Merge pull request #3072 from jreback/replace3

BUG: replace with a dict misbehaving (GH 3064), due to incorrect filtering

Author: jreback

pandas/core/frame.py

@@ -3468,8 +3468,8 @@ def replace(self, to_replace, value=None, method='pad', axis=0,
                 return self
 
             new_data = self._data
-            if isinstance(to_replace, dict):
-                if isinstance(value, dict):  # {'A' : NA} -> {'A' : 0}
+            if isinstance(to_replace, (dict, Series)):
+                if isinstance(value, (dict, Series)):  # {'A' : NA} -> {'A' : 0}
                     new_data = self._data
                     for c, src in to_replace.iteritems():
                         if c in value and c in self:
@@ -3481,7 +3481,7 @@ def replace(self, to_replace, value=None, method='pad', axis=0,
                         if k in self:
                             new_data = new_data.replace(src, value, filter = [ k ], inplace=inplace)
                 else:
-                    raise ValueError('Fill value must be scalar or dict')
+                    raise ValueError('Fill value must be scalar or dict or Series')
 
             elif isinstance(to_replace, (list, np.ndarray)):
                 # [NA, ''] -> [0, 'missing']
@@ -3501,7 +3501,7 @@ def replace(self, to_replace, value=None, method='pad', axis=0,
             else:
 
                 # dest iterable dict-like
-                if isinstance(value, dict):  # NA -> {'A' : 0, 'B' : -1}
+                if isinstance(value, (dict, Series)):  # NA -> {'A' : 0, 'B' : -1}
 
                     new_data = self._data
                     for k, v in value.iteritems():
@@ -3528,7 +3528,7 @@ def _interpolate(self, to_replace, method, axis, inplace, limit):
 
         method = com._clean_fill_method(method)
 
-        if isinstance(to_replace, dict):
+        if isinstance(to_replace, (dict, Series)):
             if axis == 1:
                 return self.T.replace(to_replace, method=method,
                                       limit=limit).T

pandas/core/internals.py

@@ -259,10 +259,15 @@ def _try_cast_result(self, result):
         we may have roundtripped thru object in the mean-time """
         return result
 
-    def replace(self, to_replace, value, inplace=False):
+    def replace(self, to_replace, value, inplace=False, filter=None):
         """ replace the to_replace value with value, possible to create new blocks here
             this is just a call to putmask """
         mask = com.mask_missing(self.values, to_replace)
+        if filter is not None:
+            for i, item in enumerate(self.items):
+                if item not in filter:
+                    mask[i] = False
+
         if not mask.any():
             if inplace:
                 return [ self ]
@@ -886,14 +891,15 @@ def apply(self, f, *args, **kwargs):
         ----------
         f : the callable or function name to operate on at the block level
         axes : optional (if not supplied, use self.axes)
-        filter : callable, if supplied, only call the block if the filter is True
+        filter : list, if supplied, only call the block if the filter is in the block
         """
 
         axes = kwargs.pop('axes',None)
-        filter = kwargs.pop('filter',None)
+        filter = kwargs.get('filter')
         result_blocks = []
         for blk in self.blocks:
             if filter is not None:
+                kwargs['filter'] = set(kwargs['filter'])
                 if not blk.items.isin(filter).any():
                     result_blocks.append(blk)
                     continue

pandas/tests/test_frame.py

@@ -5587,6 +5587,26 @@ def test_replace(self):
         df = DataFrame(index=['a', 'b'])
         assert_frame_equal(df, df.replace(5, 7))
 
+    def test_resplace_series_dict(self):
+        # from GH 3064
+        df = DataFrame({'zero': {'a': 0.0, 'b': 1}, 'one': {'a': 2.0, 'b': 0}}) 
+        result = df.replace(0, {'zero': 0.5, 'one': 1.0}) 
+        expected = DataFrame({'zero': {'a': 0.5, 'b': 1}, 'one': {'a': 2.0, 'b': 1.0}}) 
+        assert_frame_equal(result, expected) 
+
+        result = df.replace(0, df.mean()) 
+        assert_frame_equal(result, expected) 
+
+        # series to series/dict 
+        df = DataFrame({'zero': {'a': 0.0, 'b': 1}, 'one': {'a': 2.0, 'b': 0}}) 
+        s = Series({'zero': 0.0, 'one': 2.0}) 
+        result = df.replace(s, {'zero': 0.5, 'one': 1.0}) 
+        expected = DataFrame({'zero': {'a': 0.5, 'b': 1}, 'one': {'a': 1.0, 'b': 0.0}}) 
+        assert_frame_equal(result, expected) 
+
+        result = df.replace(s, df.mean()) 
+        assert_frame_equal(result, expected)
+
     def test_replace_mixed(self):
         self.mixed_frame['foo'][5:20] = nan
         self.mixed_frame['A'][-10:] = nan