TST/CLN: Remove more seldom used fixtures (pandas-dev#56625)

* Remove conftest in indexing

* Use less idx fixture in multi

* Remove other seldom used fixtures

* Revert "Use less idx fixture in multi"

This reverts commit e4f81bb.

* Remove more single use fixtures

* Fix typos

* Fix more typos

* fix typo

* pylint

* Uncomment

* add back parametrization

* Simplify

Author: mroeschke

pandas/conftest.py

@@ -1838,16 +1838,6 @@ def ip():
     return InteractiveShell(config=c)
 
 
-@pytest.fixture(params=["bsr", "coo", "csc", "csr", "dia", "dok", "lil"])
-def spmatrix(request):
-    """
-    Yields scipy sparse matrix classes.
-    """
-    sparse = pytest.importorskip("scipy.sparse")
-
-    return getattr(sparse, request.param + "_matrix")
-
-
 @pytest.fixture(
     params=[
         getattr(pd.offsets, o)

pandas/tests/arithmetic/test_numeric.py

@@ -37,14 +37,6 @@ def switch_numexpr_min_elements(request, monkeypatch):
         yield request.param
 
 
-@pytest.fixture(params=[Index, Series, tm.to_array])
-def box_pandas_1d_array(request):
-    """
-    Fixture to test behavior for Index, Series and tm.to_array classes
-    """
-    return request.param
-
-
 @pytest.fixture(
     params=[
         # TODO: add more  dtypes here
@@ -62,17 +54,6 @@ def numeric_idx(request):
     return request.param
 
 
-@pytest.fixture(
-    params=[Index, Series, tm.to_array, np.array, list], ids=lambda x: x.__name__
-)
-def box_1d_array(request):
-    """
-    Fixture to test behavior for Index, Series, tm.to_array, numpy Array and list
-    classes
-    """
-    return request.param
-
-
 def adjust_negative_zero(zero, expected):
     """
     Helper to adjust the expected result if we are dividing by -0.0
@@ -1499,6 +1480,8 @@ def test_dataframe_div_silenced():
     "data, expected_data",
     [([0, 1, 2], [0, 2, 4])],
 )
+@pytest.mark.parametrize("box_pandas_1d_array", [Index, Series, tm.to_array])
+@pytest.mark.parametrize("box_1d_array", [Index, Series, tm.to_array, np.array, list])
 def test_integer_array_add_list_like(
     box_pandas_1d_array, box_1d_array, data, expected_data
 ):

pandas/tests/dtypes/test_inference.py

@@ -1977,9 +1977,12 @@ def test_nan_to_nat_conversions():
 
 
 @pytest.mark.filterwarnings("ignore::PendingDeprecationWarning")
+@pytest.mark.parametrize("spmatrix", ["bsr", "coo", "csc", "csr", "dia", "dok", "lil"])
 def test_is_scipy_sparse(spmatrix):
-    pytest.importorskip("scipy")
-    assert is_scipy_sparse(spmatrix([[0, 1]]))
+    sparse = pytest.importorskip("scipy.sparse")
+
+    klass = getattr(sparse, spmatrix + "_matrix")
+    assert is_scipy_sparse(klass([[0, 1]]))
     assert not is_scipy_sparse(np.array([1]))
 
 

pandas/tests/frame/indexing/test_indexing.py

@@ -1662,25 +1662,6 @@ def orig(self):
         orig = DataFrame({"cats": cats, "values": values}, index=idx)
         return orig
 
-    @pytest.fixture
-    def exp_single_row(self):
-        # The expected values if we change a single row
-        cats1 = Categorical(["a", "a", "b", "a", "a", "a", "a"], categories=["a", "b"])
-        idx1 = Index(["h", "i", "j", "k", "l", "m", "n"])
-        values1 = [1, 1, 2, 1, 1, 1, 1]
-        exp_single_row = DataFrame({"cats": cats1, "values": values1}, index=idx1)
-        return exp_single_row
-
-    @pytest.fixture
-    def exp_multi_row(self):
-        # assign multiple rows (mixed values) (-> array) -> exp_multi_row
-        # changed multiple rows
-        cats2 = Categorical(["a", "a", "b", "b", "a", "a", "a"], categories=["a", "b"])
-        idx2 = Index(["h", "i", "j", "k", "l", "m", "n"])
-        values2 = [1, 1, 2, 2, 1, 1, 1]
-        exp_multi_row = DataFrame({"cats": cats2, "values": values2}, index=idx2)
-        return exp_multi_row
-
     @pytest.fixture
     def exp_parts_cats_col(self):
         # changed part of the cats column
@@ -1702,7 +1683,7 @@ def exp_single_cats_value(self):
         return exp_single_cats_value
 
     @pytest.mark.parametrize("indexer", [tm.loc, tm.iloc])
-    def test_loc_iloc_setitem_list_of_lists(self, orig, exp_multi_row, indexer):
+    def test_loc_iloc_setitem_list_of_lists(self, orig, indexer):
         #   - assign multiple rows (mixed values) -> exp_multi_row
         df = orig.copy()
 
@@ -1711,6 +1692,11 @@ def test_loc_iloc_setitem_list_of_lists(self, orig, exp_multi_row, indexer):
             key = slice("j", "k")
 
         indexer(df)[key, :] = [["b", 2], ["b", 2]]
+
+        cats2 = Categorical(["a", "a", "b", "b", "a", "a", "a"], categories=["a", "b"])
+        idx2 = Index(["h", "i", "j", "k", "l", "m", "n"])
+        values2 = [1, 1, 2, 2, 1, 1, 1]
+        exp_multi_row = DataFrame({"cats": cats2, "values": values2}, index=idx2)
         tm.assert_frame_equal(df, exp_multi_row)
 
         df = orig.copy()
@@ -1752,9 +1738,7 @@ def test_loc_iloc_setitem_mask_single_value_in_categories(
         tm.assert_frame_equal(df, exp_single_cats_value)
 
     @pytest.mark.parametrize("indexer", [tm.loc, tm.iloc])
-    def test_loc_iloc_setitem_full_row_non_categorical_rhs(
-        self, orig, exp_single_row, indexer
-    ):
+    def test_loc_iloc_setitem_full_row_non_categorical_rhs(self, orig, indexer):
         #   - assign a complete row (mixed values) -> exp_single_row
         df = orig.copy()
 
@@ -1764,6 +1748,10 @@ def test_loc_iloc_setitem_full_row_non_categorical_rhs(
 
         # not categorical dtype, but "b" _is_ among the categories for df["cat"]
         indexer(df)[key, :] = ["b", 2]
+        cats1 = Categorical(["a", "a", "b", "a", "a", "a", "a"], categories=["a", "b"])
+        idx1 = Index(["h", "i", "j", "k", "l", "m", "n"])
+        values1 = [1, 1, 2, 1, 1, 1, 1]
+        exp_single_row = DataFrame({"cats": cats1, "values": values1}, index=idx1)
         tm.assert_frame_equal(df, exp_single_row)
 
         # "c" is not among the categories for df["cat"]

pandas/tests/frame/methods/test_join.py

@@ -17,25 +17,6 @@
 from pandas.core.reshape.concat import concat
 
 
-@pytest.fixture
-def frame_with_period_index():
-    return DataFrame(
-        data=np.arange(20).reshape(4, 5),
-        columns=list("abcde"),
-        index=period_range(start="2000", freq="Y", periods=4),
-    )
-
-
-@pytest.fixture
-def left():
-    return DataFrame({"a": [20, 10, 0]}, index=[2, 1, 0])
-
-
-@pytest.fixture
-def right():
-    return DataFrame({"b": [300, 100, 200]}, index=[3, 1, 2])
-
-
 @pytest.fixture
 def left_no_dup():
     return DataFrame(
@@ -112,7 +93,9 @@ def right_w_dups(right_no_dup):
         ),
     ],
 )
-def test_join(left, right, how, sort, expected):
+def test_join(how, sort, expected):
+    left = DataFrame({"a": [20, 10, 0]}, index=[2, 1, 0])
+    right = DataFrame({"b": [300, 100, 200]}, index=[3, 1, 2])
     result = left.join(right, how=how, sort=sort, validate="1:1")
     tm.assert_frame_equal(result, expected)
 
@@ -347,7 +330,12 @@ def test_join_overlap(float_frame):
     tm.assert_frame_equal(joined, expected.loc[:, joined.columns])
 
 
-def test_join_period_index(frame_with_period_index):
+def test_join_period_index():
+    frame_with_period_index = DataFrame(
+        data=np.arange(20).reshape(4, 5),
+        columns=list("abcde"),
+        index=period_range(start="2000", freq="Y", periods=4),
+    )
     other = frame_with_period_index.rename(columns=lambda key: f"{key}{key}")
 
     joined_values = np.concatenate([frame_with_period_index.values] * 2, axis=1)

pandas/tests/frame/methods/test_nlargest.py

@@ -12,25 +12,6 @@
 from pandas.util.version import Version
 
 
-@pytest.fixture
-def df_duplicates():
-    return pd.DataFrame(
-        {"a": [1, 2, 3, 4, 4], "b": [1, 1, 1, 1, 1], "c": [0, 1, 2, 5, 4]},
-        index=[0, 0, 1, 1, 1],
-    )
-
-
-@pytest.fixture
-def df_strings():
-    return pd.DataFrame(
-        {
-            "a": np.random.default_rng(2).permutation(10),
-            "b": list(ascii_lowercase[:10]),
-            "c": np.random.default_rng(2).permutation(10).astype("float64"),
-        }
-    )
-
-
 @pytest.fixture
 def df_main_dtypes():
     return pd.DataFrame(
@@ -81,9 +62,15 @@ class TestNLargestNSmallest:
         ],
     )
     @pytest.mark.parametrize("n", range(1, 11))
-    def test_nlargest_n(self, df_strings, nselect_method, n, order):
+    def test_nlargest_n(self, nselect_method, n, order):
         # GH#10393
-        df = df_strings
+        df = pd.DataFrame(
+            {
+                "a": np.random.default_rng(2).permutation(10),
+                "b": list(ascii_lowercase[:10]),
+                "c": np.random.default_rng(2).permutation(10).astype("float64"),
+            }
+        )
         if "b" in order:
             error_msg = (
                 f"Column 'b' has dtype (object|string), "
@@ -156,10 +143,13 @@ def test_nlargest_n_identical_values(self):
         [["a", "b", "c"], ["c", "b", "a"], ["a"], ["b"], ["a", "b"], ["c", "b"]],
     )
     @pytest.mark.parametrize("n", range(1, 6))
-    def test_nlargest_n_duplicate_index(self, df_duplicates, n, order, request):
+    def test_nlargest_n_duplicate_index(self, n, order, request):
         # GH#13412
 
-        df = df_duplicates
+        df = pd.DataFrame(
+            {"a": [1, 2, 3, 4, 4], "b": [1, 1, 1, 1, 1], "c": [0, 1, 2, 5, 4]},
+            index=[0, 0, 1, 1, 1],
+        )
         result = df.nsmallest(n, order)
         expected = df.sort_values(order).head(n)
         tm.assert_frame_equal(result, expected)

pandas/tests/frame/test_subclass.py

@@ -15,16 +15,6 @@
 )
 
 
-@pytest.fixture()
-def gpd_style_subclass_df():
-    class SubclassedDataFrame(DataFrame):
-        @property
-        def _constructor(self):
-            return SubclassedDataFrame
-
-    return SubclassedDataFrame({"a": [1, 2, 3]})
-
-
 class TestDataFrameSubclassing:
     def test_frame_subclassing_and_slicing(self):
         # Subclass frame and ensure it returns the right class on slicing it
@@ -710,14 +700,21 @@ def test_idxmax_preserves_subclass(self):
         result = df.idxmax()
         assert isinstance(result, tm.SubclassedSeries)
 
-    def test_convert_dtypes_preserves_subclass(self, gpd_style_subclass_df):
+    def test_convert_dtypes_preserves_subclass(self):
         # GH 43668
         df = tm.SubclassedDataFrame({"A": [1, 2, 3], "B": [4, 5, 6], "C": [7, 8, 9]})
         result = df.convert_dtypes()
         assert isinstance(result, tm.SubclassedDataFrame)
 
-        result = gpd_style_subclass_df.convert_dtypes()
-        assert isinstance(result, type(gpd_style_subclass_df))
+    def test_convert_dtypes_preserves_subclass_with_constructor(self):
+        class SubclassedDataFrame(DataFrame):
+            @property
+            def _constructor(self):
+                return SubclassedDataFrame
+
+        df = SubclassedDataFrame({"a": [1, 2, 3]})
+        result = df.convert_dtypes()
+        assert isinstance(result, SubclassedDataFrame)
 
     def test_astype_preserves_subclass(self):
         # GH#40810

pandas/tests/frame/test_validate.py

@@ -3,11 +3,6 @@
 from pandas.core.frame import DataFrame
 
 
-@pytest.fixture
-def dataframe():
-    return DataFrame({"a": [1, 2], "b": [3, 4]})
-
-
 class TestDataFrameValidate:
     """Tests for error handling related to data types of method arguments."""
 
@@ -24,7 +19,8 @@ class TestDataFrameValidate:
         ],
     )
     @pytest.mark.parametrize("inplace", [1, "True", [1, 2, 3], 5.0])
-    def test_validate_bool_args(self, dataframe, func, inplace):
+    def test_validate_bool_args(self, func, inplace):
+        dataframe = DataFrame({"a": [1, 2], "b": [3, 4]})
         msg = 'For argument "inplace" expected type bool'
         kwargs = {"inplace": inplace}
 

pandas/tests/generic/test_finalize.py

@@ -386,18 +386,11 @@ def idfn(x):
         return str(x)
 
 
-@pytest.fixture(params=_all_methods, ids=lambda x: idfn(x[-1]))
-def ndframe_method(request):
-    """
-    An NDFrame method returning an NDFrame.
-    """
-    return request.param
-
-
 @pytest.mark.filterwarnings(
     "ignore:DataFrame.fillna with 'method' is deprecated:FutureWarning",
     "ignore:last is deprecated:FutureWarning",
 )
+@pytest.mark.parametrize("ndframe_method", _all_methods, ids=lambda x: idfn(x[-1]))
 def test_finalize_called(ndframe_method):
     cls, init_args, method = ndframe_method
     ndframe = cls(*init_args)

pandas/tests/generic/test_label_or_level_utils.py

@@ -34,15 +34,6 @@ def df_ambig(df):
     return df
 
 
-@pytest.fixture
-def df_duplabels(df):
-    """DataFrame with level 'L1' and labels 'L2', 'L3', and 'L2'"""
-    df = df.set_index(["L1"])
-    df = pd.concat([df, df["L2"]], axis=1)
-
-    return df
-
-
 # Test is label/level reference
 # =============================
 def get_labels_levels(df_levels):
@@ -229,7 +220,9 @@ def test_get_label_or_level_values_df_ambig(df_ambig, axis):
     assert_label_values(df_ambig, ["L3"], axis=axis)
 
 
-def test_get_label_or_level_values_df_duplabels(df_duplabels, axis):
+def test_get_label_or_level_values_df_duplabels(df, axis):
+    df = df.set_index(["L1"])
+    df_duplabels = pd.concat([df, df["L2"]], axis=1)
     axis = df_duplabels._get_axis_number(axis)
     # Transpose frame if axis == 1
     if axis == 1: