--

input.py

@@ -194,3 +194,59 @@ def get_data(dataset):
     feas['num_features'] = num_features
     feas['num_nodes'] = num_nodes
     return feas
+
+def get_data_by_fold(dataset):
+    # Load data
+    # adj, features, y_test, tx, ty, test_maks, true_labels = load_data(data_name)
+    adj, features, y_test, tx, ty, test_maks, true_labels = load_data(dataset)  # e  ic gpcr nr luo
+
+    # Store original adjacency matrix (without diagonal entries) for later
+    adj_orig = adj
+    # 删除对角线元素
+    adj_orig = adj_orig - sp.dia_matrix((adj_orig.diagonal()[np.newaxis, :], [0]), shape=adj_orig.shape)
+    adj_orig.eliminate_zeros()
+
+    adj_train, train_edges, val_edges, val_edges_false, test_edges, test_edges_false = mask_test_edges(adj)
+    adj = adj_train
+    adj_dense = adj.toarray()
+
+    # Some preprocessing
+    adj_norm = preprocess_graph(adj)
+
+    num_nodes = adj.shape[0]
+    features_dense = features.tocoo().toarray()
+
+    features = sparse_to_tuple(features.tocoo())
+    # num_features是feature的维度
+    num_features = features[2][1]
+    # features_nonzero就是非零feature的个数
+    features_nonzero = features[1].shape[0]
+
+    pos_weight = float(adj.shape[0] * adj.shape[0] - adj.sum()) / adj.sum()
+    norm = adj.shape[0] * adj.shape[0] / float((adj.shape[0] * adj.shape[0] - adj.sum()) * 2)
+
+    adj_label = adj_train + sp.eye(adj_train.shape[0])
+    adj_label = sparse_to_tuple(adj_label)
+    items = [
+        adj, num_features, num_nodes, features_nonzero,
+        pos_weight, norm, adj_norm, adj_label,
+        features, true_labels, train_edges, val_edges,
+        val_edges_false, test_edges, test_edges_false, adj_orig, features_dense, adj_dense, features_dense
+    ]
+
+    feas = {}
+
+    print('num_features is:', num_features)
+    print('num_nodes is:', num_nodes)
+    print('features_nonzero is:', features_nonzero)
+    print('pos_weight is:', pos_weight)
+    print('norm is:', norm)
+
+    for item in items:
+        # item_name = [ k for k,v in locals().iteritems() if v == item][0]
+        feas[retrieve_name(item)] = item
+
+    feas['num_features'] = num_features
+    feas['num_nodes'] = num_nodes
+    return feas
+

train.py

@@ -19,13 +19,13 @@ def parse_args():
     parser.add_argument('--hidden2', type=int, default=32, help='隐藏层2神经元数量.')
     parser.add_argument('--hidden3', type=int, default=64, help='隐藏层3神经元数量.')
     parser.add_argument('--learning_rate', type=float, default=.6 * 0.001, help='学习率')
-    parser.add_argument('--discriminator_learning_rate', type=float, default=0.001, help='判别器学习率')
+    parser.add_argument('--discriminator_learning_rate', type=float, default=0.0001, help='判别器学习率')  # luo 判别器学习率0.0001， 其它数据集0.001
     parser.add_argument('--epoch', type=int, default=250, help='迭代次数')
     parser.add_argument('--seed', type=int, default=50, help='用来打乱数据集')
     parser.add_argument('--features', type=int, default=1, help='是(1)否(0)使用特征')
     parser.add_argument('--dropout', type=float, default=0., help='Dropout rate (1 - keep probability).')
     parser.add_argument('--weight_decay', type=float, default=0., help='Weight for L2 loss on embedding matrix.')
-    parser.add_argument('--dataset', type=str, default='e', help='使用的数据集')
+    parser.add_argument('--dataset', type=str, default='luo', help='使用的数据集')
 
     args = parser.parse_args()
     return args
@@ -40,7 +40,7 @@ if __name__ == "__main__":
     # DPP采样和PCA降维
     DPP = FiniteDPP('correlation', **{'K': feas['adj'].toarray()})
     pca = PCA(n_components=settings.hidden2)
-    DPP.sample_exact_k_dpp(size=21)  # e 21 ic 6 gpcr 3
+    DPP.sample_exact_k_dpp(size=20)  # e 21 ic 6 gpcr 3
     index = DPP.list_of_samples[0]
     feature_sample = feas['features_dense']
     feature_sample = pca.fit_transform(feature_sample)