def _unique_segments(self):
""" Common code for unique, unique_count and value_counts"""
# make dense column
densecol = self.replace(data=self.to_dense_buffer(), mask=None)
# sort the column
sortcol, _ = densecol.sort_by_values(ascending=True)
# find segments
sortedvals = sortcol.to_gpu_array()
segs, begins = cudautils.find_segments(sortedvals)
return segs, sortedvals
def _unique_segments(self):
""" Common code for unique, unique_count and value_counts"""
# make dense column
densecol = self.dropna()
# sort the column
sortcol, _ = densecol.sort_by_values()
# find segments
sortedvals = sortcol.data_array_view
segs, begins = cudautils.find_segments(sortedvals)
return segs, sortedvals
def _group_inner_levels(self, columns, rowidcol, segs, markers):
"""Group the second and onwards level.
Parameters
----------
columns : sequence[str]
Group keys. The order is important.
rowid_column : str
The name of the special column with the original rowid.
It's internally used to determine the shuffling order.
df : DataFrame
The dataframe being grouped.
segs : Series
First level group begin offsets.
Returns
-------
(sorted_keys, reordering_indices, segments)
- sorted_keys : list[Series]
List of sorted key columns.
Column order is same as arg *columns*.
- reordering_indices : device array
The indices to gather on to shuffle the dataframe
into the grouped seqence.
- segments : Series
Group begin offsets.
"""
dsegs = segs.astype(dtype=np.int32).data.mem
sorted_keys = []
plan_cache = {}
for col in columns:
# Shuffle the key column according to the previous groups
srkeys = self._df[col].take(rowidcol.to_gpu_array(),
ignore_index=True)
# Segmented sort on the key
shuf = Column(Buffer(cudautils.arange(len(srkeys))))
cache_key = (len(srkeys), srkeys.dtype, shuf.dtype)
plan = plan_cache.get(cache_key)
plan = apply_segsort(srkeys._column, shuf, dsegs, plan=plan)
plan_cache[cache_key] = plan
sorted_keys.append(srkeys) # keep sorted key cols
# Determine segments
dsegs, markers = cudautils.find_segments(srkeys.to_gpu_array(),
dsegs,
markers=markers)
# Shuffle
rowidcol = rowidcol.take(shuf.to_gpu_array(), ignore_index=True)
reordering_indices = rowidcol.to_gpu_array()
return sorted_keys, reordering_indices, Series(dsegs)
def _find_segments(self):
seg, markers = cudautils.find_segments(self.gpu_values)
return NumericalColumn(data=Buffer(seg), dtype=seg.dtype), markers
def _find_segments(self):
seg, markers = cudautils.find_segments(self.gpu_values)
return (
column.build_column(data=Buffer(seg), dtype=seg.dtype),
markers,
)
