TST: fixturize, collect (#44242)

Author: jbrockmendel

pandas/conftest.py

@@ -995,17 +995,19 @@ def all_reductions(request):
     return request.param
 
 
-@pytest.fixture(params=["__eq__", "__ne__", "__le__", "__lt__", "__ge__", "__gt__"])
-def all_compare_operators(request):
+@pytest.fixture(
+    params=[
+        operator.eq,
+        operator.ne,
+        operator.gt,
+        operator.ge,
+        operator.lt,
+        operator.le,
+    ]
+)
+def comparison_op(request):
     """
-    Fixture for dunder names for common compare operations
-
-    * >=
-    * >
-    * ==
-    * !=
-    * <
-    * <=
+    Fixture for operator module comparison functions.
     """
     return request.param
 

pandas/tests/arithmetic/test_datetime64.py

@@ -365,18 +365,14 @@ def test_dt64arr_timestamp_equality(self, box_with_array):
 class TestDatetimeIndexComparisons:
 
     # TODO: moved from tests.indexes.test_base; parametrize and de-duplicate
-    @pytest.mark.parametrize(
-        "op",
-        [operator.eq, operator.ne, operator.gt, operator.lt, operator.ge, operator.le],
-    )
-    def test_comparators(self, op):
+    def test_comparators(self, comparison_op):
         index = tm.makeDateIndex(100)
         element = index[len(index) // 2]
         element = Timestamp(element).to_datetime64()
 
         arr = np.array(index)
-        arr_result = op(arr, element)
-        index_result = op(index, element)
+        arr_result = comparison_op(arr, element)
+        index_result = comparison_op(index, element)
 
         assert isinstance(index_result, np.ndarray)
         tm.assert_numpy_array_equal(arr_result, index_result)
@@ -554,12 +550,9 @@ def test_dti_cmp_nat_behaves_like_float_cmp_nan(self):
                 expected = np.array([True, True, False, True, True, True])
                 tm.assert_numpy_array_equal(result, expected)
 
-    @pytest.mark.parametrize(
-        "op",
-        [operator.eq, operator.ne, operator.gt, operator.ge, operator.lt, operator.le],
-    )
-    def test_comparison_tzawareness_compat(self, op, box_with_array):
+    def test_comparison_tzawareness_compat(self, comparison_op, box_with_array):
         # GH#18162
+        op = comparison_op
         box = box_with_array
 
         dr = date_range("2016-01-01", periods=6)
@@ -606,12 +599,10 @@ def test_comparison_tzawareness_compat(self, op, box_with_array):
         assert np.all(np.array(tolist(dz), dtype=object) == dz)
         assert np.all(dz == np.array(tolist(dz), dtype=object))
 
-    @pytest.mark.parametrize(
-        "op",
-        [operator.eq, operator.ne, operator.gt, operator.ge, operator.lt, operator.le],
-    )
-    def test_comparison_tzawareness_compat_scalars(self, op, box_with_array):
+    def test_comparison_tzawareness_compat_scalars(self, comparison_op, box_with_array):
         # GH#18162
+        op = comparison_op
+
         dr = date_range("2016-01-01", periods=6)
         dz = dr.tz_localize("US/Pacific")
 
@@ -638,10 +629,6 @@ def test_comparison_tzawareness_compat_scalars(self, op, box_with_array):
             with pytest.raises(TypeError, match=msg):
                 op(ts, dz)
 
-    @pytest.mark.parametrize(
-        "op",
-        [operator.eq, operator.ne, operator.gt, operator.ge, operator.lt, operator.le],
-    )
     @pytest.mark.parametrize(
         "other",
         [datetime(2016, 1, 1), Timestamp("2016-01-01"), np.datetime64("2016-01-01")],
@@ -652,8 +639,9 @@ def test_comparison_tzawareness_compat_scalars(self, op, box_with_array):
     @pytest.mark.filterwarnings("ignore:elementwise comp:DeprecationWarning")
     @pytest.mark.filterwarnings("ignore:Converting timezone-aware:FutureWarning")
     def test_scalar_comparison_tzawareness(
-        self, op, other, tz_aware_fixture, box_with_array
+        self, comparison_op, other, tz_aware_fixture, box_with_array
     ):
+        op = comparison_op
         box = box_with_array
         tz = tz_aware_fixture
         dti = date_range("2016-01-01", periods=2, tz=tz)
@@ -680,13 +668,11 @@ def test_scalar_comparison_tzawareness(
             with pytest.raises(TypeError, match=msg):
                 op(other, dtarr)
 
-    @pytest.mark.parametrize(
-        "op",
-        [operator.eq, operator.ne, operator.gt, operator.ge, operator.lt, operator.le],
-    )
-    def test_nat_comparison_tzawareness(self, op):
+    def test_nat_comparison_tzawareness(self, comparison_op):
         # GH#19276
         # tzaware DatetimeIndex should not raise when compared to NaT
+        op = comparison_op
+
         dti = DatetimeIndex(
             ["2014-01-01", NaT, "2014-03-01", NaT, "2014-05-01", "2014-07-01"]
         )

pandas/tests/arrays/boolean/test_comparison.py

@@ -21,25 +21,23 @@ def dtype():
 
 
 class TestComparisonOps(ComparisonOps):
-    def test_compare_scalar(self, data, all_compare_operators):
-        op_name = all_compare_operators
-        self._compare_other(data, op_name, True)
+    def test_compare_scalar(self, data, comparison_op):
+        self._compare_other(data, comparison_op, True)
 
-    def test_compare_array(self, data, all_compare_operators):
-        op_name = all_compare_operators
+    def test_compare_array(self, data, comparison_op):
         other = pd.array([True] * len(data), dtype="boolean")
-        self._compare_other(data, op_name, other)
+        self._compare_other(data, comparison_op, other)
         other = np.array([True] * len(data))
-        self._compare_other(data, op_name, other)
+        self._compare_other(data, comparison_op, other)
         other = pd.Series([True] * len(data))
-        self._compare_other(data, op_name, other)
+        self._compare_other(data, comparison_op, other)
 
     @pytest.mark.parametrize("other", [True, False, pd.NA])
-    def test_scalar(self, other, all_compare_operators, dtype):
-        ComparisonOps.test_scalar(self, other, all_compare_operators, dtype)
+    def test_scalar(self, other, comparison_op, dtype):
+        ComparisonOps.test_scalar(self, other, comparison_op, dtype)
 
-    def test_array(self, all_compare_operators):
-        op = self.get_op_from_name(all_compare_operators)
+    def test_array(self, comparison_op):
+        op = comparison_op
         a = pd.array([True] * 3 + [False] * 3 + [None] * 3, dtype="boolean")
         b = pd.array([True, False, None] * 3, dtype="boolean")
 

pandas/tests/arrays/categorical/test_operators.py

@@ -1,4 +1,3 @@
-import operator
 import warnings
 
 import numpy as np
@@ -145,9 +144,9 @@ def test_compare_frame(self):
         expected = DataFrame([[False, True, True, False]])
         tm.assert_frame_equal(result, expected)
 
-    def test_compare_frame_raises(self, all_compare_operators):
+    def test_compare_frame_raises(self, comparison_op):
         # alignment raises unless we transpose
-        op = getattr(operator, all_compare_operators)
+        op = comparison_op
         cat = Categorical(["a", "b", 2, "a"])
         df = DataFrame(cat)
         msg = "Unable to coerce to Series, length must be 1: given 4"

pandas/tests/arrays/floating/test_comparison.py

@@ -10,11 +10,11 @@
 
 class TestComparisonOps(NumericOps, ComparisonOps):
     @pytest.mark.parametrize("other", [True, False, pd.NA, -1.0, 0.0, 1])
-    def test_scalar(self, other, all_compare_operators, dtype):
-        ComparisonOps.test_scalar(self, other, all_compare_operators, dtype)
+    def test_scalar(self, other, comparison_op, dtype):
+        ComparisonOps.test_scalar(self, other, comparison_op, dtype)
 
-    def test_compare_with_integerarray(self, all_compare_operators):
-        op = self.get_op_from_name(all_compare_operators)
+    def test_compare_with_integerarray(self, comparison_op):
+        op = comparison_op
         a = pd.array([0, 1, None] * 3, dtype="Int64")
         b = pd.array([0] * 3 + [1] * 3 + [None] * 3, dtype="Float64")
         other = b.astype("Int64")

pandas/tests/arrays/integer/test_comparison.py

@@ -9,18 +9,19 @@
 
 class TestComparisonOps(NumericOps, ComparisonOps):
     @pytest.mark.parametrize("other", [True, False, pd.NA, -1, 0, 1])
-    def test_scalar(self, other, all_compare_operators, dtype):
-        ComparisonOps.test_scalar(self, other, all_compare_operators, dtype)
+    def test_scalar(self, other, comparison_op, dtype):
+        ComparisonOps.test_scalar(self, other, comparison_op, dtype)
 
-    def test_compare_to_int(self, dtype, all_compare_operators):
+    def test_compare_to_int(self, dtype, comparison_op):
         # GH 28930
+        op_name = f"__{comparison_op.__name__}__"
         s1 = pd.Series([1, None, 3], dtype=dtype)
         s2 = pd.Series([1, None, 3], dtype="float")
 
-        method = getattr(s1, all_compare_operators)
+        method = getattr(s1, op_name)
         result = method(2)
 
-        method = getattr(s2, all_compare_operators)
+        method = getattr(s2, op_name)
         expected = method(2).astype("boolean")
         expected[s2.isna()] = pd.NA
 

pandas/tests/arrays/masked_shared.py

@@ -9,8 +9,7 @@
 
 
 class ComparisonOps(BaseOpsUtil):
-    def _compare_other(self, data, op_name, other):
-        op = self.get_op_from_name(op_name)
+    def _compare_other(self, data, op, other):
 
         # array
         result = pd.Series(op(data, other))
@@ -34,8 +33,8 @@ def _compare_other(self, data, op_name, other):
         tm.assert_series_equal(result, expected)
 
     # subclass will override to parametrize 'other'
-    def test_scalar(self, other, all_compare_operators, dtype):
-        op = self.get_op_from_name(all_compare_operators)
+    def test_scalar(self, other, comparison_op, dtype):
+        op = comparison_op
         left = pd.array([1, 0, None], dtype=dtype)
 
         result = op(left, other)
@@ -59,8 +58,8 @@ def test_no_shared_mask(self, data):
         result = data + 1
         assert np.shares_memory(result._mask, data._mask) is False
 
-    def test_array(self, all_compare_operators, dtype):
-        op = self.get_op_from_name(all_compare_operators)
+    def test_array(self, comparison_op, dtype):
+        op = comparison_op
 
         left = pd.array([0, 1, 2, None, None, None], dtype=dtype)
         right = pd.array([0, 1, None, 0, 1, None], dtype=dtype)
@@ -81,8 +80,8 @@ def test_array(self, all_compare_operators, dtype):
             right, pd.array([0, 1, None, 0, 1, None], dtype=dtype)
         )
 
-    def test_compare_with_booleanarray(self, all_compare_operators, dtype):
-        op = self.get_op_from_name(all_compare_operators)
+    def test_compare_with_booleanarray(self, comparison_op, dtype):
+        op = comparison_op
 
         left = pd.array([True, False, None] * 3, dtype="boolean")
         right = pd.array([0] * 3 + [1] * 3 + [None] * 3, dtype=dtype)

pandas/tests/arrays/string_/test_string.py

@@ -199,8 +199,8 @@ def test_add_frame(dtype):
     tm.assert_frame_equal(result, expected)
 
 
-def test_comparison_methods_scalar(all_compare_operators, dtype):
-    op_name = all_compare_operators
+def test_comparison_methods_scalar(comparison_op, dtype):
+    op_name = f"__{comparison_op.__name__}__"
     a = pd.array(["a", None, "c"], dtype=dtype)
     other = "a"
     result = getattr(a, op_name)(other)
@@ -209,21 +209,21 @@ def test_comparison_methods_scalar(all_compare_operators, dtype):
     tm.assert_extension_array_equal(result, expected)
 
 
-def test_comparison_methods_scalar_pd_na(all_compare_operators, dtype):
-    op_name = all_compare_operators
+def test_comparison_methods_scalar_pd_na(comparison_op, dtype):
+    op_name = f"__{comparison_op.__name__}__"
     a = pd.array(["a", None, "c"], dtype=dtype)
     result = getattr(a, op_name)(pd.NA)
     expected = pd.array([None, None, None], dtype="boolean")
     tm.assert_extension_array_equal(result, expected)
 
 
-def test_comparison_methods_scalar_not_string(all_compare_operators, dtype, request):
-    if all_compare_operators not in ["__eq__", "__ne__"]:
+def test_comparison_methods_scalar_not_string(comparison_op, dtype, request):
+    op_name = f"__{comparison_op.__name__}__"
+    if op_name not in ["__eq__", "__ne__"]:
         reason = "comparison op not supported between instances of 'str' and 'int'"
         mark = pytest.mark.xfail(raises=TypeError, reason=reason)
         request.node.add_marker(mark)
 
-    op_name = all_compare_operators
     a = pd.array(["a", None, "c"], dtype=dtype)
     other = 42
     result = getattr(a, op_name)(other)
@@ -234,14 +234,14 @@ def test_comparison_methods_scalar_not_string(all_compare_operators, dtype, requ
     tm.assert_extension_array_equal(result, expected)
 
 
-def test_comparison_methods_array(all_compare_operators, dtype, request):
+def test_comparison_methods_array(comparison_op, dtype, request):
     if dtype.storage == "pyarrow":
         mark = pytest.mark.xfail(
             raises=AssertionError, reason="left is not an ExtensionArray"
         )
         request.node.add_marker(mark)
 
-    op_name = all_compare_operators
+    op_name = f"__{comparison_op.__name__}__"
 
     a = pd.array(["a", None, "c"], dtype=dtype)
     other = [None, None, "c"]

pandas/tests/arrays/test_datetimes.py

@@ -1,8 +1,6 @@
 """
 Tests for DatetimeArray
 """
-import operator
-
 import numpy as np
 import pytest
 
@@ -17,10 +15,9 @@ class TestDatetimeArrayComparisons:
     # TODO: merge this into tests/arithmetic/test_datetime64 once it is
     #  sufficiently robust
 
-    def test_cmp_dt64_arraylike_tznaive(self, all_compare_operators):
+    def test_cmp_dt64_arraylike_tznaive(self, comparison_op):
         # arbitrary tz-naive DatetimeIndex
-        opname = all_compare_operators.strip("_")
-        op = getattr(operator, opname)
+        op = comparison_op
 
         dti = pd.date_range("2016-01-1", freq="MS", periods=9, tz=None)
         arr = DatetimeArray(dti)
@@ -30,7 +27,7 @@ def test_cmp_dt64_arraylike_tznaive(self, all_compare_operators):
         right = dti
 
         expected = np.ones(len(arr), dtype=bool)
-        if opname in ["ne", "gt", "lt"]:
+        if comparison_op.__name__ in ["ne", "gt", "lt"]:
             # for these the comparisons should be all-False
             expected = ~expected
 

pandas/tests/extension/base/getitem.py

@@ -138,6 +138,7 @@ def test_getitem_invalid(self, data):
                 "list index out of range",  # json
                 "index out of bounds",  # pyarrow
                 "Out of bounds access",  # Sparse
+                f"loc must be an integer between -{ub} and {ub}",  # Sparse
                 f"index {ub+1} is out of bounds for axis 0 with size {ub}",
                 f"index -{ub+1} is out of bounds for axis 0 with size {ub}",
             ]

pandas/tests/extension/base/ops.py

@@ -130,10 +130,9 @@ def test_direct_arith_with_ndframe_returns_not_implemented(self, data, box):
 class BaseComparisonOpsTests(BaseOpsUtil):
     """Various Series and DataFrame comparison ops methods."""
 
-    def _compare_other(self, ser: pd.Series, data, op_name: str, other):
+    def _compare_other(self, ser: pd.Series, data, op, other):
 
-        op = self.get_op_from_name(op_name)
-        if op_name in ["__eq__", "__ne__"]:
+        if op.__name__ in ["eq", "ne"]:
             # comparison should match point-wise comparisons
             result = op(ser, other)
             expected = ser.combine(other, op)
@@ -154,23 +153,22 @@ def _compare_other(self, ser: pd.Series, data, op_name: str, other):
                 with pytest.raises(type(exc)):
                     ser.combine(other, op)
 
-    def test_compare_scalar(self, data, all_compare_operators):
-        op_name = all_compare_operators
+    def test_compare_scalar(self, data, comparison_op):
         ser = pd.Series(data)
-        self._compare_other(ser, data, op_name, 0)
+        self._compare_other(ser, data, comparison_op, 0)
 
-    def test_compare_array(self, data, all_compare_operators):
-        op_name = all_compare_operators
+    def test_compare_array(self, data, comparison_op):
         ser = pd.Series(data)
         other = pd.Series([data[0]] * len(data))
-        self._compare_other(ser, data, op_name, other)
+        self._compare_other(ser, data, comparison_op, other)
 
-    @pytest.mark.parametrize("box", [pd.Series, pd.DataFrame])
-    def test_direct_arith_with_ndframe_returns_not_implemented(self, data, box):
+    def test_direct_arith_with_ndframe_returns_not_implemented(
+        self, data, frame_or_series
+    ):
         # EAs should return NotImplemented for ops with Series/DataFrame
         # Pandas takes care of unboxing the series and calling the EA's op.
         other = pd.Series(data)
-        if box is pd.DataFrame:
+        if frame_or_series is pd.DataFrame:
             other = other.to_frame()
 
         if hasattr(data, "__eq__"):