BUG: Correctly localize naive ts strings with Series and datetimetz dtype (pandas-dev#17415)

Author: mroeschke

pandas/core/dtypes/cast.py

@@ -18,7 +18,7 @@
                      is_integer_dtype,
                      is_datetime_or_timedelta_dtype,
                      is_bool_dtype, is_scalar,
-                     _string_dtypes,
+                     is_string_dtype, _string_dtypes,
                      pandas_dtype,
                      _ensure_int8, _ensure_int16,
                      _ensure_int32, _ensure_int64,
@@ -965,12 +965,16 @@ def maybe_cast_to_datetime(value, dtype, errors='raise'):
                         if is_datetime64:
                             value = to_datetime(value, errors=errors)._values
                         elif is_datetime64tz:
-                            # input has to be UTC at this point, so just
-                            # localize
-                            value = (to_datetime(value, errors=errors)
-                                     .tz_localize('UTC')
-                                     .tz_convert(dtype.tz)
-                                     )
+                            is_dt_string = is_string_dtype(value)
+                            value = to_datetime(value, errors=errors)
+                            if is_dt_string:
+                                # Strings here are naive, so directly localize
+                                value = value.tz_localize(dtype.tz)
+                            else:
+                                # Numeric values are UTC at this point, 
+                                # so localize and convert
+                                value = (value.tz_localize('UTC')
+                                         .tz_convert(dtype.tz))
                         elif is_timedelta64:
                             value = to_timedelta(value, errors=errors)._values
                     except (AttributeError, ValueError, TypeError):

pandas/tests/series/test_constructors.py

@@ -553,6 +553,12 @@ def test_constructor_with_datetime_tz(self):
         expected = Series(pd.DatetimeIndex(['NaT', 'NaT'], tz='US/Eastern'))
         assert_series_equal(s, expected)
 
+        # GH 17415: With naive string
+        ts_naive = '2013-01-01 00:00:00'
+        result = Series([ts_naive], dtype='datetime64[ns, CET]')
+        expected = Series([pd.Timestamp(ts_naive, tz='CET')])
+        assert_series_equal(result, expected)
+
     def test_construction_interval(self):
         # construction from interval & array of intervals
         index = IntervalIndex.from_breaks(np.arange(3), closed='right')