コード例 #1
0
 def movie_cluster_spec(self, rating_mat, movie_idx, movies, K):
     rating_sim = 1-sk.metrics.pairwise_distances(rating_mat.toarray(), metric='cosine')
     # clamp the negative similarities
     rating_sim[rating_sim<0]=0
     spec_cluster = sk.cluster.spectral_clustering(rating_sim, n_clusters=K,
                                                   eigen_solver='arpack', assign_labels='kmeans')
     cluster_result = pd.merge(utils.movie_cluster(spec_cluster, movie_idx, 'movieId_idx'),
                               movies[['movieId', 'title']], on='movieId')
     return cluster_result
コード例 #2
0
 def movie_cluster_svd_spec(self, rating_mat, movie_idx, movies, K):
     svd = sk.decomposition.PCA(n_components=10, whiten=True)
     movie_feat = svd.fit_transform(rating_mat.toarray())
     rating_sim = 1-sk.metrics.pairwise_distances(movie_feat, metric='cosine')
     # clamp the negative similarities
     rating_sim[rating_sim<0]=0
     spec_cluster = sk.cluster.spectral_clustering(rating_sim, n_clusters=K,
                                                   eigen_solver='arpack', assign_labels='kmeans')
     cluster_result = pd.merge(utils.movie_cluster(spec_cluster, movie_idx, 'movieId_idx'),
                               movies[['movieId', 'title']], on='movieId')
     return cluster_result