support for mixed type arrays

Author: jreback

pandas/tools/hashing.py

@@ -149,6 +149,8 @@ def hash_tuples(vals, encoding='utf8', hash_key=None):
     """
     Hash an MultiIndex / list-of-tuples efficiently
 
+    .. versionadded:: 0.20.0
+
     Parameters
     ----------
     vals : MultiIndex, list-of-tuples, or single tuple
@@ -265,7 +267,13 @@ def hash_array(vals, encoding='utf8', hash_key=None, categorize=True):
                               ordered=False, fastpath=True)
             return _hash_categorical(cat, encoding, hash_key)
 
-        vals = _hash.hash_object_array(vals, hash_key, encoding)
+        try:
+            vals = _hash.hash_object_array(vals, hash_key, encoding)
+        except TypeError:
+
+            # we have mixed types
+            vals = _hash.hash_object_array(vals.astype(str).astype(object),
+                                           hash_key, encoding)
 
     # Then, redistribute these 64-bit ints within the space of 64-bit ints
     vals ^= vals >> 30

pandas/tools/tests/test_hashing.py

@@ -36,6 +36,11 @@ def test_hash_array(self):
             a = s.values
             tm.assert_numpy_array_equal(hash_array(a), hash_array(a))
 
+    def test_hash_array_mixed(self):
+        for data in [np.array([3, 4, 'All']),
+                     np.array([3, 4, 'All'], dtype=object)]:
+            tm.assert_numpy_array_equal(hash_array(data), hash_array(data))
+
     def check_equal(self, obj, **kwargs):
         a = hash_pandas_object(obj, **kwargs)
         b = hash_pandas_object(obj, **kwargs)
@@ -159,15 +164,6 @@ def f():
             hash_pandas_object(Series(list('abc')), hash_key='foo')
         self.assertRaises(ValueError, f)
 
-    def test_unsupported_objects(self):
-
-        # mixed objects are not supported
-        obj = Series(['1', 2, 3])
-
-        def f():
-            hash_pandas_object(obj)
-        self.assertRaises(TypeError, f)
-
     def test_alread_encoded(self):
         # if already encoded then ok