Merge remote branch 'chang/frame-dtype'

* chang/frame-dtype:
  Get rid of newline. Triggering Travis
  CLN: put new kwd at the end
  BUG: dtype=object should stop conversion from object in frame constructor #2255

Author: wesm

pandas/core/frame.py

@@ -399,8 +399,7 @@ def __init__(self, data=None, index=None, columns=None, dtype=None,
                     index = _get_names_from_index(data)
 
                 if isinstance(data[0], (list, tuple, dict, Series)):
-                    arrays, columns = _to_arrays(data, columns)
-
+                    arrays, columns = _to_arrays(data, columns, dtype=dtype)
                     columns = _ensure_index(columns)
 
                     if index is None:
@@ -5209,38 +5208,43 @@ def _rec_to_dict(arr):
     return columns, sdict
 
 
-def _to_arrays(data, columns, coerce_float=False):
+def _to_arrays(data, columns, coerce_float=False, dtype=None):
     """
     Return list of arrays, columns
     """
 
     if len(data) == 0:
         return [], columns if columns is not None else []
     if isinstance(data[0], (list, tuple)):
-        return _list_to_arrays(data, columns, coerce_float=coerce_float)
+        return _list_to_arrays(data, columns, coerce_float=coerce_float,
+                               dtype=dtype)
     elif isinstance(data[0], dict):
         return _list_of_dict_to_arrays(data, columns,
-                                       coerce_float=coerce_float)
+                                       coerce_float=coerce_float,
+                                       dtype=dtype)
     elif isinstance(data[0], Series):
         return _list_of_series_to_arrays(data, columns,
-                                        coerce_float=coerce_float)
+                                         coerce_float=coerce_float,
+                                         dtype=dtype)
     else:
         # last ditch effort
         data = map(tuple, data)
-        return _list_to_arrays(data, columns, coerce_float=coerce_float)
+        return _list_to_arrays(data, columns,
+                               coerce_float=coerce_float,
+                               dtype=dtype)
 
 
-def _list_to_arrays(data, columns, coerce_float=False):
+def _list_to_arrays(data, columns, coerce_float=False, dtype=None):
     if len(data) > 0 and isinstance(data[0], tuple):
         content = list(lib.to_object_array_tuples(data).T)
     else:
         # list of lists
         content = list(lib.to_object_array(data).T)
-    return _convert_object_array(content, columns,
+    return _convert_object_array(content, columns, dtype=dtype,
                                  coerce_float=coerce_float)
 
 
-def _list_of_series_to_arrays(data, columns, coerce_float=False):
+def _list_of_series_to_arrays(data, columns, coerce_float=False, dtype=None):
     from pandas.core.index import _get_combined_index
 
     if columns is None:
@@ -5261,13 +5265,13 @@ def _list_of_series_to_arrays(data, columns, coerce_float=False):
 
     if values.dtype == np.object_:
         content = list(values.T)
-        return _convert_object_array(content, columns,
+        return _convert_object_array(content, columns, dtype=dtype,
                                      coerce_float=coerce_float)
     else:
         return values.T, columns
 
 
-def _list_of_dict_to_arrays(data, columns, coerce_float=False):
+def _list_of_dict_to_arrays(data, columns, coerce_float=False, dtype=None):
     if columns is None:
         gen = (x.keys() for x in data)
         columns = lib.fast_unique_multiple_list_gen(gen)
@@ -5278,11 +5282,11 @@ def _list_of_dict_to_arrays(data, columns, coerce_float=False):
             for d in data]
 
     content = list(lib.dicts_to_array(data, list(columns)).T)
-    return _convert_object_array(content, columns,
+    return _convert_object_array(content, columns, dtype=dtype,
                                  coerce_float=coerce_float)
 
 
-def _convert_object_array(content, columns, coerce_float=False):
+def _convert_object_array(content, columns, coerce_float=False, dtype=None):
     if columns is None:
         columns = _default_index(len(content))
     else:
@@ -5291,6 +5295,7 @@ def _convert_object_array(content, columns, coerce_float=False):
                                  'columns' % (len(columns), len(content)))
 
     arrays = [lib.maybe_convert_objects(arr, try_float=coerce_float)
+              if dtype != object and dtype != np.object else arr
               for arr in content]
 
     return arrays, columns

pandas/tests/test_frame.py

@@ -1730,6 +1730,12 @@ def test_constructor_dtype_nocast_view(self):
         should_be_view[0][0] = 97
         self.assertEqual(df.values[0, 0], 97)
 
+    def test_constructor_dtype_list_data(self):
+        df = DataFrame([[1, '2'],
+                        [None, 'a']], dtype=object)
+        self.assert_(df.ix[1, 0] is None)
+        self.assert_(df.ix[0, 1] == '2')
+
     def test_constructor_rec(self):
         rec = self.frame.to_records(index=False)