TST/CLN: Reuse more fixtures (#56726)

Author: mroeschke

pandas/tests/base/test_misc.py

@@ -17,7 +17,6 @@
     Index,
     Series,
 )
-import pandas._testing as tm
 
 
 def test_isnull_notnull_docstrings():
@@ -130,9 +129,13 @@ def test_memory_usage_components_series(series_with_simple_index):
     assert total_usage == non_index_usage + index_usage
 
 
-@pytest.mark.parametrize("dtype", tm.NARROW_NP_DTYPES)
-def test_memory_usage_components_narrow_series(dtype):
-    series = Series(range(5), dtype=dtype, index=[f"i-{i}" for i in range(5)], name="a")
+def test_memory_usage_components_narrow_series(any_real_numpy_dtype):
+    series = Series(
+        range(5),
+        dtype=any_real_numpy_dtype,
+        index=[f"i-{i}" for i in range(5)],
+        name="a",
+    )
     total_usage = series.memory_usage(index=True)
     non_index_usage = series.memory_usage(index=False)
     index_usage = series.index.memory_usage()

pandas/tests/indexing/test_iloc.py

@@ -75,8 +75,7 @@ class TestiLocBaseIndependent:
             np.asarray([0, 1, 2]),
         ],
     )
-    @pytest.mark.parametrize("indexer", [tm.loc, tm.iloc])
-    def test_iloc_setitem_fullcol_categorical(self, indexer, key):
+    def test_iloc_setitem_fullcol_categorical(self, indexer_li, key):
         frame = DataFrame({0: range(3)}, dtype=object)
 
         cat = Categorical(["alpha", "beta", "gamma"])
@@ -86,7 +85,7 @@ def test_iloc_setitem_fullcol_categorical(self, indexer, key):
         df = frame.copy()
         orig_vals = df.values
 
-        indexer(df)[key, 0] = cat
+        indexer_li(df)[key, 0] = cat
 
         expected = DataFrame({0: cat}).astype(object)
         assert np.shares_memory(df[0].values, orig_vals)
@@ -102,7 +101,7 @@ def test_iloc_setitem_fullcol_categorical(self, indexer, key):
         #  we retain the object dtype.
         frame = DataFrame({0: np.array([0, 1, 2], dtype=object), 1: range(3)})
         df = frame.copy()
-        indexer(df)[key, 0] = cat
+        indexer_li(df)[key, 0] = cat
         expected = DataFrame({0: Series(cat.astype(object), dtype=object), 1: range(3)})
         tm.assert_frame_equal(df, expected)
 
@@ -985,8 +984,7 @@ def test_iloc_setitem_empty_frame_raises_with_3d_ndarray(self):
         with pytest.raises(ValueError, match=msg):
             obj.iloc[nd3] = 0
 
-    @pytest.mark.parametrize("indexer", [tm.loc, tm.iloc])
-    def test_iloc_getitem_read_only_values(self, indexer):
+    def test_iloc_getitem_read_only_values(self, indexer_li):
         # GH#10043 this is fundamentally a test for iloc, but test loc while
         #  we're here
         rw_array = np.eye(10)
@@ -996,10 +994,12 @@ def test_iloc_getitem_read_only_values(self, indexer):
         ro_array.setflags(write=False)
         ro_df = DataFrame(ro_array)
 
-        tm.assert_frame_equal(indexer(rw_df)[[1, 2, 3]], indexer(ro_df)[[1, 2, 3]])
-        tm.assert_frame_equal(indexer(rw_df)[[1]], indexer(ro_df)[[1]])
-        tm.assert_series_equal(indexer(rw_df)[1], indexer(ro_df)[1])
-        tm.assert_frame_equal(indexer(rw_df)[1:3], indexer(ro_df)[1:3])
+        tm.assert_frame_equal(
+            indexer_li(rw_df)[[1, 2, 3]], indexer_li(ro_df)[[1, 2, 3]]
+        )
+        tm.assert_frame_equal(indexer_li(rw_df)[[1]], indexer_li(ro_df)[[1]])
+        tm.assert_series_equal(indexer_li(rw_df)[1], indexer_li(ro_df)[1])
+        tm.assert_frame_equal(indexer_li(rw_df)[1:3], indexer_li(ro_df)[1:3])
 
     def test_iloc_getitem_readonly_key(self):
         # GH#17192 iloc with read-only array raising TypeError

pandas/tests/io/parser/dtypes/test_dtypes_basic.py

@@ -132,15 +132,12 @@ def test_dtype_with_converters(all_parsers):
     tm.assert_frame_equal(result, expected)
 
 
-@pytest.mark.parametrize(
-    "dtype", list(np.typecodes["AllInteger"] + np.typecodes["Float"])
-)
-def test_numeric_dtype(all_parsers, dtype):
+def test_numeric_dtype(all_parsers, any_real_numpy_dtype):
     data = "0\n1"
     parser = all_parsers
-    expected = DataFrame([0, 1], dtype=dtype)
+    expected = DataFrame([0, 1], dtype=any_real_numpy_dtype)
 
-    result = parser.read_csv(StringIO(data), header=None, dtype=dtype)
+    result = parser.read_csv(StringIO(data), header=None, dtype=any_real_numpy_dtype)
     tm.assert_frame_equal(expected, result)
 
 

pandas/tests/reductions/test_reductions.py

@@ -1417,13 +1417,10 @@ def test_mode_empty(self, dropna, expected):
             (False, [1, 1, 1, 2, 3, 3, 3], [1, 3]),
         ],
     )
-    @pytest.mark.parametrize(
-        "dt", list(np.typecodes["AllInteger"] + np.typecodes["Float"])
-    )
-    def test_mode_numerical(self, dropna, data, expected, dt):
-        s = Series(data, dtype=dt)
+    def test_mode_numerical(self, dropna, data, expected, any_real_numpy_dtype):
+        s = Series(data, dtype=any_real_numpy_dtype)
         result = s.mode(dropna)
-        expected = Series(expected, dtype=dt)
+        expected = Series(expected, dtype=any_real_numpy_dtype)
         tm.assert_series_equal(result, expected)
 
     @pytest.mark.parametrize("dropna, expected", [(True, [1.0]), (False, [1, np.nan])])

pandas/tests/reshape/merge/test_merge.py

@@ -1488,12 +1488,9 @@ def test_different(self, right_vals):
         result = merge(left, right, on="A")
         assert is_object_dtype(result.A.dtype)
 
-    @pytest.mark.parametrize(
-        "d1", [np.int64, np.int32, np.intc, np.int16, np.int8, np.uint8]
-    )
     @pytest.mark.parametrize("d2", [np.int64, np.float64, np.float32, np.float16])
-    def test_join_multi_dtypes(self, d1, d2):
-        dtype1 = np.dtype(d1)
+    def test_join_multi_dtypes(self, any_int_numpy_dtype, d2):
+        dtype1 = np.dtype(any_int_numpy_dtype)
         dtype2 = np.dtype(d2)
 
         left = DataFrame(

pandas/tests/scalar/timestamp/test_formats.py

@@ -88,9 +88,9 @@ def test_isoformat(ts, timespec, expected_iso):
 
 
 class TestTimestampRendering:
-    timezones = ["UTC", "Asia/Tokyo", "US/Eastern", "dateutil/US/Pacific"]
-
-    @pytest.mark.parametrize("tz", timezones)
+    @pytest.mark.parametrize(
+        "tz", ["UTC", "Asia/Tokyo", "US/Eastern", "dateutil/US/Pacific"]
+    )
     @pytest.mark.parametrize("freq", ["D", "M", "S", "N"])
     @pytest.mark.parametrize(
         "date", ["2014-03-07", "2014-01-01 09:00", "2014-01-01 00:00:00.000000001"]

pandas/tests/series/methods/test_astype.py

@@ -342,10 +342,9 @@ def test_astype_ignores_errors_for_extension_dtypes(self, data, dtype, errors):
             with pytest.raises((ValueError, TypeError), match=msg):
                 ser.astype(float, errors=errors)
 
-    @pytest.mark.parametrize("dtype", [np.float16, np.float32, np.float64])
-    def test_astype_from_float_to_str(self, dtype):
+    def test_astype_from_float_to_str(self, any_float_dtype):
         # https://github.com/pandas-dev/pandas/issues/36451
-        ser = Series([0.1], dtype=dtype)
+        ser = Series([0.1], dtype=any_float_dtype)
         result = ser.astype(str)
         expected = Series(["0.1"], dtype=object)
         tm.assert_series_equal(result, expected)
@@ -374,21 +373,19 @@ def test_astype(self, dtype):
         assert as_typed.name == ser.name
 
     @pytest.mark.parametrize("value", [np.nan, np.inf])
-    @pytest.mark.parametrize("dtype", [np.int32, np.int64])
-    def test_astype_cast_nan_inf_int(self, dtype, value):
+    def test_astype_cast_nan_inf_int(self, any_int_numpy_dtype, value):
         # gh-14265: check NaN and inf raise error when converting to int
         msg = "Cannot convert non-finite values \\(NA or inf\\) to integer"
         ser = Series([value])
 
         with pytest.raises(ValueError, match=msg):
-            ser.astype(dtype)
+            ser.astype(any_int_numpy_dtype)
 
-    @pytest.mark.parametrize("dtype", [int, np.int8, np.int64])
-    def test_astype_cast_object_int_fail(self, dtype):
+    def test_astype_cast_object_int_fail(self, any_int_numpy_dtype):
         arr = Series(["car", "house", "tree", "1"])
         msg = r"invalid literal for int\(\) with base 10: 'car'"
         with pytest.raises(ValueError, match=msg):
-            arr.astype(dtype)
+            arr.astype(any_int_numpy_dtype)
 
     def test_astype_float_to_uint_negatives_raise(
         self, float_numpy_dtype, any_unsigned_int_numpy_dtype

pandas/tests/series/methods/test_compare.py

@@ -5,15 +5,14 @@
 import pandas._testing as tm
 
 
-@pytest.mark.parametrize("align_axis", [0, 1, "index", "columns"])
-def test_compare_axis(align_axis):
+def test_compare_axis(axis):
     # GH#30429
     s1 = pd.Series(["a", "b", "c"])
     s2 = pd.Series(["x", "b", "z"])
 
-    result = s1.compare(s2, align_axis=align_axis)
+    result = s1.compare(s2, align_axis=axis)
 
-    if align_axis in (1, "columns"):
+    if axis in (1, "columns"):
         indices = pd.Index([0, 2])
         columns = pd.Index(["self", "other"])
         expected = pd.DataFrame(

pandas/tests/series/methods/test_cov_corr.py

@@ -56,11 +56,10 @@ def test_cov_ddof(self, test_ddof, dtype):
 
 
 class TestSeriesCorr:
-    @pytest.mark.parametrize("dtype", ["float64", "Float64"])
-    def test_corr(self, datetime_series, dtype):
+    def test_corr(self, datetime_series, any_float_dtype):
         stats = pytest.importorskip("scipy.stats")
 
-        datetime_series = datetime_series.astype(dtype)
+        datetime_series = datetime_series.astype(any_float_dtype)
 
         # full overlap
         tm.assert_almost_equal(datetime_series.corr(datetime_series), 1)

pandas/tests/series/methods/test_fillna.py

@@ -838,12 +838,11 @@ def test_fillna_categorical_raises(self):
             ser.fillna(DataFrame({1: ["a"], 3: ["b"]}))
 
     @pytest.mark.parametrize("dtype", [float, "float32", "float64"])
-    @pytest.mark.parametrize("fill_type", tm.ALL_REAL_NUMPY_DTYPES)
     @pytest.mark.parametrize("scalar", [True, False])
-    def test_fillna_float_casting(self, dtype, fill_type, scalar):
+    def test_fillna_float_casting(self, dtype, any_real_numpy_dtype, scalar):
         # GH-43424
         ser = Series([np.nan, 1.2], dtype=dtype)
-        fill_values = Series([2, 2], dtype=fill_type)
+        fill_values = Series([2, 2], dtype=any_real_numpy_dtype)
         if scalar:
             fill_values = fill_values.dtype.type(2)
 

pandas/tests/test_algos.py

@@ -1795,11 +1795,10 @@ def test_scipy_compat(self, arr):
         exp[mask] = np.nan
         tm.assert_almost_equal(result, exp)
 
-    @pytest.mark.parametrize("dtype", np.typecodes["AllInteger"])
-    def test_basic(self, writable, dtype):
+    def test_basic(self, writable, any_int_numpy_dtype):
         exp = np.array([1, 2], dtype=np.float64)
 
-        data = np.array([1, 100], dtype=dtype)
+        data = np.array([1, 100], dtype=any_int_numpy_dtype)
         data.setflags(write=writable)
         ser = Series(data)
         result = algos.rank(ser)
@@ -1836,22 +1835,21 @@ def test_no_mode(self):
         exp = Series([], dtype=np.float64, index=Index([], dtype=int))
         tm.assert_numpy_array_equal(algos.mode(np.array([])), exp.values)
 
-    @pytest.mark.parametrize("dt", np.typecodes["AllInteger"] + np.typecodes["Float"])
-    def test_mode_single(self, dt):
+    def test_mode_single(self, any_real_numpy_dtype):
         # GH 15714
         exp_single = [1]
         data_single = [1]
 
         exp_multi = [1]
         data_multi = [1, 1]
 
-        ser = Series(data_single, dtype=dt)
-        exp = Series(exp_single, dtype=dt)
+        ser = Series(data_single, dtype=any_real_numpy_dtype)
+        exp = Series(exp_single, dtype=any_real_numpy_dtype)
         tm.assert_numpy_array_equal(algos.mode(ser.values), exp.values)
         tm.assert_series_equal(ser.mode(), exp)
 
-        ser = Series(data_multi, dtype=dt)
-        exp = Series(exp_multi, dtype=dt)
+        ser = Series(data_multi, dtype=any_real_numpy_dtype)
+        exp = Series(exp_multi, dtype=any_real_numpy_dtype)
         tm.assert_numpy_array_equal(algos.mode(ser.values), exp.values)
         tm.assert_series_equal(ser.mode(), exp)
 
@@ -1862,21 +1860,20 @@ def test_mode_obj_int(self):
         exp = Series(["a", "b", "c"], dtype=object)
         tm.assert_numpy_array_equal(algos.mode(exp.values), exp.values)
 
-    @pytest.mark.parametrize("dt", np.typecodes["AllInteger"] + np.typecodes["Float"])
-    def test_number_mode(self, dt):
+    def test_number_mode(self, any_real_numpy_dtype):
         exp_single = [1]
         data_single = [1] * 5 + [2] * 3
 
         exp_multi = [1, 3]
         data_multi = [1] * 5 + [2] * 3 + [3] * 5
 
-        ser = Series(data_single, dtype=dt)
-        exp = Series(exp_single, dtype=dt)
+        ser = Series(data_single, dtype=any_real_numpy_dtype)
+        exp = Series(exp_single, dtype=any_real_numpy_dtype)
         tm.assert_numpy_array_equal(algos.mode(ser.values), exp.values)
         tm.assert_series_equal(ser.mode(), exp)
 
-        ser = Series(data_multi, dtype=dt)
-        exp = Series(exp_multi, dtype=dt)
+        ser = Series(data_multi, dtype=any_real_numpy_dtype)
+        exp = Series(exp_multi, dtype=any_real_numpy_dtype)
         tm.assert_numpy_array_equal(algos.mode(ser.values), exp.values)
         tm.assert_series_equal(ser.mode(), exp)
 

pandas/tests/util/test_assert_extension_array_equal.py

@@ -108,11 +108,10 @@ def test_assert_extension_array_equal_non_extension_array(side):
         tm.assert_extension_array_equal(*args)
 
 
-@pytest.mark.parametrize("right_dtype", ["Int32", "int64"])
-def test_assert_extension_array_equal_ignore_dtype_mismatch(right_dtype):
+def test_assert_extension_array_equal_ignore_dtype_mismatch(any_int_dtype):
     # https://github.com/pandas-dev/pandas/issues/35715
     left = array([1, 2, 3], dtype="Int64")
-    right = array([1, 2, 3], dtype=right_dtype)
+    right = array([1, 2, 3], dtype=any_int_dtype)
     tm.assert_extension_array_equal(left, right, check_dtype=False)
 
 

pandas/tests/util/test_assert_series_equal.py

@@ -106,12 +106,11 @@ def test_series_not_equal_metadata_mismatch(kwargs):
 
 
 @pytest.mark.parametrize("data1,data2", [(0.12345, 0.12346), (0.1235, 0.1236)])
-@pytest.mark.parametrize("dtype", ["float32", "float64", "Float32"])
 @pytest.mark.parametrize("decimals", [0, 1, 2, 3, 5, 10])
-def test_less_precise(data1, data2, dtype, decimals):
+def test_less_precise(data1, data2, any_float_dtype, decimals):
     rtol = 10**-decimals
-    s1 = Series([data1], dtype=dtype)
-    s2 = Series([data2], dtype=dtype)
+    s1 = Series([data1], dtype=any_float_dtype)
+    s2 = Series([data2], dtype=any_float_dtype)
 
     if decimals in (5, 10) or (decimals >= 3 and abs(data1 - data2) >= 0.0005):
         msg = "Series values are different"

pandas/tests/window/test_rolling_functions.py

@@ -471,20 +471,19 @@ def test_rolling_median_memory_error():
     ).median()
 
 
-@pytest.mark.parametrize(
-    "data_type",
-    [np.dtype(f"f{width}") for width in [4, 8]]
-    + [np.dtype(f"{sign}{width}") for width in [1, 2, 4, 8] for sign in "ui"],
-)
-def test_rolling_min_max_numeric_types(data_type):
+def test_rolling_min_max_numeric_types(any_real_numpy_dtype):
     # GH12373
 
     # Just testing that these don't throw exceptions and that
     # the return type is float64. Other tests will cover quantitative
     # correctness
-    result = DataFrame(np.arange(20, dtype=data_type)).rolling(window=5).max()
+    result = (
+        DataFrame(np.arange(20, dtype=any_real_numpy_dtype)).rolling(window=5).max()
+    )
     assert result.dtypes[0] == np.dtype("f8")
-    result = DataFrame(np.arange(20, dtype=data_type)).rolling(window=5).min()
+    result = (
+        DataFrame(np.arange(20, dtype=any_real_numpy_dtype)).rolling(window=5).min()
+    )
     assert result.dtypes[0] == np.dtype("f8")