ENH: re #720, added alternative private constructor

Author: adamklein

pandas/core/frame.py

@@ -4055,12 +4055,18 @@ def complete_dataframe(obj, prev_completions):
     except Exception:
         pass
 
-def _indexer_from_factorized(labels, shape):
+def _indexer_from_factorized(labels, shape, compress=True):
     from pandas.core.groupby import get_group_index, _compress_group_index
 
     group_index = get_group_index(labels, shape)
-    comp_ids, obs_ids = _compress_group_index(group_index)
-    max_group = len(obs_ids)
+
+    if compress:
+        comp_ids, obs_ids = _compress_group_index(group_index)
+        max_group = len(obs_ids)
+    else:
+        comp_ids = group_index
+        max_group = np.prod(shape)
+
     indexer, _ = lib.groupsort_indexer(comp_ids.astype('i4'), max_group)
 
     return indexer

pandas/core/groupby.py

@@ -1324,8 +1324,9 @@ def _get_slice(slob):
 
 def get_group_index(label_list, shape):
     """
-    Gets the offsets into what would be the cartesian product of all
-    possible labels given the label_list.
+    For the particular label_list, gets the offsets into the hypothetical list
+    representing the totally ordered cartesian product of all possible label
+    combinations.
     """
     if len(label_list) == 1:
         return label_list[0]
@@ -1409,24 +1410,38 @@ def cython_aggregate(values, group_index, ngroups, how='add'):
 # sorting levels...cleverly?
 
 def _compress_group_index(group_index, sort=True):
+    """
+    Group_index is offsets into cartesian product of all possible labels. This
+    space can be huge, so this function compresses it, by computing offsets
+    (comp_ids) into the list of unique labels (obs_group_ids).
+    """
+
     uniques = []
     table = lib.Int64HashTable(len(group_index))
 
     group_index = _ensure_int64(group_index)
+
+    # note, group labels come out ascending (ie, 1,2,3 etc)
     comp_ids = table.get_labels_groupby(group_index, uniques)
 
-    # these are the ones we observed
+    # these are the unique ones we observed, in the order we observed them
     obs_group_ids = np.array(uniques, dtype='i8')
 
     if sort and len(obs_group_ids) > 0:
+        # sorter is index where elements ought to go
         sorter = obs_group_ids.argsort()
+
+        # reverse_indexer is where elements came from
         reverse_indexer = np.empty(len(sorter), dtype='i4')
         reverse_indexer.put(sorter, np.arange(len(sorter)))
 
         mask = comp_ids < 0
+
+        # move comp_ids to right locations (ie, unsort ascending labels)
         comp_ids = reverse_indexer.take(comp_ids)
         np.putmask(comp_ids, mask, -1)
 
+        # sort observed ids
         obs_group_ids = obs_group_ids.take(sorter)
 
     return comp_ids, obs_group_ids

pandas/core/index.py

@@ -1095,6 +1095,16 @@ def copy(self, order='C'):
     def dtype(self):
         return np.dtype('O')
 
+    @staticmethod
+    def _from_elements(self, values, labels=None, levels=None, names=None,
+                       sortorder=None):
+        index = values.view(MultiIndex)
+        index.levels = levels
+        index.labels = labels
+        index.names  = names
+        index.sortorder = sortorder
+        return index
+
     def _get_level_number(self, level):
         try:
             count = self.names.count(level)
@@ -1527,14 +1537,17 @@ def sortlevel(self, level=0, ascending=True):
         level = self._get_level_number(level)
         primary = labels.pop(level)
         indexer = _indexer_from_factorized((primary,) + tuple(labels),
-                                           self.levshape)
+                                           self.levshape, compress=False)
         if not ascending:
             indexer = indexer[::-1]
 
         new_labels = [lab.take(indexer) for lab in self.labels]
 
-        new_index = MultiIndex(levels=self.levels, labels=new_labels,
-                               names=self.names, sortorder=level)
+        new_index = self._from_elements(self.values.take(indexer),
+                                        labels = new_labels,
+                                        levels = self.levels,
+                                        names = self.names,
+                                        sortorder = level)
 
         return new_index, indexer
 

vb_suite/suite.py

@@ -44,7 +44,7 @@
 """
 dependencies = ['pandas_vb_common.py']
 
-START_DATE = datetime(2010, 6, 1)
+START_DATE = datetime(2012, 1, 20)
 
 repo = GitRepo(REPO_PATH)