Nlp 从术语频率矩阵或字符串集合创建gensim语料库
我正在尝试使用gensim进行主题分类。我已经从多个文档中获得了以下形式的所有特征词:Nlp 从术语频率矩阵或字符串集合创建gensim语料库,nlp,gensim,corpus,word2vec,Nlp,Gensim,Corpus,Word2vec,我正在尝试使用gensim进行主题分类。我已经从多个文档中获得了以下形式的所有特征词: corpus = [['word1','word2',..],['A','B',...]] (python list of lists) 以及稀疏形式的术语频率矩阵和dict 我试着在这方面培训gensim LDA: lda_model = gensim.models.LdaModel(term_freq_matrix, num_topics=10, id2word=feature_names_dict,
corpus = [['word1','word2',..],['A','B',...]] (python list of lists)
以及稀疏形式的术语频率矩阵和dict
我试着在这方面培训gensim LDA:
lda_model = gensim.models.LdaModel(term_freq_matrix, num_topics=10, id2word=feature_names_dict, passes=4)
但我得到了以下错误:
File "/home/oliver/Environments/cmpdp/local/lib/python2.7/site-packages/gensim/models/ldamodel.py", line 523, in <genexpr>
corpus_words = sum(cnt for document in chunk for _, cnt in document)
ValueError: need more than 1 value to unpack
教程语料库:
打印(下一个(国际热核实验堆(mm_语料库)))
你觉得怎么样
print(next(iter(term_freq_matrix)))
(0, 12036) 1
(0, 12406) 2
...
(0, 3916) 1
(0, 3157) 1
[(24, 1.0), (38, 1.0), (53, 1.0), (103, 1.0), (111, 1.0), (213, 3.0), (237, 1.0), (242, 2.0)]