Merge pull request #6028 from jreback/series_infer

BUG: Bug in Series construction of mixed type with datelike and an integer

Author: jreback

doc/source/release.rst

@@ -130,6 +130,8 @@ Bug Fixes
     and off-diagonal plots, see (:issue:`5497`).
   - Regression in Series with a multi-index via ix (:issue:`6018`)
   - Bug in Series.xs with a multi-index (:issue:`6018`)
+  - Bug in Series construction of mixed type with datelike and an integer (which should result in
+    object type and not automatic conversion) (:issue:`6028`)
 
 pandas 0.13.0
 -------------

pandas/tests/test_indexing.py

@@ -623,6 +623,12 @@ def test_loc_general(self):
         self.assert_((result.columns == ['A','B']).all() == True)
         self.assert_((result.index == ['A','B']).all() == True)
 
+        # mixed type
+        result = DataFrame({ 'a' : [Timestamp('20130101')], 'b' : [1] }).iloc[0]
+        expected = Series([ Timestamp('20130101'), 1],index=['a','b'])
+        assert_series_equal(result,expected)
+        self.assert_(result.dtype == object)
+
     def test_loc_setitem_frame(self):
         df = self.frame_labels
 

pandas/tests/test_series.py

@@ -573,6 +573,11 @@ def test_constructor_dtype_datetime64(self):
         result = Series([datetime(3000,1,1)])
         self.assert_(result[0] == datetime(3000,1,1,0,0))
 
+        # don't mix types
+        result = Series([ Timestamp('20130101'), 1],index=['a','b'])
+        self.assert_(result['a'] == Timestamp('20130101'))
+        self.assert_(result['b'] == 1)
+
     def test_constructor_dict(self):
         d = {'a': 0., 'b': 1., 'c': 2.}
         result = Series(d, index=['b', 'c', 'd', 'a'])

pandas/tslib.pyx

@@ -1005,7 +1005,7 @@ def array_to_datetime(ndarray[object] values, raise_=False, dayfirst=False,
         ndarray[int64_t] iresult
         ndarray[object] oresult
         pandas_datetimestruct dts
-        bint utc_convert = bool(utc)
+        bint utc_convert = bool(utc), seen_integer=0, seen_datetime=0
         _TSObject _ts
         int64_t m = cast_from_unit(None,unit)
 
@@ -1017,6 +1017,7 @@ def array_to_datetime(ndarray[object] values, raise_=False, dayfirst=False,
             if _checknull_with_nat(val):
                 iresult[i] = iNaT
             elif PyDateTime_Check(val):
+                seen_datetime=1
                 if val.tzinfo is not None:
                     if utc_convert:
                         _ts = convert_to_tsobject(val, None, unit)
@@ -1047,6 +1048,7 @@ def array_to_datetime(ndarray[object] values, raise_=False, dayfirst=False,
                 iresult[i] = _date_to_datetime64(val, &dts)
                 try:
                     _check_dts_bounds(&dts)
+                    seen_datetime=1
                 except ValueError:
                     if coerce:
                         iresult[i] = iNaT
@@ -1058,6 +1060,7 @@ def array_to_datetime(ndarray[object] values, raise_=False, dayfirst=False,
                 else:
                     try:
                         iresult[i] = _get_datetime64_nanos(val)
+                        seen_datetime=1
                     except ValueError:
                         if coerce:
                             iresult[i] = iNaT
@@ -1070,11 +1073,13 @@ def array_to_datetime(ndarray[object] values, raise_=False, dayfirst=False,
                     iresult[i] = iNaT
                 else:
                     iresult[i] = val*m
+                    seen_integer=1
             elif util.is_float_object(val) and not coerce:
                 if val != val or val == iNaT:
                     iresult[i] = iNaT
                 else:
                     iresult[i] = cast_from_unit(val,unit)
+                    seen_integer=1
             else:
                 try:
                     if len(val) == 0:
@@ -1114,6 +1119,12 @@ def array_to_datetime(ndarray[object] values, raise_=False, dayfirst=False,
                         continue
                     raise
 
+        # don't allow mixed integers and datetime like
+        # higher levels can catch and coerce to object, for
+        # example
+        if seen_integer and seen_datetime:
+            raise ValueError("mixed datetimes and integers in passed array")
+
         return result
     except OutOfBoundsDatetime:
         if raise_: