updte data dist for shortest path distribution for only citation2

core/graphgps/utility/utils.py

@@ -954,3 +954,17 @@ def analyse_hyper(file_path: str):
     best_combination_df = pd.DataFrame(best_combination).transpose()
     best_combination_df.to_csv('best_hyperparameter_combination.csv', index=False)
     return 
+
+
+import time
+import random
+
+def timeit(func):
+    def wrapper(*args, **kwargs):
+        start = time.perf_counter()
+        result = func(*args, **kwargs)
+        end = time.perf_counter()
+        elapsed = end - start
+        print(f'Time taken: {elapsed:.6f} seconds')
+        return result
+    return wrapper

core/heuristic/cora_heuristic.py

@@ -95,18 +95,18 @@ def eval_cora_acc() -> None:
                                                 test_pct = 0.05,
                                                 split_labels = False
                                                 )
-    test_split = splits['test']
-    labels = test_split.edge_label
-    test_index = test_split.edge_label_index
+
+    labels = splits['test'].edge_label
+    test_index = splits['test'].edge_label_index
 
-    edge_index = splits['test'].edge_index
-    edge_weight = torch.ones(edge_index.size(1))
+    test_edge_index = splits['test'].edge_index
+    edge_weight = torch.ones(test_edge_index.size(1))
     num_nodes = dataset._data.num_nodes
 
-    m = construct_sparse_adj(edge_index)
+    m = construct_sparse_adj(test_edge_index)
     plot_coo_matrix(m, f'cora_test_edge_index.png')
 
-    A = ssp.csr_matrix((edge_weight.view(-1), (edge_index[0], edge_index[1])), shape=(num_nodes, num_nodes)) 
+    A = ssp.csr_matrix((edge_weight.view(-1), (test_edge_index[0], test_edge_index[1])), shape=(num_nodes, num_nodes)) 
 
     result_acc = {}
     for use_lsf in ['CN', 'AA', 'RA', 'InverseRA']:

core/heuristic/gsf.py

@@ -155,6 +155,7 @@ def shortest_path(A, edge_index, remove=False):
     print(f'evaluated shortest path for {len(scores)} edges')
     return torch.FloatTensor(scores)
 
+
 def katz_apro(A, edge_index, beta=0.005, path_len=3, remove=False):
 
     scores = []