TST/REF: collect Index.equals tests (#38011)

Author: jbrockmendel

pandas/tests/indexes/categorical/test_category.py

@@ -381,77 +381,6 @@ def test_ensure_copied_data(self, index):
         result = CategoricalIndex(index.values, copy=False)
         assert _base(index.values) is _base(result.values)
 
-    def test_equals_categorical(self):
-        ci1 = CategoricalIndex(["a", "b"], categories=["a", "b"], ordered=True)
-        ci2 = CategoricalIndex(["a", "b"], categories=["a", "b", "c"], ordered=True)
-
-        assert ci1.equals(ci1)
-        assert not ci1.equals(ci2)
-        assert ci1.equals(ci1.astype(object))
-        assert ci1.astype(object).equals(ci1)
-
-        assert (ci1 == ci1).all()
-        assert not (ci1 != ci1).all()
-        assert not (ci1 > ci1).all()
-        assert not (ci1 < ci1).all()
-        assert (ci1 <= ci1).all()
-        assert (ci1 >= ci1).all()
-
-        assert not (ci1 == 1).all()
-        assert (ci1 == Index(["a", "b"])).all()
-        assert (ci1 == ci1.values).all()
-
-        # invalid comparisons
-        with pytest.raises(ValueError, match="Lengths must match"):
-            ci1 == Index(["a", "b", "c"])
-
-        msg = "Categoricals can only be compared if 'categories' are the same"
-        with pytest.raises(TypeError, match=msg):
-            ci1 == ci2
-        with pytest.raises(TypeError, match=msg):
-            ci1 == Categorical(ci1.values, ordered=False)
-        with pytest.raises(TypeError, match=msg):
-            ci1 == Categorical(ci1.values, categories=list("abc"))
-
-        # tests
-        # make sure that we are testing for category inclusion properly
-        ci = CategoricalIndex(list("aabca"), categories=["c", "a", "b"])
-        assert not ci.equals(list("aabca"))
-        # Same categories, but different order
-        # Unordered
-        assert ci.equals(CategoricalIndex(list("aabca")))
-        # Ordered
-        assert not ci.equals(CategoricalIndex(list("aabca"), ordered=True))
-        assert ci.equals(ci.copy())
-
-        ci = CategoricalIndex(list("aabca") + [np.nan], categories=["c", "a", "b"])
-        assert not ci.equals(list("aabca"))
-        assert not ci.equals(CategoricalIndex(list("aabca")))
-        assert ci.equals(ci.copy())
-
-        ci = CategoricalIndex(list("aabca") + [np.nan], categories=["c", "a", "b"])
-        assert not ci.equals(list("aabca") + [np.nan])
-        assert ci.equals(CategoricalIndex(list("aabca") + [np.nan]))
-        assert not ci.equals(CategoricalIndex(list("aabca") + [np.nan], ordered=True))
-        assert ci.equals(ci.copy())
-
-    def test_equals_categorical_unordered(self):
-        # https://github.com/pandas-dev/pandas/issues/16603
-        a = CategoricalIndex(["A"], categories=["A", "B"])
-        b = CategoricalIndex(["A"], categories=["B", "A"])
-        c = CategoricalIndex(["C"], categories=["B", "A"])
-        assert a.equals(b)
-        assert not a.equals(c)
-        assert not b.equals(c)
-
-    def test_equals_non_category(self):
-        # GH#37667 Case where other contains a value not among ci's
-        #  categories ("D") and also contains np.nan
-        ci = CategoricalIndex(["A", "B", np.nan, np.nan])
-        other = Index(["A", "B", "D", np.nan])
-
-        assert not ci.equals(other)
-
     def test_frame_repr(self):
         df = pd.DataFrame({"A": [1, 2, 3]}, index=CategoricalIndex(["a", "b", "c"]))
         result = repr(df)

pandas/tests/indexes/categorical/test_equals.py

@@ -0,0 +1,77 @@
+import numpy as np
+import pytest
+
+from pandas import Categorical, CategoricalIndex, Index
+
+
+class TestEquals:
+    def test_equals_categorical(self):
+        ci1 = CategoricalIndex(["a", "b"], categories=["a", "b"], ordered=True)
+        ci2 = CategoricalIndex(["a", "b"], categories=["a", "b", "c"], ordered=True)
+
+        assert ci1.equals(ci1)
+        assert not ci1.equals(ci2)
+        assert ci1.equals(ci1.astype(object))
+        assert ci1.astype(object).equals(ci1)
+
+        assert (ci1 == ci1).all()
+        assert not (ci1 != ci1).all()
+        assert not (ci1 > ci1).all()
+        assert not (ci1 < ci1).all()
+        assert (ci1 <= ci1).all()
+        assert (ci1 >= ci1).all()
+
+        assert not (ci1 == 1).all()
+        assert (ci1 == Index(["a", "b"])).all()
+        assert (ci1 == ci1.values).all()
+
+        # invalid comparisons
+        with pytest.raises(ValueError, match="Lengths must match"):
+            ci1 == Index(["a", "b", "c"])
+
+        msg = "Categoricals can only be compared if 'categories' are the same"
+        with pytest.raises(TypeError, match=msg):
+            ci1 == ci2
+        with pytest.raises(TypeError, match=msg):
+            ci1 == Categorical(ci1.values, ordered=False)
+        with pytest.raises(TypeError, match=msg):
+            ci1 == Categorical(ci1.values, categories=list("abc"))
+
+        # tests
+        # make sure that we are testing for category inclusion properly
+        ci = CategoricalIndex(list("aabca"), categories=["c", "a", "b"])
+        assert not ci.equals(list("aabca"))
+        # Same categories, but different order
+        # Unordered
+        assert ci.equals(CategoricalIndex(list("aabca")))
+        # Ordered
+        assert not ci.equals(CategoricalIndex(list("aabca"), ordered=True))
+        assert ci.equals(ci.copy())
+
+        ci = CategoricalIndex(list("aabca") + [np.nan], categories=["c", "a", "b"])
+        assert not ci.equals(list("aabca"))
+        assert not ci.equals(CategoricalIndex(list("aabca")))
+        assert ci.equals(ci.copy())
+
+        ci = CategoricalIndex(list("aabca") + [np.nan], categories=["c", "a", "b"])
+        assert not ci.equals(list("aabca") + [np.nan])
+        assert ci.equals(CategoricalIndex(list("aabca") + [np.nan]))
+        assert not ci.equals(CategoricalIndex(list("aabca") + [np.nan], ordered=True))
+        assert ci.equals(ci.copy())
+
+    def test_equals_categorical_unordered(self):
+        # https://github.com/pandas-dev/pandas/issues/16603
+        a = CategoricalIndex(["A"], categories=["A", "B"])
+        b = CategoricalIndex(["A"], categories=["B", "A"])
+        c = CategoricalIndex(["C"], categories=["B", "A"])
+        assert a.equals(b)
+        assert not a.equals(c)
+        assert not b.equals(c)
+
+    def test_equals_non_category(self):
+        # GH#37667 Case where other contains a value not among ci's
+        #  categories ("D") and also contains np.nan
+        ci = CategoricalIndex(["A", "B", np.nan, np.nan])
+        other = Index(["A", "B", "D", np.nan])
+
+        assert not ci.equals(other)

pandas/tests/indexes/datetimelike.py

@@ -1,4 +1,5 @@
 """ generic datetimelike tests """
+
 import numpy as np
 import pytest
 
@@ -109,27 +110,6 @@ def test_getitem_preserves_freq(self):
         result = index[:]
         assert result.freq == index.freq
 
-    def test_not_equals_numeric(self):
-        index = self.create_index()
-
-        assert not index.equals(pd.Index(index.asi8))
-        assert not index.equals(pd.Index(index.asi8.astype("u8")))
-        assert not index.equals(pd.Index(index.asi8).astype("f8"))
-
-    def test_equals(self):
-        index = self.create_index()
-
-        assert index.equals(index.astype(object))
-        assert index.equals(pd.CategoricalIndex(index))
-        assert index.equals(pd.CategoricalIndex(index.astype(object)))
-
-    def test_not_equals_strings(self):
-        index = self.create_index()
-
-        other = pd.Index([str(x) for x in index], dtype=object)
-        assert not index.equals(other)
-        assert not index.equals(pd.CategoricalIndex(other))
-
     def test_where_cast_str(self):
         index = self.create_index()
 

pandas/tests/indexes/datetimes/test_datetime.py

@@ -177,12 +177,6 @@ def test_misc_coverage(self):
         result = rng.groupby(rng.day)
         assert isinstance(list(result.values())[0][0], Timestamp)
 
-        idx = DatetimeIndex(["2000-01-03", "2000-01-01", "2000-01-02"])
-        assert not idx.equals(list(idx))
-
-        non_datetime = Index(list("abc"))
-        assert not idx.equals(list(non_datetime))
-
     def test_string_index_series_name_converted(self):
         # #1644
         df = DataFrame(np.random.randn(10, 4), index=date_range("1/1/2000", periods=10))

pandas/tests/indexes/datetimes/test_ops.py

@@ -325,47 +325,6 @@ def test_nat(self, tz_naive_fixture):
         assert idx.hasnans is True
         tm.assert_numpy_array_equal(idx._nan_idxs, np.array([1], dtype=np.intp))
 
-    def test_equals(self):
-        # GH 13107
-        idx = DatetimeIndex(["2011-01-01", "2011-01-02", "NaT"])
-        assert idx.equals(idx)
-        assert idx.equals(idx.copy())
-        assert idx.equals(idx.astype(object))
-        assert idx.astype(object).equals(idx)
-        assert idx.astype(object).equals(idx.astype(object))
-        assert not idx.equals(list(idx))
-        assert not idx.equals(Series(idx))
-
-        idx2 = DatetimeIndex(["2011-01-01", "2011-01-02", "NaT"], tz="US/Pacific")
-        assert not idx.equals(idx2)
-        assert not idx.equals(idx2.copy())
-        assert not idx.equals(idx2.astype(object))
-        assert not idx.astype(object).equals(idx2)
-        assert not idx.equals(list(idx2))
-        assert not idx.equals(Series(idx2))
-
-        # same internal, different tz
-        idx3 = DatetimeIndex(idx.asi8, tz="US/Pacific")
-        tm.assert_numpy_array_equal(idx.asi8, idx3.asi8)
-        assert not idx.equals(idx3)
-        assert not idx.equals(idx3.copy())
-        assert not idx.equals(idx3.astype(object))
-        assert not idx.astype(object).equals(idx3)
-        assert not idx.equals(list(idx3))
-        assert not idx.equals(Series(idx3))
-
-        # check that we do not raise when comparing with OutOfBounds objects
-        oob = Index([datetime(2500, 1, 1)] * 3, dtype=object)
-        assert not idx.equals(oob)
-        assert not idx2.equals(oob)
-        assert not idx3.equals(oob)
-
-        # check that we do not raise when comparing with OutOfBounds dt64
-        oob2 = oob.map(np.datetime64)
-        assert not idx.equals(oob2)
-        assert not idx2.equals(oob2)
-        assert not idx3.equals(oob2)
-
     @pytest.mark.parametrize("values", [["20180101", "20180103", "20180105"], []])
     @pytest.mark.parametrize("freq", ["2D", Day(2), "2B", BDay(2), "48H", Hour(48)])
     @pytest.mark.parametrize("tz", [None, "US/Eastern"])
@@ -429,9 +388,6 @@ def test_copy(self):
         repr(cp)
         tm.assert_index_equal(cp, self.rng)
 
-    def test_equals(self):
-        assert not self.rng.equals(list(self.rng))
-
     def test_identical(self):
         t1 = self.rng.copy()
         t2 = self.rng.copy()
@@ -465,6 +421,3 @@ def test_copy(self):
         cp = self.rng.copy()
         repr(cp)
         tm.assert_index_equal(cp, self.rng)
-
-    def test_equals(self):
-        assert not self.rng.equals(list(self.rng))

pandas/tests/indexes/interval/test_base.py

@@ -21,34 +21,6 @@ def index(self):
     def create_index(self, closed="right"):
         return IntervalIndex.from_breaks(range(11), closed=closed)
 
-    def test_equals(self, closed):
-        expected = IntervalIndex.from_breaks(np.arange(5), closed=closed)
-        assert expected.equals(expected)
-        assert expected.equals(expected.copy())
-
-        assert not expected.equals(expected.astype(object))
-        assert not expected.equals(np.array(expected))
-        assert not expected.equals(list(expected))
-
-        assert not expected.equals([1, 2])
-        assert not expected.equals(np.array([1, 2]))
-        assert not expected.equals(date_range("20130101", periods=2))
-
-        expected_name1 = IntervalIndex.from_breaks(
-            np.arange(5), closed=closed, name="foo"
-        )
-        expected_name2 = IntervalIndex.from_breaks(
-            np.arange(5), closed=closed, name="bar"
-        )
-        assert expected.equals(expected_name1)
-        assert expected_name1.equals(expected_name2)
-
-        for other_closed in {"left", "right", "both", "neither"} - {closed}:
-            expected_other_closed = IntervalIndex.from_breaks(
-                np.arange(5), closed=other_closed
-            )
-            assert not expected.equals(expected_other_closed)
-
     def test_repr_max_seq_item_setting(self):
         # override base test: not a valid repr as we use interval notation
         pass

pandas/tests/indexes/interval/test_equals.py

@@ -0,0 +1,33 @@
+import numpy as np
+
+from pandas import IntervalIndex, date_range
+
+
+class TestEquals:
+    def test_equals(self, closed):
+        expected = IntervalIndex.from_breaks(np.arange(5), closed=closed)
+        assert expected.equals(expected)
+        assert expected.equals(expected.copy())
+
+        assert not expected.equals(expected.astype(object))
+        assert not expected.equals(np.array(expected))
+        assert not expected.equals(list(expected))
+
+        assert not expected.equals([1, 2])
+        assert not expected.equals(np.array([1, 2]))
+        assert not expected.equals(date_range("20130101", periods=2))
+
+        expected_name1 = IntervalIndex.from_breaks(
+            np.arange(5), closed=closed, name="foo"
+        )
+        expected_name2 = IntervalIndex.from_breaks(
+            np.arange(5), closed=closed, name="bar"
+        )
+        assert expected.equals(expected_name1)
+        assert expected_name1.equals(expected_name2)
+
+        for other_closed in {"left", "right", "both", "neither"} - {closed}:
+            expected_other_closed = IntervalIndex.from_breaks(
+                np.arange(5), closed=other_closed
+            )
+            assert not expected.equals(expected_other_closed)

pandas/tests/indexes/period/test_ops.py

@@ -287,38 +287,6 @@ def test_nat(self):
         assert idx.hasnans is True
         tm.assert_numpy_array_equal(idx._nan_idxs, np.array([1], dtype=np.intp))
 
-    @pytest.mark.parametrize("freq", ["D", "M"])
-    def test_equals(self, freq):
-        # GH#13107
-        idx = PeriodIndex(["2011-01-01", "2011-01-02", "NaT"], freq=freq)
-        assert idx.equals(idx)
-        assert idx.equals(idx.copy())
-        assert idx.equals(idx.astype(object))
-        assert idx.astype(object).equals(idx)
-        assert idx.astype(object).equals(idx.astype(object))
-        assert not idx.equals(list(idx))
-        assert not idx.equals(Series(idx))
-
-        idx2 = PeriodIndex(["2011-01-01", "2011-01-02", "NaT"], freq="H")
-        assert not idx.equals(idx2)
-        assert not idx.equals(idx2.copy())
-        assert not idx.equals(idx2.astype(object))
-        assert not idx.astype(object).equals(idx2)
-        assert not idx.equals(list(idx2))
-        assert not idx.equals(Series(idx2))
-
-        # same internal, different tz
-        idx3 = PeriodIndex._simple_new(
-            idx._values._simple_new(idx._values.asi8, freq="H")
-        )
-        tm.assert_numpy_array_equal(idx.asi8, idx3.asi8)
-        assert not idx.equals(idx3)
-        assert not idx.equals(idx3.copy())
-        assert not idx.equals(idx3.astype(object))
-        assert not idx.astype(object).equals(idx3)
-        assert not idx.equals(list(idx3))
-        assert not idx.equals(Series(idx3))
-
     def test_freq_setter_deprecated(self):
         # GH 20678
         idx = pd.period_range("2018Q1", periods=4, freq="Q")