BUG: Ensure data_columns is always an Index

Author: toobaz

pandas/io/pytables.py

@@ -3307,6 +3307,7 @@ def validate_data_columns(self, data_columns, min_itemsize):
             return []
 
         axis, axis_labels = self.non_index_axes[0]
+        axis_labels = Index(axis_labels)
         info = self.info.get(axis, dict())
         if info.get('type') == 'MultiIndex' and data_columns:
             raise ValueError("cannot use a multi-index on axis [{0}] with "
@@ -3317,19 +3318,21 @@ def validate_data_columns(self, data_columns, min_itemsize):
         if data_columns is True:
             data_columns = axis_labels
         elif data_columns is None:
-            data_columns = []
+            data_columns = Index([])
+        elif not isinstance(data_columns, Index):
+            # Support e.g. FrozenLists data_columns
+            data_columns = Index(iter(data_columns))
 
         # if min_itemsize is a dict, add the keys (exclude 'values')
         if isinstance(min_itemsize, dict):
 
-            existing_data_columns = set(data_columns)
-            data_columns.extend([
-                k for k in min_itemsize.keys()
-                if k != 'values' and k not in existing_data_columns
-            ])
+            missing_data_columns = Index(
+                [k for k in min_itemsize.keys()
+                 if k != 'values']).difference(data_columns)
+            data_columns = data_columns.append(missing_data_columns)
 
         # return valid columns in the order of our axis
-        return [c for c in data_columns if c in axis_labels]
+        return axis_labels.intersection(data_columns)
 
     def create_axes(self, axes, obj, validate=True, nan_rep=None,
                     data_columns=None, min_itemsize=None, **kwargs):
@@ -3450,7 +3453,7 @@ def get_blk_items(mgr, blocks):
                 data_columns, min_itemsize)
             if len(data_columns):
                 mgr = block_obj.reindex_axis(
-                    Index(axis_labels).difference(Index(data_columns)),
+                    Index(axis_labels).difference(data_columns),
                     axis=axis
                 )._data
 
@@ -3490,7 +3493,7 @@ def get_blk_items(mgr, blocks):
             name = None
 
             # we have a data_column
-            if (data_columns and len(b_items) == 1 and
+            if (len(data_columns) and len(b_items) == 1 and
                     b_items[0] in data_columns):
                 klass = DataIndexableCol
                 name = b_items[0]
@@ -4252,13 +4255,16 @@ def table_type_short(self):
 
     def write(self, obj, data_columns=None, **kwargs):
         if data_columns is None:
-            data_columns = []
+            data_columns = Index([])
         elif data_columns is True:
             data_columns = obj.columns[:]
+        elif not isinstance(data_columns, Index):
+            # Support e.g. FrozenLists data_columns
+            data_columns = Index(iter(data_columns))
         obj, self.levels = self.validate_multiindex(obj)
-        for n in self.levels:
-            if n not in data_columns:
-                data_columns.insert(0, n)
+        # Place elements of lev not in data_columns first, then data_columns
+        miss_data_columns = Index(self.levels).difference(data_columns)
+        data_columns = miss_data_columns.union(data_columns)
         return super(AppendableMultiFrameTable, self).write(
             obj=obj, data_columns=data_columns, **kwargs)