Merge pull request #11172 from ajcr/ptp-handle-nan

ENH: make Series.ptp ignore NaN values (GH11163)

Author: jreback

doc/source/whatsnew/v0.17.0.txt

@@ -527,6 +527,7 @@ Other enhancements
 
 - ``pd.read_csv`` is now able to infer compression type for files read from AWS S3 storage (:issue:`11070`, :issue:`11074`).
 
+
 .. _whatsnew_0170.api:
 
 .. _whatsnew_0170.api_breaking:

doc/source/whatsnew/v0.17.1.txt

@@ -60,6 +60,7 @@ API changes
 - ``Series.sort_index()`` now correctly handles the ``inplace`` option (:issue:`11402`)
 
 - ``DataFrame.itertuples()`` now returns ``namedtuple`` objects, when possible. (:issue:`11269`)
+- ``Series.ptp`` will now ignore missing values by default (:issue:`11163`)
 
 .. _whatsnew_0171.deprecations:
 

pandas/core/generic.py

@@ -4701,6 +4701,17 @@ def stat_func(self, axis=None, skipna=None, level=None,
 want the *index* of the minimum, use ``idxmin``. This is the
 equivalent of the ``numpy.ndarray`` method ``argmin``.""", nanops.nanmin)
 
+        if cls.__name__ == 'Series':
+            def nanptp(values, axis=0, skipna=True):
+                nmax = nanops.nanmax(values, axis, skipna)
+                nmin = nanops.nanmin(values, axis, skipna)
+                return nmax - nmin
+
+            cls.ptp = _make_stat_function('ptp', """
+Returns the difference between the maximum value and the minimum
+value in the object. This is the equivalent of the ``numpy.ndarray``
+method ``ptp``.""", nanptp)
+
         def _make_logical_function(name, desc, f):
 
             @Substitution(outname=name, desc=desc)

pandas/core/series.py

@@ -1277,9 +1277,6 @@ def multi(values, qs):
 
         return self._maybe_box(lambda values: multi(values, q), dropna=True)
 
-    def ptp(self, axis=None, out=None):
-        return _values_from_object(self).ptp(axis, out)
-
     def corr(self, other, method='pearson',
              min_periods=None):
         """

pandas/tests/test_series.py

@@ -5949,6 +5949,31 @@ def test_ptp(self):
         ser = Series(arr)
         self.assertEqual(np.ptp(ser), np.ptp(arr))
 
+        # GH11163
+        s = Series([3, 5, np.nan, -3, 10])
+        self.assertEqual(s.ptp(), 13)
+        self.assertTrue(pd.isnull(s.ptp(skipna=False)))
+
+        mi = pd.MultiIndex.from_product([['a','b'], [1,2,3]])
+        s = pd.Series([1, np.nan, 7, 3, 5, np.nan], index=mi)
+
+        expected = pd.Series([6, 2], index=['a', 'b'], dtype=np.float64)
+        self.assert_series_equal(s.ptp(level=0), expected)
+
+        expected = pd.Series([np.nan, np.nan], index=['a', 'b'])
+        self.assert_series_equal(s.ptp(level=0, skipna=False), expected)
+
+        with self.assertRaises(ValueError):
+            s.ptp(axis=1)
+
+        s = pd.Series(['a', 'b', 'c', 'd', 'e'])
+        with self.assertRaises(TypeError):
+            s.ptp()
+
+        with self.assertRaises(NotImplementedError):
+            s.ptp(numeric_only=True)
+
+
     def test_asof(self):
         # array or list or dates
         N = 50