_equal(result, expected)
 
-    @pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
     def test_strftime_dt64_days(self):
         ser = Series(date_range("20130101", periods=5))
         ser.iloc[0] = pd.NaT
@@ -571,7 +570,6 @@ def test_strftime_dt64_days(self):
 
         expected = Index(
             ["2015/03/01", "2015/03/02", "2015/03/03", "2015/03/04", "2015/03/05"],
-            dtype=np.object_,
         )
         # dtype may be S10 or U10 depending on python version
         tm.assert_index_equal(result, expected)

pandas/tests/series/indexing/test_indexing.py

@@ -6,8 +6,6 @@
 import numpy as np
 import pytest
 
-from pandas._config import using_string_dtype
-
 from pandas.errors import IndexingError
 
 from pandas import (
@@ -251,18 +249,29 @@ def test_slice(string_series, object_series):
     tm.assert_series_equal(string_series, original)
 
 
-@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
 def test_timedelta_assignment():
     # GH 8209
     s = Series([], dtype=object)
     s.loc["B"] = timedelta(1)
-    tm.assert_series_equal(s, Series(Timedelta("1 days"), index=["B"]))
+    expected = Series(
+        Timedelta("1 days"), dtype="timedelta64[ns]", index=Index(["B"], dtype=object)
+    )
+    tm.assert_series_equal(s, expected)
 
     s = s.reindex(s.index.insert(0, "A"))
-    tm.assert_series_equal(s, Series([np.nan, Timedelta("1 days")], index=["A", "B"]))
+    expected = Series(
+        [np.nan, Timedelta("1 days")],
+        dtype="timedelta64[ns]",
+        index=Index(["A", "B"], dtype=object),
+    )
+    tm.assert_series_equal(s, expected)
 
     s.loc["A"] = timedelta(1)
-    expected = Series(Timedelta("1 days"), index=["A", "B"])
+    expected = Series(
+        Timedelta("1 days"),
+        dtype="timedelta64[ns]",
+        index=Index(["A", "B"], dtype=object),
+    )
     tm.assert_series_equal(s, expected)
 
 

pandas/tests/series/indexing/test_setitem.py

@@ -9,12 +9,7 @@
 import numpy as np
 import pytest
 
-from pandas._config import using_string_dtype
-
-from pandas.compat import (
-    HAS_PYARROW,
-    WASM,
-)
+from pandas.compat import WASM
 from pandas.compat.numpy import np_version_gte1p24
 from pandas.errors import IndexingError
 
@@ -535,14 +530,16 @@ def test_append_timedelta_does_not_cast(self, td, using_infer_string, request):
         tm.assert_series_equal(ser, expected)
         assert isinstance(ser["td"], Timedelta)
 
-    @pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
     def test_setitem_with_expansion_type_promotion(self):
         # GH#12599
         ser = Series(dtype=object)
         ser["a"] = Timestamp("2016-01-01")
         ser["b"] = 3.0
         ser["c"] = "foo"
-        expected = Series([Timestamp("2016-01-01"), 3.0, "foo"], index=["a", "b", "c"])
+        expected = Series(
+            [Timestamp("2016-01-01"), 3.0, "foo"],
+            index=Index(["a", "b", "c"], dtype=object),
+        )
         tm.assert_series_equal(ser, expected)
 
     def test_setitem_not_contained(self, string_series):
@@ -826,11 +823,6 @@ def test_mask_key(self, obj, key, expected, raises, val, indexer_sli):
         else:
             indexer_sli(obj)[mask] = val
 
-    @pytest.mark.xfail(
-        using_string_dtype() and not HAS_PYARROW,
-        reason="TODO(infer_string)",
-        strict=False,
-    )
     def test_series_where(self, obj, key, expected, raises, val, is_inplace):
         mask = np.zeros(obj.shape, dtype=bool)
         mask[key] = True
@@ -846,6 +838,11 @@ def test_series_where(self, obj, key, expected, raises, val, is_inplace):
         obj = obj.copy()
         arr = obj._values
 
+        if raises and obj.dtype == "string":
+            with pytest.raises(TypeError, match="Invalid value"):
+                obj.where(~mask, val)
+            return
+
         res = obj.where(~mask, val)
 
         if val is NA and res.dtype == object:
@@ -858,25 +855,23 @@ def test_series_where(self, obj, key, expected, raises, val, is_inplace):
 
         self._check_inplace(is_inplace, orig, arr, obj)
 
-    @pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)", strict=False)
-    def test_index_where(self, obj, key, expected, raises, val, using_infer_string):
+    def test_index_where(self, obj, key, expected, raises, val):
         mask = np.zeros(obj.shape, dtype=bool)
         mask[key] = True
 
-        if using_infer_string and obj.dtype == object:
+        if raises and obj.dtype == "string":
             with pytest.raises(TypeError, match="Invalid value"):
                 Index(obj).where(~mask, val)
         else:
             res = Index(obj).where(~mask, val)
             expected_idx = Index(expected, dtype=expected.dtype)
             tm.assert_index_equal(res, expected_idx)
 
-    @pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)", strict=False)
-    def test_index_putmask(self, obj, key, expected, raises, val, using_infer_string):
+    def test_index_putmask(self, obj, key, expected, raises, val):
         mask = np.zeros(obj.shape, dtype=bool)
         mask[key] = True
 
-        if using_infer_string and obj.dtype == object:
+        if raises and obj.dtype == "string":
             with pytest.raises(TypeError, match="Invalid value"):
                 Index(obj).putmask(mask, val)
         else:
@@ -1372,6 +1367,19 @@ def raises(self):
         return False
 
 
+@pytest.mark.parametrize(
+    "val,exp_dtype,raises",
+    [
+        (1, object, True),
+        ("e", "str", False),
+    ],
+)
+class TestCoercionString(CoercionTest):
+    @pytest.fixture
+    def obj(self):
+        return Series(["a", "b", "c", "d"])
+
+
 @pytest.mark.parametrize(
     "val,exp_dtype,raises",
     [

pandas/tests/series/methods/test_replace.py

@@ -656,21 +656,18 @@ def test_replace_value_none_dtype_numeric(self, val):
         expected = pd.Series([1, None], dtype=object)
         tm.assert_series_equal(result, expected)
 
-    @pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
-    def test_replace_change_dtype_series(self, using_infer_string):
+    def test_replace_change_dtype_series(self):
         # GH#25797
-        df = pd.DataFrame.from_dict({"Test": ["0.5", True, "0.6"]})
-        warn = FutureWarning if using_infer_string else None
-        with tm.assert_produces_warning(warn, match="Downcasting"):
-            df["Test"] = df["Test"].replace([True], [np.nan])
-        expected = pd.DataFrame.from_dict({"Test": ["0.5", np.nan, "0.6"]})
+        df = pd.DataFrame({"Test": ["0.5", True, "0.6"]}, dtype=object)
+        df["Test"] = df["Test"].replace([True], [np.nan])
+        expected = pd.DataFrame({"Test": ["0.5", np.nan, "0.6"]}, dtype=object)
         tm.assert_frame_equal(df, expected)
 
-        df = pd.DataFrame.from_dict({"Test": ["0.5", None, "0.6"]})
+        df = pd.DataFrame({"Test": ["0.5", None, "0.6"]}, dtype=object)
         df["Test"] = df["Test"].replace([None], [np.nan])
         tm.assert_frame_equal(df, expected)
 
-        df = pd.DataFrame.from_dict({"Test": ["0.5", None, "0.6"]})
+        df = pd.DataFrame({"Test": ["0.5", None, "0.6"]},  dtype=object)
         df["Test"] = df["Test"].fillna(np.nan)
         tm.assert_frame_equal(df, expected)
 

pandas/tests/series/methods/test_unstack.py

@@ -136,11 +136,10 @@ def test_unstack_mixed_type_name_in_multiindex(
     tm.assert_frame_equal(result, expected)
 
 
-@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
 def test_unstack_multi_index_categorical_values():
     df = DataFrame(
         np.random.default_rng(2).standard_normal((10, 4)),
-        columns=Index(list("ABCD"), dtype=object),
+        columns=Index(list("ABCD")),
         index=date_range("2000-01-01", periods=10, freq="B"),
     )
     mi = df.stack().index.rename(["major", "minor"])