def cal_sim_pos(sent_a, sent_b):
"""
计算两个句子之间的词性相似度
:param sent_a:
:param sent_b:
:return:
"""
def __cal_vecmod(pos_dict):
mod_result = 0.0
for i in pos_dict.values():
mod_result += i ** 2
return math.sqrt(mod_result)
pos_a = sentence_utils.get_pos(sent_a)
pos_b = sentence_utils.get_pos(sent_b)
pos_a_dict = {}
pos_b_dict = {}
# 建立句子a的pos词典
for a in pos_a:
if a[1] in pos_a_dict.keys():
pos_a_dict[a[1]] += 1.0 / len(pos_a)
else:
pos_a_dict[a[1]] = 1.0 / len(pos_a)
# 建立句子b的pos词典
for b in pos_b:
if b[1] in pos_b_dict.keys():
pos_b_dict[b[1]] += 1.0 / len(pos_b)
else:
pos_b_dict[b[1]] = 1.0 / len(pos_b)
# 处理二者间的相似度
# 首先是分子的计算
fenzi = 0.0
for key_a in pos_a_dict:
if key_a in pos_b_dict:
fenzi += pos_a_dict[key_a] * pos_b_dict[key_a]
# 计算分母
fenmu = __cal_vecmod(pos_a_dict) * __cal_vecmod(pos_b_dict)
if fenmu == 0:
return 0
else:
return fenzi / fenmu
def get_graph_map_by_json(data_json, is_train=False):
graph_map = {}
for edge in data_json['edges']:
source = edge['source']
target = edge['target']
if source in graph_map:
graph_map[source]['neighbors'].append(target)
else:
graph_map[source] = {'content': data_json['nodes'][int(source)]['label'].split('-')[1],
'neighbors': [target], 'label': random.choice(['0', '1']),
'datetime': arrow.get(data_json['datetimes'][source], u'YYYY年MM月DD日 HH:mm',
tzinfo=tz.tzlocal()),
'feature': {'pos': get_pos(data_json['nodes'][int(source)]['label'].split('-')[1])}}
if target in graph_map:
graph_map[target]['neighbors'].append(source)
else:
graph_map[target] = {'content': data_json['nodes'][int(target)]['label'].split('-')[1],
'neighbors': [source], 'label': random.choice(['0', '1']),
'datetime': arrow.get(data_json['datetimes'][source], u'YYYY年MM月DD日 HH:mm'),
'feature': {'pos': get_pos(data_json['nodes'][int(source)]['label'].split('-')[1])}}
return graph_map
