Merge pull request #184 from martindurant/index_no_name

Prevent pandas auto-names being given to index

fastparquet/api.py

@@ -7,6 +7,7 @@
 from collections import OrderedDict
 import json
 import os
+import re
 import six
 import struct
 
@@ -500,6 +501,8 @@ def get_type(name):
     dtypes.extend(['category'] * len(cs))
     df, views = dataframe.empty(dtypes, size, cols=cols, index_name=index,
                                 index_type=index_type, cats=cats)
+    if index and re.match(r'__index_level_\d+__', index):
+        df.index.name = None
     return df, views
 
 

fastparquet/test/test_api.py

@@ -275,3 +275,26 @@ def test_index_not_in_columns(tempdir):
     assert out.index.tolist() == ['x', 'y', 'z']
     out = pf.to_pandas(columns=['b'], index=False)
     assert out.index.tolist() == [0, 1, 2]
+
+
+def test_no_index_name(tempdir):
+    df = pd.DataFrame({'__index_level_0__': ['x', 'y', 'z'],
+                       'b': [4, 5, 6]}).set_index('__index_level_0__')
+    write(tempdir, df, file_scheme='hive')
+    pf = ParquetFile(tempdir)
+    out = pf.to_pandas()
+    assert out.index.name is None
+    assert out.index.tolist() == ['x', 'y', 'z']
+
+    df = pd.DataFrame({'__index_level_0__': ['x', 'y', 'z'],
+                       'b': [4, 5, 6]})
+    write(tempdir, df, file_scheme='hive')
+    pf = ParquetFile(tempdir)
+    out = pf.to_pandas(index='__index_level_0__', columns=['b'])
+    assert out.index.name is None
+    assert out.index.tolist() == ['x', 'y', 'z']
+
+    pf = ParquetFile(tempdir)
+    out = pf.to_pandas()
+    assert out.index.name is None
+    assert out.index.tolist() == [0, 1, 2]