first pass

Author: TomAugspurger

pandas/core/arrays/categorical.py

@@ -523,6 +523,8 @@ def _from_inferred_categories(cls, inferred_categories, inferred_codes,
                 cats = to_datetime(inferred_categories, errors='coerce')
             elif is_timedelta64_dtype(dtype.categories):
                 cats = to_timedelta(inferred_categories, errors='coerce')
+            elif dtype.categories.is_boolean():
+                cats = inferred_categories == 'True'
 
         if known_categories:
             # recode from observation order to dtype.categories order

pandas/tests/io/parser/dtypes.py

@@ -229,6 +229,14 @@ def test_categoricaldtype_coerces_timedelta(self):
         result = self.read_csv(StringIO(data), dtype=dtype)
         tm.assert_frame_equal(result, expected)
 
+    def test_categoricaldtype_coerces_boolen(self):
+        # 20498
+        dtype = {'b': CategoricalDtype([False, True])}
+        data = "b\nTrue\nFalse\nNA\nFalse"
+        expected = pd.DataFrame({"b": Categorical([True, False, None, False])})
+        result = self.read_csv(StringIO(data), dtype=dtype)
+        tm.assert_frame_equal(result, expected)
+
     def test_categoricaldtype_unexpected_categories(self):
         dtype = {'b': CategoricalDtype(['a', 'b', 'd', 'e'])}
         data = "b\nd\na\nc\nd"  # Unexpected c