update tests

Author: jorisvandenbossche

pandas/tests/arithmetic/test_object.py

@@ -183,6 +183,10 @@ def test_objarr_add_invalid(self, op, box_with_array):
                 "unsupported operand type",
                 "must be str",
                 "has no kernel",
+                "operation 'add' not supported",
+                "operation 'radd' not supported",
+                "operation 'sub' not supported",
+                "operation 'rsub' not supported",
             ]
         )
         with pytest.raises(Exception, match=msg):

pandas/tests/groupby/methods/test_describe.py

@@ -71,7 +71,7 @@ def test_series_describe_as_index(as_index, keys):
     tm.assert_frame_equal(result, expected)
 
 
-def test_frame_describe_multikey(tsframe):
+def test_frame_describe_multikey(tsframe, using_infer_string):
     grouped = tsframe.groupby([lambda x: x.year, lambda x: x.month])
     result = grouped.describe()
     desc_groups = []
@@ -87,6 +87,10 @@ def test_frame_describe_multikey(tsframe):
     expected = pd.concat(desc_groups, axis=1)
     tm.assert_frame_equal(result, expected)
 
+    # remainder of the tests fails with string dtype but is testing deprecated behaviour
+    if using_infer_string:
+        return
+
     msg = "DataFrame.groupby with axis=1 is deprecated"
     with tm.assert_produces_warning(FutureWarning, match=msg):
         groupedT = tsframe.groupby({"A": 0, "B": 0, "C": 1, "D": 1}, axis=1)

pandas/tests/groupby/test_numeric_only.py

@@ -273,6 +273,7 @@ def test_axis1_numeric_only(request, groupby_func, numeric_only, using_infer_str
             # cumsum, diff, pct_change
             "unsupported operand type",
             "has no kernel",
+            "operation 'sub' not supported for dtype 'str' with dtype 'float64'",
         )
         if using_infer_string:
             pa = pytest.importorskip("pyarrow")

pandas/tests/groupby/transform/test_transform.py

@@ -513,7 +513,7 @@ def test_transform_nuisance_raises(df, using_infer_string):
     msg = "Could not convert"
     if using_infer_string:
         if df.columns.dtype.storage == "pyarrow":
-            msg = "with dtype str does not support operation 'mean'"
+            msg = "with dtype str does not support reduction 'mean'"
         else:
             msg = "Cannot perform reduction 'mean' with string dtype"
     with pytest.raises(TypeError, match=msg):
@@ -621,7 +621,7 @@ def test_groupby_transform_with_int(using_infer_string):
     msg = "Could not convert"
     if using_infer_string:
         if HAS_PYARROW:
-            msg = "with dtype str does not support operation 'mean'"
+            msg = "with dtype str does not support reduction 'mean'"
         else:
             msg = "Cannot perform reduction 'mean' with string dtype"
     with np.errstate(all="ignore"):

pandas/tests/indexing/test_iloc.py

@@ -1221,7 +1221,9 @@ def test_iloc_setitem_multicolumn_to_datetime(self, using_infer_string):
         df = DataFrame({"A": ["2022-01-01", "2022-01-02"], "B": ["2021", "2022"]})
 
         if using_infer_string:
-            with pytest.raises(TypeError, match="Invalid value"):
+            with tm.assert_produces_warning(
+                FutureWarning, match="Setting an item of incompatible dtype"
+            ):
                 df.iloc[:, [0]] = DataFrame({"A": to_datetime(["2021", "2022"])})
         else:
             df.iloc[:, [0]] = DataFrame({"A": to_datetime(["2021", "2022"])})

pandas/tests/indexing/test_loc.py

@@ -16,7 +16,6 @@
 from pandas._config import using_string_dtype
 
 from pandas._libs import index as libindex
-from pandas.compat import HAS_PYARROW
 from pandas.compat.numpy import np_version_gt2
 from pandas.errors import IndexingError
 import pandas.util._test_decorators as td
@@ -1459,9 +1458,6 @@ def test_loc_setitem_listlike_with_timedelta64index(self, indexer, expected):
 
         tm.assert_frame_equal(expected, df)
 
-    @pytest.mark.xfail(
-        using_string_dtype() and not HAS_PYARROW, reason="TODO(infer_string)"
-    )
     def test_loc_setitem_categorical_values_partial_column_slice(self):
         # Assigning a Category to parts of a int/... column uses the values of
         # the Categorical

pandas/tests/io/test_feather.py

@@ -2,8 +2,6 @@
 import numpy as np
 import pytest
 
-from pandas._config import using_string_dtype
-
 import pandas as pd
 import pandas._testing as tm
 
@@ -148,7 +146,6 @@ def test_path_localpath(self):
         result = tm.round_trip_localpath(df.to_feather, read_feather)
         tm.assert_frame_equal(df, result)
 
-    @pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
     def test_passthrough_keywords(self):
         df = pd.DataFrame(
             1.1 * np.arange(120).reshape((30, 4)),

pandas/tests/reshape/test_melt.py

@@ -1199,7 +1199,10 @@ def test_raise_of_column_name_value(self):
         ):
             df.melt(id_vars="value", value_name="value")
 
-    def test_missing_stubname(self, any_string_dtype):
+    def test_missing_stubname(self, request, any_string_dtype, using_infer_string):
+        if using_infer_string and any_string_dtype == "object":
+            # triggers object dtype inference warning of dtype=object
+            request.applymarker(pytest.mark.xfail(reason="TODO(infer_string)"))
         # GH46044
         df = DataFrame({"id": ["1", "2"], "a-1": [100, 200], "a-2": [300, 400]})
         df = df.astype({"id": any_string_dtype})