Merge pull request #9617 from shoyer/accessors-raise-AttributeError

BUG/API: Accessors like .cat raise AttributeError when invalid

Author: jreback

doc/source/whatsnew/v0.16.0.txt

@@ -302,6 +302,7 @@ API Changes
 
 - Bar and horizontal bar plots no longer add a dashed line along the info axis. The prior style can be achieved with matplotlib's ``axhline`` or ``axvline`` methods (:issue:`9088`).
 
+- ``Series`` accessors ``.dt``, ``.cat`` and ``.str`` now raise ``AttributeError`` instead of ``TypeError`` if the series does not contain the appropriate type of data (:issue:`9617`). This follows Python's built-in exception hierarchy more closely and ensures that tests like ``hasattr(s, 'cat')`` are consistent on both Python 2 and 3.
 
 - ``Series`` now supports bitwise operation for integral types (:issue:`9016`). Previously even if the input dtypes were integral, the output dtype was coerced to ``bool``.
 

pandas/core/generic.py

@@ -78,8 +78,9 @@ class NDFrame(PandasObject):
     copy : boolean, default False
     """
     _internal_names = ['_data', '_cacher', '_item_cache', '_cache',
-                       'is_copy', 'str', '_subtyp', '_index', '_default_kind',
-                       '_default_fill_value','__array_struct__','__array_interface__']
+                       'is_copy', 'dt', 'cat', 'str', '_subtyp', '_index',
+                       '_default_kind', '_default_fill_value',
+                       '__array_struct__','__array_interface__']
     _internal_names_set = set(_internal_names)
     _metadata = []
     is_copy = None

pandas/core/series.py

@@ -2521,8 +2521,9 @@ def _make_str_accessor(self):
             # this really should exclude all series with any non-string values,
             # but that isn't practical for performance reasons until we have a
             # str dtype (GH 9343)
-            raise TypeError("Can only use .str accessor with string values, "
-                            "which use np.object_ dtype in pandas")
+            raise AttributeError("Can only use .str accessor with string "
+                                 "values, which use np.object_ dtype in "
+                                 "pandas")
         return StringMethods(self)
 
     str = base.AccessorProperty(StringMethods, _make_str_accessor)
@@ -2533,8 +2534,9 @@ def _make_str_accessor(self):
     def _make_dt_accessor(self):
         try:
             return maybe_to_datetimelike(self)
-        except (Exception):
-            raise TypeError("Can only use .dt accessor with datetimelike values")
+        except Exception:
+            raise AttributeError("Can only use .dt accessor with datetimelike "
+                                 "values")
 
     dt = base.AccessorProperty(CombinedDatetimelikeProperties, _make_dt_accessor)
 
@@ -2543,7 +2545,8 @@ def _make_dt_accessor(self):
 
     def _make_cat_accessor(self):
         if not com.is_categorical_dtype(self.dtype):
-            raise TypeError("Can only use .cat accessor with a 'category' dtype")
+            raise AttributeError("Can only use .cat accessor with a "
+                                 "'category' dtype")
         return CategoricalAccessor(self.values, self.index)
 
     cat = base.AccessorProperty(CategoricalAccessor, _make_cat_accessor)

pandas/tests/test_categorical.py

@@ -2631,8 +2631,11 @@ def test_cat_accessor_api(self):
         self.assertIs(Series.cat, CategoricalAccessor)
         s = Series(list('aabbcde')).astype('category')
         self.assertIsInstance(s.cat, CategoricalAccessor)
-        with tm.assertRaisesRegexp(TypeError, "only use .cat accessor"):
-            Series([1]).cat
+
+        invalid = Series([1])
+        with tm.assertRaisesRegexp(AttributeError, "only use .cat accessor"):
+            invalid.cat
+        self.assertFalse(hasattr(invalid, 'cat'))
 
     def test_pickle_v0_14_1(self):
         cat = pd.Categorical(values=['a', 'b', 'c'],

pandas/tests/test_series.py

@@ -104,12 +104,6 @@ def compare(s, name):
             else:
                 tm.assert_series_equal(a,b)
 
-        # invalids
-        for s in [Series(np.arange(5)),
-                  Series(list('abcde')),
-                  Series(np.random.randn(5))]:
-            self.assertRaises(TypeError, lambda : s.dt)
-
         # datetimeindex
         for s in [Series(date_range('20130101',periods=5)),
                   Series(date_range('20130101',periods=5,freq='s')),
@@ -240,8 +234,13 @@ def test_dt_accessor_api(self):
         s = Series(date_range('2000-01-01', periods=3))
         self.assertIsInstance(s.dt, DatetimeProperties)
 
-        with tm.assertRaisesRegexp(TypeError, "only use .dt accessor"):
-            Series([1]).dt
+        for s in [Series(np.arange(5)),
+                  Series(list('abcde')),
+                  Series(np.random.randn(5))]:
+            with tm.assertRaisesRegexp(AttributeError,
+                                       "only use .dt accessor"):
+                s.dt
+            self.assertFalse(hasattr(s, 'dt'))
 
     def test_binop_maybe_preserve_name(self):
 

pandas/tests/test_strings.py

@@ -37,8 +37,10 @@ def test_api(self):
         self.assertIsInstance(Series(['']).str, strings.StringMethods)
 
         # GH 9184
-        with tm.assertRaisesRegexp(TypeError, "only use .str accessor"):
-            Series([1]).str
+        invalid = Series([1])
+        with tm.assertRaisesRegexp(AttributeError, "only use .str accessor"):
+            invalid.str
+        self.assertFalse(hasattr(invalid, 'str'))
 
     def test_iter(self):
         # GH3638