Merge pull request pandas-dev#6628 from jreback/fillna_limit

BUG: Bug in fillna with limit and value specified

Author: jreback

doc/source/release.rst

@@ -232,7 +232,7 @@ Bug Fixes
 - Bug in sql writing with mixed dtypes possibly leading to data loss (:issue:`6509`)
 - Bug in popping from a Series (:issue:`6600`)
 - Bug in ``iloc`` indexing when positional indexer matched Int64Index of corresponding axis no reordering happened (:issue:`6612`)
-
+- Bug in ``fillna`` with ``limit`` and ``value`` specified
 
 pandas 0.13.1
 -------------

pandas/core/generic.py

@@ -2162,7 +2162,9 @@ def fillna(self, value=None, method=None, axis=0, inplace=False,
                     from pandas import Series
                     value = Series(value)
 
-                new_data = self._data.fillna(value=value, inplace=inplace,
+                new_data = self._data.fillna(value=value,
+                                             limit=limit,
+                                             inplace=inplace,
                                              downcast=downcast)
 
             elif isinstance(value, (dict, com.ABCSeries)):
@@ -2176,10 +2178,12 @@ def fillna(self, value=None, method=None, axis=0, inplace=False,
                     if k not in result:
                         continue
                     obj = result[k]
-                    obj.fillna(v, inplace=True)
+                    obj.fillna(v, limit=limit, inplace=True)
                 return result
             else:
-                new_data = self._data.fillna(value=value, inplace=inplace,
+                new_data = self._data.fillna(value=value,
+                                             limit=limit,
+                                             inplace=inplace,
                                              downcast=downcast)
 
         if inplace:

pandas/core/internals.py

@@ -367,14 +367,19 @@ def apply(self, func, **kwargs):
         """ apply the function to my values; return a block if we are not one """
         return self.as_block(func(self.values))
 
-    def fillna(self, value, inplace=False, downcast=None):
+    def fillna(self, value, limit=None, inplace=False, downcast=None):
         if not self._can_hold_na:
             if inplace:
                 return [self]
             else:
                 return [self.copy()]
 
         mask = com.isnull(self.values)
+        if limit is not None:
+            if self.ndim > 2:
+                raise NotImplementedError
+            mask[mask.cumsum(self.ndim-1)>limit]=False
+
         value = self._try_fill(value)
         blocks = self.putmask(mask, value, inplace=inplace)
         return self._maybe_downcast(blocks, downcast)
@@ -1680,11 +1685,18 @@ def _try_fill(self, value):
             value = tslib.iNaT
         return value
 
-    def fillna(self, value, inplace=False, downcast=None):
+    def fillna(self, value, limit=None,
+               inplace=False, downcast=None):
+
         # straight putmask here
         values = self.values if inplace else self.values.copy()
         mask = com.isnull(self.values)
         value = self._try_fill(value)
+        if limit is not None:
+            if self.ndim > 2:
+                raise NotImplementedError
+            mask[mask.cumsum(self.ndim-1)>limit]=False
+
         np.putmask(values, mask, value)
         return [self if inplace else
                 make_block(values, self.items, self.ref_items, fastpath=True)]
@@ -1889,8 +1901,10 @@ def interpolate(self, method='pad', axis=0, inplace=False,
             self.values.to_dense(), method, axis, limit, fill_value)
         return self.make_block(values, self.items, self.ref_items)
 
-    def fillna(self, value, inplace=False, downcast=None):
+    def fillna(self, value, limit=None, inplace=False, downcast=None):
         # we may need to upcast our fill to match our dtype
+        if limit is not None:
+            raise NotImplementedError
         if issubclass(self.dtype.type, np.floating):
             value = float(value)
         values = self.values if inplace else self.values.copy()

pandas/tests/test_frame.py

@@ -7113,6 +7113,17 @@ def test_fillna(self):
         df.fillna({ 2: 'foo' }, inplace=True)
         assert_frame_equal(df, expected)
 
+        # limit and value
+        df = DataFrame(np.random.randn(10,3))
+        df.iloc[2:7,0] = np.nan
+        df.iloc[3:5,2] = np.nan
+
+        expected = df.copy()
+        expected.iloc[2,0] = 999
+        expected.iloc[3,2] = 999
+        result = df.fillna(999,limit=1)
+        assert_frame_equal(result, expected)
+
     def test_fillna_dtype_conversion(self):
         # make sure that fillna on an empty frame works
         df = DataFrame(index=["A","B","C"], columns = [1,2,3,4,5])

pandas/tests/test_panel.py

@@ -1322,6 +1322,11 @@ def test_fillna(self):
         self.assertRaises(TypeError, self.panel.fillna, [1, 2])
         self.assertRaises(TypeError, self.panel.fillna, (1, 2))
 
+        # limit not implemented when only value is specified
+        p = Panel(np.random.randn(3,4,5))
+        p.iloc[0:2,0:2,0:2] = np.nan
+        self.assertRaises(NotImplementedError, lambda : p.fillna(999,limit=1))
+
     def test_ffill_bfill(self):
         assert_panel_equal(self.panel.ffill(),
                            self.panel.fillna(method='ffill'))

pandas/tests/test_series.py

@@ -2941,6 +2941,16 @@ def test_fillna(self):
         expected = Series([0,0,2.], list('bac'))
         assert_series_equal(result,expected)
 
+        # limit
+        s = Series(np.nan,index=[0,1,2])
+        result = s.fillna(999,limit=1)
+        expected = Series([999,np.nan,np.nan],index=[0,1,2])
+        assert_series_equal(result,expected)
+
+        result = s.fillna(999,limit=2)
+        expected = Series([999,999,np.nan],index=[0,1,2])
+        assert_series_equal(result,expected)
+
     def test_fillna_bug(self):
         x = Series([nan, 1., nan, 3., nan], ['z', 'a', 'b', 'c', 'd'])
         filled = x.fillna(method='ffill')