def testNearbyWords(self):
thu1 = thulac.thulac() #默认模式
text = thu1.cut("人脸识别", text=True) #进行一句话分词
words, tags = [], []
data = [x.rsplit('_', 1) for x in text.split()]
for _ in data:
assert len(_) == 2, "seg len should be 2"
words.append(_[0])
tags.append(_[1])
for (k, v) in enumerate(tags):
if v.startswith("n") or v.startswith("v"): # 去停，去标，去副词、形容词、代词 etc.
synonyms.display(
words[k]) # synonyms.display calls synonyms.nearby
def test_badcase_1(self):
synonyms.display("人脸") # synonyms.display calls synonyms.nearby
def test_nearby(self):
synonyms.display("奥运") # synonyms.display calls synonyms.nearby
synonyms.display("北新桥") # synonyms.display calls synonyms.nearby
def cPrintDisplay(str):
print('@+@')
synonyms.display(str)
print('@-@')
data_long = np.loadtxt("data_test1.csv",str,delimiter=",", skiprows=1)
data_long
("国际劳工组织")
cixing=[]
for i in range(0,len(data_long)):
cixing.append(synonyms.seg(data_long[i]))
test=synonyms.nearby("人脸")
test[0]
print("识别: %s" % (synonyms.nearby("识别")))
print("NOT_EXIST: %s" % (synonyms.nearby("NOT_EXIST")))
synonyms.display("金融")
synonyms.v()
print(1)
cixiangliang=[]
for i in range(0,len(data_long)):
try:
cixiangliang.append(synonyms.v (data_long[i]))
except:
cixiangliang.append(-1)
ciqinggan=[]
for i in range(0,len(data_long)):
def test_nearby(self):
synonyms.display("人脸") # synonyms.display calls synonyms.nearby
def testNearbyWords(self):
synonyms.display("人脸") # synonyms.display calls synonyms.nearby
import synonyms
synonyms.display("你好")
def testWordExit(wordexit):
# 测试synonyms中是否存在这个词
synonyms.display(wordexit)
#!/usr/bin/env python
#coding:utf-8
import synonyms
# 获取近义词
print synonyms.nearby("计算机科学")
# 输出近义词(display调用了synonyms的nearby方法)
synonyms.display("计算机技术")
# 获取两个词语或句子的相似度
print synonyms.compare("计算机科学", "计算机技术")
import synonyms
print("人脸: %s" % (synonyms.nearby("人脸")))
print("识别: %s" % (synonyms.nearby("识别")))
print("NOT_EXIST: %s" % (synonyms.nearby("NOT_EXIST")))
print("=" * 50)
sen1 = "发生历史性变革"
sen2 = "发生历史性变革"
r = synonyms.compare(sen1, sen2, seg=True)
print("发生历史性变革 vs 发生历史性变革:", r)
print("=" * 50)
synonyms.display("飞机")
def test_nearby(self):
synonyms.display("人脸") # synonyms.display calls synonyms.nearby
:param sen1: the original sentence
:param sen2: the mutated sentence
:param threshold: how much the two sentence are likely is okay
:return: True for the two sentence are similar, false for not
"""
score = synonyms.compare(sen1, sen2)
return False if score <= threshold else True
# @online{Synonyms:hain2017,
# author = {Hai Liang Wang, Hu Ying Xi},
# title = {中文近义词工具包Synonyms},
# year = 2017,
# url = {https://github.com/huyingxi/Synonyms},
# urldate = {2017-09-27}
# }
if __name__ == "__main__":
print(synonyms.display("今天"))
print(synonyms.display("天气"))
print(synonyms.display("真好"))
print(synonyms.display("做"))
print(synonyms.display("作业"))
print(synonyms.display("喜欢"))
print(synonyms.display("故事"))
print(synonyms.display("猫"))
print(synonyms.display("可爱"))
print(synonyms.display("一种"))
print(synonyms.display("动物"))
print(synonyms.display("今天天气"))
