update exception messages

Author: jbrockmendel

pandas/core/groupby/groupby.py

@@ -4283,11 +4283,7 @@ def quantile(
         starts, ends = lib.generate_slices(splitter._slabels, splitter.ngroups)
 
         def pre_processor(vals: ArrayLike) -> tuple[np.ndarray, DtypeObj | None]:
-            if is_object_dtype(vals.dtype):
-                raise TypeError(
-                    "'quantile' cannot be performed against 'object' dtypes!"
-                )
-            elif isinstance(vals.dtype, StringDtype):
+            if isinstance(vals.dtype, StringDtype) or is_object_dtype(vals.dtype):
                 raise TypeError(
                     f"dtype '{vals.dtype}' does not support operation 'quantile'"
                 )

pandas/tests/groupby/methods/test_quantile.py

@@ -241,7 +241,6 @@ def test_groupby_quantile_nullable_array(values, q):
     tm.assert_series_equal(result, expected)
 
 
-# @pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)", strict=False)
 @pytest.mark.parametrize("q", [0.5, [0.0, 0.5, 1.0]])
 @pytest.mark.parametrize("numeric_only", [True, False])
 def test_groupby_quantile_raises_on_invalid_dtype(q, numeric_only, using_infer_string):
@@ -251,9 +250,7 @@ def test_groupby_quantile_raises_on_invalid_dtype(q, numeric_only, using_infer_s
         expected = df.groupby("a")[["b"]].quantile(q)
         tm.assert_frame_equal(result, expected)
     else:
-        msg = "'quantile' cannot be performed against 'object' dtypes!"
-        if using_infer_string:
-            msg = "dtype 'str' does not support operation 'quantile'"
+        msg = "dtype '.*' does not support operation 'quantile'"
         with pytest.raises(TypeError, match=msg):
             df.groupby("a").quantile(q, numeric_only=numeric_only)
 

pandas/tests/groupby/test_groupby.py

@@ -983,18 +983,11 @@ def test_groupby_with_hier_columns():
     tm.assert_index_equal(result.columns, df.columns[:-1])
 
 
-def test_grouping_ndarray(df, using_infer_string):
+def test_grouping_ndarray(df):
+    df = df.astype({"A": object, "B": object})
     grouped = df.groupby(df["A"].values)
     grouped2 = df.groupby(df["A"].rename(None))
 
-    if using_infer_string:
-        msg = "dtype 'str' does not support operation 'sum'"
-        with pytest.raises(TypeError, match=msg):
-            grouped.sum()
-        with pytest.raises(TypeError, match=msg):
-            grouped2.sum()
-        return
-
     result = grouped.sum()
     expected = grouped2.sum()
     tm.assert_frame_equal(result, expected)
@@ -1495,18 +1488,11 @@ def f(group):
     assert names == expected_names
 
 
-def test_no_dummy_key_names(df, using_infer_string):
+def test_no_dummy_key_names(df):
     # see gh-1291
+    df = df.astype({"A": object, "B": object})
     gb = df.groupby(df["A"].values)
     gb2 = df.groupby([df["A"].values, df["B"].values])
-    if using_infer_string:
-        msg = "dtype 'str' does not support operation 'sum'"
-        with pytest.raises(TypeError, match=msg):
-            gb.sum()
-        with pytest.raises(TypeError, match=msg):
-            gb2.sum()
-        return
-
     result = gb.sum()
     assert result.index.name is None
 

pandas/tests/groupby/test_numeric_only.py

@@ -299,7 +299,9 @@ def test_numeric_only(kernel, has_arg, numeric_only, keys):
                 re.escape(f"agg function failed [how->{kernel},dtype->object]"),
             ]
         )
-        if kernel == "idxmin":
+        if kernel == "quantile":
+            msg = "dtype 'object' does not support operation 'quantile'"
+        elif kernel == "idxmin":
             msg = "'<' not supported between instances of 'type' and 'type'"
         elif kernel == "idxmax":
             msg = "'>' not supported between instances of 'type' and 'type'"
@@ -379,7 +381,7 @@ def test_deprecate_numeric_only_series(dtype, groupby_func, request):
     # that succeed should not be allowed to fail (without deprecation, at least)
     if groupby_func in fails_on_numeric_object and dtype is object:
         if groupby_func == "quantile":
-            msg = "cannot be performed against 'object' dtypes"
+            msg = "dtype 'object' does not support operation 'quantile'"
         else:
             msg = "is not supported for object dtype"
         with pytest.raises(TypeError, match=msg):

pandas/tests/groupby/test_raises.py

@@ -204,18 +204,12 @@ def test_groupby_raises_string(
         elif groupby_func == "pct_change" and df["d"].dtype.storage == "pyarrow":
             # This doesn't go through EA._groupby_op so the message isn't controlled
             #  there.
-            import pyarrow as pa
-
-            klass = pa.lib.ArrowNotImplementedError
-            msg = "Function 'divide' has no kernel matching input types"
+            msg = "operation 'truediv' not supported for dtype 'str' with dtype 'str'"
         elif groupby_func == "diff" and df["d"].dtype.storage == "pyarrow":
             # This doesn't go through EA._groupby_op so the message isn't controlled
             #  there.
-            import pyarrow as pa
+            msg = "operation 'sub' not supported for dtype 'str' with dtype 'str'"
 
-            # TODO(infer_string): avoid bubbling up pyarrow exceptions
-            klass = pa.lib.ArrowNotImplementedError
-            msg = "Function 'subtract_checked' has no kernel matching input types"
         elif groupby_func in ["cummin", "cummax"]:
             msg = msg.replace("object", "str")
         elif groupby_func == "corrwith":