ti = lambda x: str(datetime.timedelta(seconds=round(x, 3)))[:-3]
add_times = {}
retrieve_times = {}
write_times = {}
parse_times = {}
print 'size\tadd\tretrieve\twrite\tparse'
for n in sizes:
s = str(n).zfill(4)
print s,
sys.stdout.flush()
start_time = time.time()
t.add_trees('tests/bird%s.new' % s, 'newick', 'test%s' % s)
add_times[n] = time.time() - start_time
print '\t', ti(add_times[n]),
sys.stdout.flush()
start_time = time.time()
tree = t.serialize_trees('test%s' % s)
retrieve_times[n] = time.time() - start_time
print '\t', ti(retrieve_times[n]),
sys.stdout.flush()
start_time = time.time()
bp.convert('tests/bird%s.new' % s, 'newick', 'tests/bird%s.cdao' % s, 'cdao')
write_times[n] = time.time() - start_time
print '\t', ti(write_times[n]),
sys.stdout.flush()
t = Treestore()
tree_files = [x for x in os.listdir('trees') if x.endswith('.nex')]
base_uri = 'http://www.phylocommons.org/trees/%s'
tree_list = set(t.list_trees())
if taxonomy:
sys.stdout.write('Loading taxonomy...')
sys.stdout.flush()
taxonomy = t.get_trees('%s_taxonomy' % taxonomy)[0]
taxonomy.index_labels()
print 'done.'
errors = set()
for tree_file in tree_files:
tree_id = 'TB2_' + tree_file[:-len('.nex')]
if Treestore.uri_from_id(tree_id) in tree_list: continue
print '**', tree_id
tree_path = os.path.join('trees', tree_file)
with open(tree_path) as input_file:
r = input_file.read()
if '<!DOCTYPE html' in r: continue
try:
t.add_trees(tree_path, 'nexus', tree_uri=tree_id, rooted=False,
taxonomy=taxonomy, tax_root=None)
except Exception as e:
print 'ERROR: ', e
errors.add(tree_id)
if errors:
print "Couldn't load the following trees:", ','.join(errors)