def walk_down_graph(pno,depth,threshold,trait='top_tf-idf'):
count = 0
p = collection.find_one({'_id':pno},{'_id':1, 'citedby':1, trait:1})
gens = [[p]]
just_nodes = [p['_id']]
node_gens = [[p['_id']]]
links = []
for i in range(1,depth):
parents = gens[i-1]
next_gen = []
new_nodes = []
for par in parents:
children_pnos = par['citedby']
children = collection.find({'_id': {"$in":children_pnos}}, {'_id':1, 'citedby':1, trait:1})
for child in list(children):
if 'citedby' not in child.keys():
count += 1
elif len(child['citedby']) >= threshold:
links.append((par['_id'],child['_id']))
# add only previously unseen nodes
if child['_id'] not in just_nodes:
next_gen.append(child)
new_nodes.append(child['_id'])
just_nodes.append(child['_id'])
gens.append(next_gen)
node_gens.append(new_nodes)
print(count, 'without citedby')
# get rid of the gens, just a list of records
recs = []
count = 0
for gen in gens:
recs += gen
for rec in recs:
# rename '_id' to 'pno'
rec['pno'] = rec.pop('_id')
# rename trait to 'traits'
if trait in rec.keys():
rec['traits'] = rec.pop(trait)
else:
count += 1
rec['traits'] = []
count = round(float(count)/float(len(just_nodes)) * 100)
print('%d%% without traits' % count)
recs = et.recs_by_pno(recs)
sparse = tm.sparse_matrix(just_nodes,recs,'traits')
trait_dict = {}
for i,pno in enumerate(just_nodes):
trait_dict[pno] = sparse[i]
return (just_nodes,node_gens,links,trait_dict)
def walk_down_graph(pno,depth,threshold,trait=None):
p = collection.find_one({'pno':pno},{'pno':1, 'citedby':1, 'sorted_text':1})
gens = [[p]]
just_nodes = [p['pno']]
node_gens = [[p['pno']]]
links = []
for i in range(1,depth):
parents = gens[i-1]
next_gen = []
new_nodes = []
for par in parents:
children_pnos = par['citedby']
children = collection.find({'pno': {"$in":children_pnos}}, {'pno':1, 'citedby':1, 'sorted_text':1, 'text':1})
for child in list(children):
if len(child['citedby']) >= threshold:
links.append((par['pno'],child['pno']))
# add only previously unseen nodes
if child['pno'] not in just_nodes:
next_gen.append(child)
new_nodes.append(child['pno'])
just_nodes.append(child['pno'])
gens.append(next_gen)
node_gens.append(new_nodes)
recs = []
for gen in gens:
recs += gen
# get the trait dict
recs = et.recs_by_pno(recs)
recs = et.trim_sorted_text(recs,10)
sparse = tm.sparse_matrix(just_nodes,recs,'traits')
trait_dict = {}
for i,pno in enumerate(just_nodes):
trait_dict[pno] = sparse[i]
return (just_nodes,node_gens,links,trait_dict)
import trait_matrix as tm
import ..dots
f = open('zeolites_network_5_60.p', 'rb')
network = pickle.load(f)
n = 10
just_nodes = network[0]
node_gens = network[1]
links = network[2]
recs = network[3]
primo = just_nodes[0]
recs = et.recs_by_pno(recs)
recs = et.trim_sorted_text(recs,n)
p_by_c = et.parents_by_child(links)
# first patent doesn't have any parents! we need to add it manually
p_by_c[primo] = []
# get the primogenitors traits
primo_traits = recs[primo]['words']
# the matrix is ordered by the order of pnos in just_nodes
s_matrix = tm.sparse_matrix(just_nodes,recs,'words')
traits_by_pno = tm.traits_by_pno(just_nodes,s_matrix)
real_network = p_by_c
