ENH: Allow export of mixed columns to Stata strl (#23692)

Enable export of large columns to Stata strls when the column contains None as a null value closes #23633

Author: bashtage

doc/source/whatsnew/v0.24.0.txt

@@ -239,6 +239,7 @@ Other Enhancements
 - :meth:`Timestamp.tz_localize`, :meth:`DatetimeIndex.tz_localize`, and :meth:`Series.tz_localize` have gained the ``nonexistent`` argument for alternative handling of nonexistent times. See :ref:`timeseries.timezone_nonexistent` (:issue:`8917`)
 - :meth:`read_excel()` now accepts ``usecols`` as a list of column names or callable (:issue:`18273`)
 - :meth:`MultiIndex.to_flat_index` has been added to flatten multiple levels into a single-level :class:`Index` object.
+- :meth:`DataFrame.to_stata` and :class:` pandas.io.stata.StataWriter117` can write mixed sting columns to Stata strl format (:issue:`23633`)
 
 .. _whatsnew_0240.api_breaking:
 

pandas/io/stata.py

@@ -2558,6 +2558,8 @@ def generate_table(self):
  for o, (idx, row) in enumerate(selected.iterrows()):
  for j, (col, v) in enumerate(col_index):
  val = row[col]
+ # Allow columns with mixed str and None (GH 23633)
+ val = '' if val is None else val
  key = gso_table.get(val, None)
  if key is None:
  # Stata prefers human numbers

pandas/tests/io/test_stata.py

@@ -1505,3 +1505,20 @@ def test_unicode_dta_118(self):
  expected = pd.DataFrame(values, columns=columns)
 
  tm.assert_frame_equal(unicode_df, expected)
+
+ def test_mixed_string_strl(self):
+ # GH 23633
+ output = [
+ {'mixed': 'string' * 500,
+ 'number': 0},
+ {'mixed': None,
+ 'number': 1}
+ ]
+
+ output = pd.DataFrame(output)
+ with tm.ensure_clean() as path:
+ output.to_stata(path, write_index=False, version=117)
+ reread = read_stata(path)
+ expected = output.fillna('')
+ expected.number = expected.number.astype('int32')
+ tm.assert_frame_equal(reread, expected)