Merge pull request #4970 from jreback/invalid_compare

API: raise a TypeError on invalid comparison ops on Series (e.g. integer/datetime) GH4968

Author: jreback

doc/source/release.rst

@@ -225,6 +225,7 @@ API Changes
   - moved timedeltas support to pandas.tseries.timedeltas.py; add timedeltas string parsing,
     add top-level ``to_timedelta`` function
   - ``NDFrame`` now is compatible with Python's toplevel ``abs()`` function (:issue:`4821`).
+  - raise a ``TypeError`` on invalid comparison ops on Series/DataFrame (e.g. integer/datetime) (:issue:`4968`)
 
 Internal Refactoring
 ~~~~~~~~~~~~~~~~~~~~

pandas/core/series.py

@@ -324,7 +324,13 @@ def na_op(x, y):
             else:
                 result = lib.scalar_compare(x, y, op)
         else:
-            result = op(x, y)
+
+            try:
+                result = getattr(x,name)(y)
+                if result is NotImplemented:
+                    raise TypeError("invalid type comparison")
+            except (AttributeError):
+                result = op(x, y)
 
         return result
 

pandas/tests/test_frame.py

@@ -4296,6 +4296,31 @@ def test_operators_none_as_na(self):
             result = op(df.fillna(7), df)
             assert_frame_equal(result, expected)
 
+    def test_comparison_invalid(self):
+
+        def check(df,df2):
+
+            for (x, y) in [(df,df2),(df2,df)]:
+                self.assertRaises(TypeError, lambda : x == y)
+                self.assertRaises(TypeError, lambda : x != y)
+                self.assertRaises(TypeError, lambda : x >= y)
+                self.assertRaises(TypeError, lambda : x > y)
+                self.assertRaises(TypeError, lambda : x < y)
+                self.assertRaises(TypeError, lambda : x <= y)
+
+        # GH4968
+        # invalid date/int comparisons
+        df = DataFrame(np.random.randint(10, size=(10, 1)), columns=['a'])
+        df['dates'] = date_range('20010101', periods=len(df))
+
+        df2 = df.copy()
+        df2['dates'] = df['a']
+        check(df,df2)
+
+        df = DataFrame(np.random.randint(10, size=(10, 2)), columns=['a', 'b'])
+        df2 = DataFrame({'a': date_range('20010101', periods=len(df)), 'b': date_range('20100101', periods=len(df))})
+        check(df,df2)
+
     def test_modulo(self):
 
         # GH3590, modulo as ints

pandas/tests/test_series.py

@@ -2663,6 +2663,21 @@ def test_comparison_object_numeric_nas(self):
             expected = f(s.astype(float), shifted.astype(float))
             assert_series_equal(result, expected)
 
+    def test_comparison_invalid(self):
+
+        # GH4968
+        # invalid date/int comparisons
+        s = Series(range(5))
+        s2 = Series(date_range('20010101', periods=5))
+
+        for (x, y) in [(s,s2),(s2,s)]:
+            self.assertRaises(TypeError, lambda : x == y)
+            self.assertRaises(TypeError, lambda : x != y)
+            self.assertRaises(TypeError, lambda : x >= y)
+            self.assertRaises(TypeError, lambda : x > y)
+            self.assertRaises(TypeError, lambda : x < y)
+            self.assertRaises(TypeError, lambda : x <= y)
+
     def test_more_na_comparisons(self):
         left = Series(['a', np.nan, 'c'])
         right = Series(['a', np.nan, 'd'])