ENH: test suite passes, deleted old join code, #220, #249, #267 complete

Author: wesm

pandas/core/internals.py

@@ -825,35 +825,6 @@ def _is_indexed_like(self, other):
                 return False
         return True
 
-    def join_on(self, other, on, how='left', axis=1, lsuffix=None,
-                rsuffix=None):
-        this, other = self._maybe_rename_join(other, lsuffix, rsuffix)
-
-        other_axis = other.axes[axis]
-        indexer = other_axis.get_indexer(on)
-
-        if how == 'left':
-            mask = indexer == -1
-            needs_masking = len(on) > 0 and mask.any()
-        else:
-            mask = indexer != -1
-            this = this.take(mask.nonzero()[0], axis=axis)
-            indexer = indexer[mask]
-            mask = None
-            needs_masking = False
-
-        other_blocks = []
-        for block in other.blocks:
-            newb = block.reindex_axis(indexer, mask, needs_masking, axis=axis)
-            other_blocks.append(newb)
-
-        cons_items = this.items + other.items
-        consolidated = _consolidate(this.blocks + other_blocks, cons_items)
-
-        new_axes = list(this.axes)
-        new_axes[0] = cons_items
-        return BlockManager(consolidated, new_axes)
-
     def rename_axis(self, mapper, axis=1):
         new_axis = Index([mapper(x) for x in self.axes[axis]])
         new_axis._verify_integrity()

pandas/tools/merge.py

@@ -30,15 +30,21 @@ def merge(left, right, how='left', on=None, left_on=None, right_on=None,
         * outer: use union of keys from both frames (SQL: full outer join)
         * inner: use intersection of keys from both frames (SQL: inner join)
     on : label or list
-        Field names to join on. Must be found in both DataFrames
-    left_on : label or list
-        Field names to join on in left DataFrame
-    right_on : label or list
-        Field names to join on in right DataFrame
+        Field names to join on. Must be found in both DataFrames.
+    left_on : label or list, or array-like
+        Field names to join on in left DataFrame. Can be a vector or list of
+        vectors of the length of the DataFrame to use a particular vector as
+        the join key instead of columns
+    right_on : label or list, or array-like
+        Field names to join on in right DataFrame or vector/list of vectors per
+        left_on docs
     left_index : boolean, default True
-        Use the index from the left DataFrame as the join key
+        Use the index from the left DataFrame as the join key(s). If it is a
+        MultiIndex, the number of keys in the other DataFrame (either the index
+        or a number of columns) must match the number of levels
     right_index : boolean, default True
-        Use the index from the right DataFrame as the join key
+        Use the index from the right DataFrame as the join key. Same caveats as
+        left_index
     sort : boolean, default True
         Sort the join keys lexicographically in the result DataFrame
     suffixes : 2-length sequence (tuple, list, ...)
@@ -64,13 +70,6 @@ def merge(left, right, how='left', on=None, left_on=None, right_on=None,
 # TODO: transformations??
 # TODO: only copy DataFrames when modification necessary
 
-# def join_managers(left, right, axis=1, how='left', copy=True):
-#     join_index, left_indexer, right_indexer = \
-#         left.axes[axis].join(right.axes[axis], how=how, return_indexers=True)
-#     op = _BlockJoinOperation(left, right, join_index, left_indexer,
-#                              right_indexer, axis=axis)
-#     return op.get_result(copy=copy)
-
 class _MergeOperation(object):
     """