API: change resample to infer correct closed and label value by default #2363

Author: changhiskhan

pandas/core/generic.py

@@ -203,7 +203,7 @@ def between_time(self, start_time, end_time, include_start=True,
             raise TypeError('Index must be DatetimeIndex')
 
     def resample(self, rule, how=None, axis=0, fill_method=None,
-                 closed='right', label='right', convention='start',
+                 closed=None, label=None, convention='start',
                  kind=None, loffset=None, limit=None, base=0):
         """
         Convenience method for frequency conversion and resampling of regular
@@ -216,9 +216,9 @@ def resample(self, rule, how=None, axis=0, fill_method=None,
               downsampling
         fill_method : string, fill_method for upsampling, default None
         axis : int, optional, default 0
-        closed : {'right', 'left'}, default 'right'
+        closed : {'right', 'left'}, default None
             Which side of bin interval is closed
-        label : {'right', 'left'}, default 'right'
+        label : {'right', 'left'}, default None
             Which bin edge label to label bucket with
         convention : {'start', 'end', 's', 'e'}
         loffset : timedelta

pandas/tseries/resample.py

@@ -35,11 +35,26 @@ class TimeGrouper(CustomGrouper):
     Use begin, end, nperiods to generate intervals that cannot be derived
     directly from the associated object
     """
-    def __init__(self, freq='Min', closed='right', label='right', how='mean',
+    def __init__(self, freq='Min', closed=None, label=None, how='mean',
                  nperiods=None, axis=0,
                  fill_method=None, limit=None, loffset=None, kind=None,
                  convention=None, base=0):
         self.freq = to_offset(freq)
+
+        end_types = set(['M', 'A', 'Q', 'BM', 'BA', 'BQ', 'W'])
+        rule = self.freq.rule_code
+        if (rule in end_types or
+            ('-' in rule and rule[:rule.find('-')])):
+            if closed is None:
+                closed = 'right'
+            if label is None:
+                label = 'right'
+        else:
+            if closed is None:
+                closed = 'left'
+            if label is None:
+                label = 'left'
+
         self.closed = closed
         self.label = label
         self.nperiods = nperiods

pandas/tseries/tests/test_resample.py

@@ -99,10 +99,11 @@ def test_resample_basic(self):
 
         s = self.series
         result = s.resample('5Min', how='last')
-        grouper = TimeGrouper(Minute(5), closed='right', label='right')
+        grouper = TimeGrouper(Minute(5), closed='left', label='left')
         expect = s.groupby(grouper).agg(lambda x: x[-1])
         assert_series_equal(result, expect)
 
+    def test_resample_basic_from_daily(self):
         # from daily
         dti = DatetimeIndex(start=datetime(2005,1,1), end=datetime(2005,1,10),
                             freq='D', name='index')
@@ -150,11 +151,11 @@ def test_resample_basic(self):
 
         # to biz day
         result = s.resample('B', how='last')
-        self.assertEquals(len(result), 6)
-        self.assert_((result.index.dayofweek == [0,1,2,3,4,0]).all())
-        self.assertEquals(result.irow(0), s['1/3/2005'])
-        self.assertEquals(result.irow(1), s['1/4/2005'])
-        self.assertEquals(result.irow(5), s['1/10/2005'])
+        self.assertEquals(len(result), 7)
+        self.assert_((result.index.dayofweek == [4,0,1,2,3,4,0]).all())
+        self.assertEquals(result.irow(0), s['1/2/2005'])
+        self.assertEquals(result.irow(1), s['1/3/2005'])
+        self.assertEquals(result.irow(5), s['1/9/2005'])
         self.assert_(result.index.name == 'index')
 
     def test_resample_frame_basic(self):
@@ -234,30 +235,30 @@ def test_upsample_with_limit(self):
     def test_resample_ohlc(self):
         s = self.series
 
-        grouper = TimeGrouper(Minute(5), closed='right', label='right')
+        grouper = TimeGrouper(Minute(5))
         expect = s.groupby(grouper).agg(lambda x: x[-1])
         result = s.resample('5Min', how='ohlc')
 
         self.assertEquals(len(result), len(expect))
         self.assertEquals(len(result.columns), 4)
 
-        xs = result.irow(-1)
-        self.assertEquals(xs['open'], s[-5])
-        self.assertEquals(xs['high'], s[-5:].max())
-        self.assertEquals(xs['low'], s[-5:].min())
-        self.assertEquals(xs['close'], s[-1])
+        xs = result.irow(-2)
+        self.assertEquals(xs['open'], s[-6])
+        self.assertEquals(xs['high'], s[-6:-1].max())
+        self.assertEquals(xs['low'], s[-6:-1].min())
+        self.assertEquals(xs['close'], s[-2])
 
-        xs = result.irow(1)
-        self.assertEquals(xs['open'], s[1])
-        self.assertEquals(xs['high'], s[1:6].max())
-        self.assertEquals(xs['low'], s[1:6].min())
-        self.assertEquals(xs['close'], s[5])
+        xs = result.irow(0)
+        self.assertEquals(xs['open'], s[0])
+        self.assertEquals(xs['high'], s[:5].max())
+        self.assertEquals(xs['low'], s[:5].min())
+        self.assertEquals(xs['close'], s[4])
 
     def test_resample_reresample(self):
         dti = DatetimeIndex(start=datetime(2005,1,1), end=datetime(2005,1,10),
                             freq='D')
         s = Series(np.random.rand(len(dti)), dti)
-        bs = s.resample('B')
+        bs = s.resample('B', closed='right', label='right')
         result = bs.resample('8H')
         self.assertEquals(len(result), 22)
         self.assert_(isinstance(result.index.freq, offsets.DateOffset))
@@ -296,7 +297,8 @@ def _ohlc(group):
                          freq='10s')
         ts = Series(np.random.randn(len(rng)), index=rng)
 
-        resampled = ts.resample('5min', how='ohlc')
+        resampled = ts.resample('5min', how='ohlc', closed='right',
+                                label='right')
 
         self.assert_((resampled.ix['1/1/2000 00:00'] == ts[0]).all())
 
@@ -394,7 +396,7 @@ def test_resample_base(self):
         ts = Series(np.random.randn(len(rng)), index=rng)
 
         resampled = ts.resample('5min', base=2)
-        exp_rng = date_range('1/1/2000 00:02:00', '1/1/2000 02:02',
+        exp_rng = date_range('12/31/1999 23:57:00', '1/1/2000 01:57',
                              freq='5min')
         self.assert_(resampled.index.equals(exp_rng))
 
@@ -785,7 +787,7 @@ def test_resample_irregular_sparse(self):
         dr = date_range(start='1/1/2012', freq='5min', periods=1000)
         s = Series(np.array(100), index=dr)
         # subset the data.
-        subset = s[:'2012-01-04 07:00']
+        subset = s[:'2012-01-04 06:55']
 
         result = subset.resample('10min', how=len)
         expected = s.resample('10min', how=len).ix[result.index]
@@ -828,7 +830,7 @@ def test_resample_tz_localized(self):
                          tz='Australia/Sydney')
         s = Series([1,2], index=idx)
 
-        result = s.resample('D')
+        result = s.resample('D', closed='right', label='right')
         ex_index = date_range('2001-09-21', periods=1, freq='D',
                               tz='Australia/Sydney')
         expected = Series([1.5], index=ex_index)