Merge pull request #6803 from cpcloud/bool-arith-ops-6762

BUG/API: disallow boolean arithmetic operations

Author: cpcloud

doc/source/release.rst

@@ -156,6 +156,8 @@ API Changes
 - ``to_excel`` now converts ``np.inf`` into a string representation,
   customizable by the ``inf_rep`` keyword argument (Excel has no native inf
   representation) (:issue:`6782`)
+- Arithmetic ops are now disallowed when passed two bool dtype Series or
+  DataFrames (:issue:`6762`).
 
 Deprecations
 ~~~~~~~~~~~~
@@ -307,6 +309,9 @@ Bug Fixes
 - Bug in ``DataFrame.replace()`` where regex metacharacters were being treated
   as regexs even when ``regex=False`` (:issue:`6777`).
 - Bug in timedelta ops on 32-bit platforms (:issue:`6808`)
+- Bug in setting a tz-aware index directly via ``.index`` (:issue:`6785`)
+- Bug in expressions.py where numexpr would try to evaluate arithmetic ops
+  (:issue:`6762`).
 
 pandas 0.13.1
 -------------

pandas/computation/expressions.py

@@ -154,6 +154,20 @@ def _where_numexpr(cond, a, b, raise_on_error=False):
 set_use_numexpr(True)
 
 
+def _has_bool_dtype(x):
+    try:
+        return x.dtype == bool
+    except AttributeError:
+        return 'bool' in x.blocks
+
+
+def _bool_arith_check(op_str, a, b, not_allowed=frozenset(('+', '*', '-', '/',
+                                                           '//', '**'))):
+    if op_str in not_allowed and _has_bool_dtype(a) and _has_bool_dtype(b):
+        raise NotImplementedError("operator %r not implemented for bool "
+                                  "dtypes" % op_str)
+
+
 def evaluate(op, op_str, a, b, raise_on_error=False, use_numexpr=True,
              **eval_kwargs):
     """ evaluate and return the expression of the op on a and b
@@ -170,7 +184,7 @@ def evaluate(op, op_str, a, b, raise_on_error=False, use_numexpr=True,
                          return the results
         use_numexpr : whether to try to use numexpr (default True)
         """
-
+    _bool_arith_check(op_str, a, b)
     if use_numexpr:
         return _evaluate(op, op_str, a, b, raise_on_error=raise_on_error,
                          **eval_kwargs)

pandas/tests/test_expressions.py

@@ -2,6 +2,7 @@
 # pylint: disable-msg=W0612,E1101
 
 import nose
+import re
 
 from numpy.random import randn
 
@@ -339,6 +340,24 @@ def testit():
         expr.set_numexpr_threads()
         testit()
 
+    def test_bool_ops_raise_on_arithmetic(self):
+        df = DataFrame({'a': np.random.rand(10) > 0.5,
+                        'b': np.random.rand(10) > 0.5})
+        names = 'add', 'mul', 'sub', 'div', 'truediv', 'floordiv', 'pow'
+        ops = '+', '*', '-', '/', '/', '//', '**'
+        msg = 'operator %r not implemented for bool dtypes'
+        for op, name in zip(ops, names):
+            if not compat.PY3 or name != 'div':
+                f = getattr(operator, name)
+                err_msg = re.escape(msg % op)
+
+                with tm.assertRaisesRegexp(NotImplementedError, err_msg):
+                    f(df, df)
+
+                with tm.assertRaisesRegexp(NotImplementedError, err_msg):
+                    f(df.a, df.b)
+
+
 if __name__ == '__main__':
     import nose
     nose.runmodule(argv=[__file__, '-vvs', '-x', '--pdb', '--pdb-failure'],

pandas/tests/test_frame.py

@@ -4761,13 +4761,13 @@ def _check_unary_op(op):
         _check_unary_op(operator.neg)
 
     def test_logical_typeerror(self):
-        if compat.PY3:
-            pass
-        else:
+        if not compat.PY3:
             self.assertRaises(TypeError, self.frame.__eq__, 'foo')
             self.assertRaises(TypeError, self.frame.__lt__, 'foo')
             self.assertRaises(TypeError, self.frame.__gt__, 'foo')
             self.assertRaises(TypeError, self.frame.__ne__, 'foo')
+        else:
+            raise nose.SkipTest('test_logical_typeerror not tested on PY3')
 
     def test_constructor_lists_to_object_dtype(self):
         # from #1074