CLN/TST: parametrize (#44888)

Author: jbrockmendel

asv_bench/benchmarks/arithmetic.py

@@ -144,7 +144,7 @@ def setup(self, op, shape):
         # should already be the case, but just to be sure
         df._consolidate_inplace()
 
-        # TODO: GH#33198 the setting here shoudlnt need two steps
+        # TODO: GH#33198 the setting here shouldn't need two steps
         arr1 = np.random.randn(n_rows, max(n_cols // 4, 3)).astype("f8")
         arr2 = np.random.randn(n_rows, n_cols // 2).astype("i8")
         arr3 = np.random.randn(n_rows, n_cols // 4).astype("f8")

pandas/compat/pickle_compat.py

@@ -35,9 +35,6 @@ def load_reduce(self):
     args = stack.pop()
     func = stack[-1]
 
-    if len(args) and type(args[0]) is type:
-        n = args[0].__name__  # noqa
-
     try:
         stack[-1] = func(*args)
         return

pandas/core/api.py

@@ -1,4 +1,4 @@
-# flake8: noqa
+# flake8: noqa:F401
 
 from pandas._libs import (
     NaT,

pandas/core/arrays/datetimelike.py

@@ -291,7 +291,7 @@ def asi8(self) -> npt.NDArray[np.int64]:
     # ----------------------------------------------------------------
     # Rendering Methods
 
-    def _format_native_types(self, na_rep="NaT", date_format=None):
+    def _format_native_types(self, *, na_rep="NaT", date_format=None):
         """
         Helper method for astype when converting to strings.
 

pandas/core/arrays/datetimes.py

@@ -670,7 +670,7 @@ def astype(self, dtype, copy: bool = True):
 
     @dtl.ravel_compat
     def _format_native_types(
-        self, na_rep="NaT", date_format=None, **kwargs
+        self, *, na_rep="NaT", date_format=None, **kwargs
     ) -> npt.NDArray[np.object_]:
         from pandas.io.formats.format import get_format_datetime64_from_values
 

pandas/core/arrays/period.py

@@ -632,7 +632,7 @@ def _formatter(self, boxed: bool = False):
 
     @dtl.ravel_compat
     def _format_native_types(
-        self, na_rep="NaT", date_format=None, **kwargs
+        self, *, na_rep="NaT", date_format=None, **kwargs
     ) -> np.ndarray:
         """
         actually format my specific types

pandas/core/arrays/timedeltas.py

@@ -426,7 +426,7 @@ def _formatter(self, boxed: bool = False):
 
     @dtl.ravel_compat
     def _format_native_types(
-        self, na_rep="NaT", date_format=None, **kwargs
+        self, *, na_rep="NaT", date_format=None, **kwargs
     ) -> np.ndarray:
         from pandas.io.formats.format import get_format_timedelta64
 

pandas/core/computation/api.py

@@ -1,3 +1,2 @@
-# flake8: noqa
-
+__all__ = ["eval"]
 from pandas.core.computation.eval import eval

pandas/core/dtypes/api.py

@@ -1,4 +1,4 @@
-# flake8: noqa
+# flake8: noqa:F401
 
 from pandas.core.dtypes.common import (
     is_array_like,

pandas/core/dtypes/cast.py

@@ -248,7 +248,7 @@ def maybe_downcast_to_dtype(result: ArrayLike, dtype: str | np.dtype) -> ArrayLi
 
     if isinstance(dtype, str):
         if dtype == "infer":
-            inferred_type = lib.infer_dtype(ensure_object(result), skipna=False)
+            inferred_type = lib.infer_dtype(result, skipna=False)
             if inferred_type == "boolean":
                 dtype = "bool"
             elif inferred_type == "integer":

pandas/core/dtypes/common.py

@@ -1318,7 +1318,7 @@ def is_bool_dtype(arr_or_dtype) -> bool:
     except (TypeError, ValueError):
         return False
 
-    if isinstance(arr_or_dtype, CategoricalDtype):
+    if isinstance(dtype, CategoricalDtype):
         arr_or_dtype = arr_or_dtype.categories
         # now we use the special definition for Index
 
@@ -1329,7 +1329,7 @@ def is_bool_dtype(arr_or_dtype) -> bool:
         # so its object, we need to infer to
         # guess this
         return arr_or_dtype.is_object() and arr_or_dtype.inferred_type == "boolean"
-    elif is_extension_array_dtype(arr_or_dtype):
+    elif isinstance(dtype, ExtensionDtype):
         return getattr(dtype, "_is_boolean", False)
 
     return issubclass(dtype.type, np.bool_)

pandas/core/indexes/base.py

@@ -1387,7 +1387,7 @@ def to_native_types(self, slicer=None, **kwargs) -> np.ndarray:
             values = values[slicer]
         return values._format_native_types(**kwargs)
 
-    def _format_native_types(self, na_rep="", quoting=None, **kwargs):
+    def _format_native_types(self, *, na_rep="", quoting=None, **kwargs):
         """
         Actually format specific types of the index.
         """

pandas/core/indexes/interval.py

@@ -812,7 +812,7 @@ def _format_with_header(self, header: list[str], na_rep: str) -> list[str]:
         # matches base class except for whitespace padding
         return header + list(self._format_native_types(na_rep=na_rep))
 
-    def _format_native_types(self, na_rep="NaN", quoting=None, **kwargs):
+    def _format_native_types(self, *, na_rep="NaN", quoting=None, **kwargs):
         # GH 28210: use base method but with different default na_rep
         return super()._format_native_types(na_rep=na_rep, quoting=quoting, **kwargs)
 

pandas/core/indexes/multi.py

@@ -1283,7 +1283,7 @@ def _formatter_func(self, tup):
         formatter_funcs = [level._formatter_func for level in self.levels]
         return tuple(func(val) for func, val in zip(formatter_funcs, tup))
 
-    def _format_native_types(self, na_rep="nan", **kwargs):
+    def _format_native_types(self, *, na_rep="nan", **kwargs):
         new_levels = []
         new_codes = []
 

pandas/core/indexes/numeric.py

@@ -343,7 +343,7 @@ def _is_all_dates(self) -> bool:
         return False
 
     def _format_native_types(
-        self, na_rep="", float_format=None, decimal=".", quoting=None, **kwargs
+        self, *, na_rep="", float_format=None, decimal=".", quoting=None, **kwargs
     ):
         from pandas.io.formats.format import FloatArrayFormatter
 

pandas/core/reshape/api.py

@@ -1,4 +1,4 @@
-# flake8: noqa
+# flake8: noqa:F401
 
 from pandas.core.reshape.concat import concat
 from pandas.core.reshape.melt import (

pandas/errors/__init__.py

@@ -1,12 +1,10 @@
-# flake8: noqa
-
 """
 Expose public exceptions & warnings
 """
 
-from pandas._config.config import OptionError
+from pandas._config.config import OptionError  # noqa:F401
 
-from pandas._libs.tslibs import (
+from pandas._libs.tslibs import (  # noqa:F401
     OutOfBoundsDatetime,
     OutOfBoundsTimedelta,
 )

pandas/tests/arithmetic/test_datetime64.py

@@ -228,10 +228,6 @@ def test_nat_comparisons(
     @pytest.mark.parametrize("dtype", [None, object])
     def test_nat_comparisons_scalar(self, dtype, data, box_with_array):
         box = box_with_array
-        if box_with_array is tm.to_array and dtype is object:
-            # dont bother testing ndarray comparison methods as this fails
-            #  on older numpys (since they check object identity)
-            return
 
         left = Series(data, dtype=dtype)
         left = tm.box_expected(left, box)
@@ -433,10 +429,6 @@ def test_dti_cmp_datetimelike(self, other, tz_naive_fixture):
 
     @pytest.mark.parametrize("dtype", [None, object])
     def test_dti_cmp_nat(self, dtype, box_with_array):
-        if box_with_array is tm.to_array and dtype is object:
-            # dont bother testing ndarray comparison methods as this fails
-            #  on older numpys (since they check object identity)
-            return
 
         left = DatetimeIndex([Timestamp("2011-01-01"), NaT, Timestamp("2011-01-03")])
         right = DatetimeIndex([NaT, NaT, Timestamp("2011-01-03")])

pandas/tests/arithmetic/test_numeric.py

@@ -128,8 +128,6 @@ def test_numeric_cmp_string_numexpr_path(self, box_with_array):
 
 
 class TestNumericArraylikeArithmeticWithDatetimeLike:
-
-    # TODO: also check name retentention
     @pytest.mark.parametrize("box_cls", [np.array, Index, Series])
     @pytest.mark.parametrize(
         "left", lefts, ids=lambda x: type(x).__name__ + str(x.dtype)
@@ -149,7 +147,6 @@ def test_mul_td64arr(self, left, box_cls):
         result = right * left
         tm.assert_equal(result, expected)
 
-    # TODO: also check name retentention
     @pytest.mark.parametrize("box_cls", [np.array, Index, Series])
     @pytest.mark.parametrize(
         "left", lefts, ids=lambda x: type(x).__name__ + str(x.dtype)
@@ -1241,7 +1238,7 @@ def test_binops_pow(self):
         idxs = [RangeIndex(0, 10, 1), RangeIndex(0, 20, 2)]
         self.check_binop(ops, scalars, idxs)
 
-    # TODO: mod, divmod?
+    # TODO: divmod?
     @pytest.mark.parametrize(
         "op",
         [
@@ -1251,6 +1248,7 @@ def test_binops_pow(self):
             operator.floordiv,
             operator.truediv,
             operator.pow,
+            operator.mod,
         ],
     )
     def test_arithmetic_with_frame_or_series(self, op):

pandas/tests/arithmetic/test_period.py

@@ -636,12 +636,12 @@ def test_pi_sub_pi_with_nat(self):
         expected = pd.Index([pd.NaT, 0 * off, 0 * off, 0 * off, 0 * off])
         tm.assert_index_equal(result, expected)
 
-    def test_parr_sub_pi_mismatched_freq(self, box_with_array):
+    def test_parr_sub_pi_mismatched_freq(self, box_with_array, box_with_array2):
         rng = period_range("1/1/2000", freq="D", periods=5)
         other = period_range("1/6/2000", freq="H", periods=5)
-        # TODO: parametrize over boxes for other?
 
         rng = tm.box_expected(rng, box_with_array)
+        other = tm.box_expected(other, box_with_array2)
         msg = r"Input has different freq=[HD] from PeriodArray\(freq=[DH]\)"
         with pytest.raises(IncompatibleFrequency, match=msg):
             rng - other
@@ -998,58 +998,67 @@ def test_pi_sub_intarray(self, int_holder):
     # Timedelta-like (timedelta, timedelta64, Timedelta, Tick)
     # TODO: Some of these are misnomers because of non-Tick DateOffsets
 
-    def test_pi_add_timedeltalike_minute_gt1(self, three_days):
+    def test_parr_add_timedeltalike_minute_gt1(self, three_days, box_with_array):
         # GH#23031 adding a time-delta-like offset to a PeriodArray that has
         # minute frequency with n != 1.  A more general case is tested below
         # in test_pi_add_timedeltalike_tick_gt1, but here we write out the
         # expected result more explicitly.
         other = three_days
         rng = period_range("2014-05-01", periods=3, freq="2D")
+        rng = tm.box_expected(rng, box_with_array)
 
         expected = PeriodIndex(["2014-05-04", "2014-05-06", "2014-05-08"], freq="2D")
+        expected = tm.box_expected(expected, box_with_array)
 
         result = rng + other
-        tm.assert_index_equal(result, expected)
+        tm.assert_equal(result, expected)
 
         result = other + rng
-        tm.assert_index_equal(result, expected)
+        tm.assert_equal(result, expected)
 
         # subtraction
         expected = PeriodIndex(["2014-04-28", "2014-04-30", "2014-05-02"], freq="2D")
+        expected = tm.box_expected(expected, box_with_array)
         result = rng - other
-        tm.assert_index_equal(result, expected)
+        tm.assert_equal(result, expected)
 
         msg = "|".join(
             [
-                r"(:?bad operand type for unary -: 'PeriodArray')",
-                r"(:?cannot subtract PeriodArray from timedelta64\[[hD]\])",
+                r"bad operand type for unary -: 'PeriodArray'",
+                r"cannot subtract PeriodArray from timedelta64\[[hD]\]",
             ]
         )
         with pytest.raises(TypeError, match=msg):
             other - rng
 
     @pytest.mark.parametrize("freqstr", ["5ns", "5us", "5ms", "5s", "5T", "5h", "5d"])
-    def test_pi_add_timedeltalike_tick_gt1(self, three_days, freqstr):
+    def test_parr_add_timedeltalike_tick_gt1(self, three_days, freqstr, box_with_array):
         # GH#23031 adding a time-delta-like offset to a PeriodArray that has
         # tick-like frequency with n != 1
         other = three_days
         rng = period_range("2014-05-01", periods=6, freq=freqstr)
+        first = rng[0]
+        rng = tm.box_expected(rng, box_with_array)
 
-        expected = period_range(rng[0] + other, periods=6, freq=freqstr)
+        expected = period_range(first + other, periods=6, freq=freqstr)
+        expected = tm.box_expected(expected, box_with_array)
 
         result = rng + other
-        tm.assert_index_equal(result, expected)
+        tm.assert_equal(result, expected)
 
         result = other + rng
-        tm.assert_index_equal(result, expected)
+        tm.assert_equal(result, expected)
 
         # subtraction
-        expected = period_range(rng[0] - other, periods=6, freq=freqstr)
+        expected = period_range(first - other, periods=6, freq=freqstr)
+        expected = tm.box_expected(expected, box_with_array)
         result = rng - other
-        tm.assert_index_equal(result, expected)
-        msg = (
-            r"(:?bad operand type for unary -: 'PeriodArray')"
-            r"|(:?cannot subtract PeriodArray from timedelta64\[[hD]\])"
+        tm.assert_equal(result, expected)
+        msg = "|".join(
+            [
+                r"bad operand type for unary -: 'PeriodArray'",
+                r"cannot subtract PeriodArray from timedelta64\[[hD]\]",
+            ]
         )
         with pytest.raises(TypeError, match=msg):
             other - rng
@@ -1078,9 +1087,13 @@ def test_pi_sub_isub_timedeltalike_daily(self, three_days):
         rng -= other
         tm.assert_index_equal(rng, expected)
 
-    def test_pi_add_sub_timedeltalike_freq_mismatch_daily(self, not_daily):
+    def test_parr_add_sub_timedeltalike_freq_mismatch_daily(
+        self, not_daily, box_with_array
+    ):
         other = not_daily
         rng = period_range("2014-05-01", "2014-05-15", freq="D")
+        rng = tm.box_expected(rng, box_with_array)
+
         msg = "Input has different freq(=.+)? from Period.*?\\(freq=D\\)"
         with pytest.raises(IncompatibleFrequency, match=msg):
             rng + other
@@ -1102,9 +1115,12 @@ def test_pi_add_iadd_timedeltalike_hourly(self, two_hours):
         rng += other
         tm.assert_index_equal(rng, expected)
 
-    def test_pi_add_timedeltalike_mismatched_freq_hourly(self, not_hourly):
+    def test_parr_add_timedeltalike_mismatched_freq_hourly(
+        self, not_hourly, box_with_array
+    ):
         other = not_hourly
         rng = period_range("2014-01-01 10:00", "2014-01-05 10:00", freq="H")
+        rng = tm.box_expected(rng, box_with_array)
         msg = "Input has different freq(=.+)? from Period.*?\\(freq=H\\)"
 
         with pytest.raises(IncompatibleFrequency, match=msg):