additional test fixes (for tests that changed or no longer exist on main)

Author: jorisvandenbossche

pandas/tests/frame/indexing/test_indexing.py

@@ -519,7 +519,7 @@ def test_setitem_ambig(self, using_infer_string):
         else:
             assert dm[2].dtype == np.object_
 
-    @pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
+    @pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)", strict=False)
     def test_setitem_None(self, float_frame, using_infer_string):
         # GH #766
         float_frame[None] = float_frame["A"]

pandas/tests/frame/methods/test_align.py

@@ -3,6 +3,8 @@
 import numpy as np
 import pytest
 
+from pandas._config import using_string_dtype
+
 import pandas as pd
 from pandas import (
     DataFrame,
@@ -155,6 +157,7 @@ def test_align_series_condition(self):
         expected = DataFrame({"a": [0, 2, 0], "b": [0, 5, 0]})
         tm.assert_frame_equal(result, expected)
 
+    @pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
     def test_align_int(self, int_frame):
         # test other non-float types
         other = DataFrame(index=range(5), columns=["A", "B", "C"])

pandas/tests/frame/methods/test_quantile.py

@@ -354,7 +354,6 @@ def test_quantile_multi_empty(self, interp_method):
         )
         tm.assert_frame_equal(result, expected)
 
-    @pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
     def test_quantile_datetime(self, unit):
         dti = pd.to_datetime(["2010", "2011"]).as_unit(unit)
         df = DataFrame({"a": dti, "b": [0, 5]})
@@ -408,7 +407,6 @@ def test_quantile_datetime(self, unit):
         expected = DataFrame(index=[0.5], columns=[])
         tm.assert_frame_equal(result, expected)
 
-    @pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
     @pytest.mark.parametrize(
         "dtype",
         [
@@ -679,7 +677,6 @@ def test_quantile_nat(self, interp_method, request, using_array_manager, unit):
         )
         tm.assert_frame_equal(res, exp)
 
-    @pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
     def test_quantile_empty_no_rows_floats(self, interp_method):
         interpolation, method = interp_method
 

pandas/tests/frame/methods/test_to_csv.py

@@ -35,6 +35,7 @@ def read_csv(self, path, **kwargs):
 
         return read_csv(path, **params)
 
+    @pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
     def test_to_csv_from_csv1(self, float_frame, datetime_frame):
         with tm.ensure_clean("__tmp_to_csv_from_csv1__") as path:
             float_frame.iloc[:5, float_frame.columns.get_loc("A")] = np.nan

pandas/tests/frame/methods/test_update.py

@@ -169,7 +169,7 @@ def test_update_with_different_dtype(self, using_copy_on_write):
             {
                 "a": [1, 3],
                 "b": [np.nan, 2],
-                "c": Series(["foo", np.nan], dtype="object"),
+                "c": Series(["foo", np.nan]),
             }
         )
         tm.assert_frame_equal(df, expected)

pandas/tests/groupby/test_apply.py

@@ -6,6 +6,8 @@
 import numpy as np
 import pytest
 
+from pandas._config import using_string_dtype
+
 import pandas as pd
 from pandas import (
     DataFrame,
@@ -126,7 +128,7 @@ def test_apply_trivial(using_infer_string):
         {"key": ["a", "a", "b", "b", "a"], "data": [1.0, 2.0, 3.0, 4.0, 5.0]},
         columns=["key", "data"],
     )
-    dtype = "string" if using_infer_string else "object"
+    dtype = "str" if using_infer_string else "object"
     expected = pd.concat([df.iloc[1:], df.iloc[1:]], axis=1, keys=["float64", dtype])
 
     msg = "DataFrame.groupby with axis=1 is deprecated"
@@ -143,7 +145,7 @@ def test_apply_trivial_fail(using_infer_string):
         {"key": ["a", "a", "b", "b", "a"], "data": [1.0, 2.0, 3.0, 4.0, 5.0]},
         columns=["key", "data"],
     )
-    dtype = "string" if using_infer_string else "object"
+    dtype = "str" if using_infer_string else "object"
     expected = pd.concat([df, df], axis=1, keys=["float64", dtype])
     msg = "DataFrame.groupby with axis=1 is deprecated"
     with tm.assert_produces_warning(FutureWarning, match=msg):
@@ -1299,12 +1301,13 @@ def test_apply_dropna_with_indexed_same(dropna):
 @pytest.mark.parametrize(
     "as_index, expected",
     [
-        [
+        pytest.param(
             False,
             DataFrame(
                 [[1, 1, 1], [2, 2, 1]], columns=Index(["a", "b", None], dtype=object)
             ),
-        ],
+            marks=pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)"),
+        ),
         [
             True,
             Series(

pandas/tests/groupby/test_groupby.py

@@ -1005,7 +1005,7 @@ def test_raises_on_nuisance(df):
     depr_msg = "DataFrame.groupby with axis=1 is deprecated"
     with tm.assert_produces_warning(FutureWarning, match=depr_msg):
         grouped = df.groupby({"A": 0, "C": 0, "D": 1, "E": 1}, axis=1)
-    msg = "does not support reduction 'sum'"
+    msg = "does not support reduction 'sum'|Cannot perform reduction 'sum'"
     with pytest.raises(TypeError, match=msg):
         grouped.agg(lambda x: x.sum(0, numeric_only=False))
 

pandas/tests/groupby/test_raises.py

@@ -219,7 +219,7 @@ def func(x):
         getattr(gb, how)(func)
 
 
-@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
+@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)", strict=False)
 @pytest.mark.parametrize("how", ["agg", "transform"])
 @pytest.mark.parametrize("groupby_func_np", [np.sum, np.mean])
 def test_groupby_raises_string_np(

pandas/tests/indexing/test_coercion.py

@@ -834,6 +834,7 @@ def replacer(self, how, from_key, to_key):
     def test_replace_series(self, how, to_key, from_key, replacer):
         index = pd.Index([3, 4], name="xxx")
         obj = pd.Series(self.rep[from_key], index=index, name="yyy")
+        obj = obj.astype(from_key)
         assert obj.dtype == from_key
 
         if from_key.startswith("datetime") and to_key.startswith("datetime"):
@@ -854,7 +855,6 @@ def test_replace_series(self, how, to_key, from_key, replacer):
 
         else:
             exp = pd.Series(self.rep[to_key], index=index, name="yyy")
-            assert exp.dtype == to_key
 
         msg = "Downcasting behavior in `replace`"
         warn = FutureWarning

pandas/tests/indexing/test_indexing.py

@@ -687,7 +687,7 @@ def test_loc_setitem_fullindex_views(self):
         df.loc[df.index] = df.loc[df.index]
         tm.assert_frame_equal(df, df2)
 
-    def test_rhs_alignment(self):
+    def test_rhs_alignment(self, using_infer_string):
         # GH8258, tests that both rows & columns are aligned to what is
         # assigned to. covers both uniform data-type & multi-type cases
         def run_tests(df, rhs, right_loc, right_iloc):
@@ -731,8 +731,17 @@ def run_tests(df, rhs, right_loc, right_iloc):
             frame["jolie"] = frame["jolie"].map(lambda x: f"@{x}")
         right_iloc["joe"] = [1.0, "@-28", "@-20", "@-12", 17.0]
         right_iloc["jolie"] = ["@2", -26.0, -18.0, -10.0, "@18"]
-        with tm.assert_produces_warning(FutureWarning, match="incompatible dtype"):
-            run_tests(df, rhs, right_loc, right_iloc)
+        if using_infer_string:
+            with pytest.raises(
+                TypeError, match="Must provide strings|Scalar must be NA or str"
+            ):
+                with tm.assert_produces_warning(
+                    FutureWarning, match="incompatible dtype"
+                ):
+                    run_tests(df, rhs, right_loc, right_iloc)
+        else:
+            with tm.assert_produces_warning(FutureWarning, match="incompatible dtype"):
+                run_tests(df, rhs, right_loc, right_iloc)
 
     @pytest.mark.parametrize(
         "idx", [_mklbl("A", 20), np.arange(20) + 100, np.linspace(100, 150, 20)]

pandas/tests/io/parser/common/test_file_buffer_url.py

@@ -87,8 +87,8 @@ def test_path_local_path(all_parsers):
     parser = all_parsers
     df = DataFrame(
         1.1 * np.arange(120).reshape((30, 4)),
-        columns=Index(list("ABCD"), dtype=object),
-        index=Index([f"i-{i}" for i in range(30)], dtype=object),
+        columns=Index(list("ABCD")),
+        index=Index([f"i-{i}" for i in range(30)]),
     )
     result = tm.round_trip_localpath(
         df.to_csv, lambda p: parser.read_csv(p, index_col=0)

pandas/tests/io/test_common.py

@@ -308,10 +308,12 @@ def test_read_expands_user_home_dir(
                 "pyarrow",
                 ("io", "data", "feather", "feather-0_3_1.feather"),
             ),
-            (
+            pytest.param(
                 pd.read_hdf,
                 "tables",
                 ("io", "data", "legacy_hdf", "datetimetz_object.h5"),
+                # cleaned-up in https://github.com/pandas-dev/pandas/pull/57387 on main
+                marks=pytest.mark.xfail(reason="TODO(infer_string)", strict=False),
             ),
             (pd.read_stata, "os", ("io", "data", "stata", "stata10_115.dta")),
             (pd.read_sas, "os", ("io", "sas", "data", "test1.sas7bdat")),

pandas/tests/io/test_pickle.py

@@ -413,10 +413,16 @@ def test_read(self, protocol, get_random_path):
 @pytest.mark.parametrize(
     ["pickle_file", "excols"],
     [
-        ("test_py27.pkl", Index(["a", "b", "c"])),
+        ("test_py27.pkl", Index(["a", "b", "c"], dtype=object)),
         (
             "test_mi_py27.pkl",
-            pd.MultiIndex.from_arrays([["a", "b", "c"], ["A", "B", "C"]]),
+            pd.MultiIndex(
+                [
+                    Index(["a", "b", "c"], dtype=object),
+                    Index(["A", "B", "C"], dtype=object),
+                ],
+                [np.array([0, 1, 2]), np.array([0, 1, 2])],
+            ),
         ),
     ],
 )

pandas/tests/io/test_stata.py

@@ -1563,8 +1563,8 @@ def test_path_pathlib(self):
     def test_pickle_path_localpath(self):
         df = DataFrame(
             1.1 * np.arange(120).reshape((30, 4)),
-            columns=pd.Index(list("ABCD"), dtype=object),
-            index=pd.Index([f"i-{i}" for i in range(30)], dtype=object),
+            columns=pd.Index(list("ABCD")),
+            index=pd.Index([f"i-{i}" for i in range(30)]),
         )
         df.index.name = "index"
         reader = lambda x: read_stata(x).set_index("index")

pandas/tests/tools/test_to_datetime.py

@@ -1207,10 +1207,8 @@ def test_out_of_bounds_errors_ignore2(self):
         # GH#12424
         msg = "errors='ignore' is deprecated"
         with tm.assert_produces_warning(FutureWarning, match=msg):
-            res = to_datetime(
-                Series(["2362-01-01", np.nan], dtype=object), errors="ignore"
-            )
-        exp = Series(["2362-01-01", np.nan], dtype=object)
+            res = to_datetime(Series(["2362-01-01", np.nan]), errors="ignore")
+        exp = Series(["2362-01-01", np.nan])
         tm.assert_series_equal(res, exp)
 
     def test_to_datetime_tz(self, cache):