ENH: Add length attribute to Interval and IntervalIndex

Author: jschendel

doc/source/whatsnew/v0.22.0.txt

@@ -139,6 +139,7 @@ Other Enhancements
 - :func:`read_excel()` has gained the ``nrows`` parameter (:issue:`16645`)
 - :func:``DataFrame.to_json`` and ``Series.to_json`` now accept an ``index`` argument which allows the user to exclude the index from the JSON output (:issue:`17394`)
 - ``IntervalIndex.to_tuples()`` has gained the ``na_tuple`` parameter to control whether NA is returned as a tuple of NA, or NA itself (:issue:`18756`)
+- :class:`Interval` and :class:`IntervalIndex` have gained a ``length`` attribute (:issue:`18789`)
 
 .. _whatsnew_0220.api_breaking:
 

pandas/_libs/interval.pyx

@@ -54,7 +54,12 @@ cdef class IntervalMixin(object):
             return 0.5 * (self.left + self.right)
         except TypeError:
             # datetime safe version
-            return self.left + 0.5 * (self.right - self.left)
+            return self.left + 0.5 * self.length
+
+    @property
+    def length(self):
+        """Return the length of the Interval"""
+        return self.right - self.left
 
 
 cdef _interval_like(other):

pandas/core/indexes/interval.py

@@ -599,6 +599,14 @@ def closed(self):
         """
         return self._closed
 
+    @property
+    def length(self):
+        """
+        Return an Index with entries denoting the length of each Interval in
+        the IntervalIndex
+        """
+        return self.right - self.left
+
     def __len__(self):
         return len(self.left)
 
@@ -683,11 +691,10 @@ def mid(self):
         Return the midpoint of each Interval in the IntervalIndex as an Index
         """
         try:
-            return Index(0.5 * (self.left.values + self.right.values))
+            return 0.5 * (self.left + self.right)
         except TypeError:
             # datetime safe version
-            delta = self.right - self.left
-            return self.left + 0.5 * delta
+            return self.left + 0.5 * self.length
 
     @cache_readonly
     def is_monotonic(self):

pandas/tests/indexes/test_interval.py

@@ -283,6 +283,23 @@ def test_properties(self, closed):
         tm.assert_numpy_array_equal(np.asarray(index), expected)
         tm.assert_numpy_array_equal(index.values, expected)
 
+    @pytest.mark.parametrize('breaks', [
+        [1, 1, 2, 5, 15, 53, 217, 1014, 5335, 31240, 201608],
+        [-np.inf, -100, -10, 0.5, 1, 1.5, 3.8, 101, 202, np.inf],
+        pd.to_datetime(['20170101', '20170202', '20170303', '20170404']),
+        pd.to_timedelta(['1ns', '2ms', '3s', '4M', '5H', '6D'])])
+    def test_length(self, closed, breaks):
+        index = IntervalIndex.from_breaks(breaks, closed=closed)
+        result = index.length
+        expected = Index(iv.length for iv in index)
+        tm.assert_index_equal(result, expected)
+
+        # with NA
+        index = index.insert(1, np.nan)
+        result = index.length
+        expected = Index(iv.length if notna(iv) else iv for iv in index)
+        tm.assert_index_equal(result, expected)
+
     def test_with_nans(self, closed):
         index = self.create_index(closed=closed)
         assert not index.hasnans

pandas/tests/scalar/test_interval.py

@@ -1,6 +1,7 @@
 from __future__ import division
 
-from pandas import Interval, Timestamp
+import numpy as np
+from pandas import Interval, Timestamp, Timedelta
 from pandas.core.common import _any_none
 
 import pytest
@@ -66,6 +67,36 @@ def test_hash(self, interval):
         # should not raise
         hash(interval)
 
+    @pytest.mark.parametrize('left, right, expected', [
+        (0, 5, 5),
+        (-2, 5.5, 7.5),
+        (10, 10, 0),
+        (10, np.inf, np.inf),
+        (-np.inf, -5, np.inf),
+        (-np.inf, np.inf, np.inf),
+        (Timedelta('0 days'), Timedelta('5 days'), Timedelta('5 days')),
+        (Timedelta('10 days'), Timedelta('10 days'), Timedelta('0 days')),
+        (Timedelta('1H10M'), Timedelta('5H5M'), Timedelta('3H55M')),
+        (Timedelta('5S'), Timedelta('1H'), Timedelta('59M55S'))])
+    def test_length(self, left, right, expected):
+        # GH 18789
+        iv = Interval(left, right)
+        result = iv.length
+        assert result == expected
+
+    @pytest.mark.parametrize('left, right, expected', [
+        ('2017-01-01', '2017-01-06', '5 days'),
+        ('2017-01-01', '2017-01-01 12:00:00', '12 hours'),
+        ('2017-01-01 12:00', '2017-01-01 12:00:00', '0 days'),
+        ('2017-01-01 12:01', '2017-01-05 17:31:00', '4 days 5 hours 30 min')])
+    @pytest.mark.parametrize('tz', (None, 'UTC', 'CET', 'US/Eastern'))
+    def test_length_timestamp(self, tz, left, right, expected):
+        # GH 18789
+        iv = Interval(Timestamp(left, tz=tz), Timestamp(right, tz=tz))
+        result = iv.length
+        expected = Timedelta(expected)
+        assert result == expected
+
     def test_math_add(self, interval):
         expected = Interval(1, 2)
         actual = interval + 1