def main():
edges = prep.read_edges(path + fn)
net = prep.build_net(edges)
train, test = prep.divide_net(net, ratio)
#CN
sim = CN.predict_link(train)
#Jaccard
sim = Jaccard.predict_link(train)
#AA
sim = AA.predict_link(train)
#RA
sim = RA.predict_link(train)
#PA
sim = PA.predict_link(train)
#Katz
sim = Katz.predict_link(train)
#SimRank
sim = SimRank.predict_link(train)
def main():
edges = prep.read_edges(path + fn)
net = prep.build_net(edges)
train, test = prep.divide_net(net, ratio)
#CN
sim = CN.predict_link(train)
#Jaccard
sim = Jaccard.predict_link(train)
#AA
sim = AA.predict_link(train)
#RA
sim = RA.predict_link(train)
#PA
sim = PA.predict_link(train)
#Katz
sim = Katz.predict_link(train)
#SimRank
sim = SimRank.predict_link(train)
def test():
edges = prep.read_edges(path + in_fn)
net = prep.build_net(edges)
my = SimRank.predict_link(net, 0.8)
output_mat(my, path + 'my.txt')
oth = read_mat(path + 'oth.txt')
print cmp_mat(my, oth)
def test():
edges = prep.read_edges(path + in_fn)
net = prep.build_net(edges)
my = SimRank.predict_link(net, 0.8)
output_mat(my, path + 'my.txt')
oth = read_mat(path + 'oth.txt')
print cmp_mat(my, oth)
print "开始构建伴病网络"
G, bad_names = build_network(medical_records, normal_disease,
normal_surgeries, last_res)
end_time = datetime.datetime.now()
print "构建伴病网络时间为 %d秒" % (end_time - start_time).seconds
cnt_node = len(G)
cnt_edge = 0
for x in G:
cnt_edge += len(G[x])
print "节点数：%d" % cnt_node
print "边数：%d" % cnt_edge
net = WLM("texts/out/graph.txt")
start_time = datetime.datetime.now()
s = sr.SimRank(graph_file="texts/out/graph.txt")
s.sim_rank()
res = s.get_result() # simrank 结果字典
s.print_result("texts/out/similarity.txt")
end_time = datetime.datetime.now()
print '节点数: %d' % len(s.nodes)
print 'sim_rank运行时间为%d' % (end_time - start_time).seconds
d = db.DataBase()
values = d.query('select 非标准名称, 标准疾病名 from labeleddata')
cnt_before = 0
cnt_after = 0
cnt_weighted = 0
cnt_noise = 0
cnt_correct = 0
damp = 0.15
tStart = time.time()
pageRank = PageRank.PageRank(graph, damp)
tEnd = time.time()
timeCost = tEnd - tStart
with open("output.txt", 'w', encoding='UTF-8') as f:
f.write("time cost: %f\n" % timeCost)
f.write("PageRank\n")
for key in pageRank:
f.write("%s: " % key)
f.write("%f\n" % pageRank[key])
f.close()
elif method == 'simrank':
c = 0.8 #decay factor
tStart = time.time()
simMatrix = SimRank.SimRank(graph, c)
tEnd = time.time()
timeCost = tEnd - tStart
# df = pd.DataFrame.from_dict(simMatrix,orient='index').transpose()
# # ax = sns.heatmap(df, cmap="YlGnBu", annot=True, fmt="f")
# ax = sns.heatmap(df, cmap="YlGnBu")
# label_y = ax.get_yticklabels()
# plt.setp(label_y, rotation=45, horizontalalignment='right')
# label_x = ax.get_xticklabels()
# plt.setp(label_x, rotation=45, horizontalalignment='right')
# plt.xlabel('vertex')
# plt.ylabel('vertex')
# plt.title('Heatmap')
# plt.show()
with open("output.txt", 'w', encoding='UTF-8') as f:
f.write("time cost: %f\n" % timeCost)
for k, v in union_times.iteritems():
v1 = v * 1.0 / single_times[k[0]] # 权值1
G.add_edge(k[0], k[1], weight=v1)
v2 = v * 1.0 / single_times[k[1]] # 权值2
G.add_edge(k[1], k[0], weight=v2)
return G, bad_names
def disambiguate(labeled_data, sim_res, bad_names):
normal, icd4_dic = get_cand_init()
for u_name, n_name in labeled_data:
name_dic = get_cand(u_name, normal, icd4_dic)
name_list = dic2list(name_dic)
name_list[0][0]
normal_dis, normal_sur, records, labeled_data = init()
G, bad_names = get_graph(normal_dis, normal_sur, records, labeled_data)
write_G(G, "iteration_texts/out/graph.txt")
write_bad_names(bad_names, "iteration_texts/out/bad_names.txt")
s = SimRank.SimRank(graph_file="iteration_texts/out/graph.txt")
s.sim_rank()
res = s.get_result()
s.print_result("iteration_texts/out/similarity.txt")
ret = disambiguate(labeled_data, res, bad_names)
