BUG: Fix IntervalIndex.insert to allow inserting NaN (#18300)

Author: jschendel

doc/source/whatsnew/v0.22.0.txt

@@ -78,6 +78,7 @@ Other API Changes
 - :func:`Index.map` can now accept ``Series`` and dictionary input objects (:issue:`12756`).
 - :func:`Dataframe.unstack` will now default to filling with ``np.nan`` for ``object`` columns. (:issue:`12815`)
 - :class:`IntervalIndex` constructor will raise if the ``closed`` parameter conflicts with how the input data is inferred to be closed (:issue:`18421`)
+- Inserting missing values into indexes will work for all types of indexes and automatically insert the correct type of missing value (``NaN``, ``NaT``, etc.) regardless of the type passed in (:issue:`18295`)
 
 
 .. _whatsnew_0220.deprecations:

pandas/core/indexes/base.py

@@ -3767,6 +3767,10 @@ def insert(self, loc, item):
         -------
         new_index : Index
         """
+        if is_scalar(item) and isna(item):
+            # GH 18295
+            item = self._na_value
+
         _self = np.asarray(self)
         item = self._coerce_scalar_to_index(item)._values
         idx = np.concatenate((_self[:loc], item, _self[loc:]))

pandas/core/indexes/category.py

@@ -12,7 +12,7 @@
     is_scalar)
 from pandas.core.common import (_asarray_tuplesafe,
                                 _values_from_object)
-from pandas.core.dtypes.missing import array_equivalent
+from pandas.core.dtypes.missing import array_equivalent, isna
 from pandas.core.algorithms import take_1d
 
 
@@ -690,7 +690,7 @@ def insert(self, loc, item):
 
         """
         code = self.categories.get_indexer([item])
-        if (code == -1):
+        if (code == -1) and not (is_scalar(item) and isna(item)):
             raise TypeError("cannot insert an item into a CategoricalIndex "
                             "that is not already an existing category")
 

pandas/core/indexes/datetimes.py

@@ -1768,6 +1768,9 @@ def insert(self, loc, item):
         -------
         new_index : Index
         """
+        if is_scalar(item) and isna(item):
+            # GH 18295
+            item = self._na_value
 
         freq = None
 
@@ -1784,14 +1787,14 @@ def insert(self, loc, item):
                 elif (loc == len(self)) and item - self.freq == self[-1]:
                     freq = self.freq
             item = _to_m8(item, tz=self.tz)
+
         try:
             new_dates = np.concatenate((self[:loc].asi8, [item.view(np.int64)],
                                         self[loc:].asi8))
             if self.tz is not None:
                 new_dates = conversion.tz_convert(new_dates, 'UTC', self.tz)
             return DatetimeIndex(new_dates, name=self.name, freq=freq,
                                  tz=self.tz)
-
         except (AttributeError, TypeError):
 
             # fall back to object index

pandas/core/indexes/interval.py

@@ -1001,14 +1001,21 @@ def delete(self, loc):
         return self._shallow_copy(new_left, new_right)
 
     def insert(self, loc, item):
-        if not isinstance(item, Interval):
-            raise ValueError('can only insert Interval objects into an '
-                             'IntervalIndex')
-        if not item.closed == self.closed:
-            raise ValueError('inserted item must be closed on the same side '
-                             'as the index')
-        new_left = self.left.insert(loc, item.left)
-        new_right = self.right.insert(loc, item.right)
+        if isinstance(item, Interval):
+            if item.closed != self.closed:
+                raise ValueError('inserted item must be closed on the same '
+                                 'side as the index')
+            left_insert = item.left
+            right_insert = item.right
+        elif is_scalar(item) and isna(item):
+            # GH 18295
+            left_insert = right_insert = item
+        else:
+            raise ValueError('can only insert Interval objects and NA into '
+                             'an IntervalIndex')
+
+        new_left = self.left.insert(loc, left_insert)
+        new_right = self.right.insert(loc, right_insert)
         return self._shallow_copy(new_left, new_right)
 
     def _as_like_interval_index(self, other, error_msg):

pandas/core/indexes/timedeltas.py

@@ -852,16 +852,18 @@ def insert(self, loc, item):
         -------
         new_index : Index
         """
-
         # try to convert if possible
         if _is_convertible_to_td(item):
             try:
                 item = Timedelta(item)
             except Exception:
                 pass
+        elif is_scalar(item) and isna(item):
+            # GH 18295
+            item = self._na_value
 
         freq = None
-        if isinstance(item, Timedelta) or item is NaT:
+        if isinstance(item, Timedelta) or (is_scalar(item) and isna(item)):
 
             # check freq can be preserved on edge cases
             if self.freq is not None:

pandas/tests/indexes/datetimes/test_indexing.py

@@ -145,6 +145,13 @@ def test_insert(self):
                 assert result.tz == expected.tz
                 assert result.freq is None
 
+        # GH 18295 (test missing)
+        expected = DatetimeIndex(
+            ['20170101', pd.NaT, '20170102', '20170103', '20170104'])
+        for na in (np.nan, pd.NaT, None):
+            result = date_range('20170101', periods=4).insert(1, na)
+            tm.assert_index_equal(result, expected)
+
     def test_delete(self):
         idx = date_range(start='2000-01-01', periods=5, freq='M', name='idx')
 

pandas/tests/indexes/period/test_period.py

@@ -695,3 +695,11 @@ def test_join_self(self, how):
         index = period_range('1/1/2000', periods=10)
         joined = index.join(index, how=how)
         assert index is joined
+
+    def test_insert(self):
+        # GH 18295 (test missing)
+        expected = PeriodIndex(
+            ['2017Q1', pd.NaT, '2017Q2', '2017Q3', '2017Q4'], freq='Q')
+        for na in (np.nan, pd.NaT, None):
+            result = period_range('2017Q1', periods=4, freq='Q').insert(1, na)
+            tm.assert_index_equal(result, expected)

pandas/tests/indexes/test_base.py

@@ -459,6 +459,12 @@ def test_insert(self):
         null_index = Index([])
         tm.assert_index_equal(Index(['a']), null_index.insert(0, 'a'))
 
+        # GH 18295 (test missing)
+        expected = Index(['a', np.nan, 'b', 'c'])
+        for na in (np.nan, pd.NaT, None):
+            result = Index(list('abc')).insert(1, na)
+            tm.assert_index_equal(result, expected)
+
     def test_delete(self):
         idx = Index(['a', 'b', 'c', 'd'], name='idx')
 

pandas/tests/indexes/test_category.py

@@ -362,6 +362,12 @@ def test_insert(self):
         # invalid
         pytest.raises(TypeError, lambda: ci.insert(0, 'd'))
 
+        # GH 18295 (test missing)
+        expected = CategoricalIndex(['a', np.nan, 'a', 'b', 'c', 'b'])
+        for na in (np.nan, pd.NaT, None):
+            result = CategoricalIndex(list('aabcb')).insert(1, na)
+            tm.assert_index_equal(result, expected)
+
     def test_delete(self):
 
         ci = self.create_index()