engine.py 文件源码

def _train(self, training_frame):
        hashing_vectorizer = HashingVectorizer(analyzer="word", n_features=(2 ** 30),
                                               ngram_range=(1, 3), stop_words="english")
        training_hashing_matrix = hashing_vectorizer.fit_transform(training_frame["description"])

        self.log.info("starting kernel")
        start = time()
        cosine_similarities = cosine_similarity(training_hashing_matrix, training_hashing_matrix)
        self.log.info("finished kernel. this took {} s".format(time() - start))

        self.log.info("starting adding to redis database")
        start = time()
        i = 0
        l = len(training_frame.index)
        print_progress(i, l, prefix="Progress:", suffix="Complete", bar_length=50)
        for idx, row in training_frame.iterrows():
            similar_indices = cosine_similarities[idx].argsort()[:-100:-1]
            similar_items = [(cosine_similarities[idx][i], training_frame['id'][i]) for i in similar_indices]

            flattened = sum(similar_items[1:], ())
            self._r.zadd(self.SIMKEY % row['id'], *flattened)
            i += 1
            print_progress(i, l, prefix="Progress:", suffix="Complete", bar_length=50)
        self.log.info("finished adding {} rows to redis database. this took {} s".format(i, time() - start))