Merge pull request #5192 from jreback/compound_dtypes

BUG: raise NotImplementedError on passing of compound dtypes in constructors (GH5191)

Author: jreback

doc/source/release.rst

@@ -590,6 +590,7 @@ Bug Fixes
   - Fixed segfault on ``isnull(MultiIndex)`` (now raises an error instead)
     (:issue:`5123`, :issue:`5125`)
   - Allow duplicate indices when performing operations that align (:issue:`5185`)
+  - Compound dtypes in a constructor raise ``NotImplementedError`` (:issue:`5191`)
 
 pandas 0.12.0
 -------------

pandas/core/frame.py

@@ -189,6 +189,8 @@ def __init__(self, data=None, index=None, columns=None, dtype=None,
                  copy=False):
         if data is None:
             data = {}
+        if dtype is not None:
+            dtype = self._validate_dtype(dtype)
 
         if isinstance(data, DataFrame):
             data = data._data
@@ -276,9 +278,6 @@ def _init_dict(self, data, index, columns, dtype=None):
         Segregate Series based on type and coerce into matrices.
         Needs to handle a lot of exceptional cases.
         """
-        if dtype is not None:
-            dtype = np.dtype(dtype)
-
         if columns is not None:
             columns = _ensure_index(columns)
 
@@ -4659,9 +4658,6 @@ def _get_names_from_index(data):
 def _homogenize(data, index, dtype=None):
     from pandas.core.series import _sanitize_array
 
-    if dtype is not None:
-        dtype = np.dtype(dtype)
-
     oindex = None
     homogenized = []
 

pandas/core/generic.py

@@ -89,6 +89,18 @@ def __init__(self, data, axes=None, copy=False, dtype=None, fastpath=False):
         object.__setattr__(self, '_data', data)
         object.__setattr__(self, '_item_cache', {})
 
+    def _validate_dtype(self, dtype):
+        """ validate the passed dtype """
+
+        if dtype is not None:
+            dtype = np.dtype(dtype)
+
+            # a compound dtype
+            if dtype.kind == 'V':
+                raise NotImplementedError("compound dtypes are not implemented"
+                                          "in the {0} constructor".format(self.__class__.__name__))
+        return dtype
+
     def _init_mgr(self, mgr, axes=None, dtype=None, copy=False):
         """ passed a manager and a axes dict """
         for a, axe in axes.items():

pandas/core/panel.py

@@ -140,6 +140,8 @@ def _init_data(self, data, copy, dtype, **kwargs):
         """
         if data is None:
             data = {}
+        if dtype is not None:
+            dtype = self._validate_dtype(dtype)
 
         passed_axes = [kwargs.get(a) for a in self._AXIS_ORDERS]
         axes = None

pandas/core/series.py

@@ -139,6 +139,8 @@ def __init__(self, data=None, index=None, dtype=None, name=None,
 
             if data is None:
                 data = {}
+            if dtype is not None:
+                dtype = self._validate_dtype(dtype)
 
             if isinstance(data, MultiIndex):
                 raise NotImplementedError

pandas/tests/test_frame.py

@@ -10709,6 +10709,21 @@ def test_constructor_series_copy(self):
 
         self.assert_(not (series['A'] == 5).all())
 
+    def test_constructor_compound_dtypes(self):
+        # GH 5191
+        # compound dtypes should raise not-implementederror
+
+        def f(dtype):
+            return DataFrame(data = list(itertools.repeat((datetime(2001, 1, 1), "aa", 20), 9)),
+                             columns=["A", "B", "C"], dtype=dtype)
+
+        self.assertRaises(NotImplementedError, f, [("A","datetime64[h]"), ("B","str"), ("C","int32")])
+
+        # these work (though results may be unexpected)
+        f('int64')
+        f('float64')
+        f('M8[ns]')
+
     def test_assign_columns(self):
         self.frame['hi'] = 'there'
 

pandas/tests/test_generic.py

@@ -86,7 +86,7 @@ def _construct(self, shape, value=None, dtype=None, **kwargs):
                 arr = np.repeat(arr,new_shape).reshape(shape)
         else:
             arr = np.random.randn(*shape)
-        return self._typ(arr,**kwargs)
+        return self._typ(arr,dtype=dtype,**kwargs)
 
     def _compare(self, result, expected):
         self._comparator(result,expected)
@@ -210,6 +210,20 @@ def test_downcast(self):
         expected = o.astype(np.int64)
         self._compare(result, expected)
 
+    def test_constructor_compound_dtypes(self):
+        # GH 5191
+        # compound dtypes should raise not-implementederror
+
+        def f(dtype):
+            return self._construct(shape=3, dtype=dtype)
+
+        self.assertRaises(NotImplementedError, f, [("A","datetime64[h]"), ("B","str"), ("C","int32")])
+
+        # these work (though results may be unexpected)
+        f('int64')
+        f('float64')
+        f('M8[ns]')
+
 class TestSeries(unittest.TestCase, Generic):
     _typ = Series
     _comparator = lambda self, x, y: assert_series_equal(x,y)