with open('data/%s.csv' % dataset) as data_file:
reader = csv.reader(data_file)
reader.next()
for route, lat, lon, genus, species, count in reader:
route = (round(float(lat), 3), round(float(lon), 3))
spname = '%s %s' % (genus, species)
if not spname in all_species: continue
count_data_spp.add(spname)
count = int(count)
if not route in routes: routes[route] = set()
routes[route].add(spname)
data = {}
color_clusters(tree,
threshold=0,
draw=False,
all_colors=xrange(len(tips)),
color_attr='group',
min_clade_size=1)
thresholds = [0] + sorted(
set([
s.percentileofscore(tree._distances, clade._med_distance)
for clade in tree.find_elements() if hasattr(clade, '_med_distance')
]))
print thresholds
data = {}
for threshold in thresholds:
if threshold > 50: break
sys.stdout.write(str(threshold) + '...')
sys.stdout.flush()
color_clusters(tree,
threshold=threshold,
tips = tree.get_terminals()
all_species = {t.name: t for t in tips}
routes = {}
with open('fia.csv') as data_file:
reader = csv.reader(data_file)
reader.next()
for lat, lon, genus, species, count in reader:
spname = '%s %s' % (genus, species)
if not spname in all_species: continue
lat, lon = round(float(lat)), round(float(lon))
count = int(count)
route = lat, lon
if not route in routes: routes[route] = set()
routes[route].add(spname)
results = {}
for threshold in np.arange(0, 40, 5):
print threshold
results[threshold] = {}
color_clusters(tree, threshold=threshold, draw=False, all_colors = xrange(len(tips)),
color_attr='group', min_clade_size=1)
for route, spp in routes.iteritems():
results[threshold][route] = set()
for sp in spp:
if sp in all_species and hasattr(all_species[sp], 'group'):
results[threshold][route].add(all_species[sp].group)
with open('evolutionary_scale.pkl', 'w') as pickle_file:
pkl.dump(results, pickle_file, -1)
import Bio.Phylo as bp import geophy.cluster as g import sys try: tree_file = sys.argv[1] except: tree_file = 'bbs_granivores.new' t = bp.read(tree_file,'newick') g.color_clusters(t, threshold=10)
