similarity.py 文件源码

def get_topic_distributions(examples, vectorizer, lda_model):
    """
    Retrieve the topic distributions of a collection of documents.
    :param examples: a list of tokenised documents
    :param vectorizer: the CountVectorizer used for transforming the documents
    :param lda_model: the trained LDA model
    :return: an array of shape (num_examples, num_topics) containing the topic
             distribution of each example
    """
    vectorized_corpus = vectorizer.transform(examples)
    gensim_corpus = gensim.matutils.Sparse2Corpus(vectorized_corpus,
                                                  documents_columns=False)
    topic_representations = []
    for doc in gensim_corpus:
        topic_representations.append(
            [topic_prob for (topic_id, topic_prob) in
             lda_model.get_document_topics(doc, minimum_probability=0.)])
    return np.array(topic_representations)


# PRE-TRAINED WORD EMBEDDINGS METHODS