Merge pull request #10055 from ajamian/master

BUG: read_hdf modifying passed columns list (GH7212)

Author: shoyer

doc/source/whatsnew/v0.17.0.txt

@@ -60,6 +60,8 @@ Performance Improvements
 Bug Fixes
 ~~~~~~~~~
 
+- Bug where read_hdf store.select modifies the passed columns list when
+  multi-indexed (:issue:`7212`)
 - Bug in ``Categorical`` repr with ``display.width`` of ``None`` in Python 3 (:issue:`10087`)
 
 

pandas/io/pytables.py

@@ -3453,6 +3453,10 @@ def get_blk_items(mgr, blocks):
     def process_axes(self, obj, columns=None):
         """ process axes filters """
 
+        # make a copy to avoid side effects
+        if columns is not None:
+            columns = list(columns)
+
         # make sure to include levels if we have them
         if columns is not None and self.is_multi_index:
             for n in self.levels:

pandas/io/tests/test_pytables.py

@@ -4617,6 +4617,29 @@ def test_preserve_timedeltaindex_type(self):
             store['df'] = df
             assert_frame_equal(store['df'], df)
 
+    def test_colums_multiindex_modified(self):
+        # BUG: 7212
+        # read_hdf store.select modified the passed columns parameters
+        # when multi-indexed.
+
+        df = DataFrame(np.random.rand(4, 5),
+                       index=list('abcd'),
+                       columns=list('ABCDE'))
+        df.index.name = 'letters'
+        df = df.set_index(keys='E', append=True)
+
+        data_columns = df.index.names+df.columns.tolist()
+        with ensure_clean_path(self.path) as path:
+            df.to_hdf(path, 'df',
+                      mode='a',
+                      append=True,
+                      data_columns=data_columns,
+                      index=False)
+            cols2load = list('BCD')
+            cols2load_original = list(cols2load)
+            df_loaded = read_hdf(path, 'df', columns=cols2load)
+            self.assertTrue(cols2load_original == cols2load)
+
 
 def _test_sort(obj):
     if isinstance(obj, DataFrame):