song2vec_operator.py 文件源码

def cluster_song_in_playlist(self, playlist_id, cluster_n=5, is_detailed=False):
        """
        ??????????????
        Args:
            playlist_id: ??id
            cluster_n:???
            is_detailed: ???????????

        Returns:
            ??????
        """
        playlist_obj = playlist_detail(playlist_id)
        song_list = []
        vec_list = []
        song_info_dict = {}
        ap_cluster = AffinityPropagation()
        data_process_logger.info('clustering playlist: %s' % playlist_obj['name'])
        for item in playlist_obj['tracks']:
            song = item['name'].lower()
            song_info_dict[song] = {
                'name': song,
                'artist': item['artists'][0]['name'],
                'id': item['id'],
                'album_img_url': item['album']['picUrl'],
                'site_url': 'http://music.163.com/#/song?id=%s' % item['id']
            }
            # print song
            if song not in song_list:
                song_list.append(song)
                # print self.song2vec_model.vocab.get(song)
                # print self.song2vec_model.syn0norm == None
                if self.song2vec_model.vocab.get(song) and len(self.song2vec_model.syn0norm):
                    song_vec = self.song2vec_model.syn0norm[self.song2vec_model.vocab[song].index]
                else:
                    data_process_logger.warn(
                        'The song %s of playlist-%s is not in dataset' % (song, playlist_obj['name']))
                    song_vec = [0 for i in range(self.song2vec_model.vector_size)]
                vec_list.append(song_vec)
        # song_list = list(song_list)
        if len(vec_list) > 1:
            cluster_result = ap_cluster.fit(vec_list, song_list)
            cluster_array = [[] for i in range(len(cluster_result.cluster_centers_indices_))]
            for i in range(len(cluster_result.labels_)):
                label = cluster_result.labels_[i]
                index = i
                cluster_array[label].append(song_list[i])
            return cluster_array, playlist_obj['name'], song_info_dict
        else:
            return [song_list], playlist_obj['name'], song_info_dict