CLN: move PeriodIndex binning code to TimeGrouper

Simplifies PeriodIndexResampler and makes it more similar to Resampler,
DatetimeIndexResampler and TimedeltaIndexResampler.

Author: winklerand

pandas/core/resample.py

@@ -13,7 +13,7 @@
 from pandas.core.indexes.datetimes import DatetimeIndex, date_range
 from pandas.core.indexes.timedeltas import TimedeltaIndex
 from pandas.tseries.offsets import DateOffset, Tick, Day, _delta_to_nanoseconds
-from pandas.core.indexes.period import PeriodIndex, period_range
+from pandas.core.indexes.period import PeriodIndex
 import pandas.core.common as com
 import pandas.core.algorithms as algos
 
@@ -793,6 +793,11 @@ class PeriodIndexResampler(DatetimeIndexResampler):
     def _resampler_for_grouping(self):
         return PeriodIndexResamplerGroupby
 
+    def _get_binner_for_time(self):
+        if self.kind == 'timestamp':
+            return super(PeriodIndexResampler, self)._get_binner_for_time()
+        return self.groupby._get_period_bins(self.ax)
+
     def _convert_obj(self, obj):
         obj = super(PeriodIndexResampler, self)._convert_obj(obj)
 
@@ -817,29 +822,6 @@ def _convert_obj(self, obj):
 
         return obj
 
-    def aggregate(self, arg, *args, **kwargs):
-        result, how = self._aggregate(arg, *args, **kwargs)
-        if result is None:
-            result = self._downsample(arg, *args, **kwargs)
-
-        result = self._apply_loffset(result)
-        return result
-
-    agg = aggregate
-
-    def _get_new_index(self):
-        """ return our new index """
-        ax = self.ax
-
-        if len(ax) == 0:
-            values = []
-        else:
-            start = ax[0].asfreq(self.freq, how=self.convention)
-            end = ax[-1].asfreq(self.freq, how='end')
-            values = period_range(start, end, freq=self.freq).asi8
-
-        return ax._shallow_copy(values, freq=self.freq)
-
     def _downsample(self, how, **kwargs):
         """
         Downsample the cython defined function
@@ -857,21 +839,9 @@ def _downsample(self, how, **kwargs):
         how = self._is_cython_func(how) or how
         ax = self.ax
 
-        new_index = self._get_new_index()
-
-        # Start vs. end of period
-        memb = ax.asfreq(self.freq, how=self.convention)
-
         if is_subperiod(ax.freq, self.freq):
             # Downsampling
-            if len(new_index) == 0:
-                bins = []
-            else:
-                i8 = memb.asi8
-                rng = np.arange(i8[0], i8[-1] + 1)
-                bins = memb.searchsorted(rng, side='right')
-            grouper = BinGrouper(bins, new_index)
-            return self._groupby_and_aggregate(how, grouper=grouper)
+            return self._groupby_and_aggregate(how, grouper=self.grouper)
         elif is_superperiod(ax.freq, self.freq):
             return self.asfreq()
         elif ax.freq == self.freq:
@@ -905,9 +875,10 @@ def _upsample(self, method, limit=None, fill_value=None):
             return super(PeriodIndexResampler, self)._upsample(
                 method, limit=limit, fill_value=fill_value)
 
+        self._set_binner()
         ax = self.ax
         obj = self.obj
-        new_index = self._get_new_index()
+        new_index = self.binner
 
         # Start vs. end of period
         memb = ax.asfreq(self.freq, how=self.convention)
@@ -1269,6 +1240,29 @@ def _get_time_period_bins(self, ax):
 
         return binner, bins, labels
 
+    def _get_period_bins(self, ax):
+        if not isinstance(ax, PeriodIndex):
+            raise TypeError('axis must be a PeriodIndex, but got '
+                            'an instance of %r' % type(ax).__name__)
+
+        if not len(ax):
+            binner = labels = PeriodIndex(
+                data=[], freq=self.freq, name=ax.name)
+            return binner, [], labels
+
+        start = ax[0].asfreq(self.freq, how=self.convention)
+        end = ax[-1].asfreq(self.freq, how='end')
+
+        labels = binner = PeriodIndex(start=start, end=end,
+                                      freq=self.freq, name=ax.name)
+
+        memb = ax.asfreq(self.freq, how=self.convention)
+        i8 = memb.asi8
+        rng = np.arange(i8[0], i8[-1] + 1)
+        bins = memb.searchsorted(rng, side='right')
+
+        return binner, bins, labels
+
 
 def _take_new_index(obj, indexer, new_index, axis=0):
     from pandas.core.api import Series, DataFrame

pandas/tests/test_resample.py

@@ -3088,13 +3088,6 @@ def test_fails_on_no_datetime_index(self):
                                         "instance of %r" % name):
                 df.groupby(TimeGrouper('D'))
 
-        # PeriodIndex gives a specific error message
-        df = DataFrame({'a': np.random.randn(n)}, index=tm.makePeriodIndex(n))
-        with tm.assert_raises_regex(TypeError,
-                                    "axis must be a DatetimeIndex, but "
-                                    "got an instance of 'PeriodIndex'"):
-            df.groupby(TimeGrouper('D'))
-
     def test_aaa_group_order(self):
         # GH 12840
         # check TimeGrouper perform stable sorts