fixups

Author: jreback

pandas/core/groupby.py

@@ -256,11 +256,13 @@ def __init__(self, key=None, level=None, freq=None, axis=0, sort=False):
  def ax(self):
  return self.grouper
 
- def _get_grouper(self, obj):
+ def _get_grouper(self, obj, validate=True):
  """
  Parameters
  ----------
  obj : the subject object
+ validate : boolean, default True
+ if True, validate the grouper
 
  Returns
  -------
@@ -271,7 +273,8 @@ def _get_grouper(self, obj):
  self.grouper, exclusions, self.obj = _get_grouper(self.obj, [self.key],
  axis=self.axis,
  level=self.level,
- sort=self.sort)
+ sort=self.sort,
+ validate=validate)
  return self.binner, self.grouper, self.obj
 
  def _set_grouper(self, obj, sort=False):
@@ -1739,8 +1742,9 @@ class BaseGrouper(object):
  whether this grouper will give sorted result or not
  group_keys : boolean, default True
  mutated : boolean, default False
- indexer : the indexer created by Grouper
- some grouper (TimeGrouper eg) will sort its axis and its
+ indexer : intp array, optional
+ the indexer created by Grouper
+ some groupers (TimeGrouper) will sort its axis and its
  group_info is also sorted, so need the indexer to reorder
 
  """
@@ -2514,8 +2518,11 @@ def __init__(self, index, grouper=None, obj=None, name=None, level=None,
  # a passed Grouper like, directly get the grouper in the same way
  # as single grouper groupby, use the group_info to get labels
  elif isinstance(self.grouper, Grouper):
- # get the new grouper
- _, grouper, _ = self.grouper._get_grouper(self.obj)
+ # get the new grouper; we already have disambiguated
+ # what key/level refer to exactly, don't need to
+ # check again as we have by this point converted these
+ # to an actual value (rather than a pd.Grouper)
+ _, grouper, _ = self.grouper._get_grouper(self.obj, validate=False)
  if self.name is None:
  self.name = grouper.result_index.name
  self.obj = self.grouper.obj
@@ -2587,12 +2594,12 @@ def ngroups(self):
 
  @cache_readonly
  def indices(self):
- # for the situation of groupby list of groupers
+ # we have a list of groupers
  if isinstance(self.grouper, BaseGrouper):
  return self.grouper.indices
- else:
-  values = _ensure_categorical(self.grouper)
-  return values._reverse_indexer()
+
+ values = _ensure_categorical(self.grouper)
+ return values._reverse_indexer()
 
  @property
  def labels(self):
@@ -2608,7 +2615,7 @@ def group_index(self):
 
  def _make_labels(self):
  if self._labels is None or self._group_index is None:
- # for the situation of groupby list of groupers
+ # we have a list of groupers
  if isinstance(self.grouper, BaseGrouper):
  labels = self.grouper.label_info
  uniques = self.grouper.result_index
@@ -2626,7 +2633,7 @@ def groups(self):
 
 
 def _get_grouper(obj, key=None, axis=0, level=None, sort=True,
- mutated=False):
+ mutated=False, validate=True):
  """
  create and return a BaseGrouper, which is an internal
  mapping of how to create the grouper indexers.
@@ -2643,6 +2650,8 @@ def _get_grouper(obj, key=None, axis=0, level=None, sort=True,
  are and then creates a Grouping for each one, combined into
  a BaseGrouper.
 
+ If validate, then check for key/level overlaps
+
  """
  group_axis = obj._get_axis(axis)
 
@@ -2767,7 +2776,7 @@ def is_in_obj(gpr):
 
  elif is_in_axis(gpr): # df.groupby('name')
  if gpr in obj:
- if gpr in obj.index.names:
+ if validate and gpr in obj.index.names:
  warnings.warn(
  ("'%s' is both a column name and an index level.\n"
  "Defaulting to column but "

pandas/core/resample.py

@@ -879,14 +879,7 @@ def _downsample(self, how, **kwargs):
 
  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, indexer=self.groupby.indexer)
- return self._groupby_and_aggregate(how, grouper=grouper)
+ return self._groupby_and_aggregate(how, grouper=self.grouper)
  elif is_superperiod(ax.freq, self.freq):
  if how == 'ohlc':
  # GH #13083
@@ -1112,7 +1105,7 @@ def _get_resampler(self, obj, kind=None):
  "TimedeltaIndex or PeriodIndex, "
  "but got an instance of %r" % type(ax).__name__)
 
- def _get_grouper(self, obj):
+ def _get_grouper(self, obj, validate=True):
  # create the resampler and return our binner
  r = self._get_resampler(obj)
  r._set_binner()

pandas/tests/groupby/test_timegrouper.py

@@ -634,9 +634,11 @@ def test_scalar_call_versus_list_call(self):
  'value': [1, 2, 3]
  }
  data_frame = pd.DataFrame(data_frame).set_index('time')
- grouper = pd.TimeGrouper('D')
+ grouper = pd.Grouper(freq='D')
+
  grouped = data_frame.groupby(grouper)
- data1 = grouped.count()
+ result = grouped.count()
  grouped = data_frame.groupby([grouper])
- data2 = grouped.count()
- assert_frame_equal(data1, data2)
+ expected = grouped.count()
+
+ assert_frame_equal(result, expected)