Merge pull request #4677 from jreback/numeric2

BUG: preserve empty dtype if possible when creating an empty BlockManager

Author: jreback

pandas/core/internals.py

@@ -1582,7 +1582,10 @@ def make_empty(self, axes=None):
         """ return an empty BlockManager with the items axis of len 0 """
         if axes is None:
             axes = [_ensure_index([]) ] + [ _ensure_index(a) for a in self.axes[1:] ]
-        return self.__class__(np.array([]), axes)
+
+        # preserve dtype if possible
+        dtype = self.dtype if self.ndim == 1 else object
+        return self.__class__(np.array([],dtype=dtype), axes)
 
     def __nonzero__(self):
         return True

pandas/tests/test_generic.py

@@ -129,6 +129,31 @@ def test_rename_mi(self):
                    index=MultiIndex.from_tuples([("A",x) for x in ["a","B","c"]]))
         result = s.rename(str.lower)
 
+    def test_get_numeric_data_preserve_dtype(self):
+
+        # get the numeric data
+        o = Series([1,2,3])
+        result = o._get_numeric_data()
+        self._compare(result, o)
+
+        o = Series([1,'2',3.])
+        result = o._get_numeric_data()
+        expected = Series([],dtype=object)
+        self._compare(result, expected)
+
+        o = Series([True,False,True])
+        result = o._get_numeric_data()
+        self._compare(result, o)
+
+        o = Series([True,False,True])
+        result = o._get_bool_data()
+        self._compare(result, o)
+
+        o = Series(date_range('20130101',periods=3))
+        result = o._get_numeric_data()
+        expected = Series([],dtype='M8[ns]')
+        self._compare(result, expected)
+
 class TestDataFrame(unittest.TestCase, Generic):
     _typ = DataFrame
     _comparator = lambda self, x, y: assert_frame_equal(x,y)
@@ -138,6 +163,14 @@ def test_rename_mi(self):
                        index=MultiIndex.from_tuples([("A",x) for x in ["a","B","c"]]))
         result = df.rename(str.lower)
 
+    def test_get_numeric_data_preserve_dtype(self):
+
+        # get the numeric data
+        o = DataFrame({'A' : [1,'2',3.] })
+        result = o._get_numeric_data()
+        expected = DataFrame(index=[0,1,2],dtype=object)
+        self._compare(result, expected)
+
 class TestPanel(unittest.TestCase, Generic):
     _typ = Panel
     _comparator = lambda self, x, y: assert_panel_equal(x,y)