TST: Avoid bare pytest.raises in mult files (#32906)

Author: Vlek

pandas/core/dtypes/common.py

@@ -188,7 +188,9 @@ def ensure_python_int(value: Union[int, np.integer]) -> int:
     TypeError: if the value isn't an int or can't be converted to one.
     """
     if not is_scalar(value):
-        raise TypeError(f"Value needs to be a scalar value, was type {type(value)}")
+        raise TypeError(
+            f"Value needs to be a scalar value, was type {type(value).__name__}"
+        )
     try:
         new_value = int(value)
         assert new_value == value

pandas/tests/groupby/test_groupby.py

@@ -1765,7 +1765,7 @@ def test_tuple_as_grouping():
         }
     )
 
-    with pytest.raises(KeyError):
+    with pytest.raises(KeyError, match=r"('a', 'b')"):
         df[["a", "b", "c"]].groupby(("a", "b"))
 
     result = df.groupby(("a", "b"))["c"].sum()

pandas/tests/groupby/test_timegrouper.py

@@ -214,7 +214,7 @@ def test_timegrouper_with_reg_groups(self):
             result = df.groupby([pd.Grouper(freq="1M", level=0), "Buyer"]).sum()
             tm.assert_frame_equal(result, expected)
 
-            with pytest.raises(ValueError):
+            with pytest.raises(ValueError, match="The level foo is not valid"):
                 df.groupby([pd.Grouper(freq="1M", level="foo"), "Buyer"]).sum()
 
             # multi names
@@ -235,7 +235,8 @@ def test_timegrouper_with_reg_groups(self):
             tm.assert_frame_equal(result, expected)
 
             # error as we have both a level and a name!
-            with pytest.raises(ValueError):
+            msg = "The Grouper cannot specify both a key and a level!"
+            with pytest.raises(ValueError, match=msg):
                 df.groupby(
                     [pd.Grouper(freq="1M", key="Date", level="Date"), "Buyer"]
                 ).sum()

pandas/tests/indexes/datetimes/test_to_period.py

@@ -147,7 +147,8 @@ def test_to_period_tz_utc_offset_consistency(self, tz):
 
     def test_to_period_nofreq(self):
         idx = DatetimeIndex(["2000-01-01", "2000-01-02", "2000-01-04"])
-        with pytest.raises(ValueError):
+        msg = "You must pass a freq argument as current index has none."
+        with pytest.raises(ValueError, match=msg):
             idx.to_period()
 
         idx = DatetimeIndex(["2000-01-01", "2000-01-02", "2000-01-03"], freq="infer")

pandas/tests/indexes/multi/test_compat.py

@@ -37,7 +37,11 @@ def test_logical_compat(idx, method):
 
 def test_boolean_context_compat(idx):
 
-    with pytest.raises(ValueError):
+    msg = (
+        "The truth value of a MultiIndex is ambiguous. "
+        r"Use a.empty, a.bool\(\), a.item\(\), a.any\(\) or a.all\(\)."
+    )
+    with pytest.raises(ValueError, match=msg):
         bool(idx)
 
 

pandas/tests/indexes/multi/test_duplicates.py

@@ -83,12 +83,14 @@ def test_get_unique_index(idx, dropna):
 def test_duplicate_multiindex_codes():
     # GH 17464
     # Make sure that a MultiIndex with duplicate levels throws a ValueError
-    with pytest.raises(ValueError):
+    msg = r"Level values must be unique: \[[A', ]+\] on level 0"
+    with pytest.raises(ValueError, match=msg):
         mi = MultiIndex([["A"] * 10, range(10)], [[0] * 10, range(10)])
 
     # And that using set_levels with duplicate levels fails
     mi = MultiIndex.from_arrays([["A", "A", "B", "B", "B"], [1, 2, 1, 2, 3]])
-    with pytest.raises(ValueError):
+    msg = r"Level values must be unique: \[[AB', ]+\] on level 0"
+    with pytest.raises(ValueError, match=msg):
         mi.set_levels([["A", "B", "A", "A", "B"], [2, 1, 3, -2, 5]], inplace=True)
 
 

pandas/tests/indexes/multi/test_format.py

@@ -58,7 +58,8 @@ def test_repr_with_unicode_data():
 
 def test_repr_roundtrip_raises():
     mi = MultiIndex.from_product([list("ab"), range(3)], names=["first", "second"])
-    with pytest.raises(TypeError):
+    msg = "Must pass both levels and codes"
+    with pytest.raises(TypeError, match=msg):
         eval(repr(mi))
 
 

pandas/tests/indexes/multi/test_setops.py

@@ -209,7 +209,8 @@ def test_difference_sort_incomparable():
     # sort=None, the default
     # MultiIndex.difference deviates here from other difference
     # implementations in not catching the TypeError
-    with pytest.raises(TypeError):
+    msg = "'<' not supported between instances of 'Timestamp' and 'int'"
+    with pytest.raises(TypeError, match=msg):
         result = idx.difference(other)
 
     # sort=False

pandas/tests/indexes/period/test_shift.py

@@ -63,7 +63,8 @@ def test_shift_corner_cases(self):
         # GH#9903
         idx = PeriodIndex([], name="xxx", freq="H")
 
-        with pytest.raises(TypeError):
+        msg = "`freq` argument is not supported for PeriodArray._time_shift"
+        with pytest.raises(TypeError, match=msg):
             # period shift doesn't accept freq
             idx.shift(1, freq="H")
 

pandas/tests/indexes/ranges/test_constructors.py

@@ -37,28 +37,36 @@ def test_constructor_invalid_args(self):
         with pytest.raises(TypeError, match=msg):
             RangeIndex(name="Foo")
 
-        # invalid args
-        for i in [
+        # we don't allow on a bare Index
+        msg = (
+            r"Index\(\.\.\.\) must be called with a collection of some "
+            r"kind, 0 was passed"
+        )
+        with pytest.raises(TypeError, match=msg):
+            Index(0, 1000)
+
+    @pytest.mark.parametrize(
+        "args",
+        [
             Index(["a", "b"]),
             Series(["a", "b"]),
             np.array(["a", "b"]),
             [],
-            "foo",
-            datetime(2000, 1, 1, 0, 0),
             np.arange(0, 10),
             np.array([1]),
             [1],
-        ]:
-            with pytest.raises(TypeError):
-                RangeIndex(i)
+        ],
+    )
+    def test_constructor_additional_invalid_args(self, args):
+        msg = f"Value needs to be a scalar value, was type {type(args).__name__}"
+        with pytest.raises(TypeError, match=msg):
+            RangeIndex(args)
 
-        # we don't allow on a bare Index
-        msg = (
-            r"Index\(\.\.\.\) must be called with a collection of some "
-            r"kind, 0 was passed"
-        )
+    @pytest.mark.parametrize("args", ["foo", datetime(2000, 1, 1, 0, 0)])
+    def test_constructor_invalid_args_wrong_type(self, args):
+        msg = f"Wrong type {type(args)} for value {args}"
         with pytest.raises(TypeError, match=msg):
-            Index(0, 1000)
+            RangeIndex(args)
 
     def test_constructor_same(self):
 
@@ -81,7 +89,7 @@ def test_constructor_same(self):
 
     def test_constructor_range(self):
 
-        msg = "Value needs to be a scalar value, was type <class 'range'>"
+        msg = "Value needs to be a scalar value, was type range"
         with pytest.raises(TypeError, match=msg):
             result = RangeIndex(range(1, 5, 2))
 

pandas/tests/indexes/ranges/test_range.py

@@ -304,14 +304,19 @@ def test_nbytes(self):
         i2 = RangeIndex(0, 10)
         assert i.nbytes == i2.nbytes
 
-    def test_cant_or_shouldnt_cast(self):
-        # can't
-        with pytest.raises(TypeError):
-            RangeIndex("foo", "bar", "baz")
-
-        # shouldn't
-        with pytest.raises(TypeError):
-            RangeIndex("0", "1", "2")
+    @pytest.mark.parametrize(
+        "start,stop,step",
+        [
+            # can't
+            ("foo", "bar", "baz"),
+            # shouldn't
+            ("0", "1", "2"),
+        ],
+    )
+    def test_cant_or_shouldnt_cast(self, start, stop, step):
+        msg = f"Wrong type {type(start)} for value {start}"
+        with pytest.raises(TypeError, match=msg):
+            RangeIndex(start, stop, step)
 
     def test_view_index(self):
         index = self.create_index()
@@ -350,7 +355,8 @@ def test_take_fill_value(self):
         with pytest.raises(ValueError, match=msg):
             idx.take(np.array([1, 0, -5]), fill_value=True)
 
-        with pytest.raises(IndexError):
+        msg = "index -5 is out of bounds for (axis 0 with )?size 3"
+        with pytest.raises(IndexError, match=msg):
             idx.take(np.array([1, -5]))
 
     def test_repr_roundtrip(self):

pandas/tests/indexes/test_base.py

@@ -2263,7 +2263,8 @@ def test_contains_method_removed(self, indices):
         if isinstance(indices, pd.IntervalIndex):
             indices.contains(1)
         else:
-            with pytest.raises(AttributeError):
+            msg = f"'{type(indices).__name__}' object has no attribute 'contains'"
+            with pytest.raises(AttributeError, match=msg):
                 indices.contains(1)
 
 

pandas/tests/indexes/test_frozen.py

@@ -17,7 +17,8 @@ def check_mutable_error(self, *args, **kwargs):
         # Pass whatever function you normally would to pytest.raises
         # (after the Exception kind).
         mutable_regex = re.compile("does not support mutable operations")
-        with pytest.raises(TypeError):
+        msg = "'(_s)?re.(SRE_)?Pattern' object is not callable"
+        with pytest.raises(TypeError, match=msg):
             mutable_regex(*args, **kwargs)
 
     def test_no_mutable_funcs(self):

pandas/tests/indexes/test_numeric.py

@@ -506,7 +506,8 @@ def test_take_fill_value(self):
         with pytest.raises(ValueError, match=msg):
             idx.take(np.array([1, 0, -5]), fill_value=True)
 
-        with pytest.raises(IndexError):
+        msg = "index -5 is out of bounds for (axis 0 with )?size 3"
+        with pytest.raises(IndexError, match=msg):
             idx.take(np.array([1, -5]))
 
 
@@ -645,7 +646,8 @@ def test_take_fill_value(self):
         with pytest.raises(ValueError, match=msg):
             idx.take(np.array([1, 0, -5]), fill_value=True)
 
-        with pytest.raises(IndexError):
+        msg = "index -5 is out of bounds for (axis 0 with )?size 3"
+        with pytest.raises(IndexError, match=msg):
             idx.take(np.array([1, -5]))
 
 

pandas/tests/indexes/timedeltas/test_constructors.py

@@ -168,7 +168,11 @@ def test_constructor_coverage(self):
         with pytest.raises(TypeError, match=msg):
             timedelta_range(start="1 days", periods="foo", freq="D")
 
-        with pytest.raises(TypeError):
+        msg = (
+            r"TimedeltaIndex\(\) must be called with a collection of some kind,"
+            " '1 days' was passed"
+        )
+        with pytest.raises(TypeError, match=msg):
             TimedeltaIndex("1 days")
 
         # generator expression
@@ -220,5 +224,6 @@ def test_constructor_no_precision_raises(self):
             pd.Index(["2000"], dtype="timedelta64")
 
     def test_constructor_wrong_precision_raises(self):
-        with pytest.raises(ValueError):
+        msg = r"dtype timedelta64\[us\] cannot be converted to timedelta64\[ns\]"
+        with pytest.raises(ValueError, match=msg):
             pd.TimedeltaIndex(["2000"], dtype="timedelta64[us]")

pandas/tests/indexes/timedeltas/test_indexing.py

@@ -184,7 +184,8 @@ def test_take_fill_value(self):
         with pytest.raises(ValueError, match=msg):
             idx.take(np.array([1, 0, -5]), fill_value=True)
 
-        with pytest.raises(IndexError):
+        msg = "index -5 is out of bounds for (axis 0 with )?size 3"
+        with pytest.raises(IndexError, match=msg):
             idx.take(np.array([1, -5]))
 
 

pandas/tests/indexes/timedeltas/test_shift.py

@@ -71,5 +71,5 @@ def test_tdi_shift_nonstandard_freq(self):
     def test_shift_no_freq(self):
         # GH#19147
         tdi = TimedeltaIndex(["1 days 01:00:00", "2 days 01:00:00"], freq=None)
-        with pytest.raises(NullFrequencyError):
+        with pytest.raises(NullFrequencyError, match="Cannot shift with no freq"):
             tdi.shift(2)

pandas/tests/indexing/multiindex/test_setitem.py

@@ -137,7 +137,8 @@ def test_multiindex_setitem(self):
         tm.assert_frame_equal(df.loc[["bar"]], expected)
 
         # raise because these have differing levels
-        with pytest.raises(TypeError):
+        msg = "cannot align on a multi-index with out specifying the join levels"
+        with pytest.raises(TypeError, match=msg):
             df.loc["bar"] *= 2
 
         # from SO
@@ -203,10 +204,14 @@ def test_multiindex_assignment(self):
         tm.assert_series_equal(df.loc[4, "c"], exp)
 
         # invalid assignments
-        with pytest.raises(ValueError):
+        msg = (
+            "cannot set using a multi-index selection indexer "
+            "with a different length than the value"
+        )
+        with pytest.raises(ValueError, match=msg):
             df.loc[4, "c"] = [0, 1, 2, 3]
 
-        with pytest.raises(ValueError):
+        with pytest.raises(ValueError, match=msg):
             df.loc[4, "c"] = [0]
 
         # groupby example

pandas/tests/indexing/multiindex/test_slice.py

@@ -111,7 +111,11 @@ def test_per_axis_per_level_getitem(self):
         expected = df.iloc[[2, 3]]
         tm.assert_frame_equal(result, expected)
 
-        with pytest.raises(ValueError):
+        msg = (
+            "cannot index with a boolean indexer "
+            "that is not the same length as the index"
+        )
+        with pytest.raises(ValueError, match=msg):
             df.loc[(slice(None), np.array([True, False])), :]
 
         # ambiguous notation
@@ -411,7 +415,11 @@ def test_per_axis_per_level_doc_examples(self):
         tm.assert_frame_equal(result, expected)
 
         # not sorted
-        with pytest.raises(UnsortedIndexError):
+        msg = (
+            "MultiIndex slicing requires the index to be lexsorted: "
+            r"slicing on levels \[1\], lexsort depth 1"
+        )
+        with pytest.raises(UnsortedIndexError, match=msg):
             df.loc["A1", ("a", slice("foo"))]
 
         # GH 16734: not sorted, but no real slicing
@@ -480,14 +488,10 @@ def test_loc_axis_arguments(self):
         tm.assert_frame_equal(result, expected)
 
         # invalid axis
-        with pytest.raises(ValueError):
-            df.loc(axis=-1)[:, :, ["C1", "C3"]]
-
-        with pytest.raises(ValueError):
-            df.loc(axis=2)[:, :, ["C1", "C3"]]
-
-        with pytest.raises(ValueError):
-            df.loc(axis="foo")[:, :, ["C1", "C3"]]
+        for i in [-1, 2, "foo"]:
+            msg = f"No axis named {i} for object type DataFrame"
+            with pytest.raises(ValueError, match=msg):
+                df.loc(axis=i)[:, :, ["C1", "C3"]]
 
     def test_loc_axis_single_level_multi_col_indexing_multiindex_col_df(self):
 
@@ -628,12 +632,14 @@ def test_per_axis_per_level_setitem(self):
         # not enough values
         df = df_orig.copy()
 
-        with pytest.raises(ValueError):
+        msg = "setting an array element with a sequence."
+        with pytest.raises(ValueError, match=msg):
             df.loc[(slice(None), 1), (slice(None), ["foo"])] = np.array(
                 [[100], [100, 100]], dtype="int64"
             )
 
-        with pytest.raises(ValueError):
+        msg = "Must have equal len keys and value when setting with an iterable"
+        with pytest.raises(ValueError, match=msg):
             df.loc[(slice(None), 1), (slice(None), ["foo"])] = np.array(
                 [100, 100, 100, 100], dtype="int64"
             )

pandas/tests/indexing/test_coercion.py

@@ -297,7 +297,8 @@ def test_setitem_index_object(self, val, exp_dtype):
 
         if exp_dtype is IndexError:
             temp = obj.copy()
-            with pytest.raises(exp_dtype):
+            msg = "index 5 is out of bounds for axis 0 with size 4"
+            with pytest.raises(exp_dtype, match=msg):
                 temp[5] = 5
         else:
             exp_index = pd.Index(list("abcd") + [val])