use str alias more in tests instead of object or str

Author: jorisvandenbossche

pandas/tests/arrays/string_/test_string_arrow.py

@@ -26,11 +26,7 @@ def test_eq_all_na():
     tm.assert_extension_array_equal(result, expected)
 
 
-def test_config(string_storage, request, using_infer_string):
-    if using_infer_string and string_storage == "python":
-        # python string storage with na_value=NaN is not yet implemented
-        request.applymarker(pytest.mark.xfail(reason="TODO(infer_string)"))
-
+def test_config(string_storage, using_infer_string):
     with pd.option_context("string_storage", string_storage):
         assert StringDtype().storage == string_storage
         result = pd.array(["a", "b"])

pandas/tests/frame/methods/test_to_csv.py

@@ -714,10 +714,7 @@ 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("str")
-        else:
-            expected.index = expected.index.astype(str)
+        expected.index = expected.index.astype("str")
 
         tm.assert_frame_equal(result, expected)
 

pandas/tests/groupby/test_apply.py

@@ -77,7 +77,7 @@ def test_apply_index_date(using_infer_string):
     tm.assert_frame_equal(result, expected)
 
 
-def test_apply_index_date_object(using_infer_string):
+def test_apply_index_date_object():
     # GH 5789
     # don't auto coerce dates
     ts = [
@@ -109,10 +109,7 @@ def test_apply_index_date_object(using_infer_string):
         1.40750,
         1.40649,
     ]
-    dtype = "str" if using_infer_string else object
-    exp_idx = Index(
-        ["2011-05-16", "2011-05-17", "2011-05-18"], dtype=dtype, name="date"
-    )
+    exp_idx = Index(["2011-05-16", "2011-05-17", "2011-05-18"], name="date")
     expected = Series(["00:00", "02:00", "02:00"], index=exp_idx)
     msg = "DataFrameGroupBy.apply operated on the grouping columns"
     with tm.assert_produces_warning(DeprecationWarning, match=msg):
@@ -924,7 +921,7 @@ def test_func_returns_object():
     "group_column_dtlike",
     [datetime.today(), datetime.today().date(), datetime.today().time()],
 )
-def test_apply_datetime_issue(group_column_dtlike, using_infer_string):
+def test_apply_datetime_issue(group_column_dtlike):
     # GH-28247
     # groupby-apply throws an error if one of the columns in the DataFrame
     #   is a datetime object and the column labels are different from
@@ -935,8 +932,7 @@ def test_apply_datetime_issue(group_column_dtlike, using_infer_string):
     with tm.assert_produces_warning(DeprecationWarning, match=msg):
         result = df.groupby("a").apply(lambda x: Series(["spam"], index=[42]))
 
-    dtype = "str" if using_infer_string else "object"
-    expected = DataFrame(["spam"], Index(["foo"], dtype=dtype, name="a"), columns=[42])
+    expected = DataFrame(["spam"], Index(["foo"], dtype="str", name="a"), columns=[42])
     tm.assert_frame_equal(result, expected)
 
 

pandas/tests/groupby/test_groupby.py

@@ -889,7 +889,7 @@ def test_groupby_complex_mean():
     tm.assert_frame_equal(result, expected)
 
 
-def test_groupby_complex_numbers(using_infer_string):
+def test_groupby_complex_numbers():
     # GH 17927
     df = DataFrame(
         [
@@ -898,11 +898,10 @@ def test_groupby_complex_numbers(using_infer_string):
             {"a": 4, "b": 1},
         ]
     )
-    dtype = "str" if using_infer_string else object
     expected = DataFrame(
         np.array([1, 1, 1], dtype=np.int64),
         index=Index([(1 + 1j), (1 + 2j), (1 + 0j)], name="b"),
-        columns=Index(["a"], dtype=dtype),
+        columns=Index(["a"]),
     )
     result = df.groupby("b", sort=False).count()
     tm.assert_frame_equal(result, expected)

pandas/tests/series/indexing/test_delitem.py

@@ -31,16 +31,15 @@ def test_delitem(self):
         del s[0]
         tm.assert_series_equal(s, Series(dtype="int64", index=Index([], dtype="int64")))
 
-    def test_delitem_object_index(self, using_infer_string):
+    def test_delitem_object_index(self):
         # Index(dtype=object)
-        dtype = "str" if using_infer_string else object
-        s = Series(1, index=Index(["a"], dtype=dtype))
+        s = Series(1, index=Index(["a"], dtype="str"))
         del s["a"]
-        tm.assert_series_equal(s, Series(dtype="int64", index=Index([], dtype=dtype)))
+        tm.assert_series_equal(s, Series(dtype="int64", index=Index([], dtype="str")))
         s["a"] = 1
-        tm.assert_series_equal(s, Series(1, index=Index(["a"], dtype=dtype)))
+        tm.assert_series_equal(s, Series(1, index=Index(["a"], dtype="str")))
         del s["a"]
-        tm.assert_series_equal(s, Series(dtype="int64", index=Index([], dtype=dtype)))
+        tm.assert_series_equal(s, Series(dtype="int64", index=Index([], dtype="str")))
 
     def test_delitem_missing_key(self):
         # empty

pandas/tests/series/methods/test_astype.py

@@ -524,7 +524,7 @@ def test_astype_string_to_extension_dtype_roundtrip(
 
 
 class TestAstypeCategorical:
-    def test_astype_categorical_to_other(self, using_infer_string):
+    def test_astype_categorical_to_other(self):
         cat = Categorical([f"{i} - {i + 499}" for i in range(0, 10000, 500)])
         ser = Series(np.random.default_rng(2).integers(0, 10000, 100)).sort_values()
         ser = cut(ser, range(0, 10500, 500), right=False, labels=cat)
@@ -537,8 +537,7 @@ def test_astype_categorical_to_other(self, using_infer_string):
             ser.astype("float64")
 
         cat = Series(Categorical(["a", "b", "b", "a", "a", "c", "c", "c"]))
-        dtype = "str" if using_infer_string else "object"
-        exp = Series(["a", "b", "b", "a", "a", "c", "c", "c"], dtype=dtype)
+        exp = Series(["a", "b", "b", "a", "a", "c", "c", "c"], dtype="str")
         tm.assert_series_equal(cat.astype("str"), exp)
         s2 = Series(Categorical(["1", "2", "3", "4"]))
         exp2 = Series([1, 2, 3, 4]).astype("int")

pandas/tests/series/methods/test_to_csv.py

@@ -176,8 +176,5 @@ def test_to_csv_interval_index(self, using_infer_string, temp_file):
 
         # can't roundtrip intervalindex via read_csv so check string repr (GH 23595)
         expected = s
-        if using_infer_string:
-            expected.index = expected.index.astype("str")
-        else:
-            expected.index = expected.index.astype(str)
+        expected.index = expected.index.astype("str")
         tm.assert_series_equal(result, expected)