Merge pull request #3136 from jreback/GH2437_2

ENH: GH2437 added selection to an unordered timeseries

Author: jreback

RELEASE.rst

@@ -203,6 +203,8 @@ pandas 0.11.0
   - series.plot(kind='bar') now respects pylab color schem (GH3115_)
   - Fixed bug in reshape if not passed correct input, now raises TypeError (GH2719_)
   - Fix NameError issue on RESO_US (GH2787_)
+  - Allow selection in an *unordered* timeseries to work similary 
+    to an *ordered* timeseries (GH2437_).
 
  .. _GH2758: https://github.com/pydata/pandas/issues/2758
 .. _GH2809: https://github.com/pydata/pandas/issues/2809
@@ -229,6 +231,7 @@ pandas 0.11.0
 .. _GH2776: https://github.com/pydata/pandas/issues/2776
 .. _GH2778: https://github.com/pydata/pandas/issues/2778
 .. _GH2787: https://github.com/pydata/pandas/issues/2787
+.. _GH2437: https://github.com/pydata/pandas/issues/2437
 .. _GH2793: https://github.com/pydata/pandas/issues/2793
 .. _GH2795: https://github.com/pydata/pandas/issues/2795
 .. _GH2819: https://github.com/pydata/pandas/issues/2819

doc/source/v0.11.0.txt

@@ -243,6 +243,8 @@ Enhancements
   - In ``HDFStore``, new keywords ``iterator=boolean``, and ``chunksize=number_in_a_chunk`` are
     provided to support iteration on ``select`` and ``select_as_multiple`` (GH3076_)
 
+  - You can now select timestamps from an *unordered* timeseries similarly to an *ordered* timeseries (GH2437_)
+
   - ``Squeeze`` to possibly remove length 1 dimensions from an object.
 
     .. ipython:: python
@@ -293,6 +295,7 @@ See the `full release notes
 <https://github.com/pydata/pandas/blob/master/RELEASE.rst>`__ or issue tracker
 on GitHub for a complete list.
 
+.. _GH2437: https://github.com/pydata/pandas/issues/2437
 .. _GH2809: https://github.com/pydata/pandas/issues/2809
 .. _GH2810: https://github.com/pydata/pandas/issues/2810
 .. _GH2837: https://github.com/pydata/pandas/issues/2837

pandas/tseries/index.py

@@ -1042,9 +1042,6 @@ def intersection(self, other):
             return self._view_like(left_chunk)
 
     def _partial_date_slice(self, reso, parsed):
-        if not self.is_monotonic:
-            raise TimeSeriesError('Partial indexing only valid for ordered '
-                                  'time series.')
 
         if reso == 'year':
             t1 = Timestamp(datetime(parsed.year, 1, 1), tz=self.tz)
@@ -1079,11 +1076,19 @@ def _partial_date_slice(self, reso, parsed):
                                      tz=self.tz).value - 1)
         else:
             raise KeyError
+        
 
         stamps = self.asi8
-        left = stamps.searchsorted(t1.value, side='left')
-        right = stamps.searchsorted(t2.value, side='right')
-        return slice(left, right)
+
+        if self.is_monotonic:
+
+            # a monotonic (sorted) series can be sliced
+            left = stamps.searchsorted(t1.value, side='left')
+            right = stamps.searchsorted(t2.value, side='right')
+            return slice(left, right)
+
+        # try to find a the dates
+        return ((stamps>=t1.value) & (stamps<=t2.value)).nonzero()[0]
 
     def _possibly_promote(self, other):
         if other.inferred_type == 'date':

pandas/tseries/tests/test_timeseries.py

@@ -18,6 +18,7 @@
 import pandas.core.datetools as datetools
 import pandas.tseries.offsets as offsets
 import pandas.tseries.frequencies as fmod
+from pandas.tseries.index import TimeSeriesError
 import pandas as pd
 
 from pandas.util.testing import assert_series_equal, assert_almost_equal
@@ -168,6 +169,32 @@ def test_indexing_over_size_cutoff(self):
         finally:
             _index._SIZE_CUTOFF = old_cutoff
 
+    def test_indexing_unordered(self):
+
+        # GH 2437
+        from pandas import concat
+        rng = date_range(start='2011-01-01', end='2011-01-15')
+        ts  = Series(randn(len(rng)), index=rng)
+        ts2 = concat([ts[0:4],ts[-4:],ts[4:-4]])
+
+        for t in ts.index:
+            s = str(t)
+            expected = ts[t]
+            result = ts2[t]
+            self.assertTrue(expected == result)
+
+        result = ts2['2011'].sort_index()
+        expected = ts['2011']
+        assert_series_equal(result,expected)
+
+        # diff freq
+        rng = date_range(datetime(2005, 1, 1), periods=20, freq='M')
+        ts = Series(np.arange(len(rng)), index=rng)
+        ts = ts.take(np.random.permutation(20))
+
+        result = ts['2005']
+        for t in result.index:
+            self.assertTrue(t.year == 2005)
 
 def assert_range_equal(left, right):
     assert(left.equals(right))
@@ -2017,13 +2044,6 @@ def test_partial_slice_minutely(self):
         self.assert_(s['2005-1-1 23:59:00'] == s.ix[0])
         self.assertRaises(Exception, s.__getitem__, '2004-12-31 00:00:00')
 
-    def test_partial_not_monotonic(self):
-        rng = date_range(datetime(2005, 1, 1), periods=20, freq='M')
-        ts = Series(np.arange(len(rng)), index=rng)
-        ts = ts.take(np.random.permutation(20))
-
-        self.assertRaises(Exception, ts.__getitem__, '2005')
-
     def test_date_range_normalize(self):
         snap = datetime.today()
         n = 50