如何从大Pandas的字典中为特定单词列表创建前5个接近单词的数据框

Question

我有一本word2vec字典，它给出了一个与给定单词最相似的单词。你知道吗

我想传递需要从文件或列表中计算相似度的单词列表

输入

word_list =['wan,'floor','street']

应根据word2vec字典检查这些单词的相似性，必须找到与输入单词列表相似的单词，并以下面显示的格式写入数据帧。你知道吗

model.most_similar("wan")

[('wan.', 0.7509685754776001),
 ('want', 0.7326164245605469),
 ('aupuiwan', 0.7161564230918884),
 ('puiwan', 0.7119397521018982),
 ('wanstreet', 0.7096157073974609),
 ('woshing', 0.7046518921852112),
 ('futan', 0.6979573369026184),
 ('won', 0.696295440196991),
 ('fota', 0.6961145401000977),
 ('pul', 0.6921802759170532)]

我想创建一个包含两列Word和类似单词的dataframe。你知道吗

输出数据帧

Word    Similar Words
wan     ('wan.', 'want','aupuiwan','puiwan','wanstreet')
floor   ('fl','flooor','flor','flr','gf')
street  ('st','rosestreet','stret','strt','str')

感谢您的帮助。你知道吗

Answer 1

试试这个：

words = ['wan', 'floor', 'street']
similar = [[item[0] for item in model.most_similar(word)[:5]] for word in words]
df = pd.DataFrame({'Word': words, 'Similar Words': similar})