ENH: Allow referencing of Excel columns by their Excel column names.

pandas/io/parsers.py

@@ -1312,6 +1312,8 @@ def parse(self, sheetname, header=0, skiprows=None, skip_footer=0,
             If None then parse all columns,
             If int then indicates last column to be parsed
             If list of ints then indicates list of column numbers to be parsed
+            If string then indicates comma separated list of column names and
+                column ranges (e.g. "A:E" or "A,C,E:F")
         na_values : list-like, default None
             List of additional strings to recognize as NA/NaN
 
@@ -1336,8 +1338,34 @@ def parse(self, sheetname, header=0, skiprows=None, skip_footer=0,
                                      skip_footer=skip_footer)
 
     def _should_parse(self, i, parse_cols):
+        
+        def _range2cols(areas):
+            """
+            Convert comma separated list of column names and column ranges to a
+            list of 0-based column indexes.
+
+            >>> _range2cols('A:E')
+            [0, 1, 2, 3, 4]
+            >>> _range2cols('A,C,Z:AB')
+            [0, 2, 25, 26, 27]
+            """
+            def _excel2num(x): 
+                "Convert Excel column name like 'AB' to 0-based column index"
+                return reduce(lambda s,a: s*26+ord(a)-ord('A')+1, x.upper().strip(), 0)-1
+            
+            cols = []
+            for rng in areas.split(','):
+                if ':' in rng:
+                    rng = rng.split(':')
+                    cols += range(_excel2num(rng[0]), _excel2num(rng[1])+1)
+                else:
+                    cols.append(_excel2num(rng))
+            return cols
+
         if isinstance(parse_cols, int):
             return i <= parse_cols
+        elif isinstance(parse_cols, basestring):
+            return i in _range2cols(parse_cols)
         else:
             return i in parse_cols
 

pandas/io/tests/test_parsers.py

@@ -861,6 +861,48 @@ def test_parse_cols_list(self):
             assert_frame_equal(df, df2)
             assert_frame_equal(df3, df2)
 
+    def test_parse_cols_str(self):
+        _skip_if_no_openpyxl()
+        _skip_if_no_xlrd()
+
+        suffix = ['', 'x']
+
+        for s in suffix:
+
+            pth = os.path.join(self.dirpath, 'test.xls%s' % s)
+            xls = ExcelFile(pth)
+
+            df = xls.parse('Sheet1', index_col=0, parse_dates=True,
+                            parse_cols='A:D')
+            df2 = read_csv(self.csv1, index_col=0, parse_dates=True)
+            df2 = df2.reindex(columns=['A', 'B', 'C'])
+            df3 = xls.parse('Sheet2', skiprows=[1], index_col=0,
+                            parse_dates=True, parse_cols='A:D')
+            assert_frame_equal(df, df2)
+            assert_frame_equal(df3, df2)
+            del df, df2, df3
+
+            df = xls.parse('Sheet1', index_col=0, parse_dates=True,
+                            parse_cols='A,C,D')
+            df2 = read_csv(self.csv1, index_col=0, parse_dates=True)
+            df2 = df2.reindex(columns=['B', 'C'])
+            df3 = xls.parse('Sheet2', skiprows=[1], index_col=0,
+                             parse_dates=True,
+                             parse_cols='A,C,D')
+            assert_frame_equal(df, df2)
+            assert_frame_equal(df3, df2)
+            del df, df2, df3
+
+            df = xls.parse('Sheet1', index_col=0, parse_dates=True,
+                            parse_cols='A,C:D')
+            df2 = read_csv(self.csv1, index_col=0, parse_dates=True)
+            df2 = df2.reindex(columns=['B', 'C'])
+            df3 = xls.parse('Sheet2', skiprows=[1], index_col=0,
+                             parse_dates=True,
+                             parse_cols='A,C:D')
+            assert_frame_equal(df, df2)
+            assert_frame_equal(df3, df2)
+
     def test_read_table_unicode(self):
         fin = StringIO('\u0141aski, Jan;1')
         df1 = read_table(fin, sep=";", encoding="utf-8", header=None)