TST/CLN: Test parametrizations (#56737)

Author: mroeschke

pandas/tests/arithmetic/test_datetime64.py

@@ -182,12 +182,12 @@ class TestDatetime64SeriesComparison:
     @pytest.mark.parametrize(
         "op, expected",
         [
-            (operator.eq, Series([False, False, True])),
-            (operator.ne, Series([True, True, False])),
-            (operator.lt, Series([False, False, False])),
-            (operator.gt, Series([False, False, False])),
-            (operator.ge, Series([False, False, True])),
-            (operator.le, Series([False, False, True])),
+            (operator.eq, [False, False, True]),
+            (operator.ne, [True, True, False]),
+            (operator.lt, [False, False, False]),
+            (operator.gt, [False, False, False]),
+            (operator.ge, [False, False, True]),
+            (operator.le, [False, False, True]),
         ],
     )
     def test_nat_comparisons(
@@ -210,7 +210,7 @@ def test_nat_comparisons(
 
         result = op(left, right)
 
-        tm.assert_series_equal(result, expected)
+        tm.assert_series_equal(result, Series(expected))
 
     @pytest.mark.parametrize(
         "data",
@@ -1485,11 +1485,10 @@ def test_dt64arr_add_sub_DateOffsets(
     @pytest.mark.parametrize(
         "other",
         [
-            np.array([pd.offsets.MonthEnd(), pd.offsets.Day(n=2)]),
-            np.array([pd.offsets.DateOffset(years=1), pd.offsets.MonthEnd()]),
-            np.array(  # matching offsets
-                [pd.offsets.DateOffset(years=1), pd.offsets.DateOffset(years=1)]
-            ),
+            [pd.offsets.MonthEnd(), pd.offsets.Day(n=2)],
+            [pd.offsets.DateOffset(years=1), pd.offsets.MonthEnd()],
+            # matching offsets
+            [pd.offsets.DateOffset(years=1), pd.offsets.DateOffset(years=1)],
         ],
     )
     @pytest.mark.parametrize("op", [operator.add, roperator.radd, operator.sub])
@@ -1502,7 +1501,7 @@ def test_dt64arr_add_sub_offset_array(
         tz = tz_naive_fixture
         dti = date_range("2017-01-01", periods=2, tz=tz)
         dtarr = tm.box_expected(dti, box_with_array)
-
+        other = np.array(other)
         expected = DatetimeIndex([op(dti[n], other[n]) for n in range(len(dti))])
         expected = tm.box_expected(expected, box_with_array).astype(object)
 

pandas/tests/arithmetic/test_timedelta64.py

@@ -1960,19 +1960,20 @@ def test_td64arr_floordiv_numeric_scalar(self, box_with_array, two):
             two // tdser
 
     @pytest.mark.parametrize(
-        "vector",
-        [np.array([20, 30, 40]), Index([20, 30, 40]), Series([20, 30, 40])],
-        ids=lambda x: type(x).__name__,
+        "klass",
+        [np.array, Index, Series],
+        ids=lambda x: x.__name__,
     )
     def test_td64arr_rmul_numeric_array(
         self,
         box_with_array,
-        vector,
+        klass,
         any_real_numpy_dtype,
     ):
         # GH#4521
         # divide/multiply by integers
 
+        vector = klass([20, 30, 40])
         tdser = Series(["59 Days", "59 Days", "NaT"], dtype="m8[ns]")
         vector = vector.astype(any_real_numpy_dtype)
 
@@ -1990,16 +1991,17 @@ def test_td64arr_rmul_numeric_array(
         tm.assert_equal(result, expected)
 
     @pytest.mark.parametrize(
-        "vector",
-        [np.array([20, 30, 40]), Index([20, 30, 40]), Series([20, 30, 40])],
-        ids=lambda x: type(x).__name__,
+        "klass",
+        [np.array, Index, Series],
+        ids=lambda x: x.__name__,
     )
     def test_td64arr_div_numeric_array(
-        self, box_with_array, vector, any_real_numpy_dtype
+        self, box_with_array, klass, any_real_numpy_dtype
     ):
         # GH#4521
         # divide/multiply by integers
 
+        vector = klass([20, 30, 40])
         tdser = Series(["59 Days", "59 Days", "NaT"], dtype="m8[ns]")
         vector = vector.astype(any_real_numpy_dtype)
 

pandas/tests/arrays/categorical/test_indexing.py

@@ -51,12 +51,10 @@ def test_setitem(self):
 
         tm.assert_categorical_equal(c, expected)
 
-    @pytest.mark.parametrize(
-        "other",
-        [Categorical(["b", "a"]), Categorical(["b", "a"], categories=["b", "a"])],
-    )
-    def test_setitem_same_but_unordered(self, other):
+    @pytest.mark.parametrize("categories", [None, ["b", "a"]])
+    def test_setitem_same_but_unordered(self, categories):
         # GH-24142
+        other = Categorical(["b", "a"], categories=categories)
         target = Categorical(["a", "b"], categories=["a", "b"])
         mask = np.array([True, False])
         target[mask] = other[mask]

pandas/tests/arrays/categorical/test_operators.py

@@ -307,29 +307,23 @@ def test_comparisons(self, data, reverse, base):
         with pytest.raises(TypeError, match=msg):
             a < cat_rev
 
-    @pytest.mark.parametrize(
-        "ctor",
-        [
-            lambda *args, **kwargs: Categorical(*args, **kwargs),
-            lambda *args, **kwargs: Series(Categorical(*args, **kwargs)),
-        ],
-    )
-    def test_unordered_different_order_equal(self, ctor):
+    @pytest.mark.parametrize("box", [lambda x: x, Series])
+    def test_unordered_different_order_equal(self, box):
         # https://github.com/pandas-dev/pandas/issues/16014
-        c1 = ctor(["a", "b"], categories=["a", "b"], ordered=False)
-        c2 = ctor(["a", "b"], categories=["b", "a"], ordered=False)
+        c1 = box(Categorical(["a", "b"], categories=["a", "b"], ordered=False))
+        c2 = box(Categorical(["a", "b"], categories=["b", "a"], ordered=False))
         assert (c1 == c2).all()
 
-        c1 = ctor(["a", "b"], categories=["a", "b"], ordered=False)
-        c2 = ctor(["b", "a"], categories=["b", "a"], ordered=False)
+        c1 = box(Categorical(["a", "b"], categories=["a", "b"], ordered=False))
+        c2 = box(Categorical(["b", "a"], categories=["b", "a"], ordered=False))
         assert (c1 != c2).all()
 
-        c1 = ctor(["a", "a"], categories=["a", "b"], ordered=False)
-        c2 = ctor(["b", "b"], categories=["b", "a"], ordered=False)
+        c1 = box(Categorical(["a", "a"], categories=["a", "b"], ordered=False))
+        c2 = box(Categorical(["b", "b"], categories=["b", "a"], ordered=False))
         assert (c1 != c2).all()
 
-        c1 = ctor(["a", "a"], categories=["a", "b"], ordered=False)
-        c2 = ctor(["a", "b"], categories=["b", "a"], ordered=False)
+        c1 = box(Categorical(["a", "a"], categories=["a", "b"], ordered=False))
+        c2 = box(Categorical(["a", "b"], categories=["b", "a"], ordered=False))
         result = c1 == c2
         tm.assert_numpy_array_equal(np.array(result), np.array([True, False]))
 

pandas/tests/arrays/sparse/test_dtype.py

@@ -99,15 +99,15 @@ def test_construct_from_string_raises():
 @pytest.mark.parametrize(
     "dtype, expected",
     [
-        (SparseDtype(int), True),
-        (SparseDtype(float), True),
-        (SparseDtype(bool), True),
-        (SparseDtype(object), False),
-        (SparseDtype(str), False),
+        (int, True),
+        (float, True),
+        (bool, True),
+        (object, False),
+        (str, False),
     ],
 )
 def test_is_numeric(dtype, expected):
-    assert dtype._is_numeric is expected
+    assert SparseDtype(dtype)._is_numeric is expected
 
 
 def test_str_uses_object():

pandas/tests/arrays/sparse/test_reductions.py

@@ -126,13 +126,13 @@ def test_sum(self):
 
     @pytest.mark.parametrize(
         "arr",
-        [np.array([0, 1, np.nan, 1]), np.array([0, 1, 1])],
+        [[0, 1, np.nan, 1], [0, 1, 1]],
     )
     @pytest.mark.parametrize("fill_value", [0, 1, np.nan])
     @pytest.mark.parametrize("min_count, expected", [(3, 2), (4, np.nan)])
     def test_sum_min_count(self, arr, fill_value, min_count, expected):
         # GH#25777
-        sparray = SparseArray(arr, fill_value=fill_value)
+        sparray = SparseArray(np.array(arr), fill_value=fill_value)
         result = sparray.sum(min_count=min_count)
         if np.isnan(expected):
             assert np.isnan(result)
@@ -296,11 +296,9 @@ def test_argmax_argmin(self, arr, argmax_expected, argmin_expected):
         assert argmax_result == argmax_expected
         assert argmin_result == argmin_expected
 
-    @pytest.mark.parametrize(
-        "arr,method",
-        [(SparseArray([]), "argmax"), (SparseArray([]), "argmin")],
-    )
-    def test_empty_array(self, arr, method):
+    @pytest.mark.parametrize("method", ["argmax", "argmin"])
+    def test_empty_array(self, method):
         msg = f"attempt to get {method} of an empty sequence"
+        arr = SparseArray([])
         with pytest.raises(ValueError, match=msg):
-            arr.argmax() if method == "argmax" else arr.argmin()
+            getattr(arr, method)()

pandas/tests/base/test_conversion.py

@@ -499,22 +499,23 @@ def test_to_numpy_dataframe_na_value(data, dtype, na_value):
 
 
 @pytest.mark.parametrize(
-    "data, expected",
+    "data, expected_data",
     [
         (
             {"a": pd.array([1, 2, None])},
-            np.array([[1.0], [2.0], [np.nan]], dtype=float),
+            [[1.0], [2.0], [np.nan]],
         ),
         (
             {"a": [1, 2, 3], "b": [1, 2, 3]},
-            np.array([[1, 1], [2, 2], [3, 3]], dtype=float),
+            [[1, 1], [2, 2], [3, 3]],
         ),
     ],
 )
-def test_to_numpy_dataframe_single_block(data, expected):
+def test_to_numpy_dataframe_single_block(data, expected_data):
     # https://github.com/pandas-dev/pandas/issues/33820
     df = pd.DataFrame(data)
     result = df.to_numpy(dtype=float, na_value=np.nan)
+    expected = np.array(expected_data, dtype=float)
     tm.assert_numpy_array_equal(result, expected)
 
 

pandas/tests/computation/test_eval.py

@@ -522,14 +522,15 @@ def test_series_negate(self, engine, parser):
         "lhs",
         [
             # Float
-            DataFrame(np.random.default_rng(2).standard_normal((5, 2))),
+            np.random.default_rng(2).standard_normal((5, 2)),
             # Int
-            DataFrame(np.random.default_rng(2).integers(5, size=(5, 2))),
+            np.random.default_rng(2).integers(5, size=(5, 2)),
             # bool doesn't work with numexpr but works elsewhere
-            DataFrame(np.random.default_rng(2).standard_normal((5, 2)) > 0.5),
+            np.array([True, False, True, False, True], dtype=np.bool_),
         ],
     )
     def test_frame_pos(self, lhs, engine, parser):
+        lhs = DataFrame(lhs)
         expr = "+lhs"
         expect = lhs
 
@@ -540,14 +541,15 @@ def test_frame_pos(self, lhs, engine, parser):
         "lhs",
         [
             # Float
-            Series(np.random.default_rng(2).standard_normal(5)),
+            np.random.default_rng(2).standard_normal(5),
             # Int
-            Series(np.random.default_rng(2).integers(5, size=5)),
+            np.random.default_rng(2).integers(5, size=5),
             # bool doesn't work with numexpr but works elsewhere
-            Series(np.random.default_rng(2).standard_normal(5) > 0.5),
+            np.array([True, False, True, False, True], dtype=np.bool_),
         ],
     )
     def test_series_pos(self, lhs, engine, parser):
+        lhs = Series(lhs)
         expr = "+lhs"
         expect = lhs
 

pandas/tests/copy_view/index/test_datetimeindex.py

@@ -13,17 +13,11 @@
 )
 
 
-@pytest.mark.parametrize(
-    "cons",
-    [
-        lambda x: DatetimeIndex(x),
-        lambda x: DatetimeIndex(DatetimeIndex(x)),
-    ],
-)
-def test_datetimeindex(using_copy_on_write, cons):
+@pytest.mark.parametrize("box", [lambda x: x, DatetimeIndex])
+def test_datetimeindex(using_copy_on_write, box):
     dt = date_range("2019-12-31", periods=3, freq="D")
     ser = Series(dt)
-    idx = cons(ser)
+    idx = box(DatetimeIndex(ser))
     expected = idx.copy(deep=True)
     ser.iloc[0] = Timestamp("2020-12-31")
     if using_copy_on_write:

pandas/tests/copy_view/index/test_periodindex.py

@@ -13,17 +13,11 @@
 )
 
 
-@pytest.mark.parametrize(
-    "cons",
-    [
-        lambda x: PeriodIndex(x),
-        lambda x: PeriodIndex(PeriodIndex(x)),
-    ],
-)
-def test_periodindex(using_copy_on_write, cons):
+@pytest.mark.parametrize("box", [lambda x: x, PeriodIndex])
+def test_periodindex(using_copy_on_write, box):
     dt = period_range("2019-12-31", periods=3, freq="D")
     ser = Series(dt)
-    idx = cons(ser)
+    idx = box(PeriodIndex(ser))
     expected = idx.copy(deep=True)
     ser.iloc[0] = Period("2020-12-31")
     if using_copy_on_write:

pandas/tests/dtypes/test_inference.py

@@ -1078,15 +1078,15 @@ def test_integers(self):
     @pytest.mark.parametrize(
         "arr, skipna",
         [
-            (np.array([1, 2, np.nan, np.nan, 3], dtype="O"), False),
-            (np.array([1, 2, np.nan, np.nan, 3], dtype="O"), True),
-            (np.array([1, 2, 3, np.int64(4), np.int32(5), np.nan], dtype="O"), False),
-            (np.array([1, 2, 3, np.int64(4), np.int32(5), np.nan], dtype="O"), True),
+            ([1, 2, np.nan, np.nan, 3], False),
+            ([1, 2, np.nan, np.nan, 3], True),
+            ([1, 2, 3, np.int64(4), np.int32(5), np.nan], False),
+            ([1, 2, 3, np.int64(4), np.int32(5), np.nan], True),
         ],
     )
     def test_integer_na(self, arr, skipna):
         # GH 27392
-        result = lib.infer_dtype(arr, skipna=skipna)
+        result = lib.infer_dtype(np.array(arr, dtype="O"), skipna=skipna)
         expected = "integer" if skipna else "integer-na"
         assert result == expected
 
@@ -1287,13 +1287,13 @@ def test_infer_dtype_mixed_integer(self):
     @pytest.mark.parametrize(
         "arr",
         [
-            np.array([Timestamp("2011-01-01"), Timestamp("2011-01-02")]),
-            np.array([datetime(2011, 1, 1), datetime(2012, 2, 1)]),
-            np.array([datetime(2011, 1, 1), Timestamp("2011-01-02")]),
+            [Timestamp("2011-01-01"), Timestamp("2011-01-02")],
+            [datetime(2011, 1, 1), datetime(2012, 2, 1)],
+            [datetime(2011, 1, 1), Timestamp("2011-01-02")],
         ],
     )
     def test_infer_dtype_datetime(self, arr):
-        assert lib.infer_dtype(arr, skipna=True) == "datetime"
+        assert lib.infer_dtype(np.array(arr), skipna=True) == "datetime"
 
     @pytest.mark.parametrize("na_value", [pd.NaT, np.nan])
     @pytest.mark.parametrize(
@@ -1902,14 +1902,15 @@ def test_is_scalar_numpy_array_scalars(self):
     @pytest.mark.parametrize(
         "zerodim",
         [
-            np.array(1),
-            np.array("foobar"),
-            np.array(np.datetime64("2014-01-01")),
-            np.array(np.timedelta64(1, "h")),
-            np.array(np.datetime64("NaT")),
+            1,
+            "foobar",
+            np.datetime64("2014-01-01"),
+            np.timedelta64(1, "h"),
+            np.datetime64("NaT"),
         ],
     )
     def test_is_scalar_numpy_zerodim_arrays(self, zerodim):
+        zerodim = np.array(zerodim)
         assert not is_scalar(zerodim)
         assert is_scalar(lib.item_from_zerodim(zerodim))
 

pandas/tests/frame/indexing/test_get.py

@@ -15,13 +15,13 @@ def test_get(self, float_frame):
         )
 
     @pytest.mark.parametrize(
-        "df",
+        "columns, index",
         [
-            DataFrame(),
-            DataFrame(columns=list("AB")),
-            DataFrame(columns=list("AB"), index=range(3)),
+            [None, None],
+            [list("AB"), None],
+            [list("AB"), range(3)],
         ],
     )
-    def test_get_none(self, df):
+    def test_get_none(self, columns, index):
         # see gh-5652
-        assert df.get(None) is None
+        assert DataFrame(columns=columns, index=index).get(None) is None