StataWriter: Replace missing values in string columns by an empty string

Author: PKEuS

doc/source/release.rst

@@ -156,7 +156,8 @@ API Changes
 - ``DataFrame.sort`` now places NaNs at the beginning or end of the sort according to the ``na_position`` parameter. (:issue:`3917`)
 
 - all offset operations now return ``Timestamp`` types (rather than datetime), Business/Week frequencies were incorrect (:issue:`4069`)
-
+- ``Series.iteritems()`` is now lazy (returns an iterator rather than a list). This was the documented behavior prior to 0.14. (:issue:`6760`)
+- ``Panel.shift`` now uses ``NDFrame.shift``. It no longer drops the ``nan`` data and retains its original shape.  (:issue:`4867`)
 
 Deprecations
 ~~~~~~~~~~~~
@@ -305,8 +306,7 @@ Bug Fixes
 - Bug in downcasting inference with empty arrays (:issue:`6733`)
 - Bug in ``obj.blocks`` on sparse containers dropping all but the last items of same for dtype (:issue:`6748`)
 - Bug in unpickling ``NaT (NaTType)`` (:issue:`4606`)
-- Bug in ``DataFrame.replace()`` where regex metacharacters were being treated
-  as regexs even when ``regex=False`` (:issue:`6777`).
+- Bug in setting a tz-aware index directly via ``.index`` (:issue:`6785`)
 
 pandas 0.13.1
 -------------

pandas/io/stata.py

@@ -1319,6 +1319,8 @@ def _write_data_nodates(self):
             for i, var in enumerate(row):
                 typ = ord(typlist[i])
                 if typ <= 244:  # we've got a string
+                    if var is None or var == np.nan:
+                        var = _pad_bytes('', typ)
                     if len(var) < typ:
                         var = _pad_bytes(var, typ)
                     self._write(var)

pandas/io/tests/test_stata.py

@@ -508,6 +508,16 @@ def test_date_export_formats(self):
             tm.assert_frame_equal(written_and_read_again.set_index('index'),
                                   expected)
 
+    def test_write_missing_strings(self):
+        original = DataFrame([["1"], [None]], columns=["foo"])
+        expected = DataFrame([["1"], [""]], columns=["foo"])
+        expected.index.name = 'index'
+        with tm.ensure_clean() as path:
+            original.to_stata(path)
+            written_and_read_again = self.read_dta(path)
+            tm.assert_frame_equal(written_and_read_again.set_index('index'),
+                                  expected)
+
 
 if __name__ == '__main__':
     nose.runmodule(argv=[__file__, '-vvs', '-x', '--pdb', '--pdb-failure'],