use str alias more in tests

Author: jorisvandenbossche

pandas/tests/apply/test_series_apply.py

@@ -224,7 +224,7 @@ def test_apply_categorical(by_row, using_infer_string):
     result = ser.apply(lambda x: "A")
     exp = Series(["A"] * 7, name="XX", index=list("abcdefg"))
     tm.assert_series_equal(result, exp)
-    assert result.dtype == object if not using_infer_string else "string[pyarrow_numpy]"
+    assert result.dtype == object if not using_infer_string else "str"
 
 
 @pytest.mark.parametrize("series", [["1-1", "1-1", np.nan], ["1-1", "1-2", np.nan]])

pandas/tests/frame/indexing/test_indexing.py

@@ -323,7 +323,7 @@ def test_setitem(self, float_frame, using_infer_string):
         smaller["col10"] = ["1", "2"]
 
         if using_infer_string:
-            assert smaller["col10"].dtype == "string"
+            assert smaller["col10"].dtype == "str"
         else:
             assert smaller["col10"].dtype == np.object_
         assert (smaller["col10"] == ["1", "2"]).all()
@@ -458,13 +458,13 @@ def test_setitem_corner(self, float_frame, using_infer_string):
         del dm["foo"]
         dm["foo"] = "bar"
         if using_infer_string:
-            assert dm["foo"].dtype == "string"
+            assert dm["foo"].dtype == "str"
         else:
             assert dm["foo"].dtype == np.object_
 
         dm["coercible"] = ["1", "2", "3"]
         if using_infer_string:
-            assert dm["coercible"].dtype == "string"
+            assert dm["coercible"].dtype == "str"
         else:
             assert dm["coercible"].dtype == np.object_
 
@@ -500,7 +500,7 @@ def test_setitem_ambig(self, using_infer_string):
         dm[2] = uncoercable_series
         assert len(dm.columns) == 3
         if using_infer_string:
-            assert dm[2].dtype == "string"
+            assert dm[2].dtype == "str"
         else:
             assert dm[2].dtype == np.object_
 

pandas/tests/frame/indexing/test_set_value.py

@@ -28,7 +28,7 @@ def test_set_value_resize(self, float_frame, using_infer_string):
         res = float_frame.copy()
         res._set_value("foobar", "baz", "sam")
         if using_infer_string:
-            assert res["baz"].dtype == "string"
+            assert res["baz"].dtype == "str"
         else:
             assert res["baz"].dtype == np.object_
         res = float_frame.copy()

pandas/tests/frame/methods/test_get_numeric_data.py

@@ -33,7 +33,9 @@ def test_get_numeric_data(self, using_infer_string):
             [
                 np.dtype("float64"),
                 np.dtype("int64"),
-                np.dtype(objectname) if not using_infer_string else "string",
+                np.dtype(objectname)
+                if not using_infer_string
+                else pd.StringDtype(na_value=np.nan),
                 np.dtype(datetime64name),
             ],
             index=["a", "b", "c", "f"],

pandas/tests/frame/methods/test_reset_index.py

@@ -695,7 +695,7 @@ def test_reset_index_empty_frame_with_datetime64_multiindex_from_groupby(
     expected["c3"] = expected["c3"].astype("datetime64[ns]")
     expected["c1"] = expected["c1"].astype("float64")
     if using_infer_string:
-        expected["c2"] = expected["c2"].astype("string[pyarrow_numpy]")
+        expected["c2"] = expected["c2"].astype("str")
     tm.assert_frame_equal(result, expected)
 
 

pandas/tests/frame/methods/test_to_csv.py

@@ -715,7 +715,7 @@ def test_to_csv_interval_index(self, temp_file, using_infer_string):
         # can't roundtrip intervalindex via read_csv so check string repr (GH 23595)
         expected = df.copy()
         if using_infer_string:
-            expected.index = expected.index.astype("string[pyarrow_numpy]")
+            expected.index = expected.index.astype("str")
         else:
             expected.index = expected.index.astype(str)
 

pandas/tests/frame/test_block_internals.py

@@ -186,7 +186,7 @@ def test_construction_with_mixed(self, float_string_frame, using_infer_string):
         expected = Series(
             [np.dtype("float64")] * 4
             + [
-                np.dtype("object") if not using_infer_string else "string",
+                np.dtype("object") if not using_infer_string else "str",
                 np.dtype("datetime64[us]"),
                 np.dtype("timedelta64[us]"),
             ],

pandas/tests/frame/test_constructors.py

@@ -760,7 +760,7 @@ def test_constructor_dict_cast(self, using_infer_string):
 
         frame = DataFrame(test_data)
         assert len(frame) == 3
-        assert frame["B"].dtype == np.object_ if not using_infer_string else "string"
+        assert frame["B"].dtype == np.object_ if not using_infer_string else "str"
         assert frame["A"].dtype == np.float64
 
     def test_constructor_dict_cast2(self):
@@ -1182,7 +1182,7 @@ def test_constructor_scalar_inference(self, using_infer_string):
         assert df["bool"].dtype == np.bool_
         assert df["float"].dtype == np.float64
         assert df["complex"].dtype == np.complex128
-        assert df["object"].dtype == np.object_ if not using_infer_string else "string"
+        assert df["object"].dtype == np.object_ if not using_infer_string else "str"
 
     def test_constructor_arrays_and_scalars(self):
         df = DataFrame({"a": np.random.default_rng(2).standard_normal(10), "b": True})
@@ -1265,7 +1265,7 @@ def test_constructor_list_of_lists(self, using_infer_string):
         # GH #484
         df = DataFrame(data=[[1, "a"], [2, "b"]], columns=["num", "str"])
         assert is_integer_dtype(df["num"])
-        assert df["str"].dtype == np.object_ if not using_infer_string else "string"
+        assert df["str"].dtype == np.object_ if not using_infer_string else "str"
 
         # GH 4851
         # list of 0-dim ndarrays
@@ -1833,7 +1833,12 @@ def test_constructor_with_datetimes(self, using_infer_string):
         result = df.dtypes
         expected = Series(
             [np.dtype("int64")]
-            + [np.dtype(objectname) if not using_infer_string else "string"] * 2
+            + [
+                np.dtype(objectname)
+                if not using_infer_string
+                else pd.StringDtype(na_value=np.nan)
+            ]
+            * 2
             + [np.dtype("M8[s]"), np.dtype("M8[us]")],
             index=list("ABCDE"),
         )
@@ -1855,7 +1860,11 @@ def test_constructor_with_datetimes(self, using_infer_string):
         expected = Series(
             [np.dtype("float64")]
             + [np.dtype("int64")]
-            + [np.dtype("object") if not using_infer_string else "string"]
+            + [
+                np.dtype("object")
+                if not using_infer_string
+                else pd.StringDtype(na_value=np.nan)
+            ]
             + [np.dtype("float64")]
             + [np.dtype(intname)],
             index=["a", "b", "c", floatname, intname],
@@ -1877,7 +1886,11 @@ def test_constructor_with_datetimes(self, using_infer_string):
         expected = Series(
             [np.dtype("float64")]
             + [np.dtype("int64")]
-            + [np.dtype("object") if not using_infer_string else "string"]
+            + [
+                np.dtype("object")
+                if not using_infer_string
+                else pd.StringDtype(na_value=np.nan)
+            ]
             + [np.dtype("float64")]
             + [np.dtype(intname)],
             index=["a", "b", "c", floatname, intname],
@@ -2103,7 +2116,9 @@ def test_constructor_for_list_with_dtypes(self, using_infer_string):
             [
                 np.dtype("int64"),
                 np.dtype("float64"),
-                np.dtype("object") if not using_infer_string else "string",
+                np.dtype("object")
+                if not using_infer_string
+                else pd.StringDtype(na_value=np.nan),
                 np.dtype("datetime64[us]"),
                 np.dtype("float64"),
             ],

pandas/tests/generic/test_to_xarray.py

@@ -52,7 +52,7 @@ def test_to_xarray_index_types(self, index_flat, df, using_infer_string):
         # column names are lost
         expected = df.copy()
         expected["f"] = expected["f"].astype(
-            object if not using_infer_string else "string[pyarrow_numpy]"
+            object if not using_infer_string else "str"
         )
         expected.columns.name = None
         tm.assert_frame_equal(result.to_dataframe(), expected)
@@ -81,7 +81,7 @@ def test_to_xarray_with_multiindex(self, df, using_infer_string):
         result = result.to_dataframe()
         expected = df.copy()
         expected["f"] = expected["f"].astype(
-            object if not using_infer_string else "string[pyarrow_numpy]"
+            object if not using_infer_string else "str"
         )
         expected.columns.name = None
         tm.assert_frame_equal(result, expected)

pandas/tests/groupby/test_apply.py

@@ -109,7 +109,7 @@ def test_apply_index_date_object(using_infer_string):
         1.40750,
         1.40649,
     ]
-    dtype = "string[pyarrow_numpy]" if using_infer_string else object
+    dtype = "str" if using_infer_string else object
     exp_idx = Index(
         ["2011-05-16", "2011-05-17", "2011-05-18"], dtype=dtype, name="date"
     )