Merge pull request #6330 from jreback/align

BUG: Regression in join of non_unique_indexes (GH6329)

Author: jreback

doc/source/release.rst

@@ -90,6 +90,7 @@ Bug Fixes
 - ``HDFStore.remove`` now handles start and stop (:issue:`6177`)
 - ``HDFStore.select_as_multiple`` handles start and stop the same way as ``select`` (:issue:`6177`)
 - ``HDFStore.select_as_coordinates`` and ``select_column`` works where clauses that result in filters (:issue:`6177`)
+- Regression in join of non_unique_indexes (:issue:`6329`)
 
 pandas 0.13.1
 -------------

pandas/core/ops.py

@@ -476,16 +476,15 @@ def wrapper(left, right, name=name):
             wrap_results = time_converted.wrap_results
 
         if isinstance(rvalues, pd.Series):
-            join_idx, lidx, ridx = left.index.join(rvalues.index, how='outer',
-                                                   return_indexers=True)
-            rindex = rvalues.index
+            rindex = getattr(rvalues,'index',rvalues)
             name = _maybe_match_name(left, rvalues)
             lvalues = getattr(lvalues, 'values', lvalues)
             rvalues = getattr(rvalues, 'values', rvalues)
             if left.index.equals(rindex):
                 index = left.index
             else:
-                index = join_idx
+                index, lidx, ridx = left.index.join(rindex, how='outer',
+                                                       return_indexers=True)
 
                 if lidx is not None:
                     lvalues = com.take_1d(lvalues, lidx)

vb_suite/join_merge.py

@@ -202,3 +202,23 @@ def sample(values, k):
 """
 
 stmt = "ordered_merge(left, right, on='key', left_by='group')"
+
+#----------------------------------------------------------------------
+# outer join of non-unique
+# GH 6329
+
+setup = common_setup + """
+date_index = pd.date_range('01-Jan-2013', '23-Jan-2013', freq='T')
+daily_dates = date_index.to_period('D').to_timestamp('S','S')
+fracofday = date_index.view(np.ndarray) - daily_dates.view(np.ndarray)
+fracofday = fracofday.astype('timedelta64[ns]').astype(np.float64)/864e11
+fracofday = pd.TimeSeries(fracofday, daily_dates)
+index = pd.date_range(date_index.min().to_period('A').to_timestamp('D','S'),
+                      date_index.max().to_period('A').to_timestamp('D','E'),
+                      freq='D')
+temp = pd.TimeSeries(1.0, index)
+"""
+
+join_non_unique_equal = Benchmark('fracofday * temp[fracofday.index]', setup,
+                                   start_date=datetime(2013 1, 1))
+