BUG: GH4119 Fixed bug in convert_objects(convert_numeric=True) where a mixed numeric and

     object Series/Frame was not converting properly

BUG: convert_numeric=False changed for default in convert_objects for Series (which mastches Frame)

Author: jreback

doc/source/release.rst

@@ -316,6 +316,8 @@ pandas 0.12
   - Better error messages on inserting incompatible columns to a frame (:issue:`4107`)
   - Fixed bug in ``DataFrame.replace`` where a nested dict wasn't being
     iterated over when regex=False (:issue:`4115`)
+  - Fixed bug in ``convert_objects(convert_numeric=True)`` where a mixed numeric and
+    object Series/Frame was not converting properly (:issue:`4119`)
 
 
 pandas 0.11.0

pandas/core/series.py

@@ -928,7 +928,7 @@ def astype(self, dtype):
         return self._constructor(values, index=self.index, name=self.name,
                                  dtype=values.dtype)
 
-    def convert_objects(self, convert_dates=True, convert_numeric=True, copy=True):
+    def convert_objects(self, convert_dates=True, convert_numeric=False, copy=True):
         """
         Attempt to infer better dtype
 

pandas/src/inference.pyx

@@ -379,11 +379,14 @@ def maybe_convert_numeric(ndarray[object] values, set na_values,
         elif util.is_float_object(val):
             floats[i] = complexes[i] = val
             seen_float = 1
+        elif util.is_integer_object(val):
+            floats[i] = ints[i] = val
+            seen_int = 1
         elif val is None:
             floats[i] = complexes[i] = nan
             seen_float = 1
-        elif len(val) == 0:
-            if convert_empty:
+        elif hasattr(val,'__len__') and len(val) == 0:
+            if convert_empty or coerce_numeric:
                 floats[i] = complexes[i] = nan
                 seen_float = 1
             else:

pandas/tests/test_frame.py

@@ -5476,6 +5476,12 @@ def test_convert_objects(self):
         converted = self.mixed_frame.copy()
         self.assertRaises(Exception, converted['H'].astype, 'int32')
 
+        # mixed in a single column
+        df = DataFrame(dict(s = Series([1, 'na', 3 ,4])))
+        result = df.convert_objects(convert_numeric=True)
+        expected = DataFrame(dict(s = Series([1, np.nan, 3 ,4])))
+        assert_frame_equal(result, expected)
+
     def test_convert_objects_no_conversion(self):
         mixed1 = DataFrame(
             {'a': [1, 2, 3], 'b': [4.0, 5, 6], 'c': ['x', 'y', 'z']})

pandas/tests/test_series.py

@@ -3430,44 +3430,54 @@ def test_convert_objects(self):
 
         s = Series([1., 2, 3],index=['a','b','c'])
         result = s.convert_objects(convert_dates=False,convert_numeric=True)
-        assert_series_equal(s,result)
+        assert_series_equal(result, s)
 
         # force numeric conversion
         r = s.copy().astype('O')
         r['a'] = '1'
         result = r.convert_objects(convert_dates=False,convert_numeric=True)
-        assert_series_equal(s,result)
+        assert_series_equal(result, s)
 
         r = s.copy().astype('O')
         r['a'] = '1.'
         result = r.convert_objects(convert_dates=False,convert_numeric=True)
-        assert_series_equal(s,result)
+        assert_series_equal(result, s)
 
         r = s.copy().astype('O')
         r['a'] = 'garbled'
         expected = s.copy()
         expected['a'] = np.nan
         result = r.convert_objects(convert_dates=False,convert_numeric=True)
-        assert_series_equal(expected,result)
+        assert_series_equal(result, expected)
+
+        # GH 4119, not converting a mixed type (e.g.floats and object)
+        s = Series([1, 'na', 3 ,4])
+        result = s.convert_objects(convert_numeric=True)
+        expected = Series([1,np.nan,3,4])
+        assert_series_equal(result, expected)
+
+        s = Series([1, '', 3 ,4])
+        result = s.convert_objects(convert_numeric=True)
+        expected = Series([1,np.nan,3,4])
+        assert_series_equal(result, expected)
 
         # dates
         s = Series([datetime(2001,1,1,0,0), datetime(2001,1,2,0,0), datetime(2001,1,3,0,0) ])
         s2 = Series([datetime(2001,1,1,0,0), datetime(2001,1,2,0,0), datetime(2001,1,3,0,0), 'foo', 1.0, 1, Timestamp('20010104'), '20010105'],dtype='O')
 
         result = s.convert_objects(convert_dates=True,convert_numeric=False)
         expected = Series([Timestamp('20010101'),Timestamp('20010102'),Timestamp('20010103')],dtype='M8[ns]')
-        assert_series_equal(expected,result)
+        assert_series_equal(result, expected)
 
         result = s.convert_objects(convert_dates='coerce',convert_numeric=False)
-        assert_series_equal(expected,result)
         result = s.convert_objects(convert_dates='coerce',convert_numeric=True)
-        assert_series_equal(expected,result)
+        assert_series_equal(result, expected)
 
         expected = Series([Timestamp('20010101'),Timestamp('20010102'),Timestamp('20010103'),lib.NaT,lib.NaT,lib.NaT,Timestamp('20010104'),Timestamp('20010105')],dtype='M8[ns]')
         result = s2.convert_objects(convert_dates='coerce',convert_numeric=False)
-        assert_series_equal(expected,result)
+        assert_series_equal(result, expected)
         result = s2.convert_objects(convert_dates='coerce',convert_numeric=True)
-        assert_series_equal(expected,result)
+        assert_series_equal(result, expected)
 
         # preserver all-nans (if convert_dates='coerce')
         s = Series(['foo','bar',1,1.0],dtype='O')