Merge pull request #11131 from jreback/error

ERR: make sure raising TypeError on invalid nanops reductions xref #10472

Author: jreback

doc/source/whatsnew/v0.17.0.txt

@@ -915,6 +915,7 @@ Other API Changes
 - ``groupby`` using ``Categorical`` follows the same rule as ``Categorical.unique`` described above  (:issue:`10508`)
 - When constructing ``DataFrame`` with an array of ``complex64`` dtype previously meant the corresponding column
   was automatically promoted to the ``complex128`` dtype. Pandas will now preserve the itemsize of the input for complex data (:issue:`10952`)
+- some numeric reduction operators would return ``ValueError``, rather than ``TypeError`` on object types that includes strings and numbers (:issue:`11131`)
 
 - ``NaT``'s methods now either raise ``ValueError``, or return ``np.nan`` or ``NaT`` (:issue:`9513`)
 

pandas/core/nanops.py

@@ -43,7 +43,16 @@ def _f(*args, **kwargs):
                 raise TypeError('reduction operation {0!r} not allowed for '
                                 'this dtype'.format(f.__name__.replace('nan',
                                                                        '')))
-            return f(*args, **kwargs)
+            try:
+                return f(*args, **kwargs)
+            except ValueError as e:
+                # we want to transform an object array
+                # ValueError message to the more typical TypeError
+                # e.g. this is normally a disallowed function on
+                # object arrays that contain strings
+                if is_object_dtype(args[0]):
+                    raise TypeError(e)
+                raise
         return _f
 
 
@@ -93,7 +102,17 @@ def f(values, axis=None, skipna=True, **kwds):
                 else:
                     result = alt(values, axis=axis, skipna=skipna, **kwds)
             except Exception:
-                result = alt(values, axis=axis, skipna=skipna, **kwds)
+                try:
+                    result = alt(values, axis=axis, skipna=skipna, **kwds)
+                except ValueError as e:
+                    # we want to transform an object array
+                    # ValueError message to the more typical TypeError
+                    # e.g. this is normally a disallowed function on
+                    # object arrays that contain strings
+
+                    if is_object_dtype(values):
+                        raise TypeError(e)
+                    raise
 
             return result
 
@@ -372,7 +391,6 @@ def nanvar(values, axis=None, skipna=True, ddof=1):
         values = values.copy()
         np.putmask(values, mask, 0)
 
-
     # xref GH10242
     # Compute variance via two-pass algorithm, which is stable against
     # cancellation errors and relatively accurate for small numbers of

pandas/tests/test_frame.py

@@ -12792,7 +12792,7 @@ def test_numeric_only_flag(self):
 
             # df1 has all numbers, df2 has a letter inside
             self.assertRaises(TypeError, lambda : getattr(df1, meth)(axis=1, numeric_only=False))
-            self.assertRaises(ValueError, lambda : getattr(df2, meth)(axis=1, numeric_only=False))
+            self.assertRaises(TypeError, lambda : getattr(df2, meth)(axis=1, numeric_only=False))
 
     def test_sem(self):
         alt = lambda x: np.std(x, ddof=1)/np.sqrt(len(x))

pandas/tests/test_series.py

@@ -2912,6 +2912,10 @@ def testit():
                 exp = alternate(s)
                 self.assertEqual(res, exp)
 
+            # check on string data
+            if name not in ['sum','min','max']:
+                self.assertRaises(TypeError, f, Series(list('abc')))
+
             # Invalid axis.
             self.assertRaises(ValueError, f, self.series, axis=1)