BUG: (GH3611) revisited; read_excel not passing thru options to ExcelFile.parse

RELEASE.rst

@@ -120,6 +120,8 @@ pandas 0.11.1
   - Implement ``__nonzero__`` for ``NDFrame`` objects (GH3691_, GH3696_)
   - ``as_matrix`` with mixed signed and unsigned dtypes will result in 2 x the lcd of the unsigned
     as an int, maxing with ``int64``, to avoid precision issues (GH3733_)
+  - ``na_values`` in a list provided to ``read_csv/read_excel`` will match string and numeric versions
+    e.g. ``na_values=['99']`` will match 99 whether the column ends up being int, float, or string (GH3611_)
 
 **Bug Fixes**
 
@@ -174,7 +176,7 @@ pandas 0.11.1
   - Fix modulo and integer division on Series,DataFrames to act similary to ``float`` dtypes to return
     ``np.nan`` or ``np.inf`` as appropriate (GH3590_)
   - Fix incorrect dtype on groupby with ``as_index=False`` (GH3610_)
-  - Fix ``read_csv`` to correctly encode identical na_values, e.g. ``na_values=[-999.0,-999]``
+  - Fix ``read_csv/read_excel`` to correctly encode identical na_values, e.g. ``na_values=[-999.0,-999]``
     was failing (GH3611_)
   - Disable HTML output in qtconsole again. (GH3657_)
   - Reworked the new repr display logic, which users found confusing. (GH3663_)

pandas/io/excel.py

@@ -13,10 +13,7 @@
 from pandas.tseries.period import Period
 import json
 
-def read_excel(path_or_buf, sheetname, header=0, skiprows=None, skip_footer=0,
-               index_col=None, parse_cols=None, parse_dates=False,
-               date_parser=None, na_values=None, thousands=None, chunksize=None,
-               kind=None, **kwds):
+def read_excel(path_or_buf, sheetname, kind=None, **kwds):
     """Read an Excel table into a pandas DataFrame
 
     Parameters
@@ -47,16 +44,7 @@ def read_excel(path_or_buf, sheetname, header=0, skiprows=None, skip_footer=0,
         DataFrame from the passed in Excel file
     """
     return ExcelFile(path_or_buf,kind=kind).parse(sheetname=sheetname,
-                                                  header=0, skiprows=None,
-                                                  skip_footer=0,
-                                                  index_col=None,
-                                                  parse_cols=None,
-                                                  parse_dates=False,
-                                                  date_parser=None,
-                                                  na_values=None,
-                                                  thousands=None,
-                                                  chunksize=None, kind=None,
-                                                  **kwds)
+                                                  kind=kind, **kwds)
 
 class ExcelFile(object):
     """

pandas/io/parsers.py

@@ -1853,7 +1853,20 @@ def _clean_na_values(na_values, keep_default_na=True):
     return na_values
 
 def _stringify_na_values(na_values):
-    return [ str(x) for x in na_values ]
+    """ return a stringified and numeric for these values """
+    result = []
+    for x in na_values:
+        result.append(str(x))
+        result.append(x)
+        try:
+            result.append(float(x))
+        except:
+            pass
+        try:
+            result.append(int(x))
+        except:
+            pass
+    return result
 
 def _clean_index_names(columns, index_col):
     if not _is_index_col(index_col):

pandas/io/tests/test_excel.py

@@ -285,6 +285,15 @@ def _check_extension(self, ext):
             recons = read_excel(path, 'test1', index_col=0, na_values=['NA'])
             tm.assert_frame_equal(self.frame, recons)
 
+            # GH 3611
+            self.frame.to_excel(path, 'test1', na_rep='88')
+            recons = read_excel(path, 'test1', index_col=0, na_values=['88'])
+            tm.assert_frame_equal(self.frame, recons)
+
+            self.frame.to_excel(path, 'test1', na_rep='88')
+            recons = read_excel(path, 'test1', index_col=0, na_values=[88,88.0])
+            tm.assert_frame_equal(self.frame, recons)
+
     def test_excel_roundtrip_xls_mixed(self):
         _skip_if_no_xlrd()
         _skip_if_no_xlwt()

pandas/src/inference.pyx

@@ -373,12 +373,12 @@ def maybe_convert_numeric(ndarray[object] values, set na_values,
     for i from 0 <= i < n:
         val = values[i]
 
-        if util.is_float_object(val):
-            floats[i] = complexes[i] = val
-            seen_float = 1
-        elif val in na_values:
+        if val in na_values:
             floats[i] = complexes[i] = nan
             seen_float = 1
+        elif util.is_float_object(val):
+            floats[i] = complexes[i] = val
+            seen_float = 1
         elif val is None:
             floats[i] = complexes[i] = nan
             seen_float = 1