BUG-20591 read_csv raises ValueError for bool columns with missing values

Author: JustinZhengBC

doc/source/whatsnew/v0.24.0.rst

@@ -330,6 +330,7 @@ Backwards incompatible API changes
 - :meth:`Series.str.cat` will now raise if `others` is a `set` (:issue:`23009`)
 - Passing scalar values to :class:`DatetimeIndex` or :class:`TimedeltaIndex` will now raise ``TypeError`` instead of ``ValueError`` (:issue:`23539`)
 - ``max_rows`` and ``max_cols`` parameters removed from :class:`HTMLFormatter` since truncation is handled by :class:`DataFrameFormatter` (:issue:`23818`)
+- :meth:`read_csv` will now throw a ``ValueError`` if a column with missing values is declared as having ``dtype`` ``bool`` (:issue:`20591`)
 
 .. _whatsnew_0240.api_breaking.deps:
 

pandas/_libs/parsers.pyx

@@ -1245,6 +1245,10 @@ cdef class TextReader:
             result, na_count = _try_bool_flex(self.parser, i, start, end,
                                               na_filter, na_hashset,
                                               self.true_set, self.false_set)
+            if user_dtype and na_count is not None:
+                if na_count > 0:
+                    raise ValueError("Bool column has NA values in "
+                                     "column {column}".format(column=i))
             return result, na_count
 
         elif dtype.kind == 'S':

pandas/tests/io/parser/test_na_values.py

@@ -421,3 +421,12 @@ def test_na_values_with_dtype_str_and_na_filter(all_parsers, na_filter):
 
     result = parser.read_csv(StringIO(data), na_filter=na_filter, dtype=str)
     tm.assert_frame_equal(result, expected)
+
+
+@pytest.mark.xfail
+def test_cast_NA_to_bool_raises_error(all_parsers):
+    parser = all_parsers
+    data = "false,1\n,1\ntrue,"
+
+    parser.read_csv(StringIO(data), header=None, names=['a', 'b'],
+                    dtype={'a': 'bool'})