STFIWF.py 文件源码

def get_term_topic(self, X):
        n_features = X.shape[1]
        id2word = self.vocabulary_
        word2topic = {}

        with open('word_topic.txt', 'r') as f:
            for line in f:
                strs = line.decode('utf-8').strip('\n').split('\t')
                word2topic[strs[0]] = strs[2]

        topic = np.zeros((len(id2word),))

        for i, key in enumerate(id2word):
            if key in word2topic:
                topic[id2word[key]] = word2topic[key]
            else:
                print key

        topic = preprocessing.MinMaxScaler().fit_transform(topic)
        # topic = sp.spdiags(topic, diags=0, m=n_features,
        #                    n=n_features, format='csr')
        return topic