BUG: Ensure incomplete stata files are deleted

Attempt to delete failed writes and warn if not able to delete

Author: bashtage

doc/source/whatsnew/v0.24.0.rst

@@ -1576,6 +1576,7 @@ Notice how we now instead output ``np.nan`` itself instead of a stringified form
 - :func:`DataFrame.to_string()`, :func:`DataFrame.to_html()`, :func:`DataFrame.to_latex()` will correctly format output when a string is passed as the ``float_format`` argument (:issue:`21625`, :issue:`22270`)
 - Bug in :func:`read_csv` that caused it to raise ``OverflowError`` when trying to use 'inf' as ``na_value`` with integer index column (:issue:`17128`)
 - Bug in :func:`pandas.io.json.json_normalize` that caused it to raise ``TypeError`` when two consecutive elements of ``record_path`` are dicts (:issue:`22706`)
+- Bug in :meth:`DataFrame.to_stata`, :class:`pandas.io.stata.StataWriter` and :class:`pandas.io.stata.StataWriter117` where a exception would leave a partially written and invalid dta file (:issue:`23573`)
 
 Plotting
 ^^^^^^^^

pandas/io/stata.py

@@ -12,6 +12,7 @@
 
 from collections import OrderedDict
 import datetime
+import os
 import struct
 import sys
 import warnings
@@ -502,6 +503,9 @@ class InvalidColumnName(Warning):
 alphanumerics and underscores, no Stata reserved words)
 """
 
+class IOWarning(Warning):
+    pass
+
 
 def _cast_to_stata_types(data):
     """Checks the dtypes of the columns of a pandas DataFrame for
@@ -2209,7 +2213,17 @@ def write_file(self):
             self._write_value_labels()
             self._write_file_close_tag()
             self._write_map()
-        finally:
+        except Exception as exc:
+            self._close()
+            try:
+                if self._own_file:
+                    os.unlink(self._fname)
+            except Exception:
+                warnings.warn('This save was not successful but {0} could not '
+                              'be deleted.  This file is not '
+                              'valid.'.format(self._fname), IOWarning)
+            raise exc
+        else:
             self._close()
 
     def _close(self):

pandas/tests/io/test_stata.py

@@ -16,12 +16,13 @@
 import pandas as pd
 import pandas.util.testing as tm
 import pandas.compat as compat
-from pandas.compat import iterkeys
+from pandas.compat import iterkeys, PY3
 from pandas.core.dtypes.common import is_categorical_dtype
 from pandas.core.frame import DataFrame, Series
 from pandas.io.parsers import read_csv
 from pandas.io.stata import (InvalidColumnName, PossiblePrecisionLoss,
-                             StataMissingValue, StataReader, read_stata)
+                             StataMissingValue, StataReader, read_stata,
+                             IOWarning)
 
 
 @pytest.fixture
@@ -1546,3 +1547,13 @@ def test_all_none_exception(self, version):
                 output.to_stata(path, version=version)
         assert 'Only string-like' in excinfo.value.args[0]
         assert 'Column `none`' in excinfo.value.args[0]
+
+    @pytest.mark.parametrize('version', [114, 117])
+    def test_invalid_file_not_written(self, version):
+        content = 'Here is one __�__ Another one __·__ Another one __½__'
+        df = DataFrame([content], columns=['invalid'])
+        expected_exc = UnicodeEncodeError if PY3 else UnicodeDecodeError
+        with tm.ensure_clean() as path:
+            with pytest.raises(expected_exc):
+                with pytest.warns(IOWarning):
+                    df.to_stata(path)