Use a trained Gensim LDA model to classify the topics in a list of text

find_document_topic.py

def find_topic(textlist, dictionary, lda):
    '''
    https://stackoverflow.com/questions/16262016/how-to-predict-the-topic-of-a-new-query-using-a-trained-lda-model-using-gensim
    
     For each query ( document in the test file) , tokenize the 
     query, create a feature vector just like how it was done while training
     and create text_corpus
    '''
    
    text_corpus = []

    for query in textlist:
        temp_doc = tokenize(query.strip())
        current_doc = []
        temp_doc = list(temp_doc)
        for word in range(len(temp_doc)):
            current_doc.append(temp_doc[word])

        text_corpus.append(current_doc)
    '''
     For each feature vector text, lda[doc_bow] gives the topic
     distribution, which can be sorted in descending order to print the 
     very first topic
    ''' 
    tops = []
    for text in text_corpus:
        doc_bow = dictionary.doc2bow(text)
        topics = sorted(lda[doc_bow],key=lambda x:x[1],reverse=True)[0]
        tops.append(topics)
    return(tops)