def pkmpopana():
df=pd.read_csv("pkm-19-clean.csv")
for i in range(20,27):
df=df.append(pd.read_csv(f'pkm-{str(i)}-clean.csv'),ignore_index=True)
sen=''
for j in df['text']:
sen+=j
sen=sen.lower()
toker=RegexpTokenizer(r'\w+')
words=toker.tokenize(sen)
stop_words = set(stopwords.words('english'))
filtered_sentence = [w for w in words if not w in stop_words]
fdist=FreqDist(filtered_sentence)
pk=pd.read_csv('pokemon.csv')
pk=pk[pk['id']<152]
pkmname=list(pk['pokemon'])
re={}
for n in pkmname:
if n in fdist.keys():
re[n]=fdist[n]
so=sorted(re.items(),key=lambda item:item[1],reverse = True)
l,p=[],[]
tar=so[0:2]
for i in tar:
l.append(i[1])
p.append(i[0])
plt.barh(list(range(len(tar))),width=l[::-1],align='center')
plt.xlabel('count')
plt.ylabel('name')
plt.yticks(list(range(len(tar))),p[::-1])
plt.show()
def _expand_requires_extra(re):
for extra, reqs in sorted(re.items()):
for req in reqs:
if ';' in req:
name, envmark = req.split(';', 1)
yield '{} ; extra == "{}" and ({})'.format(
name, extra, envmark)
else:
yield '{} ; extra == "{}"'.format(req, extra)
def get_url(self, path):
conf = self.get_config()
data = self.get_case(path)
url_li = []
if "base_url" in conf.keys():
for i in data:
re = i["request"]
for k, v in re.items():
if k == "URL":
value = conf["base_url"] + v
url_li.append(value)
else:
for i in data:
re = i["request"]
for k, v in re.items():
if k == "URL":
url_li.append(v)
return url_li
def get_params(self, path):
data = self.get_case(path)
params_li = []
for i in data:
re = i["request"]
for k, v in re.items():
if k == "params":
params_li.append(v)
return params_li
def get_headers(self, path):
data = self.get_case(path)
headers_li = []
for i in data:
re = i["request"]
for k, v in re.items():
if k == "headers":
headers_li.append(v)
return headers_li
def get_method(self, path):
data = self.get_case(path)
method_li = []
for i in data:
re = i["request"]
for k, v in re.items():
if k == "method":
method_li.append(v)
return method_li
# 3. 相似度分析
tfidf[doc_test_vec] # 获取测试文档中，每个词的TF-IDF值
index = similarities.SparseMatrixSimilarity(tfidf[corpus], num_features=len(dictionary.keys())) # 对每个目标文档，分析测试文档的相似度
sims = index[tfidf[doc_test_vec]]
# 整理输出
simss = []
for i in range(len(sims)):
if sims[i] != 0:
sims[i] += weighList[i]
simss.append(sims[i]) # 将每个句子对应的相似度放在列表中
print("最终的结果是（文本和相似度对应）：")
re = dict(zip(kownledge, simss)) # 将相似度和对应题目组合成为字典
d_order = sorted(re.items(), key=lambda x: x[1], reverse=True)
for i in range(10):
print(d_order[i], end="")
print(kownDict[(d_order[i][0]).encode("utf-8")])
baseKownledge = []
for i in range(3):
baseKownledge.append(d_order[i][0])
print(baseKownledge)
'''
print("排序后的结果")
re2 = sorted(enumerate(sims), key=lambda item: -item[1]) # 根据相似度排序
for i in range(3):
print(re2[i])
'''
