update print and output json statements

graph_dit/metrics/property_metric.py

@@ -102,6 +102,7 @@ class TaskModel():
         mask = ~np.isnan(labels)
         labels = labels[mask]
         features = features[mask]
+        # features = str(features)
         self.model.fit(features, labels)
         y_pred = self.model.predict(features)
         perf = self.metric_func(labels, y_pred)
@@ -136,7 +137,7 @@ class TaskModel():
         print(f'{self.task_name} performance: {perf}')
         return perf
 
-    def __call__(self, smiles_list):
+    def __call(self, smiles_list):
         fps = []
         mask = []
         for i,smiles in enumerate(smiles_list):
@@ -153,6 +154,54 @@ class TaskModel():
         scores = scores * np.array(mask)
         return np.float32(scores)
 
+    def __call__(self, graph_list):
+        # def read_adj_ops_from_json(filename):
+        #     with open(filename, 'r') as json_file:
+        #         data = json.load(json_file)
+
+        #     adj_ops_pairs = []
+        #     for item in data:
+        #         adj_matrix = np.array(item['adj_matrix'])
+        #         ops = item['ops']
+        #         acc = item['train'][0]['accuracy']
+        #         adj_ops_pairs.append((adj_matrix, ops, acc))
+            
+        #     return adj_ops_pairs
+        def feature_from_adj_and_ops(ops, adj):
+            return np.concatenate([adj.flatten(), ops])
+        # filename = '/home/stud/hanzhang/nasbenchDiT/graph_dit/nasbench-201-graph.json'
+        # graphs = read_adj_ops_from_json(filename)
+        # adjs = []
+        # opss = []
+        # accs = []
+        # features = []
+        # for graph in graphs:
+        #     adj, ops, acc=graph
+        #     op_code = [op_type[op] for op in ops]
+        #     adjs.append(adj)
+        #     opss.append(op_code)
+        #     accs.append(acc)
+        features = []
+        print(f"graphlist: {graph_list[0]}")
+        print(f"len graphlist: {len(graph_list)}") 
+        for op_code, adj in graph_list:
+            features.append(feature_from_adj_and_ops(op_code, adj))
+        print(f"len features: {len(features)}")
+        # print(f"features: {features[0].shape}")
+        features = np.stack(features)
+        features = features.astype(np.float32)
+        print(f"features shape: {features.shape}")
+
+
+        fps = features
+        if 'classification' in self.task_type:
+            scores = self.model.predict_proba(fps)[:, 1]
+        else:
+            scores = self.model.predict(fps)
+        # scores = scores * np.array(mask)
+        return np.float32(scores)
+
+
     @classmethod
     def fingerprints_from_mol(cls, mol):  # use ECFP4
         features_vec = AllChem.GetMorganFingerprintAsBitVect(mol, 2, nBits=2048)