Merge pull request #4740 from hayd/ohlc_dataframe

ENH ohlc resample for DataFrame

Author: hayd

doc/source/release.rst

@@ -79,6 +79,7 @@ Improvements to existing features
   - Significant table writing performance improvements in ``HDFStore``
   - JSON date serialisation now performed in low-level C code.
   - Add ``drop_level`` argument to xs (:issue:`4180`)
+  - Can now resample a DataFrame with ohlc (:issue:`2320`)
   - ``Index.copy()`` and ``MultiIndex.copy()`` now accept keyword arguments to
     change attributes (i.e., ``names``, ``levels``, ``labels``)
     (:issue:`4039`)

pandas/core/groupby.py

@@ -1616,7 +1616,6 @@ def _iterate_slices(self):
         for val in slice_axis:
             if val in self.exclusions:
                 continue
-
             yield val, slicer(val)
 
     def _cython_agg_general(self, how, numeric_only=True):
@@ -2230,6 +2229,26 @@ def _wrap_agged_blocks(self, blocks):
 
         return result.convert_objects()
 
+    def _iterate_column_groupbys(self):
+        for i, colname in enumerate(self.obj.columns):
+            yield colname, SeriesGroupBy(self.obj.iloc[:, i], selection=colname,
+                                         grouper=self.grouper,
+                                         exclusions=self.exclusions)
+
+    def _apply_to_column_groupbys(self, func):
+        from pandas.tools.merge import concat
+        return concat((func(col_groupby)
+                            for _, col_groupby in self._iterate_column_groupbys()),
+                        keys=self.obj.columns,
+                        axis=1)
+
+    def ohlc(self):
+        """
+        Compute sum of values, excluding missing values
+
+        For multiple groupings, the result index will be a MultiIndex
+        """
+        return self._apply_to_column_groupbys(lambda x: x._cython_agg_general('ohlc'))
 
 from pandas.tools.plotting import boxplot_frame_groupby
 DataFrameGroupBy.boxplot = boxplot_frame_groupby

pandas/tseries/tests/test_resample.py

@@ -259,6 +259,31 @@ def test_resample_ohlc(self):
         self.assertEquals(xs['low'], s[:5].min())
         self.assertEquals(xs['close'], s[4])
 
+    def test_resample_ohlc_dataframe(self):
+        df = (pd.DataFrame({'PRICE': {Timestamp('2011-01-06 10:59:05', tz=None): 24990,
+                                     Timestamp('2011-01-06 12:43:33', tz=None): 25499,
+                                     Timestamp('2011-01-06 12:54:09', tz=None): 25499},
+                           'VOLUME': {Timestamp('2011-01-06 10:59:05', tz=None): 1500000000,
+                                      Timestamp('2011-01-06 12:43:33', tz=None): 5000000000,
+                                      Timestamp('2011-01-06 12:54:09', tz=None): 100000000}})
+            ).reindex_axis(['VOLUME', 'PRICE'], axis=1)
+        res = df.resample('H', how='ohlc')
+        exp = pd.concat([df['VOLUME'].resample('H', how='ohlc'),
+                          df['PRICE'].resample('H', how='ohlc')],
+                        axis=1,
+                        keys=['VOLUME', 'PRICE'])
+        assert_frame_equal(exp, res)
+
+        df.columns = [['a', 'b'], ['c', 'd']]
+        res = df.resample('H', how='ohlc')
+        exp.columns = pd.MultiIndex.from_tuples([('a', 'c', 'open'), ('a', 'c', 'high'),
+            ('a', 'c', 'low'), ('a', 'c', 'close'), ('b', 'd', 'open'),
+            ('b', 'd', 'high'), ('b', 'd', 'low'), ('b', 'd', 'close')])
+        assert_frame_equal(exp, res)
+
+        # dupe columns fail atm
+        # df.columns = ['PRICE', 'PRICE']
+
     def test_resample_reresample(self):
         dti = DatetimeIndex(
             start=datetime(2005, 1, 1), end=datetime(2005, 1, 10),