TST/CLN: Use more shared fixtures (#56708)

Author: mroeschke

pandas/tests/arithmetic/test_numeric.py

@@ -1116,11 +1116,10 @@ def test_ufunc_compat(self, holder, dtype):
         tm.assert_equal(result, expected)
 
     # TODO: add more dtypes
-    @pytest.mark.parametrize("holder", [Index, Series])
     @pytest.mark.parametrize("dtype", [np.int64, np.uint64, np.float64])
-    def test_ufunc_coercions(self, holder, dtype):
-        idx = holder([1, 2, 3, 4, 5], dtype=dtype, name="x")
-        box = Series if holder is Series else Index
+    def test_ufunc_coercions(self, index_or_series, dtype):
+        idx = index_or_series([1, 2, 3, 4, 5], dtype=dtype, name="x")
+        box = index_or_series
 
         result = np.sqrt(idx)
         assert result.dtype == "f8" and isinstance(result, box)

pandas/tests/copy_view/test_constructors.py

@@ -283,14 +283,13 @@ def test_dataframe_from_dict_of_series_with_reindex(dtype):
     assert np.shares_memory(arr_before, arr_after)
 
 
-@pytest.mark.parametrize("cons", [Series, Index])
 @pytest.mark.parametrize(
     "data, dtype", [([1, 2], None), ([1, 2], "int64"), (["a", "b"], None)]
 )
 def test_dataframe_from_series_or_index(
-    using_copy_on_write, warn_copy_on_write, data, dtype, cons
+    using_copy_on_write, warn_copy_on_write, data, dtype, index_or_series
 ):
-    obj = cons(data, dtype=dtype)
+    obj = index_or_series(data, dtype=dtype)
     obj_orig = obj.copy()
     df = DataFrame(obj, dtype=dtype)
     assert np.shares_memory(get_array(obj), get_array(df, 0))
@@ -303,9 +302,10 @@ def test_dataframe_from_series_or_index(
         tm.assert_equal(obj, obj_orig)
 
 
-@pytest.mark.parametrize("cons", [Series, Index])
-def test_dataframe_from_series_or_index_different_dtype(using_copy_on_write, cons):
-    obj = cons([1, 2], dtype="int64")
+def test_dataframe_from_series_or_index_different_dtype(
+    using_copy_on_write, index_or_series
+):
+    obj = index_or_series([1, 2], dtype="int64")
     df = DataFrame(obj, dtype="int32")
     assert not np.shares_memory(get_array(obj), get_array(df, 0))
     if using_copy_on_write:

pandas/tests/dtypes/test_inference.py

@@ -1701,19 +1701,19 @@ def test_interval_mismatched_subtype(self):
         arr = np.array([first, flt_interval], dtype=object)
         assert lib.infer_dtype(arr, skipna=False) == "interval"
 
-    @pytest.mark.parametrize("klass", [pd.array, Series])
     @pytest.mark.parametrize("data", [["a", "b", "c"], ["a", "b", pd.NA]])
-    def test_string_dtype(self, data, skipna, klass, nullable_string_dtype):
+    def test_string_dtype(
+        self, data, skipna, index_or_series_or_array, nullable_string_dtype
+    ):
         # StringArray
-        val = klass(data, dtype=nullable_string_dtype)
+        val = index_or_series_or_array(data, dtype=nullable_string_dtype)
         inferred = lib.infer_dtype(val, skipna=skipna)
         assert inferred == "string"
 
-    @pytest.mark.parametrize("klass", [pd.array, Series])
     @pytest.mark.parametrize("data", [[True, False, True], [True, False, pd.NA]])
-    def test_boolean_dtype(self, data, skipna, klass):
+    def test_boolean_dtype(self, data, skipna, index_or_series_or_array):
         # BooleanArray
-        val = klass(data, dtype="boolean")
+        val = index_or_series_or_array(data, dtype="boolean")
         inferred = lib.infer_dtype(val, skipna=skipna)
         assert inferred == "boolean"
 

pandas/tests/extension/decimal/test_decimal.py

@@ -302,8 +302,7 @@ def test_dataframe_constructor_with_dtype():
     tm.assert_frame_equal(result, expected)
 
 
-@pytest.mark.parametrize("frame", [True, False])
-def test_astype_dispatches(frame):
+def test_astype_dispatches(frame_or_series):
     # This is a dtype-specific test that ensures Series[decimal].astype
     # gets all the way through to ExtensionArray.astype
     # Designing a reliable smoke test that works for arbitrary data types
@@ -312,12 +311,11 @@ def test_astype_dispatches(frame):
     ctx = decimal.Context()
     ctx.prec = 5
 
-    if frame:
-        data = data.to_frame()
+    data = frame_or_series(data)
 
     result = data.astype(DecimalDtype(ctx))
 
-    if frame:
+    if frame_or_series is pd.DataFrame:
         result = result["a"]
 
     assert result.dtype.context.prec == ctx.prec

pandas/tests/frame/methods/test_set_index.py

@@ -577,8 +577,8 @@ def test_set_index_raise_keys(self, frame_of_index_cols, drop, append):
 
     @pytest.mark.parametrize("append", [True, False])
     @pytest.mark.parametrize("drop", [True, False])
-    @pytest.mark.parametrize("box", [set], ids=["set"])
-    def test_set_index_raise_on_type(self, frame_of_index_cols, box, drop, append):
+    def test_set_index_raise_on_type(self, frame_of_index_cols, drop, append):
+        box = set
         df = frame_of_index_cols
 
         msg = 'The parameter "keys" may be a column key, .*'

pandas/tests/groupby/aggregate/test_numba.py

@@ -52,8 +52,7 @@ def incorrect_function(values, index):
 @pytest.mark.filterwarnings("ignore")
 # Filter warnings when parallel=True and the function can't be parallelized by Numba
 @pytest.mark.parametrize("jit", [True, False])
-@pytest.mark.parametrize("pandas_obj", ["Series", "DataFrame"])
-def test_numba_vs_cython(jit, pandas_obj, nogil, parallel, nopython, as_index):
+def test_numba_vs_cython(jit, frame_or_series, nogil, parallel, nopython, as_index):
     pytest.importorskip("numba")
 
     def func_numba(values, index):
@@ -70,7 +69,7 @@ def func_numba(values, index):
     )
     engine_kwargs = {"nogil": nogil, "parallel": parallel, "nopython": nopython}
     grouped = data.groupby(0, as_index=as_index)
-    if pandas_obj == "Series":
+    if frame_or_series is Series:
         grouped = grouped[1]
 
     result = grouped.agg(func_numba, engine="numba", engine_kwargs=engine_kwargs)
@@ -82,8 +81,7 @@ def func_numba(values, index):
 @pytest.mark.filterwarnings("ignore")
 # Filter warnings when parallel=True and the function can't be parallelized by Numba
 @pytest.mark.parametrize("jit", [True, False])
-@pytest.mark.parametrize("pandas_obj", ["Series", "DataFrame"])
-def test_cache(jit, pandas_obj, nogil, parallel, nopython):
+def test_cache(jit, frame_or_series, nogil, parallel, nopython):
     # Test that the functions are cached correctly if we switch functions
     pytest.importorskip("numba")
 
@@ -104,7 +102,7 @@ def func_2(values, index):
     )
     engine_kwargs = {"nogil": nogil, "parallel": parallel, "nopython": nopython}
     grouped = data.groupby(0)
-    if pandas_obj == "Series":
+    if frame_or_series is Series:
         grouped = grouped[1]
 
     result = grouped.agg(func_1, engine="numba", engine_kwargs=engine_kwargs)

pandas/tests/groupby/transform/test_numba.py

@@ -50,8 +50,7 @@ def incorrect_function(values, index):
 @pytest.mark.filterwarnings("ignore")
 # Filter warnings when parallel=True and the function can't be parallelized by Numba
 @pytest.mark.parametrize("jit", [True, False])
-@pytest.mark.parametrize("pandas_obj", ["Series", "DataFrame"])
-def test_numba_vs_cython(jit, pandas_obj, nogil, parallel, nopython, as_index):
+def test_numba_vs_cython(jit, frame_or_series, nogil, parallel, nopython, as_index):
     pytest.importorskip("numba")
 
     def func(values, index):
@@ -68,7 +67,7 @@ def func(values, index):
     )
     engine_kwargs = {"nogil": nogil, "parallel": parallel, "nopython": nopython}
     grouped = data.groupby(0, as_index=as_index)
-    if pandas_obj == "Series":
+    if frame_or_series is Series:
         grouped = grouped[1]
 
     result = grouped.transform(func, engine="numba", engine_kwargs=engine_kwargs)
@@ -80,8 +79,7 @@ def func(values, index):
 @pytest.mark.filterwarnings("ignore")
 # Filter warnings when parallel=True and the function can't be parallelized by Numba
 @pytest.mark.parametrize("jit", [True, False])
-@pytest.mark.parametrize("pandas_obj", ["Series", "DataFrame"])
-def test_cache(jit, pandas_obj, nogil, parallel, nopython):
+def test_cache(jit, frame_or_series, nogil, parallel, nopython):
     # Test that the functions are cached correctly if we switch functions
     pytest.importorskip("numba")
 
@@ -102,7 +100,7 @@ def func_2(values, index):
     )
     engine_kwargs = {"nogil": nogil, "parallel": parallel, "nopython": nopython}
     grouped = data.groupby(0)
-    if pandas_obj == "Series":
+    if frame_or_series is Series:
         grouped = grouped[1]
 
     result = grouped.transform(func_1, engine="numba", engine_kwargs=engine_kwargs)

pandas/tests/indexing/test_iloc.py

@@ -106,8 +106,9 @@ def test_iloc_setitem_fullcol_categorical(self, indexer, key):
         expected = DataFrame({0: Series(cat.astype(object), dtype=object), 1: range(3)})
         tm.assert_frame_equal(df, expected)
 
-    @pytest.mark.parametrize("box", [array, Series])
-    def test_iloc_setitem_ea_inplace(self, frame_or_series, box, using_copy_on_write):
+    def test_iloc_setitem_ea_inplace(
+        self, frame_or_series, index_or_series_or_array, using_copy_on_write
+    ):
         # GH#38952 Case with not setting a full column
         #  IntegerArray without NAs
         arr = array([1, 2, 3, 4])
@@ -119,9 +120,9 @@ def test_iloc_setitem_ea_inplace(self, frame_or_series, box, using_copy_on_write
             values = obj._mgr.arrays[0]
 
         if frame_or_series is Series:
-            obj.iloc[:2] = box(arr[2:])
+            obj.iloc[:2] = index_or_series_or_array(arr[2:])
         else:
-            obj.iloc[:2, 0] = box(arr[2:])
+            obj.iloc[:2, 0] = index_or_series_or_array(arr[2:])
 
         expected = frame_or_series(np.array([3, 4, 3, 4], dtype="i8"))
         tm.assert_equal(obj, expected)

pandas/tests/reductions/test_stat_reductions.py

@@ -16,29 +16,27 @@
 
 
 class TestDatetimeLikeStatReductions:
-    @pytest.mark.parametrize("box", [Series, pd.Index, pd.array])
-    def test_dt64_mean(self, tz_naive_fixture, box):
+    def test_dt64_mean(self, tz_naive_fixture, index_or_series_or_array):
         tz = tz_naive_fixture
 
         dti = date_range("2001-01-01", periods=11, tz=tz)
         # shuffle so that we are not just working with monotone-increasing
         dti = dti.take([4, 1, 3, 10, 9, 7, 8, 5, 0, 2, 6])
         dtarr = dti._data
 
-        obj = box(dtarr)
+        obj = index_or_series_or_array(dtarr)
         assert obj.mean() == pd.Timestamp("2001-01-06", tz=tz)
         assert obj.mean(skipna=False) == pd.Timestamp("2001-01-06", tz=tz)
 
         # dtarr[-2] will be the first date 2001-01-1
         dtarr[-2] = pd.NaT
 
-        obj = box(dtarr)
+        obj = index_or_series_or_array(dtarr)
         assert obj.mean() == pd.Timestamp("2001-01-06 07:12:00", tz=tz)
         assert obj.mean(skipna=False) is pd.NaT
 
-    @pytest.mark.parametrize("box", [Series, pd.Index, pd.array])
     @pytest.mark.parametrize("freq", ["s", "h", "D", "W", "B"])
-    def test_period_mean(self, box, freq):
+    def test_period_mean(self, index_or_series_or_array, freq):
         # GH#24757
         dti = date_range("2001-01-01", periods=11)
         # shuffle so that we are not just working with monotone-increasing
@@ -48,7 +46,7 @@ def test_period_mean(self, box, freq):
         msg = r"PeriodDtype\[B\] is deprecated"
         with tm.assert_produces_warning(warn, match=msg):
             parr = dti._data.to_period(freq)
-        obj = box(parr)
+        obj = index_or_series_or_array(parr)
         with pytest.raises(TypeError, match="ambiguous"):
             obj.mean()
         with pytest.raises(TypeError, match="ambiguous"):
@@ -62,13 +60,12 @@ def test_period_mean(self, box, freq):
         with pytest.raises(TypeError, match="ambiguous"):
             obj.mean(skipna=True)
 
-    @pytest.mark.parametrize("box", [Series, pd.Index, pd.array])
-    def test_td64_mean(self, box):
+    def test_td64_mean(self, index_or_series_or_array):
         m8values = np.array([0, 3, -2, -7, 1, 2, -1, 3, 5, -2, 4], "m8[D]")
         tdi = pd.TimedeltaIndex(m8values).as_unit("ns")
 
         tdarr = tdi._data
-        obj = box(tdarr, copy=False)
+        obj = index_or_series_or_array(tdarr, copy=False)
 
         result = obj.mean()
         expected = np.array(tdarr).mean()

pandas/tests/resample/test_base.py

@@ -30,9 +30,8 @@
         date_range(datetime(2005, 1, 1), datetime(2005, 1, 10), freq="D"),
     ],
 )
-@pytest.mark.parametrize("klass", [DataFrame, Series])
-def test_asfreq(klass, index, freq):
-    obj = klass(range(len(index)), index=index)
+def test_asfreq(frame_or_series, index, freq):
+    obj = frame_or_series(range(len(index)), index=index)
     idx_range = date_range if isinstance(index, DatetimeIndex) else timedelta_range
 
     result = obj.resample(freq).asfreq()