STY: Enable ruff pytest checks (pandas-dev#56671)

* Enable PT001

* Add PT002

* Add PT003

* ignore 4 and 5

* Ignore 6, 7, 8

* Ignore PT009

* Enable PT010

* Enable PT011

* Ignore 12, enable 13

* Enable PT014

* Enforce PT015

* Enable 16

* Disable 17

* Ignore 18

* Ignore 19

* Add 20

* add 21

* Enable 22

* Add 23

* Add 24

* Add 25

* add 26

* Add 27

* use PT

* fix some tests

* Deduplcate test

* Add tests

* Added nested tuple case

Author: mroeschke

.pre-commit-config.yaml

@@ -272,13 +272,6 @@ repos:
         language: python
         types: [rst]
         files: ^doc/source/(development|reference)/
-    -   id: unwanted-patterns-bare-pytest-raises
-        name: Check for use of bare pytest raises
-        language: python
-        entry: python scripts/validate_unwanted_patterns.py --validation-type="bare_pytest_raises"
-        types: [python]
-        files: ^pandas/tests/
-        exclude: ^pandas/tests/extension/
     -   id: unwanted-patterns-private-function-across-module
         name: Check for use of private functions across modules
         language: python

pandas/conftest.py

@@ -1971,6 +1971,6 @@ def warsaw(request) -> str:
     return request.param
 
 
-@pytest.fixture()
+@pytest.fixture
 def arrow_string_storage():
     return ("pyarrow", "pyarrow_numpy")

pandas/tests/arithmetic/test_datetime64.py

@@ -1385,7 +1385,6 @@ def test_dt64arr_add_sub_relativedelta_offsets(self, box_with_array, unit):
             "SemiMonthBegin",
             "Week",
             ("Week", {"weekday": 3}),
-            "Week",
             ("Week", {"weekday": 6}),
             "BusinessDay",
             "BDay",

pandas/tests/arrays/categorical/test_api.py

@@ -291,12 +291,12 @@ def test_set_categories(self):
             (["a", "b", "c"], ["a", "b"], ["a", "b"]),
             (["a", "b", "c"], ["a", "b"], ["b", "a"]),
             (["b", "a", "c"], ["a", "b"], ["a", "b"]),
-            (["b", "a", "c"], ["a", "b"], ["a", "b"]),
+            (["b", "a", "c"], ["a", "b"], ["b", "a"]),
             # Introduce NaNs
             (["a", "b", "c"], ["a", "b"], ["a"]),
             (["a", "b", "c"], ["a", "b"], ["b"]),
             (["b", "a", "c"], ["a", "b"], ["a"]),
-            (["b", "a", "c"], ["a", "b"], ["a"]),
+            (["b", "a", "c"], ["a", "b"], ["b"]),
             # No overlap
             (["a", "b", "c"], ["a", "b"], ["d", "e"]),
         ],

pandas/tests/arrays/categorical/test_dtypes.py

@@ -73,12 +73,12 @@ def test_set_dtype_new_categories(self):
             (["a", "b", "c"], ["a", "b"], ["a", "b"]),
             (["a", "b", "c"], ["a", "b"], ["b", "a"]),
             (["b", "a", "c"], ["a", "b"], ["a", "b"]),
-            (["b", "a", "c"], ["a", "b"], ["a", "b"]),
+            (["b", "a", "c"], ["a", "b"], ["b", "a"]),
             # Introduce NaNs
             (["a", "b", "c"], ["a", "b"], ["a"]),
             (["a", "b", "c"], ["a", "b"], ["b"]),
             (["b", "a", "c"], ["a", "b"], ["a"]),
-            (["b", "a", "c"], ["a", "b"], ["a"]),
+            (["b", "a", "c"], ["a", "b"], ["b"]),
             # No overlap
             (["a", "b", "c"], ["a", "b"], ["d", "e"]),
         ],

pandas/tests/arrays/masked/test_function.py

@@ -21,7 +21,7 @@ def data(request):
     return request.param
 
 
-@pytest.fixture()
+@pytest.fixture
 def numpy_dtype(data):
     """
     Fixture returning numpy dtype from 'data' input array.

pandas/tests/arrays/sparse/test_arithmetics.py

@@ -433,9 +433,6 @@ def test_ufuncs(ufunc, arr):
     [
         (SparseArray([0, 0, 0]), np.array([0, 1, 2])),
         (SparseArray([0, 0, 0], fill_value=1), np.array([0, 1, 2])),
-        (SparseArray([0, 0, 0], fill_value=1), np.array([0, 1, 2])),
-        (SparseArray([0, 0, 0], fill_value=1), np.array([0, 1, 2])),
-        (SparseArray([0, 0, 0], fill_value=1), np.array([0, 1, 2])),
     ],
 )
 @pytest.mark.parametrize("ufunc", [np.add, np.greater])

pandas/tests/arrays/string_/test_string_arrow.py

@@ -220,22 +220,22 @@ def test_setitem_invalid_indexer_raises():
 
     arr = ArrowStringArray(pa.array(list("abcde")))
 
-    with pytest.raises(IndexError, match=None):
+    with tm.external_error_raised(IndexError):
         arr[5] = "foo"
 
-    with pytest.raises(IndexError, match=None):
+    with tm.external_error_raised(IndexError):
         arr[-6] = "foo"
 
-    with pytest.raises(IndexError, match=None):
+    with tm.external_error_raised(IndexError):
         arr[[0, 5]] = "foo"
 
-    with pytest.raises(IndexError, match=None):
+    with tm.external_error_raised(IndexError):
         arr[[0, -6]] = "foo"
 
-    with pytest.raises(IndexError, match=None):
+    with tm.external_error_raised(IndexError):
         arr[[True, True, False]] = "foo"
 
-    with pytest.raises(ValueError, match=None):
+    with tm.external_error_raised(ValueError):
         arr[[0, 1]] = ["foo", "bar", "baz"]
 
 

pandas/tests/arrays/test_array.py

@@ -29,7 +29,7 @@
 )
 
 
-@pytest.mark.parametrize("dtype_unit", ["M8[h]", "M8[m]", "m8[h]", "M8[m]"])
+@pytest.mark.parametrize("dtype_unit", ["M8[h]", "M8[m]", "m8[h]"])
 def test_dt64_array(dtype_unit):
     # PR 53817
     dtype_var = np.dtype(dtype_unit)

pandas/tests/copy_view/test_internals.py

@@ -83,7 +83,6 @@ def test_switch_options():
         ([0, 1, 2], np.array([[-1, -2, -3], [-4, -5, -6], [-4, -5, -6]]).T),
         ([1, 2], np.array([[-1, -2, -3], [-4, -5, -6]]).T),
         ([1, 3], np.array([[-1, -2, -3], [-4, -5, -6]]).T),
-        ([1, 3], np.array([[-1, -2, -3], [-4, -5, -6]]).T),
     ],
 )
 def test_iset_splits_blocks_inplace(using_copy_on_write, locs, arr, dtype):

pandas/tests/dtypes/test_missing.py

@@ -531,7 +531,6 @@ def test_array_equivalent_different_dtype_but_equal():
         (fix_now, fix_utcnow),
         (fix_now.to_datetime64(), fix_utcnow),
         (fix_now.to_pydatetime(), fix_utcnow),
-        (fix_now, fix_utcnow),
         (fix_now.to_datetime64(), fix_utcnow.to_pydatetime()),
         (fix_now.to_pydatetime(), fix_utcnow.to_pydatetime()),
     ],

pandas/tests/extension/base/dim2.py

@@ -90,9 +90,9 @@ def test_reshape(self, data):
         assert arr2d.shape == (data.size, 1)
         assert len(arr2d) == len(data)
 
-        with pytest.raises(ValueError):
+        with tm.external_error_raised(ValueError):
             data.reshape((data.size, 2))
-        with pytest.raises(ValueError):
+        with tm.external_error_raised(ValueError):
             data.reshape(data.size, 2)
 
     def test_getitem_2d(self, data):

pandas/tests/extension/base/getitem.py

@@ -394,7 +394,7 @@ def test_take_non_na_fill_value(self, data_missing):
         tm.assert_extension_array_equal(result, expected)
 
     def test_take_pandas_style_negative_raises(self, data, na_value):
-        with pytest.raises(ValueError, match=""):
+        with tm.external_error_raised(ValueError):
             data.take([0, -2], fill_value=na_value, allow_fill=True)
 
     @pytest.mark.parametrize("allow_fill", [True, False])

pandas/tests/extension/base/setitem.py

@@ -209,7 +209,8 @@ def test_setitem_integer_array(self, data, idx, box_in_series):
                 [0, 1, 2, pd.NA], True, marks=pytest.mark.xfail(reason="GH-31948")
             ),
             (pd.array([0, 1, 2, pd.NA], dtype="Int64"), False),
-            (pd.array([0, 1, 2, pd.NA], dtype="Int64"), False),
+            # TODO: change False to True?
+            (pd.array([0, 1, 2, pd.NA], dtype="Int64"), False),  # noqa: PT014
         ],
         ids=["list-False", "list-True", "integer-array-False", "integer-array-True"],
     )
@@ -332,7 +333,7 @@ def test_setitem_loc_iloc_slice(self, data):
 
     def test_setitem_slice_mismatch_length_raises(self, data):
         arr = data[:5]
-        with pytest.raises(ValueError):
+        with tm.external_error_raised(ValueError):
             arr[:1] = arr[:2]
 
     def test_setitem_slice_array(self, data):
@@ -342,7 +343,7 @@ def test_setitem_slice_array(self, data):
 
     def test_setitem_scalar_key_sequence_raise(self, data):
         arr = data[:5].copy()
-        with pytest.raises(ValueError):
+        with tm.external_error_raised(ValueError):
             arr[0] = arr[[0, 1]]
 
     def test_setitem_preserves_views(self, data):

pandas/tests/extension/json/test_json.py

@@ -355,7 +355,7 @@ def test_setitem_integer_array(self, data, idx, box_in_series, request):
                 [0, 1, 2, pd.NA], True, marks=pytest.mark.xfail(reason="GH-31948")
             ),
             (pd.array([0, 1, 2, pd.NA], dtype="Int64"), False),
-            (pd.array([0, 1, 2, pd.NA], dtype="Int64"), False),
+            (pd.array([0, 1, 2, pd.NA], dtype="Int64"), True),
         ],
         ids=["list-False", "list-True", "integer-array-False", "integer-array-True"],
     )

pandas/tests/extension/test_numpy.py

@@ -373,19 +373,6 @@ def test_setitem_mask(self, data, mask, box_in_series):
     def test_setitem_integer_array(self, data, idx, box_in_series):
         super().test_setitem_integer_array(data, idx, box_in_series)
 
-    @pytest.mark.parametrize(
-        "idx, box_in_series",
-        [
-            ([0, 1, 2, pd.NA], False),
-            pytest.param([0, 1, 2, pd.NA], True, marks=pytest.mark.xfail),
-            (pd.array([0, 1, 2, pd.NA], dtype="Int64"), False),
-            (pd.array([0, 1, 2, pd.NA], dtype="Int64"), False),
-        ],
-        ids=["list-False", "list-True", "integer-array-False", "integer-array-True"],
-    )
-    def test_setitem_integer_with_missing_raises(self, data, idx, box_in_series):
-        super().test_setitem_integer_with_missing_raises(data, idx, box_in_series)
-
     @skip_nested
     def test_setitem_slice(self, data, box_in_series):
         super().test_setitem_slice(data, box_in_series)

pandas/tests/extension/test_sparse.py

@@ -70,7 +70,7 @@ def gen(count):
         for _ in range(count):
             yield SparseArray(make_data(request.param), fill_value=request.param)
 
-    yield gen
+    return gen
 
 
 @pytest.fixture(params=[0, np.nan])

pandas/tests/frame/methods/test_astype.py

@@ -867,7 +867,7 @@ class IntegerArrayNoCopy(pd.core.arrays.IntegerArray):
     # GH 42501
 
     def copy(self):
-        assert False
+        raise NotImplementedError
 
 
 class Int16DtypeNoCopy(pd.Int16Dtype):

pandas/tests/frame/methods/test_explode.py

@@ -38,10 +38,6 @@ def test_error():
             [],
             "column must be nonempty",
         ),
-        (
-            list("AC"),
-            "columns must have matching element counts",
-        ),
     ],
 )
 def test_error_multi_columns(input_subset, error_message):

pandas/tests/frame/methods/test_filter.py

@@ -100,7 +100,6 @@ def test_filter_regex_search(self, float_frame):
     @pytest.mark.parametrize(
         "name,expected",
         [
-            ("a", DataFrame({"a": [1, 2]})),
             ("a", DataFrame({"a": [1, 2]})),
             ("あ", DataFrame({"あ": [3, 4]})),
         ],
@@ -112,9 +111,9 @@ def test_filter_unicode(self, name, expected):
         tm.assert_frame_equal(df.filter(like=name), expected)
         tm.assert_frame_equal(df.filter(regex=name), expected)
 
-    @pytest.mark.parametrize("name", ["a", "a"])
-    def test_filter_bytestring(self, name):
+    def test_filter_bytestring(self):
         # GH13101
+        name = "a"
         df = DataFrame({b"a": [1, 2], b"b": [3, 4]})
         expected = DataFrame({b"a": [1, 2]})
 

pandas/tests/frame/methods/test_reindex.py

@@ -452,19 +452,16 @@ def f(val):
             ("mid",),
             ("mid", "btm"),
             ("mid", "btm", "top"),
-            ("mid",),
             ("mid", "top"),
             ("mid", "top", "btm"),
             ("btm",),
             ("btm", "mid"),
             ("btm", "mid", "top"),
-            ("btm",),
             ("btm", "top"),
             ("btm", "top", "mid"),
             ("top",),
             ("top", "mid"),
             ("top", "mid", "btm"),
-            ("top",),
             ("top", "btm"),
             ("top", "btm", "mid"),
         ],

pandas/tests/frame/methods/test_reset_index.py

@@ -27,7 +27,7 @@
 import pandas._testing as tm
 
 
-@pytest.fixture()
+@pytest.fixture
 def multiindex_df():
     levels = [["A", ""], ["B", "b"]]
     return DataFrame([[0, 2], [1, 3]], columns=MultiIndex.from_tuples(levels))

pandas/tests/frame/test_constructors.py

@@ -1555,7 +1555,7 @@ def test_constructor_mixed_type_rows(self):
         "tuples,lists",
         [
             ((), []),
-            ((()), []),
+            (((),), [[]]),
             (((), ()), [(), ()]),
             (((), ()), [[], []]),
             (([], []), [[], []]),

pandas/tests/frame/test_query_eval.py

@@ -1187,7 +1187,7 @@ def df(self):
         by backticks. The last two columns cannot be escaped by backticks
         and should raise a ValueError.
         """
-        yield DataFrame(
+        return DataFrame(
             {
                 "A": [1, 2, 3],
                 "B B": [3, 2, 1],

pandas/tests/frame/test_reductions.py

@@ -1866,7 +1866,6 @@ def test_df_empty_min_count_1(self, opname, dtype, exp_dtype):
         [
             ("sum", "Int8", 0, ("Int32" if is_windows_np2_or_is32 else "Int64")),
             ("prod", "Int8", 1, ("Int32" if is_windows_np2_or_is32 else "Int64")),
-            ("prod", "Int8", 1, ("Int32" if is_windows_np2_or_is32 else "Int64")),
             ("sum", "Int64", 0, "Int64"),
             ("prod", "Int64", 1, "Int64"),
             ("sum", "UInt8", 0, ("UInt32" if is_windows_np2_or_is32 else "UInt64")),

pandas/tests/groupby/conftest.py

@@ -92,7 +92,7 @@ def three_group():
     )
 
 
-@pytest.fixture()
+@pytest.fixture
 def slice_test_df():
     data = [
         [0, "a", "a0_at_0"],
@@ -108,7 +108,7 @@ def slice_test_df():
     return df.set_index("Index")
 
 
-@pytest.fixture()
+@pytest.fixture
 def slice_test_grouped(slice_test_df):
     return slice_test_df.groupby("Group", as_index=False)
 

pandas/tests/groupby/test_categorical.py

@@ -647,7 +647,7 @@ def test_dataframe_categorical_ordered_observed_sort(ordered, observed, sort):
             f"for (ordered={ordered}, observed={observed}, sort={sort})\n"
             f"Result:\n{result}"
         )
-        assert False, msg
+        pytest.fail(msg)
 
 
 def test_datetime():

pandas/tests/groupby/test_groupby_dropna.py

@@ -410,7 +410,6 @@ def test_groupby_drop_nan_with_multi_index():
         "UInt64",
         "Int64",
         "Float32",
-        "Int64",
         "Float64",
         "category",
         "string",

pandas/tests/indexes/datetimelike_/test_sort_values.py

@@ -185,10 +185,6 @@ def test_sort_values_without_freq_timedeltaindex(self):
     @pytest.mark.parametrize(
         "index_dates,expected_dates",
         [
-            (
-                ["2011-01-01", "2011-01-03", "2011-01-05", "2011-01-02", "2011-01-01"],
-                ["2011-01-01", "2011-01-01", "2011-01-02", "2011-01-03", "2011-01-05"],
-            ),
             (
                 ["2011-01-01", "2011-01-03", "2011-01-05", "2011-01-02", "2011-01-01"],
                 ["2011-01-01", "2011-01-01", "2011-01-02", "2011-01-03", "2011-01-05"],

pandas/tests/indexes/multi/test_constructors.py

@@ -304,7 +304,6 @@ def test_from_arrays_empty():
         (1, 2),
         ([1], 2),
         (1, [2]),
-        "a",
         ("a",),
         ("a", "b"),
         (["a"], "b"),

pandas/tests/internals/test_internals.py

@@ -1158,7 +1158,6 @@ def test_array_to_slice_conversion(self, arr, slc):
             [-1],
             [-1, -2, -3],
             [-10],
-            [-1],
             [-1, 0, 1, 2],
             [-2, 0, 2, 4],
             [1, 0, -1],

pandas/tests/io/formats/test_css.py

@@ -243,7 +243,6 @@ def test_css_none_absent(style, equiv):
         ("02.54cm", "72pt"),
         ("25.4mm", "72pt"),
         ("101.6q", "72pt"),
-        ("101.6q", "72pt"),
     ],
 )
 @pytest.mark.parametrize("relative_to", [None, "16pt"])  # invariant to inherited size