def group_sample((sample, featureid)):
model = CrossCat()
with open_compressed(sample['model']) as f:
model.ParseFromString(f.read())
for kindid, kind in enumerate(model.kinds):
if featureid in kind.featureids:
break
assignments = assignment_stream_load(sample['assign'])
return collate((a.groupids(kindid), a.rowid) for a in assignments)
def group_sample((sample, featureid)):
model = CrossCat()
with open_compressed(sample['model']) as f:
model.ParseFromString(f.read())
for kindid, kind in enumerate(model.kinds):
if featureid in kind.featureids:
break
assignments = assignment_stream_load(sample['assign'])
return collate((a.groupids(kindid), a.rowid) for a in assignments)
def _retrieve_row_partitions(path, sample):
"""Return row partition from CrossCat `sample` at `path`.
The returned structure is of the form `cgpm.crosscat.state.State.Zrv`.
"""
cross_cat = _loom_cross_cat(path, sample)
num_kinds = len(cross_cat.kinds)
assign_in = os.path.join(path, 'samples', 'sample.%d' % (sample, ),
'assign.pbs.gz')
assignments = {
a.rowid: [a.groupids(k) for k in xrange(num_kinds)]
for a in assignment_stream_load(assign_in)
}
rowids = sorted(assignments)
return {
k: [assignments[rowid][k] for rowid in rowids]
for k in xrange(num_kinds)
}
def _retrieve_row_partition(self, bdb, generator_id, modelno):
"""Return row partition from a CrossCat model.
The returned structure is of the form `cgpm.crosscat.state.State.Zv`.
"""
cross_cat = self._get_cross_cat(bdb, generator_id, modelno)
num_kinds = len(cross_cat.kinds)
assign_in = os.path.join(
self._get_loom_project_path(bdb, generator_id), 'samples',
'sample.%d' % (modelno, ), 'assign.pbs.gz')
assignments = {
a.rowid: [a.groupids(k) for k in xrange(num_kinds)]
for a in assignment_stream_load(assign_in)
}
rowids = sorted(assignments)
return {
k: [assignments[rowid][k] for rowid in rowids]
for k in xrange(num_kinds)
}
def _retrieve_row_partition(self, bdb, generator_id, modelno):
"""Return row partition from a CrossCat model.
The returned structure is of the form `cgpm.crosscat.state.State.Zv`.
"""
cross_cat = self._get_cross_cat(bdb, generator_id, modelno)
num_kinds = len(cross_cat.kinds)
assign_in = os.path.join(
self._get_loom_project_path(bdb, generator_id),
'samples', 'sample.%d' % (modelno,), 'assign.pbs.gz')
assignments = {
a.rowid: [a.groupids(k) for k in xrange(num_kinds)]
for a in assignment_stream_load(assign_in)
}
rowids = sorted(assignments)
return {
k: [assignments[rowid][k] for rowid in rowids]
for k in xrange(num_kinds)
}