Merge pull request #4139 from jtratner/excel_fix

BUG: Make ExcelFile.parse pass kwds to TextParser

Author: hayd

pandas/io/excel.py

@@ -126,7 +126,8 @@ def parse(self, sheetname, header=0, skiprows=None, skip_footer=0,
                                      na_values=na_values,
                                      thousands=thousands,
                                      chunksize=chunksize,
-                                     skip_footer=skip_footer)
+                                     skip_footer=skip_footer,
+                                     **kwds)
 
     def _should_parse(self, i, parse_cols):
 
@@ -163,7 +164,8 @@ def _excel2num(x):
     def _parse_excel(self, sheetname, header=0, skiprows=None,
                    skip_footer=0, index_col=None, has_index_names=None,
                    parse_cols=None, parse_dates=False, date_parser=None,
-                   na_values=None, thousands=None, chunksize=None):
+                   na_values=None, thousands=None, chunksize=None,
+                   **kwds):
         from xlrd import (xldate_as_tuple, XL_CELL_DATE,
                           XL_CELL_ERROR, XL_CELL_BOOLEAN)
 
@@ -206,7 +208,8 @@ def _parse_excel(self, sheetname, header=0, skiprows=None,
                             date_parser=date_parser,
                             skiprows=skiprows,
                             skip_footer=skip_footer,
-                            chunksize=chunksize)
+                            chunksize=chunksize,
+                            **kwds)
 
         return parser.read()
 

pandas/io/tests/data/test2.xlsx

@@ -182,6 +182,22 @@ def test_excel_cell_error_na(self):
         expected = DataFrame([[np.nan]], columns=['Test'])
         tm.assert_frame_equal(parsed, expected)
 
+    def test_excel_passes_na(self):
+        _skip_if_no_xlrd()
+
+        excel_data = ExcelFile(os.path.join(self.dirpath, 'test2.xlsx'))
+        parsed = excel_data.parse('Sheet1', keep_default_na=False,
+                                  na_values=['apple'])
+        expected = DataFrame([['NA'], [1], ['NA'], [np.nan], ['rabbit']],
+                             columns=['Test'])
+        tm.assert_frame_equal(parsed, expected)
+
+        parsed = excel_data.parse('Sheet1', keep_default_na=True,
+                                  na_values=['apple'])
+        expected = DataFrame([[np.nan], [1], [np.nan], [np.nan], ['rabbit']],
+                             columns=['Test'])
+        tm.assert_frame_equal(parsed, expected)
+
     def test_excel_table(self):
         _skip_if_no_xlrd()