BUG GH11733

Author: stephenrauch

pandas/io/excel.py

@@ -189,7 +189,7 @@ def get_writer(engine_name):
 
 @Appender(_read_excel_doc)
 def read_excel(io, sheetname=0, header=0, skiprows=None, skip_footer=0,
-               index_col=None, names=None, parse_cols=None, parse_dates=False,
+               index_col='infer', names=None, parse_cols=None, parse_dates=False,
                date_parser=None, na_values=None, thousands=None,
                convert_float=True, has_index_names=None, converters=None,
                dtype=None, true_values=None, false_values=None, engine=None,
@@ -322,7 +322,7 @@ def _excel2num(x):
             return i in parse_cols
 
     def _parse_excel(self, sheetname=0, header=0, skiprows=None, names=None,
-                     skip_footer=0, index_col=None, has_index_names=None,
+                     skip_footer=0, index_col='infer', has_index_names=None,
                      parse_cols=None, parse_dates=False, date_parser=None,
                      na_values=None, thousands=None, convert_float=True,
                      true_values=None, false_values=None, verbose=False,
@@ -351,6 +351,12 @@ def _parse_excel(self, sheetname=0, header=0, skiprows=None, names=None,
             raise NotImplementedError("date_parser keyword of read_excel "
                                       "is not implemented")
 
+        # At the API, index_col == None means just that,
+        # but lower down it can also mean infer.
+        have_index_col = (index_col is not None)
+        if index_col == 'infer':
+            index_col = None
+
         import xlrd
         from xlrd import (xldate, XL_CELL_DATE,
                           XL_CELL_ERROR, XL_CELL_BOOLEAN,
@@ -472,10 +478,13 @@ def _parse_cell(cell_contents, cell_typ):
 
                         data[row], control_row = _fill_mi_header(
                             data[row], control_row)
-                        header_name, data[row] = _pop_header_name(
-                            data[row], index_col)
+                        if have_index_col:
+                            header_name, data[row] = _pop_header_name(
+                                data[row], index_col)
+                        else:
+                            header_name = ''
                         header_names.append(header_name)
-                else:
+                elif have_index_col:
                     data[header] = _trim_excel_header(data[header])
 
             if is_list_like(index_col):

pandas/tests/io/test_excel.py

@@ -777,6 +777,41 @@ def test_read_excel_multiindex(self):
                             header=[0, 1], skiprows=2)
         tm.assert_frame_equal(actual, expected)
 
+    def test_read_excel_multiindex_colindex_none(self):
+        # GH 11733
+        mi = MultiIndex(levels=[['Unnamed: 0_level_0', u'bar', u'foo'],
+                                ['Unnamed: 0_level_1', u'a', u'b']],
+                        labels=[[0, 2, 2, 1, 1], [0, 1, 2, 1, 2]],
+                        names=[u'', u''])
+        mi_file = os.path.join(self.dirpath, 'testmultiindex' + self.ext)
+
+        expected = DataFrame([[0, 1, 2.5, pd.Timestamp('2015-01-01'), True],
+                              [1, 2, 3.5, pd.Timestamp('2015-01-02'), False],
+                              [2, 3, 4.5, pd.Timestamp('2015-01-03'), False],
+                              [3, 4, 5.5, pd.Timestamp('2015-01-04'), True]],
+                             columns=mi)
+
+        actual = read_excel(mi_file, 'mi_column', header=[0, 1], index_col=None)
+        tm.assert_frame_equal(actual, expected)
+
+        mi = MultiIndex(levels=[[u'c1', u'bar', u'foo'],
+                                [u'c2', u'a', u'b']],
+                        labels=[[0, 2, 2, 1, 1], [0, 1, 2, 1, 2]],
+                        names=[u'', u''])
+        expected.columns = mi
+        actual = read_excel(mi_file, 'mi_column_name',
+                            header=[0, 1], index_col=None)
+        tm.assert_frame_equal(actual, expected)
+
+        mi = MultiIndex(levels=[[u'c1', u'bar', u'foo'],
+                                [u'c2', 1, 2]],
+                        labels=[[0, 2, 2, 1, 1], [0, 1, 2, 1, 2]],
+                        names=[u'', u''])
+        expected.columns = mi
+        actual = read_excel(mi_file, 'name_with_int',
+                            index_col=None, header=[0, 1])
+        tm.assert_frame_equal(actual, expected)
+
     def test_read_excel_multiindex_empty_level(self):
         # GH 12453
         _skip_if_no_xlsxwriter()
@@ -1344,8 +1379,8 @@ def test_excel_date_datetime_format(self):
                 reader1 = ExcelFile(filename1)
                 reader2 = ExcelFile(filename2)
 
-                rs1 = read_excel(reader1, 'test1', index_col=None)
-                rs2 = read_excel(reader2, 'test1', index_col=None)
+                rs1 = read_excel(reader1, 'test1')
+                rs2 = read_excel(reader2, 'test1')
 
                 tm.assert_frame_equal(rs1, rs2)
 
@@ -1486,7 +1521,7 @@ def test_to_excel_float_format(self):
             df.to_excel(filename, 'test1', float_format='%.2f')
 
             reader = ExcelFile(filename)
-            rs = read_excel(reader, 'test1', index_col=None)
+            rs = read_excel(reader, 'test1')
             xp = DataFrame([[0.12, 0.23, 0.57],
                             [12.32, 123123.20, 321321.20]],
                            index=['A', 'B'], columns=['X', 'Y', 'Z'])
@@ -1524,7 +1559,7 @@ def test_to_excel_unicode_filename(self):
             df.to_excel(filename, 'test1', float_format='%.2f')
 
             reader = ExcelFile(filename)
-            rs = read_excel(reader, 'test1', index_col=None)
+            rs = read_excel(reader, 'test1')
             xp = DataFrame([[0.12, 0.23, 0.57],
                             [12.32, 123123.20, 321321.20]],
                            index=['A', 'B'], columns=['X', 'Y', 'Z'])