TST: collect/share Index tests (#44413)

Author: jbrockmendel

pandas/tests/frame/indexing/test_setitem.py

@@ -44,6 +44,19 @@
 
 
 class TestDataFrameSetItem:
+    def test_setitem_str_subclass(self):
+        # GH#37366
+        class mystring(str):
+            pass
+
+        data = ["2020-10-22 01:21:00+00:00"]
+        index = DatetimeIndex(data)
+        df = DataFrame({"a": [1]}, index=index)
+        df["b"] = 2
+        df[mystring("c")] = 3
+        expected = DataFrame({"a": [1], "b": [2], mystring("c"): [3]}, index=index)
+        tm.assert_equal(df, expected)
+
     @pytest.mark.parametrize("dtype", ["int32", "int64", "float32", "float64"])
     def test_setitem_dtype(self, dtype, float_frame):
         arr = np.random.randn(len(float_frame))

pandas/tests/indexes/base_class/test_formats.py

@@ -122,6 +122,14 @@ def test_repr_summary(self):
             assert len(result) < 200
             assert "..." in result
 
+    def test_summary_bug(self):
+        # GH#3869
+        ind = Index(["{other}%s", "~:{range}:0"], name="A")
+        result = ind._summary()
+        # shouldn't be formatted accidentally.
+        assert "~:{range}:0" in result
+        assert "{other}%s" in result
+
     def test_index_repr_bool_nan(self):
         # GH32146
         arr = Index([True, False, np.nan], dtype=object)
@@ -132,3 +140,9 @@ def test_index_repr_bool_nan(self):
         exp2 = repr(arr)
         out2 = "Index([True, False, nan], dtype='object')"
         assert out2 == exp2
+
+    def test_format_different_scalar_lengths(self):
+        # GH#35439
+        idx = Index(["aaaaaaaaa", "b"])
+        expected = ["aaaaaaaaa", "b"]
+        assert idx.format() == expected

pandas/tests/indexes/common.py

@@ -69,26 +69,6 @@ def test_pickle_compat_construction(self):
         with pytest.raises(TypeError, match=msg):
             self._index_cls()
 
-    @pytest.mark.parametrize("name", [None, "new_name"])
-    def test_to_frame(self, name, simple_index):
-        # see GH-15230, GH-22580
-        idx = simple_index
-
-        if name:
-            idx_name = name
-        else:
-            idx_name = idx.name or 0
-
-        df = idx.to_frame(name=idx_name)
-
-        assert df.index is idx
-        assert len(df.columns) == 1
-        assert df.columns[0] == idx_name
-        assert df[idx_name].values is not idx.values
-
-        df = idx.to_frame(index=False, name=idx_name)
-        assert df.index is not idx
-
     def test_shift(self, simple_index):
 
         # GH8083 test the base class for shift
@@ -226,46 +206,6 @@ def test_repr_max_seq_item_setting(self, simple_index):
             repr(idx)
             assert "..." not in str(idx)
 
-    def test_copy_name(self, index):
-        # gh-12309: Check that the "name" argument
-        # passed at initialization is honored.
-        if isinstance(index, MultiIndex):
-            return
-
-        first = type(index)(index, copy=True, name="mario")
-        second = type(first)(first, copy=False)
-
-        # Even though "copy=False", we want a new object.
-        assert first is not second
-
-        # Not using tm.assert_index_equal() since names differ.
-        assert index.equals(first)
-
-        assert first.name == "mario"
-        assert second.name == "mario"
-
-        s1 = Series(2, index=first)
-        s2 = Series(3, index=second[:-1])
-
-        if not isinstance(index, CategoricalIndex):
-            # See gh-13365
-            s3 = s1 * s2
-            assert s3.index.name == "mario"
-
-    def test_copy_name2(self, index):
-        # gh-35592
-        if isinstance(index, MultiIndex):
-            return
-
-        assert index.copy(name="mario").name == "mario"
-
-        with pytest.raises(ValueError, match="Length of new names must be 1, got 2"):
-            index.copy(name=["mario", "luigi"])
-
-        msg = f"{type(index).__name__}.name must be a hashable type"
-        with pytest.raises(TypeError, match=msg):
-            index.copy(name=[["mario"]])
-
     def test_ensure_copied_data(self, index):
         # Check the "copy" argument of each Index.__new__ is honoured
         # GH12309

pandas/tests/indexes/datetimes/test_formats.py

@@ -254,3 +254,20 @@ def test_dti_custom_business_summary_dateutil(self):
         pd.bdate_range(
             "1/1/2005", "1/1/2009", freq="C", tz=dateutil.tz.tzutc()
         )._summary()
+
+
+class TestFormat:
+    def test_format_with_name_time_info(self):
+        # bug I fixed 12/20/2011
+        dates = pd.date_range("2011-01-01 04:00:00", periods=10, name="something")
+
+        formatted = dates.format(name=True)
+        assert formatted[0] == "something"
+
+    def test_format_datetime_with_time(self):
+        dti = DatetimeIndex([datetime(2012, 2, 7), datetime(2012, 2, 7, 23)])
+
+        result = dti.format()
+        expected = ["2012-02-07 00:00:00", "2012-02-07 23:00:00"]
+        assert len(result) == 2
+        assert result == expected

pandas/tests/indexes/datetimes/test_indexing.py

@@ -21,25 +21,12 @@
 )
 import pandas._testing as tm
 
-from pandas.tseries.offsets import (
-    BDay,
-    CDay,
-)
+from pandas.tseries.frequencies import to_offset
 
 START, END = datetime(2009, 1, 1), datetime(2010, 1, 1)
 
 
 class TestGetItem:
-    def test_ellipsis(self):
-        # GH#21282
-        idx = date_range(
-            "2011-01-01", "2011-01-31", freq="D", tz="Asia/Tokyo", name="idx"
-        )
-
-        result = idx[...]
-        assert result.equals(idx)
-        assert result is not idx
-
     def test_getitem_slice_keeps_name(self):
         # GH4226
         st = Timestamp("2013-07-01 00:00:00", tz="America/Los_Angeles")
@@ -88,44 +75,17 @@ def test_getitem(self):
             tm.assert_index_equal(result, expected)
             assert result.freq == expected.freq
 
-    def test_dti_business_getitem(self):
-        rng = bdate_range(START, END)
-        smaller = rng[:5]
-        exp = DatetimeIndex(rng.view(np.ndarray)[:5], freq="B")
-        tm.assert_index_equal(smaller, exp)
-        assert smaller.freq == exp.freq
-
-        assert smaller.freq == rng.freq
-
-        sliced = rng[::5]
-        assert sliced.freq == BDay() * 5
-
-        fancy_indexed = rng[[4, 3, 2, 1, 0]]
-        assert len(fancy_indexed) == 5
-        assert isinstance(fancy_indexed, DatetimeIndex)
-        assert fancy_indexed.freq is None
-
-        # 32-bit vs. 64-bit platforms
-        assert rng[4] == rng[np.int_(4)]
-
-    def test_dti_business_getitem_matplotlib_hackaround(self):
-        rng = bdate_range(START, END)
-        with tm.assert_produces_warning(FutureWarning):
-            # GH#30588 multi-dimensional indexing deprecated
-            values = rng[:, None]
-        expected = rng.values[:, None]
-        tm.assert_numpy_array_equal(values, expected)
-
-    def test_dti_custom_getitem(self):
-        rng = bdate_range(START, END, freq="C")
+    @pytest.mark.parametrize("freq", ["B", "C"])
+    def test_dti_business_getitem(self, freq):
+        rng = bdate_range(START, END, freq=freq)
         smaller = rng[:5]
-        exp = DatetimeIndex(rng.view(np.ndarray)[:5], freq="C")
+        exp = DatetimeIndex(rng.view(np.ndarray)[:5], freq=freq)
         tm.assert_index_equal(smaller, exp)
         assert smaller.freq == exp.freq
         assert smaller.freq == rng.freq
 
         sliced = rng[::5]
-        assert sliced.freq == CDay() * 5
+        assert sliced.freq == to_offset(freq) * 5
 
         fancy_indexed = rng[[4, 3, 2, 1, 0]]
         assert len(fancy_indexed) == 5
@@ -135,8 +95,9 @@ def test_dti_custom_getitem(self):
         # 32-bit vs. 64-bit platforms
         assert rng[4] == rng[np.int_(4)]
 
-    def test_dti_custom_getitem_matplotlib_hackaround(self):
-        rng = bdate_range(START, END, freq="C")
+    @pytest.mark.parametrize("freq", ["B", "C"])
+    def test_dti_business_getitem_matplotlib_hackaround(self, freq):
+        rng = bdate_range(START, END, freq=freq)
         with tm.assert_produces_warning(FutureWarning):
             # GH#30588 multi-dimensional indexing deprecated
             values = rng[:, None]
@@ -255,6 +216,12 @@ def test_where_tz(self):
 
 
 class TestTake:
+    def test_take_nan_first_datetime(self):
+        index = DatetimeIndex([pd.NaT, Timestamp("20130101"), Timestamp("20130102")])
+        result = index.take([-1, 0, 1])
+        expected = DatetimeIndex([index[-1], index[0], index[1]])
+        tm.assert_index_equal(result, expected)
+
     def test_take(self):
         # GH#10295
         idx1 = date_range("2011-01-01", "2011-01-31", freq="D", name="idx")

pandas/tests/indexes/interval/test_indexing.py

@@ -11,6 +11,7 @@
     Interval,
     IntervalIndex,
     NaT,
+    Series,
     Timedelta,
     date_range,
     timedelta_range,
@@ -523,3 +524,37 @@ def test_putmask_td64(self):
         result = idx.putmask(mask, idx[-1])
         expected = IntervalIndex([idx[-1]] * 3 + list(idx[3:]))
         tm.assert_index_equal(result, expected)
+
+
+class TestGetValue:
+    @pytest.mark.parametrize("key", [[5], (2, 3)])
+    def test_get_value_non_scalar_errors(self, key):
+        # GH#31117
+        idx = IntervalIndex.from_tuples([(1, 3), (2, 4), (3, 5), (7, 10), (3, 10)])
+        ser = Series(range(len(idx)), index=idx)
+
+        msg = str(key)
+        with pytest.raises(InvalidIndexError, match=msg):
+            with tm.assert_produces_warning(FutureWarning):
+                idx.get_value(ser, key)
+
+
+class TestContains:
+    # .__contains__, not .contains
+
+    def test_contains_dunder(self):
+
+        index = IntervalIndex.from_arrays([0, 1], [1, 2], closed="right")
+
+        # __contains__ requires perfect matches to intervals.
+        assert 0 not in index
+        assert 1 not in index
+        assert 2 not in index
+
+        assert Interval(0, 1, closed="right") in index
+        assert Interval(0, 2, closed="right") not in index
+        assert Interval(0, 0.5, closed="right") not in index
+        assert Interval(3, 5, closed="right") not in index
+        assert Interval(-1, 0, closed="left") not in index
+        assert Interval(0, 1, closed="left") not in index
+        assert Interval(0, 1, closed="both") not in index

pandas/tests/indexes/interval/test_interval.py

@@ -4,8 +4,6 @@
 import numpy as np
 import pytest
 
-from pandas.errors import InvalidIndexError
-
 import pandas as pd
 from pandas import (
     Index,
@@ -500,23 +498,6 @@ def test_contains_method(self):
         ):
             i.contains(Interval(0, 1))
 
-    def test_contains_dunder(self):
-
-        index = IntervalIndex.from_arrays([0, 1], [1, 2], closed="right")
-
-        # __contains__ requires perfect matches to intervals.
-        assert 0 not in index
-        assert 1 not in index
-        assert 2 not in index
-
-        assert Interval(0, 1, closed="right") in index
-        assert Interval(0, 2, closed="right") not in index
-        assert Interval(0, 0.5, closed="right") not in index
-        assert Interval(3, 5, closed="right") not in index
-        assert Interval(-1, 0, closed="left") not in index
-        assert Interval(0, 1, closed="left") not in index
-        assert Interval(0, 1, closed="both") not in index
-
     def test_dropna(self, closed):
 
         expected = IntervalIndex.from_tuples([(0.0, 1.0), (1.0, 2.0)], closed=closed)
@@ -908,24 +889,6 @@ def test_is_all_dates(self):
         year_2017_index = IntervalIndex([year_2017])
         assert not year_2017_index._is_all_dates
 
-    @pytest.mark.parametrize("key", [[5], (2, 3)])
-    def test_get_value_non_scalar_errors(self, key):
-        # GH 31117
-        idx = IntervalIndex.from_tuples([(1, 3), (2, 4), (3, 5), (7, 10), (3, 10)])
-        s = pd.Series(range(len(idx)), index=idx)
-
-        msg = str(key)
-        with pytest.raises(InvalidIndexError, match=msg):
-            with tm.assert_produces_warning(FutureWarning):
-                idx.get_value(s, key)
-
-    @pytest.mark.parametrize("closed", ["left", "right", "both"])
-    def test_pickle_round_trip_closed(self, closed):
-        # https://github.com/pandas-dev/pandas/issues/35658
-        idx = IntervalIndex.from_tuples([(1, 2), (2, 3)], closed=closed)
-        result = tm.round_trip_pickle(idx)
-        tm.assert_index_equal(result, idx)
-
 
 def test_dir():
     # GH#27571 dir(interval_index) should not raise

pandas/tests/indexes/interval/test_pickle.py

@@ -0,0 +1,13 @@
+import pytest
+
+from pandas import IntervalIndex
+import pandas._testing as tm
+
+
+class TestPickle:
+    @pytest.mark.parametrize("closed", ["left", "right", "both"])
+    def test_pickle_round_trip_closed(self, closed):
+        # https://github.com/pandas-dev/pandas/issues/35658
+        idx = IntervalIndex.from_tuples([(1, 2), (2, 3)], closed=closed)
+        result = tm.round_trip_pickle(idx)
+        tm.assert_index_equal(result, idx)

pandas/tests/indexes/multi/test_compat.py

@@ -96,10 +96,3 @@ def test_inplace_mutation_resets_values():
     assert "_values" not in mi2._cache
     tm.assert_almost_equal(mi2.values, new_values)
     assert "_values" in mi2._cache
-
-
-def test_pickle_compat_construction():
-    # this is testing for pickle compat
-    # need an object to create with
-    with pytest.raises(TypeError, match="Must pass both levels and codes"):
-        MultiIndex()

pandas/tests/indexes/multi/test_pickle.py

@@ -0,0 +1,10 @@
+import pytest
+
+from pandas import MultiIndex
+
+
+def test_pickle_compat_construction():
+    # this is testing for pickle compat
+    # need an object to create with
+    with pytest.raises(TypeError, match="Must pass both levels and codes"):
+        MultiIndex()

pandas/tests/indexes/period/test_indexing.py

@@ -52,14 +52,6 @@ def non_comparable_idx(request):
 
 
 class TestGetItem:
-    def test_ellipsis(self):
-        # GH#21282
-        idx = period_range("2011-01-01", "2011-01-31", freq="D", name="idx")
-
-        result = idx[...]
-        assert result.equals(idx)
-        assert result is not idx
-
     def test_getitem_slice_keeps_name(self):
         idx = period_range("20010101", periods=10, freq="D", name="bob")
         assert idx.name == idx[1:].name