BUG: int dtype diff for frame. refactored diff into common

Author: changhiskhan

pandas/core/common.py

@@ -373,6 +373,35 @@ def mask_out_axis(arr, mask, axis, fill_value=np.nan):
 
     arr[tuple(indexer)] = fill_value
 
+def diff(arr, n, indexer, axis=0):
+    out_arr = arr - arr.take(indexer, axis=axis)
+    out_arr = _maybe_upcast(out_arr)
+
+    if axis == 0:
+        if n > 0:
+            out_arr[:n] = np.nan
+        elif n < 0:
+            out_arr[n:] = np.nan
+        else:
+            out_arr[:] = np.nan
+    elif axis == 1:
+        if n > 0:
+            out_arr[:, :n] = np.nan
+        elif n < 0:
+            out_arr[:, n:] = np.nan
+        else:
+            out_arr[:, :] = np.nan
+    elif axis == 2:
+        if n > 0:
+            out_arr[:, :, :n] = np.nan
+        elif n < 0:
+            out_arr[:, :, n:] = np.nan
+        else:
+            out_arr[:, :, :] = np.nan
+    else:
+        raise NotImplementedError()
+    return out_arr
+
 
 def take_fast(arr, indexer, mask, needs_masking, axis=0, out=None,
               fill_value=np.nan):

pandas/core/frame.py

@@ -29,7 +29,8 @@
 from pandas.core.generic import NDFrame
 from pandas.core.index import Index, MultiIndex, _ensure_index
 from pandas.core.indexing import _NDFrameIndexer, _maybe_droplevels
-from pandas.core.internals import BlockManager, make_block, form_blocks
+from pandas.core.internals import (BlockManager, make_block, form_blocks,
+                                   IntBlock)
 from pandas.core.series import Series, _radd_compat
 from pandas.compat.scipy import scoreatpercentile as _quantile
 from pandas.util import py3compat
@@ -3679,7 +3680,10 @@ def diff(self, periods=1):
         -------
         diffed : DataFrame
         """
-        return self - self.shift(periods)
+        indexer = com._shift_indexer(len(self), periods)
+        new_blocks = [b.diff(periods, indexer) for b in self._data.blocks]
+        new_data = BlockManager(new_blocks, [self.columns, self.index])
+        return self._constructor(new_data)
 
     def shift(self, periods=1, freq=None, **kwds):
         """

pandas/core/internals.py

@@ -294,6 +294,13 @@ def take(self, indexer, axis=1, fill_value=np.nan):
     def get_values(self, dtype):
         return self.values
 
+    def diff(self, n, indexer=None):
+        if indexer is None:
+            indexer = com._shift_indexer(self.shape[1], n)
+        new_values = com.diff(self.values, n, indexer, axis=1)
+        return make_block(new_values, self.items, self.ref_items)
+
+
 def _mask_missing(array, missing_values):
     if not isinstance(missing_values, (list, np.ndarray)):
         missing_values = [missing_values]

pandas/core/series.py

@@ -1511,22 +1511,9 @@ def diff(self, periods=1):
         -------
         diffed : Series
         """
-        if com.is_integer_dtype(self):
-            new_values = np.empty(len(self), dtype=self.dtype)
-            new_values = _maybe_upcast(new_values)
-
-            if periods > 0:
-                new_values[periods:] = (self.values[periods:] -
-                                        self.values[:-periods])
-                new_values[:periods] = nan
-            elif periods < 0:
-                new_values[:periods] = (self.values[:periods] -
-                                        self.values[-periods:])
-                new_values[periods:] = nan
-
-            return Series(new_values, index=self.index, name=self.name)
-        else:
-            return self - self.shift(periods)
+        indexer = com._shift_indexer(len(self), periods)
+        val = com.diff(self.values, periods, indexer)
+        return Series(val, self.index, name=self.name)
 
     def autocorr(self):
         """

pandas/tests/test_frame.py

@@ -5215,6 +5215,14 @@ def test_diff(self):
         assert_series_equal(the_diff['A'],
                             self.tsframe['A'] - self.tsframe['A'].shift(1))
 
+        # int dtype
+        a = 10000000000000000
+        b = a + 1
+        s = Series([a, b])
+
+        rs = DataFrame({'s': s}).diff()
+        self.assertEqual(rs.s[1], 1)
+
     def test_diff_mixed_dtype(self):
         df = DataFrame(np.random.randn(5, 3))
         df['A'] = np.array([1, 2, 3, 4, 5], dtype=object)