TST: collect Index tests by method (#40070)

Author: jbrockmendel

pandas/core/groupby/ops.py

@@ -774,7 +774,7 @@ def _aggregate_series_pure_python(self, obj: Series, func: F):
             counts[label] = group.shape[0]
             result[label] = res
 
-        result = lib.maybe_convert_objects(result, try_float=0)
+        result = lib.maybe_convert_objects(result, try_float=False)
         result = maybe_cast_result(result, obj, numeric_only=True)
 
         return result, counts

pandas/core/indexes/base.py

@@ -1152,7 +1152,7 @@ def _format_with_header(
         values = self._values
 
         if is_object_dtype(values.dtype):
-            values = lib.maybe_convert_objects(values, safe=1)
+            values = lib.maybe_convert_objects(values, safe=True)
 
             result = [pprint_thing(x, escape_chars=("\t", "\r", "\n")) for x in values]
 

pandas/tests/dtypes/test_inference.py

@@ -564,17 +564,23 @@ def test_maybe_convert_objects_datetime(self):
             [np.datetime64("2000-01-01"), np.timedelta64(1, "s")], dtype=object
         )
         exp = arr.copy()
-        out = lib.maybe_convert_objects(arr, convert_datetime=1, convert_timedelta=1)
+        out = lib.maybe_convert_objects(
+            arr, convert_datetime=True, convert_timedelta=True
+        )
         tm.assert_numpy_array_equal(out, exp)
 
         arr = np.array([pd.NaT, np.timedelta64(1, "s")], dtype=object)
         exp = np.array([np.timedelta64("NaT"), np.timedelta64(1, "s")], dtype="m8[ns]")
-        out = lib.maybe_convert_objects(arr, convert_datetime=1, convert_timedelta=1)
+        out = lib.maybe_convert_objects(
+            arr, convert_datetime=True, convert_timedelta=True
+        )
         tm.assert_numpy_array_equal(out, exp)
 
         arr = np.array([np.timedelta64(1, "s"), np.nan], dtype=object)
         exp = arr.copy()
-        out = lib.maybe_convert_objects(arr, convert_datetime=1, convert_timedelta=1)
+        out = lib.maybe_convert_objects(
+            arr, convert_datetime=True, convert_timedelta=True
+        )
         tm.assert_numpy_array_equal(out, exp)
 
     @pytest.mark.parametrize(
@@ -587,7 +593,7 @@ def test_maybe_convert_objects_datetime(self):
     def test_maybe_convert_objects_nullable_integer(self, exp):
         # GH27335
         arr = np.array([2, np.NaN], dtype=object)
-        result = lib.maybe_convert_objects(arr, convert_to_nullable_integer=1)
+        result = lib.maybe_convert_objects(arr, convert_to_nullable_integer=True)
 
         tm.assert_extension_array_equal(result, exp)
 
@@ -601,7 +607,7 @@ def test_maybe_convert_objects_bool_nan(self):
     def test_mixed_dtypes_remain_object_array(self):
         # GH14956
         array = np.array([datetime(2015, 1, 1, tzinfo=pytz.utc), 1], dtype=object)
-        result = lib.maybe_convert_objects(array, convert_datetime=1)
+        result = lib.maybe_convert_objects(array, convert_datetime=True)
         tm.assert_numpy_array_equal(result, array)
 
 

pandas/tests/indexes/datetimelike_/test_drop_duplicates.py

@@ -0,0 +1,80 @@
+import numpy as np
+import pytest
+
+from pandas import (
+    PeriodIndex,
+    Series,
+    date_range,
+    period_range,
+    timedelta_range,
+)
+import pandas._testing as tm
+
+
+class DropDuplicates:
+    def test_drop_duplicates_metadata(self, idx):
+        # GH#10115
+        result = idx.drop_duplicates()
+        tm.assert_index_equal(idx, result)
+        assert idx.freq == result.freq
+
+        idx_dup = idx.append(idx)
+        result = idx_dup.drop_duplicates()
+
+        expected = idx
+        if not isinstance(idx, PeriodIndex):
+            # freq is reset except for PeriodIndex
+            assert idx_dup.freq is None
+            assert result.freq is None
+            expected = idx._with_freq(None)
+        else:
+            assert result.freq == expected.freq
+
+        tm.assert_index_equal(result, expected)
+
+    @pytest.mark.parametrize(
+        "keep, expected, index",
+        [
+            ("first", np.concatenate(([False] * 10, [True] * 5)), np.arange(0, 10)),
+            ("last", np.concatenate(([True] * 5, [False] * 10)), np.arange(5, 15)),
+            (
+                False,
+                np.concatenate(([True] * 5, [False] * 5, [True] * 5)),
+                np.arange(5, 10),
+            ),
+        ],
+    )
+    def test_drop_duplicates(self, keep, expected, index, idx):
+        # to check Index/Series compat
+        idx = idx.append(idx[:5])
+
+        tm.assert_numpy_array_equal(idx.duplicated(keep=keep), expected)
+        expected = idx[~expected]
+
+        result = idx.drop_duplicates(keep=keep)
+        tm.assert_index_equal(result, expected)
+
+        result = Series(idx).drop_duplicates(keep=keep)
+        tm.assert_series_equal(result, Series(expected, index=index))
+
+
+class TestDropDuplicatesPeriodIndex(DropDuplicates):
+    @pytest.fixture(params=["D", "3D", "H", "2H", "T", "2T", "S", "3S"])
+    def freq(self, request):
+        return request.param
+
+    @pytest.fixture
+    def idx(self, freq):
+        return period_range("2011-01-01", periods=10, freq=freq, name="idx")
+
+
+class TestDropDuplicatesDatetimeIndex(DropDuplicates):
+    @pytest.fixture
+    def idx(self, freq_sample):
+        return date_range("2011-01-01", freq=freq_sample, periods=10, name="idx")
+
+
+class TestDropDuplicatesTimedeltaIndex(DropDuplicates):
+    @pytest.fixture
+    def idx(self, freq_sample):
+        return timedelta_range("1 day", periods=10, freq=freq_sample, name="idx")

pandas/tests/indexes/datetimelike_/test_nat.py

@@ -0,0 +1,54 @@
+import numpy as np
+import pytest
+
+from pandas import (
+    DatetimeIndex,
+    NaT,
+    PeriodIndex,
+    TimedeltaIndex,
+)
+import pandas._testing as tm
+
+
+class NATests:
+    def test_nat(self, index_without_na):
+        empty_index = index_without_na[:0]
+
+        index_with_na = index_without_na.copy(deep=True)
+        index_with_na._data[1] = NaT
+
+        assert type(index_without_na)._na_value is NaT
+        assert empty_index._na_value is NaT
+        assert index_with_na._na_value is NaT
+        assert index_without_na._na_value is NaT
+
+        idx = index_without_na
+        assert idx._can_hold_na
+
+        tm.assert_numpy_array_equal(idx._isnan, np.array([False, False]))
+        assert idx.hasnans is False
+
+        idx = index_with_na
+        assert idx._can_hold_na
+
+        tm.assert_numpy_array_equal(idx._isnan, np.array([False, True]))
+        assert idx.hasnans is True
+
+
+class TestDatetimeIndexNA(NATests):
+    @pytest.fixture
+    def index_without_na(self, tz_naive_fixture):
+        tz = tz_naive_fixture
+        return DatetimeIndex(["2011-01-01", "2011-01-02"], tz=tz)
+
+
+class TestTimedeltaIndexNA(NATests):
+    @pytest.fixture
+    def index_without_na(self):
+        return TimedeltaIndex(["1 days", "2 days"])
+
+
+class TestPeriodIndexNA(NATests):
+    @pytest.fixture
+    def index_without_na(self):
+        return PeriodIndex(["2011-01-01", "2011-01-02"], freq="D")