song2vec_operator.py 文件源码

def cluster_artist_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)
        artist_list = []
        vec_list = []
        ap_cluster = AffinityPropagation()
        data_process_logger.info('clustering playlist: %s' % playlist_obj['name'])
        for item in playlist_obj['tracks']:
            artist = item['artists'][0]['name'].lower()
            # print artist
            if artist not in artist_list:
                artist_list.append(artist)
                # print self.song2vec_model.vocab.get(artist)
                # print self.song2vec_model.syn0norm == None
                if self.artist2vec_model.vocab.get(artist) and len(self.artist2vec_model.syn0norm):
                    artist_vec = self.artist2vec_model.syn0norm[self.artist2vec_model.vocab[artist].index]
                else:
                    data_process_logger.warn(
                        'The artist %s of playlist-%s is not in dataset' % (artist, playlist_obj['name']))
                    artist_vec = [0 for i in range(self.artist2vec_model.vector_size)]
                vec_list.append(artist_vec)
        # artist_list = list(artist_list)
        # vec_list = list(vec_list)
        if len(vec_list) > 1:
            cluster_result = ap_cluster.fit(vec_list, artist_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(artist_list[i])
            return cluster_array, playlist_obj['name'], {}
        else:
            return [artist_list], playlist_obj['name'], {}