BUG: (GH3748) Incorrectly read a HDFStore multi-index Frame witha column specification

RELEASE.rst

@@ -81,6 +81,8 @@ pandas 0.11.1
 
   - When removing an object from a ``HDFStore``, ``remove(key)`` raises
     ``KeyError`` if the key is not a valid store object.
+  - In an ``HDFStore``, raise a ``TypeError`` on passing ``where`` or ``columns`` 
+    to select with a Storer; these are invalid parameters at this time
   - The repr() for (Multi)Index now obeys display.max_seq_items rather
     then numpy threshold print options. (GH3426_, GH3466_)
   - Added mangle_dupe_cols option to read_table/csv, allowing users
@@ -197,6 +199,7 @@ pandas 0.11.1
     their first argument (GH3702_)
   - Fix file tokenization error with \r delimiter and quoted fields (GH3453_)
   - Groupby transform with item-by-item not upcasting correctly (GH3740_)
+  - Incorrectly read a HDFStore multi-index Frame witha column specification (GH3748_)
 
 .. _GH3164: https://github.com/pydata/pandas/issues/3164
 .. _GH2786: https://github.com/pydata/pandas/issues/2786
@@ -280,6 +283,7 @@ pandas 0.11.1
 .. _GH3667: https://github.com/pydata/pandas/issues/3667
 .. _GH3733: https://github.com/pydata/pandas/issues/3733
 .. _GH3740: https://github.com/pydata/pandas/issues/3740
+.. _GH3748: https://github.com/pydata/pandas/issues/3748
 
 pandas 0.11.0
 =============

pandas/io/pytables.py

@@ -1664,6 +1664,12 @@ def f(values, freq=None, tz=None):
             return f
         return klass
 
+    def validate_read(self, kwargs):
+        if kwargs.get('columns') is not None:
+            raise TypeError("cannot pass a column specification when reading a Storer")
+        if kwargs.get('where') is not None:
+            raise TypeError("cannot pass a where specification when reading a Storer")
+
     @property
     def is_exists(self):
         return True
@@ -1921,13 +1927,15 @@ def read_index_legacy(self, key):
 class LegacySeriesStorer(LegacyStorer):
 
     def read(self, **kwargs):
+        self.validate_read(kwargs)
         index = self.read_index_legacy('index')
         values = self.read_array('values')
         return Series(values, index=index)
 
 class LegacyFrameStorer(LegacyStorer):
 
     def read(self, **kwargs):
+        self.validate_read(kwargs)
         index = self.read_index_legacy('index')
         columns = self.read_index_legacy('columns')
         values = self.read_array('values')
@@ -1945,6 +1953,7 @@ def shape(self):
             return None
 
     def read(self, **kwargs):
+        self.validate_read(kwargs)
         index = self.read_index('index')
         if len(index) > 0:
             values = self.read_array('values')
@@ -1963,6 +1972,7 @@ class SparseSeriesStorer(GenericStorer):
     attributes = ['name','fill_value','kind']
 
     def read(self, **kwargs):
+        self.validate_read(kwargs)
         index = self.read_index('index')
         sp_values = self.read_array('sp_values')
         sp_index = self.read_index('sp_index')
@@ -1983,6 +1993,7 @@ class SparseFrameStorer(GenericStorer):
     attributes = ['default_kind','default_fill_value']
 
     def read(self, **kwargs):
+        self.validate_read(kwargs)
         columns = self.read_index('columns')
         sdict = {}
         for c in columns:
@@ -2013,6 +2024,7 @@ class SparsePanelStorer(GenericStorer):
     attributes = ['default_kind','default_fill_value']
 
     def read(self, **kwargs):
+        self.validate_read(kwargs)
         items = self.read_index('items')
 
         sdict = {}
@@ -2075,6 +2087,8 @@ def shape(self):
             return None
 
     def read(self, **kwargs):
+        self.validate_read(kwargs)
+
         axes = []
         for i in xrange(self.ndim):
             ax = self.read_index('axis%d' % i)
@@ -3124,8 +3138,12 @@ def write(self, obj, data_columns=None, **kwargs):
         self.levels = obj.index.names
         return super(AppendableMultiFrameTable, self).write(obj=obj.reset_index(), data_columns=data_columns, **kwargs)
 
-    def read(self, *args, **kwargs):
-        df = super(AppendableMultiFrameTable, self).read(*args, **kwargs)
+    def read(self, columns=None, **kwargs):
+        if columns is not None:
+            for n in self.levels:
+                if n not in columns:
+                    columns.insert(0, n)
+        df = super(AppendableMultiFrameTable, self).read(columns=columns, **kwargs)
         df.set_index(self.levels, inplace=True)
         return df
 

pandas/io/tests/test_pytables.py

@@ -1072,6 +1072,26 @@ def test_append_hierarchical(self):
             result = store.select('mi')
             tm.assert_frame_equal(result, df)
 
+            # GH 3748
+            result = store.select('mi',columns=['A','B'])
+            expected = df.reindex(columns=['A','B'])
+            tm.assert_frame_equal(result,expected)
+
+        with tm.ensure_clean('test.hdf') as path:
+            df.to_hdf(path,'df',table=True)
+            result = read_hdf(path,'df',columns=['A','B'])
+            expected = df.reindex(columns=['A','B'])
+            tm.assert_frame_equal(result,expected)
+
+    def test_pass_spec_to_storer(self):
+
+        df = tm.makeDataFrame()
+
+        with ensure_clean(self.path) as store:
+            store.put('df',df)
+            self.assertRaises(TypeError, store.select, 'df', columns=['A'])
+            self.assertRaises(TypeError, store.select, 'df',where=[('columns=A')])
+
     def test_append_misc(self):
 
         with ensure_clean(self.path) as store: