#!/usr/bin/env python
import sys
import os
from treestore import Treestore
try: taxonomy = sys.argv[1]
except: taxonomy = None
t = Treestore()
treebase_uri = 'http://purl.org/phylo/treebase/phylows/tree/%s'
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())
for tree_uri in tree_list:
if not 'TB2_' in tree_uri: continue
tree_id = t.id_from_uri(tree_uri)
tb_uri = treebase_uri % (tree_id.replace('_', ':'))
print tree_id, tb_uri
t.annotate(tree_uri, annotations='?tree bibo:cites <%s> .' % tb_uri)
from treestore import Treestore
import Bio.Phylo as bp
import time
import datetime
from cStringIO import StringIO
import sys
import cPickle as pkl
t = Treestore()
sizes = [10, 50, 100, 200, 500, 1000, 2000, 5000]
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()
def uri_from_tree_id(tree_id):
return Treestore.uri_from_id(tree_id, base_uri=settings.TREE_URI)
#!/usr/bin/env python
import sys
import os
from treestore import Treestore
try: taxonomy = sys.argv[1]
except: taxonomy = None
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:
def tree_id_from_uri(uri):
return Treestore.id_from_uri(uri, base_uri=settings.TREE_URI)
