ENH: Explicit range checking when writing Stata

Add explicit error checking for out-of-range doubles when writing Stata files

closes pandas-dev#14618

Author: bashtage

doc/source/whatsnew/v0.20.0.txt

@@ -80,3 +80,5 @@ Performance Improvements
 
 Bug Fixes
 ~~~~~~~~~
+
+- Explicit check in ``to_stata`` and ````StataWriter `` for out-of-range values when writing doubles (:issue:`14618`)

pandas/io/stata.py

@@ -550,6 +550,24 @@ def _cast_to_stata_types(data):
     return data
 
 
+def _check_double_values(data):
+    """Checks double columns against the range supported by Stata
+
+    Parameters
+    ----------
+    data : DataFrame
+        The DataFrame to check
+    """
+    DOUBLE_MAX = struct.unpack('<d', b'\x00\x00\x00\x00\x00\x00\xe0\x7f')[0]
+    for col in data:
+        if data[col].dtype == np.double:
+            value = data[col].max()
+            if value > DOUBLE_MAX:
+                msg = 'Column {0} has a maximum value ({1}) outside the ' \
+                      'range supported by Stata ({1})'
+                raise ValueError(msg.format(col, value, DOUBLE_MAX))
+
+
 class StataValueLabel(object):
     """
     Parse a categorical column and prepare formatted output
@@ -2050,6 +2068,9 @@ def _prepare_pandas(self, data):
         # Check columns for compatibility with stata, upcast if necessary
         data = _cast_to_stata_types(data)
 
+        # Check for values outside the range supported for doubles
+        _check_double_values(data)
+
         # Replace NaNs with Stata missing values
         data = self._replace_nans(data)
 

pandas/io/tests/test_stata.py

@@ -1234,6 +1234,18 @@ def test_stata_111(self):
         original = original[['y', 'x', 'w', 'z']]
         tm.assert_frame_equal(original, df)
 
+    def test_out_of_range_double(self):
+        # GH 14618
+        df = DataFrame({'ColumnOk': [0.0,
+                                     np.finfo(np.double).eps,
+                                     4.49423283715579e+307],
+                        'ColumnTooBig': [0.0,
+                                         np.finfo(np.double).eps,
+                                         np.finfo(np.double).max]})
+        with tm.assertRaises(ValueError) as cm:
+            with tm.ensure_clean() as path:
+                df.to_stata(path)
+            tm.assertTrue('ColumnTooBig' in cm.exception)
 
 if __name__ == '__main__':
     nose.runmodule(argv=[__file__, '-vvs', '-x', '--pdb', '--pdb-failure'],