TST/CLN: Tests parametrizations 3 (#56745)

* TST/CLN: Tests parametrizations

* Fix typos

* fix typos

* Add pytest

Author: mroeschke

pandas/tests/plotting/frame/test_frame.py

@@ -1199,12 +1199,10 @@ def test_hist_df_orientation(self):
         axes = df.plot.hist(rot=50, fontsize=8, orientation="horizontal")
         _check_ticks_props(axes, xrot=0, yrot=50, ylabelsize=8)
 
-    @pytest.mark.parametrize(
-        "weights", [0.1 * np.ones(shape=(100,)), 0.1 * np.ones(shape=(100, 2))]
-    )
-    def test_hist_weights(self, weights):
+    @pytest.mark.parametrize("weight_shape", [(100,), (100, 2)])
+    def test_hist_weights(self, weight_shape):
         # GH 33173
-
+        weights = 0.1 * np.ones(shape=weight_shape)
         df = DataFrame(
             dict(zip(["A", "B"], np.random.default_rng(2).standard_normal((2, 100))))
         )

pandas/tests/plotting/frame/test_frame_color.py

@@ -30,11 +30,10 @@ def _check_colors_box(bp, box_c, whiskers_c, medians_c, caps_c="k", fliers_c=Non
 
 
 class TestDataFrameColor:
-    @pytest.mark.parametrize(
-        "color", ["C0", "C1", "C2", "C3", "C4", "C5", "C6", "C7", "C8", "C9"]
-    )
+    @pytest.mark.parametrize("color", list(range(10)))
     def test_mpl2_color_cycle_str(self, color):
         # GH 15516
+        color = f"C{color}"
         df = DataFrame(
             np.random.default_rng(2).standard_normal((10, 3)), columns=["a", "b", "c"]
         )

pandas/tests/reductions/test_reductions.py

@@ -1144,18 +1144,7 @@ def test_timedelta64_analytics(self):
         expected = Timedelta("1 days")
         assert result == expected
 
-    @pytest.mark.parametrize(
-        "test_input,error_type",
-        [
-            (Series([], dtype="float64"), ValueError),
-            # For strings, or any Series with dtype 'O'
-            (Series(["foo", "bar", "baz"]), TypeError),
-            (Series([(1,), (2,)]), TypeError),
-            # For mixed data types
-            (Series(["foo", "foo", "bar", "bar", None, np.nan, "baz"]), TypeError),
-        ],
-    )
-    def test_assert_idxminmax_empty_raises(self, test_input, error_type):
+    def test_assert_idxminmax_empty_raises(self):
         """
         Cases where ``Series.argmax`` and related should raise an exception
         """
@@ -1294,13 +1283,14 @@ def test_minmax_nat_series(self, nat_ser):
     @pytest.mark.parametrize(
         "nat_df",
         [
-            DataFrame([NaT, NaT]),
-            DataFrame([NaT, Timedelta("nat")]),
-            DataFrame([Timedelta("nat"), Timedelta("nat")]),
+            [NaT, NaT],
+            [NaT, Timedelta("nat")],
+            [Timedelta("nat"), Timedelta("nat")],
         ],
     )
     def test_minmax_nat_dataframe(self, nat_df):
         # GH#23282
+        nat_df = DataFrame(nat_df)
         assert nat_df.min()[0] is NaT
         assert nat_df.max()[0] is NaT
         assert nat_df.min(skipna=False)[0] is NaT
@@ -1399,14 +1389,10 @@ class TestSeriesMode:
     #  were moved from a series-specific test file, _not_ that these tests are
     #  intended long-term to be series-specific
 
-    @pytest.mark.parametrize(
-        "dropna, expected",
-        [(True, Series([], dtype=np.float64)), (False, Series([], dtype=np.float64))],
-    )
-    def test_mode_empty(self, dropna, expected):
+    def test_mode_empty(self, dropna):
         s = Series([], dtype=np.float64)
         result = s.mode(dropna)
-        tm.assert_series_equal(result, expected)
+        tm.assert_series_equal(result, s)
 
     @pytest.mark.parametrize(
         "dropna, data, expected",
@@ -1619,23 +1605,24 @@ def test_mode_boolean_with_na(self):
         [
             (
                 [0, 1j, 1, 1, 1 + 1j, 1 + 2j],
-                Series([1], dtype=np.complex128),
+                [1],
                 np.complex128,
             ),
             (
                 [0, 1j, 1, 1, 1 + 1j, 1 + 2j],
-                Series([1], dtype=np.complex64),
+                [1],
                 np.complex64,
             ),
             (
                 [1 + 1j, 2j, 1 + 1j],
-                Series([1 + 1j], dtype=np.complex128),
+                [1 + 1j],
                 np.complex128,
             ),
         ],
     )
     def test_single_mode_value_complex(self, array, expected, dtype):
         result = Series(array, dtype=dtype).mode()
+        expected = Series(expected, dtype=dtype)
         tm.assert_series_equal(result, expected)
 
     @pytest.mark.parametrize(
@@ -1644,12 +1631,12 @@ def test_single_mode_value_complex(self, array, expected, dtype):
             (
                 # no modes
                 [0, 1j, 1, 1 + 1j, 1 + 2j],
-                Series([0j, 1j, 1 + 0j, 1 + 1j, 1 + 2j], dtype=np.complex128),
+                [0j, 1j, 1 + 0j, 1 + 1j, 1 + 2j],
                 np.complex128,
             ),
             (
                 [1 + 1j, 2j, 1 + 1j, 2j, 3],
-                Series([2j, 1 + 1j], dtype=np.complex64),
+                [2j, 1 + 1j],
                 np.complex64,
             ),
         ],
@@ -1659,4 +1646,5 @@ def test_multimode_complex(self, array, expected, dtype):
         # mode tries to sort multimodal series.
         # Complex numbers are sorted by their magnitude
         result = Series(array, dtype=dtype).mode()
+        expected = Series(expected, dtype=dtype)
         tm.assert_series_equal(result, expected)

pandas/tests/reshape/concat/test_series.py

@@ -128,11 +128,10 @@ def test_concat_series_axis1_same_names_ignore_index(self):
 
         tm.assert_index_equal(result.columns, expected, exact=True)
 
-    @pytest.mark.parametrize(
-        "s1name,s2name", [(np.int64(190), (43, 0)), (190, (43, 0))]
-    )
-    def test_concat_series_name_npscalar_tuple(self, s1name, s2name):
+    @pytest.mark.parametrize("s1name", [np.int64(190), 190])
+    def test_concat_series_name_npscalar_tuple(self, s1name):
         # GH21015
+        s2name = (43, 0)
         s1 = Series({"a": 1, "b": 2}, name=s1name)
         s2 = Series({"c": 5, "d": 6}, name=s2name)
         result = concat([s1, s2])

pandas/tests/reshape/merge/test_merge.py

@@ -1466,10 +1466,8 @@ def _check_merge(x, y):
 
 
 class TestMergeDtypes:
-    @pytest.mark.parametrize(
-        "right_vals", [["foo", "bar"], Series(["foo", "bar"]).astype("category")]
-    )
-    def test_different(self, right_vals):
+    @pytest.mark.parametrize("dtype", [object, "category"])
+    def test_different(self, dtype):
         left = DataFrame(
             {
                 "A": ["foo", "bar"],
@@ -1480,6 +1478,7 @@ def test_different(self, right_vals):
                 "F": Series([1, 2], dtype="int32"),
             }
         )
+        right_vals = Series(["foo", "bar"], dtype=dtype)
         right = DataFrame({"A": right_vals})
 
         # GH 9780
@@ -2311,26 +2310,23 @@ def test_merge_suffix(col1, col2, kwargs, expected_cols):
     [
         (
             "right",
-            DataFrame(
-                {"A": [100, 200, 300], "B1": [60, 70, np.nan], "B2": [600, 700, 800]}
-            ),
+            {"A": [100, 200, 300], "B1": [60, 70, np.nan], "B2": [600, 700, 800]},
         ),
         (
             "outer",
-            DataFrame(
-                {
-                    "A": [1, 100, 200, 300],
-                    "B1": [80, 60, 70, np.nan],
-                    "B2": [np.nan, 600, 700, 800],
-                }
-            ),
+            {
+                "A": [1, 100, 200, 300],
+                "B1": [80, 60, 70, np.nan],
+                "B2": [np.nan, 600, 700, 800],
+            },
         ),
     ],
 )
 def test_merge_duplicate_suffix(how, expected):
     left_df = DataFrame({"A": [100, 200, 1], "B": [60, 70, 80]})
     right_df = DataFrame({"A": [100, 200, 300], "B": [600, 700, 800]})
     result = merge(left_df, right_df, on="A", how=how, suffixes=("_x", "_x"))
+    expected = DataFrame(expected)
     expected.columns = ["A", "B_x", "B_x"]
 
     tm.assert_frame_equal(result, expected)

pandas/tests/reshape/merge/test_merge_asof.py

@@ -3099,7 +3099,7 @@ def test_merge_groupby_multiple_column_with_categorical_column(self):
         tm.assert_frame_equal(result, expected)
 
     @pytest.mark.parametrize(
-        "func", [lambda x: x, lambda x: to_datetime(x)], ids=["numeric", "datetime"]
+        "func", [lambda x: x, to_datetime], ids=["numeric", "datetime"]
     )
     @pytest.mark.parametrize("side", ["left", "right"])
     def test_merge_on_nans(self, func, side):

pandas/tests/reshape/merge/test_merge_ordered.py

@@ -135,61 +135,58 @@ def test_doc_example(self):
         "left, right, on, left_by, right_by, expected",
         [
             (
-                DataFrame({"G": ["g", "g"], "H": ["h", "h"], "T": [1, 3]}),
-                DataFrame({"T": [2], "E": [1]}),
+                {"G": ["g", "g"], "H": ["h", "h"], "T": [1, 3]},
+                {"T": [2], "E": [1]},
                 ["T"],
                 ["G", "H"],
                 None,
-                DataFrame(
-                    {
-                        "G": ["g"] * 3,
-                        "H": ["h"] * 3,
-                        "T": [1, 2, 3],
-                        "E": [np.nan, 1.0, np.nan],
-                    }
-                ),
+                {
+                    "G": ["g"] * 3,
+                    "H": ["h"] * 3,
+                    "T": [1, 2, 3],
+                    "E": [np.nan, 1.0, np.nan],
+                },
             ),
             (
-                DataFrame({"G": ["g", "g"], "H": ["h", "h"], "T": [1, 3]}),
-                DataFrame({"T": [2], "E": [1]}),
+                {"G": ["g", "g"], "H": ["h", "h"], "T": [1, 3]},
+                {"T": [2], "E": [1]},
                 "T",
                 ["G", "H"],
                 None,
-                DataFrame(
-                    {
-                        "G": ["g"] * 3,
-                        "H": ["h"] * 3,
-                        "T": [1, 2, 3],
-                        "E": [np.nan, 1.0, np.nan],
-                    }
-                ),
+                {
+                    "G": ["g"] * 3,
+                    "H": ["h"] * 3,
+                    "T": [1, 2, 3],
+                    "E": [np.nan, 1.0, np.nan],
+                },
             ),
             (
-                DataFrame({"T": [2], "E": [1]}),
-                DataFrame({"G": ["g", "g"], "H": ["h", "h"], "T": [1, 3]}),
+                {"T": [2], "E": [1]},
+                {"G": ["g", "g"], "H": ["h", "h"], "T": [1, 3]},
                 ["T"],
                 None,
                 ["G", "H"],
-                DataFrame(
-                    {
-                        "T": [1, 2, 3],
-                        "E": [np.nan, 1.0, np.nan],
-                        "G": ["g"] * 3,
-                        "H": ["h"] * 3,
-                    }
-                ),
+                {
+                    "T": [1, 2, 3],
+                    "E": [np.nan, 1.0, np.nan],
+                    "G": ["g"] * 3,
+                    "H": ["h"] * 3,
+                },
             ),
         ],
     )
     def test_list_type_by(self, left, right, on, left_by, right_by, expected):
         # GH 35269
+        left = DataFrame(left)
+        right = DataFrame(right)
         result = merge_ordered(
             left=left,
             right=right,
             on=on,
             left_by=left_by,
             right_by=right_by,
         )
+        expected = DataFrame(expected)
 
         tm.assert_frame_equal(result, expected)
 

pandas/tests/reshape/test_from_dummies.py

@@ -298,32 +298,32 @@ def test_no_prefix_string_cats_contains_get_dummies_NaN_column():
     [
         pytest.param(
             "c",
-            DataFrame({"": ["a", "b", "c"]}),
+            {"": ["a", "b", "c"]},
             id="default_category is a str",
         ),
         pytest.param(
             1,
-            DataFrame({"": ["a", "b", 1]}),
+            {"": ["a", "b", 1]},
             id="default_category is a int",
         ),
         pytest.param(
             1.25,
-            DataFrame({"": ["a", "b", 1.25]}),
+            {"": ["a", "b", 1.25]},
             id="default_category is a float",
         ),
         pytest.param(
             0,
-            DataFrame({"": ["a", "b", 0]}),
+            {"": ["a", "b", 0]},
             id="default_category is a 0",
         ),
         pytest.param(
             False,
-            DataFrame({"": ["a", "b", False]}),
+            {"": ["a", "b", False]},
             id="default_category is a bool",
         ),
         pytest.param(
             (1, 2),
-            DataFrame({"": ["a", "b", (1, 2)]}),
+            {"": ["a", "b", (1, 2)]},
             id="default_category is a tuple",
         ),
     ],
@@ -333,6 +333,7 @@ def test_no_prefix_string_cats_default_category(
 ):
     dummies = DataFrame({"a": [1, 0, 0], "b": [0, 1, 0]})
     result = from_dummies(dummies, default_category=default_category)
+    expected = DataFrame(expected)
     if using_infer_string:
         expected[""] = expected[""].astype("string[pyarrow_numpy]")
     tm.assert_frame_equal(result, expected)
@@ -366,32 +367,32 @@ def test_with_prefix_contains_get_dummies_NaN_column():
     [
         pytest.param(
             "x",
-            DataFrame({"col1": ["a", "b", "x"], "col2": ["x", "a", "c"]}),
+            {"col1": ["a", "b", "x"], "col2": ["x", "a", "c"]},
             id="default_category is a str",
         ),
         pytest.param(
             0,
-            DataFrame({"col1": ["a", "b", 0], "col2": [0, "a", "c"]}),
+            {"col1": ["a", "b", 0], "col2": [0, "a", "c"]},
             id="default_category is a 0",
         ),
         pytest.param(
             False,
-            DataFrame({"col1": ["a", "b", False], "col2": [False, "a", "c"]}),
+            {"col1": ["a", "b", False], "col2": [False, "a", "c"]},
             id="default_category is a False",
         ),
         pytest.param(
             {"col2": 1, "col1": 2.5},
-            DataFrame({"col1": ["a", "b", 2.5], "col2": [1, "a", "c"]}),
+            {"col1": ["a", "b", 2.5], "col2": [1, "a", "c"]},
             id="default_category is a dict with int and float values",
         ),
         pytest.param(
             {"col2": None, "col1": False},
-            DataFrame({"col1": ["a", "b", False], "col2": [None, "a", "c"]}),
+            {"col1": ["a", "b", False], "col2": [None, "a", "c"]},
             id="default_category is a dict with bool and None values",
         ),
         pytest.param(
             {"col2": (1, 2), "col1": [1.25, False]},
-            DataFrame({"col1": ["a", "b", [1.25, False]], "col2": [(1, 2), "a", "c"]}),
+            {"col1": ["a", "b", [1.25, False]], "col2": [(1, 2), "a", "c"]},
             id="default_category is a dict with list and tuple values",
         ),
     ],
@@ -402,6 +403,7 @@ def test_with_prefix_default_category(
     result = from_dummies(
         dummies_with_unassigned, sep="_", default_category=default_category
     )
+    expected = DataFrame(expected)
     tm.assert_frame_equal(result, expected)