REGR: assure .unique of mixed strings does not stringize

closes pandas-dev#16107

Author: jreback

pandas/core/algorithms.py

@@ -78,6 +78,16 @@ def _ensure_data(values, dtype=None):
         elif is_float_dtype(values) or is_float_dtype(dtype):
             return _ensure_float64(values), 'float64', 'float64'
         elif is_object_dtype(values) and dtype is None:
+
+            # if we can infer a numeric then do this
+            inferred = lib.infer_dtype(values)
+            if inferred in ['integer']:
+                return _ensure_int64(values), 'int64', 'int64'
+            elif inferred in ['floating']:
+                return _ensure_float64(values), 'float64', 'float64'
+            elif inferred in ['boolean']:
+                return np.asarray(values).astype('uint64'), 'bool', 'uint64'
+
             return _ensure_object(np.asarray(values)), 'object', 'object'
         elif is_complex_dtype(values) or is_complex_dtype(dtype):
 
@@ -87,7 +97,7 @@ def _ensure_data(values, dtype=None):
                 values = _ensure_float64(values)
             return values, 'float64', 'float64'
 
-    except (TypeError, ValueError):
+    except (TypeError, ValueError, OverflowError):
         # if we are trying to coerce to a dtype
         # and it is incompat this will fall thru to here
         return _ensure_object(values), 'object', 'object'
@@ -150,7 +160,13 @@ def _reconstruct_data(values, dtype, original):
     elif is_datetime64tz_dtype(dtype) or is_period_dtype(dtype):
         values = Index(original)._shallow_copy(values, name=None)
     elif dtype is not None:
-        values = values.astype(dtype)
+
+        # don't cast to object if we are numeric
+        if is_object_dtype(dtype):
+            if not is_numeric_dtype(values):
+                values = values.astype(dtype)
+        else:
+            values = values.astype(dtype)
 
     return values
 
@@ -161,7 +177,7 @@ def _ensure_arraylike(values):
     """
     if not isinstance(values, (np.ndarray, ABCCategorical,
                                ABCIndexClass, ABCSeries)):
-        values = np.array(values)
+        values = np.array(values, dtype=object)
     return values
 
 

pandas/tests/test_algos.py

@@ -387,6 +387,12 @@ def test_uint64_overflow(self):
         exp = np.array([1, 2, 2**63], dtype=np.uint64)
         tm.assert_numpy_array_equal(algos.unique(s), exp)
 
+    def test_nan_in_object_array(self):
+        l = ['a', np.nan, 'c', 'c']
+        result = pd.unique(l)
+        expected = np.array(['a', np.nan, 'c'], dtype=object)
+        tm.assert_numpy_array_equal(result, expected)
+
     def test_categorical(self):
 
         # we are expecting to return in the order
@@ -1375,11 +1381,11 @@ def test_int64_add_overflow():
 class TestMode(tm.TestCase):
 
     def test_no_mode(self):
-        exp = Series([], dtype=np.float64)
+        exp = Series([], dtype=object)
         tm.assert_series_equal(algos.mode([]), exp)
 
-    # GH 15714
     def test_mode_single(self):
+        # GH 15714
         exp_single = [1]
         data_single = [1]