def test_group_by_distance_all(self):
obs = group_by_distance(self.testclusterslt10, 10)
exp = {
'(((...)))...(((...)))': [(9, 10)],
'(((...)))': [(1, 2), (3, 4), (11, 12), (5, 6)],
'.....((((.......))))...': [(15, 16), (7, 8)],
'............': [(13, 14)]}
self.assertEqual(obs, exp)
def test_group_by_distance_lt10_specific_nogroup(self):
obs = group_by_distance(self.testclusterslt10, 10, ['.....((((.......))))...'])
exp = {
"(((...)))": [(1, 2), (3, 4)],
"((.....))": [(5, 6)],
".....((((.......))))...": [(7, 8)],
"(((...)))...(((...)))": [(9, 10)],
"((((....))))": [(11, 12)],
'............': [(13, 14)]
}
self.assertEqual(obs, exp)
def test_group_by_distance_lt10_specific_group(self):
obs = group_by_distance(self.testclusterslt10, 15, specstructs=['(((...)))'])
print obs
files = []
hold = {}
pool = Pool(processes=args.c)
#run the pool over all shape groups to get final grouped structgroups
fout = open(otufolder + "shapesizes.txt", 'w')
groupnum = 1
for shapegroup in groups_shape.keys():
#write out each group to file for use in subprocess
groupinfo = {struct: structgroups[struct] for struct in groups_shape[shapegroup]}
fout.write(shapegroup + "\t" + str(len(groupinfo)) + "\n")
pool.apply_async(func=group_by_distance,
args=(groupinfo, structscore), callback=hold.update)
structgroups.clear()
del structgroups
stime = time()
hold.update(group_by_distance(groupinfo, structscore, None, None, args.nr))
print len(groupinfo), "clusters:", str((time()-stime)/60), "min"
fout.close()
#memory saving wipe of structgroups, groups_shape, and groupinfo
groups_shape.clear()
del groups_shape
groupinfo.clear()
del groupinfo
pool.close()
pool.join()
print "Grouped ("+str((time()-stime)/60)+" min)"
structgroups = dict(hold)
del hold
#sort all structure sequences by count, highest to lowest
for struct in structgroups: