API: change IntervalIndex.contains to work elementwise (#17753)

Author: jorisvandenbossche

doc/source/reference/arrays.rst

@@ -335,6 +335,7 @@ A collection of intervals may be stored in an :class:`arrays.IntervalArray`.
       arrays.IntervalArray.from_arrays
       arrays.IntervalArray.from_tuples
       arrays.IntervalArray.from_breaks
+      arrays.IntervalArray.contains
       arrays.IntervalArray.overlaps
       arrays.IntervalArray.set_closed
       arrays.IntervalArray.to_tuples

doc/source/reference/indexing.rst

@@ -248,7 +248,6 @@ IntervalIndex components
    IntervalIndex.from_arrays
    IntervalIndex.from_tuples
    IntervalIndex.from_breaks
-   IntervalIndex.contains
    IntervalIndex.left
    IntervalIndex.right
    IntervalIndex.mid
@@ -260,6 +259,7 @@ IntervalIndex components
    IntervalIndex.get_loc
    IntervalIndex.get_indexer
    IntervalIndex.set_closed
+   IntervalIndex.contains
    IntervalIndex.overlaps
    IntervalIndex.to_tuples
 

doc/source/whatsnew/v0.25.0.rst

@@ -624,6 +624,7 @@ Other deprecations
 - :attr:`Series.imag` and :attr:`Series.real` are deprecated. (:issue:`18262`)
 - :meth:`Series.put` is deprecated. (:issue:`18262`)
 - :meth:`Index.item` and :meth:`Series.item` is deprecated. (:issue:`18262`)
+- :meth:`Index.contains` is deprecated. Use ``key in index`` (``__contains__``) instead (:issue:`17753`).
 
 .. _whatsnew_0250.prior_deprecations:
 

pandas/core/arrays/interval.py

@@ -79,6 +79,7 @@
 from_arrays
 from_tuples
 from_breaks
+contains
 overlaps
 set_closed
 to_tuples
@@ -1017,6 +1018,52 @@ def repeat(self, repeats, axis=None):
         right_repeat = self.right.repeat(repeats)
         return self._shallow_copy(left=left_repeat, right=right_repeat)
 
+    _interval_shared_docs['contains'] = """
+        Check elementwise if the Intervals contain the value.
+
+        Return a boolean mask whether the value is contained in the Intervals
+        of the %(klass)s.
+
+        .. versionadded:: 0.25.0
+
+        Parameters
+        ----------
+        other : scalar
+            The value to check whether it is contained in the Intervals.
+
+        Returns
+        -------
+        boolean array
+
+        See Also
+        --------
+        Interval.contains : Check whether Interval object contains value.
+        %(klass)s.overlaps : Check if an Interval overlaps the values in the
+            %(klass)s.
+
+        Examples
+        --------
+        >>> intervals = pd.%(qualname)s.from_tuples([(0, 1), (1, 3), (2, 4)])
+        >>> intervals
+        %(klass)s([(0, 1], (1, 3], (2, 4]],
+              closed='right',
+              dtype='interval[int64]')
+        >>> intervals.contains(0.5)
+        array([ True, False, False])
+    """
+
+    @Appender(_interval_shared_docs['contains'] % _shared_docs_kwargs)
+    def contains(self, other):
+        if isinstance(other, Interval):
+            raise NotImplementedError(
+                'contains not implemented for two intervals'
+            )
+
+        return (
+            (self.left < other if self.open_left else self.left <= other) &
+            (other < self.right if self.open_right else other <= self.right)
+        )
+
     _interval_shared_docs['overlaps'] = """
         Check elementwise if an Interval overlaps the values in the %(klass)s.
 

pandas/core/indexes/base.py

@@ -4019,13 +4019,6 @@ def is_type_compatible(self, kind):
         >>> idx
         Int64Index([1, 2, 3, 4], dtype='int64')
 
-        >>> idx.contains(2)
-        True
-        >>> idx.contains(6)
-        False
-
-        This is equivalent to:
-
         >>> 2 in idx
         True
         >>> 6 in idx
@@ -4040,8 +4033,21 @@ def __contains__(self, key):
         except (OverflowError, TypeError, ValueError):
             return False
 
-    @Appender(_index_shared_docs['contains'] % _index_doc_kwargs)
     def contains(self, key):
+        """
+        Return a boolean indicating whether the provided key is in the index.
+
+        .. deprecated:: 0.25.0
+            Use ``key in index`` instead of ``index.contains(key)``.
+
+        Returns
+        -------
+        bool
+        """
+        warnings.warn(
+            "The 'contains' method is deprecated and will be removed in a "
+            "future version. Use 'key in index' instead of "
+            "'index.contains(key)'", FutureWarning, stacklevel=2)
         return key in self
 
     def __hash__(self):

pandas/core/indexes/category.py

@@ -386,10 +386,6 @@ def __contains__(self, key):
 
         return contains(self, key, container=self._engine)
 
-    @Appender(_index_shared_docs['contains'] % _index_doc_kwargs)
-    def contains(self, key):
-        return key in self
-
     def __array__(self, dtype=None):
         """ the array interface, return my values """
         return np.array(self._data, dtype=dtype)

pandas/core/indexes/datetimelike.py

@@ -221,8 +221,6 @@ def __contains__(self, key):
         except (KeyError, TypeError, ValueError):
             return False
 
-    contains = __contains__
-
     # Try to run function on index first, and then on elements of index
     # Especially important for group-by functionality
     def map(self, mapper, na_action=None):

pandas/core/indexes/interval.py

@@ -139,7 +139,7 @@ def func(intvidx_self, other, sort=False):
     name=_index_doc_kwargs['name'],
     versionadded="0.20.0",
     extra_attributes="is_overlapping\nvalues\n",
-    extra_methods="contains\n",
+    extra_methods="",
     examples=textwrap.dedent("""\
     Examples
     --------
@@ -291,27 +291,6 @@ def __contains__(self, key):
         except KeyError:
             return False
 
-    def contains(self, key):
-        """
-        Return a boolean indicating if the key is IN the index
-
-        We accept / allow keys to be not *just* actual
-        objects.
-
-        Parameters
-        ----------
-        key : int, float, Interval
-
-        Returns
-        -------
-        boolean
-        """
-        try:
-            self.get_loc(key)
-            return True
-        except KeyError:
-            return False
-
     @Appender(_interval_shared_docs['to_tuples'] % dict(
         return_type="Index",
         examples="""
@@ -1137,6 +1116,10 @@ def equals(self, other):
                 self.right.equals(other.right) and
                 self.closed == other.closed)
 
+    @Appender(_interval_shared_docs['contains'] % _index_doc_kwargs)
+    def contains(self, other):
+        return self._data.contains(other)
+
     @Appender(_interval_shared_docs['overlaps'] % _index_doc_kwargs)
     def overlaps(self, other):
         return self._data.overlaps(other)

pandas/core/indexes/multi.py

@@ -922,8 +922,6 @@ def __contains__(self, key):
         except (LookupError, TypeError, ValueError):
             return False
 
-    contains = __contains__
-
     @Appender(_index_shared_docs['_shallow_copy'])
     def _shallow_copy(self, values=None, **kwargs):
         if values is not None:

pandas/core/indexes/period.py

@@ -433,8 +433,6 @@ def __contains__(self, key):
             except Exception:
                 return False
 
-    contains = __contains__
-
     @cache_readonly
     def _int64index(self):
         return Int64Index._simple_new(self.asi8, name=self.name)

pandas/core/indexing.py

@@ -2393,7 +2393,7 @@ def convert_to_index_sliceable(obj, key):
     elif isinstance(key, str):
 
         # we are an actual column
-        if obj._data.items.contains(key):
+        if key in obj._data.items:
             return None
 
         # We might have a datetimelike string that we can translate to a

pandas/tests/indexes/interval/test_interval.py

@@ -753,23 +753,28 @@ def test_contains(self):
         assert Interval(3, 5) not in i
         assert Interval(-1, 0, closed='left') not in i
 
-    # To be removed, replaced by test_interval_new.py (see #16316, #16386)
-    def testcontains(self):
+    def test_contains_method(self):
         # can select values that are IN the range of a value
         i = IntervalIndex.from_arrays([0, 1], [1, 2])
 
-        assert i.contains(0.1)
-        assert i.contains(0.5)
-        assert i.contains(1)
-        assert i.contains(Interval(0, 1))
-        assert i.contains(Interval(0, 2))
+        expected = np.array([False, False], dtype='bool')
+        actual = i.contains(0)
+        tm.assert_numpy_array_equal(actual, expected)
+        actual = i.contains(3)
+        tm.assert_numpy_array_equal(actual, expected)
 
-        # these overlaps completely
-        assert i.contains(Interval(0, 3))
-        assert i.contains(Interval(1, 3))
+        expected = np.array([True, False], dtype='bool')
+        actual = i.contains(0.5)
+        tm.assert_numpy_array_equal(actual, expected)
+        actual = i.contains(1)
+        tm.assert_numpy_array_equal(actual, expected)
 
-        assert not i.contains(20)
-        assert not i.contains(-20)
+        # __contains__ not implemented for "interval in interval", follow
+        # that for the contains method for now
+        with pytest.raises(
+                NotImplementedError,
+                match='contains not implemented for two'):
+            i.contains(Interval(0, 1))
 
     def test_dropna(self, closed):
 
@@ -939,11 +944,9 @@ def test_datetime(self, tz):
         assert iv_false not in index
 
         # .contains does check individual points
-        assert not index.contains(Timestamp('2000-01-01', tz=tz))
-        assert index.contains(Timestamp('2000-01-01T12', tz=tz))
-        assert index.contains(Timestamp('2000-01-02', tz=tz))
-        assert index.contains(iv_true)
-        assert not index.contains(iv_false)
+        assert not index.contains(Timestamp('2000-01-01', tz=tz)).any()
+        assert index.contains(Timestamp('2000-01-01T12', tz=tz)).any()
+        assert index.contains(Timestamp('2000-01-02', tz=tz)).any()
 
         # test get_indexer
         start = Timestamp('1999-12-31T12:00', tz=tz)

pandas/tests/indexes/period/test_indexing.py

@@ -464,19 +464,13 @@ def test_contains(self):
         idx0 = pd.PeriodIndex(ps0)
 
         for p in ps0:
-            assert idx0.contains(p)
             assert p in idx0
-
-            assert idx0.contains(str(p))
             assert str(p) in idx0
 
-        assert idx0.contains('2017-09-01 00:00:01')
         assert '2017-09-01 00:00:01' in idx0
 
-        assert idx0.contains('2017-09')
         assert '2017-09' in idx0
 
-        assert not idx0.contains(p3)
         assert p3 not in idx0
 
     def test_get_value(self):

pandas/tests/indexes/test_base.py

@@ -2159,6 +2159,11 @@ def test_tab_complete_warning(self, ip):
             with provisionalcompleter('ignore'):
                 list(ip.Completer.completions('idx.', 4))
 
+    def test_deprecated_contains(self):
+        for index in self.indices.values():
+            with tm.assert_produces_warning(FutureWarning):
+                index.contains(1)
+
 
 class TestMixedIntIndex(Base):
     # Mostly the tests from common.py for which the results differ

pandas/tests/indexes/test_range.py

@@ -273,10 +273,12 @@ def test_cached_data(self):
         91 in idx
         assert idx._cached_data is None
 
-        idx.contains(90)
+        with tm.assert_produces_warning(FutureWarning):
+            idx.contains(90)
         assert idx._cached_data is None
 
-        idx.contains(91)
+        with tm.assert_produces_warning(FutureWarning):
+            idx.contains(91)
         assert idx._cached_data is None
 
         idx.all()