我正在尝试一些未知的单词,并通过添加字典甚至没有的“ Polytechnic”,“ Diploma”来给出0%,我尝试查找能够将单词添加到我发现无法添加的单词的源中找到
这是我正在调用的代码的功能
def similarityChecker(txt1,txt2):
result = 0.00
file_docs = []
tokens1 = sentence(txt1)
for line in tokens1:
file_docs.append(line)
print("Number of sentence:",len(file_docs))
gen_docs = [[w.lower() for w in removestop(text)]
for text in file_docs]
dictionary = gensim.corpora.Dictionary(gen_docs)
corpus = [dictionary.doc2bow(gen_doc) for gen_doc in gen_docs]
# This tf_idf cannot add unknown words?
tf_idf = gensim.models.Tfidfmodel(corpus)
# Gives out an empty array [] for using words not in the english dictionary
for doc in tf_idf[corpus]:
print([[dictionary[id],np.around(freq,decimals=2)] for id,freq in doc])
# building the index
sims = gensim.similarities.Similarity('/',tf_idf[corpus],num_features=len(dictionary))
file2_docs = []
tokens2 = sentence(txt2)
for line in tokens2:
file2_docs.append(line)
print("Number of sentence:",len(file2_docs))
avg_sims = []
for line in file2_docs:
# tokenize words
query_doc = [w.lower() for w in removestop(line)]
# create bag of words
query_doc_bow = dictionary.doc2bow(query_doc)
# find similarity for each document
query_doc_tf_idf = tf_idf[query_doc_bow]
# print (document_number,document_similarity)
print('Comparing Result:',sims[query_doc_tf_idf])
# calculate sum of similarities for each query doc
sum_of_sims = (np.sum(sims[query_doc_tf_idf],dtype=np.float32))
# calculate average of similarity for each query doc
avg = sum_of_sims / len(file_docs)
# print average of similarity for each query doc
print(f'avg: {sum_of_sims / len(file_docs)}')
# add average values into array
avg_sims.append(avg)
total_avg = np.sum(avg_sims,dtype=np.float)
result = round(float(total_avg) * 100)
if result >= 100:
result = 100
return result
我添加的一些功能是调用正在运行的nltk。 我是这个gensim编码的新手,我真的需要帮助。