Update GraphSAGE.py

Author: AnirudhDagar

GraphSAGE/GraphSAGE.py

@@ -205,79 +205,5 @@ def run_cora():
     print ("Validation F1:", f1_score(labels[val], val_output.data.numpy().argmax(axis=1), average="micro"))
     print ("Average batch time:", np.mean(times))
 
-# =============================================================================
-# def load_pubmed():
-#     #hardcoded for simplicity...
-#     num_nodes = 19717
-#     num_feats = 500
-#     feat_data = np.zeros((num_nodes, num_feats))
-#     labels = np.empty((num_nodes, 1), dtype=np.int64)
-#     node_map = {}
-#     with open("pubmed-data/Pubmed-Diabetes.NODE.paper.tab") as fp:
-#         fp.readline()
-#         feat_map = {entry.split(":")[1]:i-1 for i,entry in enumerate(fp.readline().split("\t"))}
-#         for i, line in enumerate(fp):
-#             info = line.split("\t")
-#             node_map[info[0]] = i
-#             labels[i] = int(info[1].split("=")[1])-1
-#             for word_info in info[2:-1]:
-#                 word_info = word_info.split("=")
-#                 feat_data[i][feat_map[word_info[0]]] = float(word_info[1])
-#     adj_lists = defaultdict(set)
-#     with open("pubmed-data/Pubmed-Diabetes.DIRECTED.cites.tab") as fp:
-#         fp.readline()
-#         fp.readline()
-#         for line in fp:
-#             info = line.strip().split("\t")
-#             paper1 = node_map[info[1].split(":")[1]]
-#             paper2 = node_map[info[-1].split(":")[1]]
-#             adj_lists[paper1].add(paper2)
-#             adj_lists[paper2].add(paper1)
-#     return feat_data, labels, adj_lists
-# 
-# def run_pubmed():
-#     np.random.seed(1)
-#     random.seed(1)
-#     num_nodes = 19717
-#     feat_data, labels, adj_lists = load_pubmed()
-#     features = nn.Embedding(19717, 500)
-#     features.weight = nn.Parameter(torch.FloatTensor(feat_data), requires_grad=False)
-#    # features.cuda()
-# 
-#     agg1 = MeanAggregator(features, cuda=True)
-#     enc1 = Encoder(features, 500, 128, adj_lists, agg1, gcn=True, cuda=False)
-#     agg2 = MeanAggregator(lambda nodes : enc1(nodes).t(), cuda=False)
-#     enc2 = Encoder(lambda nodes : enc1(nodes).t(), enc1.embed_dim, 128, adj_lists, agg2,
-#             base_model=enc1, gcn=True, cuda=False)
-#     enc1.num_samples = 10
-#     enc2.num_samples = 25
-# 
-#     graphsage = SupervisedGraphSage(3, enc2)
-# #    graphsage.cuda()
-#     rand_indices = np.random.permutation(num_nodes)
-#     test = rand_indices[:1000]
-#     val = rand_indices[1000:1500]
-#     train = list(rand_indices[1500:])
-# 
-#     optimizer = torch.optim.SGD(filter(lambda p : p.requires_grad, graphsage.parameters()), lr=0.7)
-#     times = []
-#     for batch in range(200):
-#         batch_nodes = train[:1024]
-#         random.shuffle(train)
-#         start_time = time.time()
-#         optimizer.zero_grad()
-#         loss = graphsage.loss(batch_nodes, 
-#                 Variable(torch.LongTensor(labels[np.array(batch_nodes)])))
-#         loss.backward()
-#         optimizer.step()
-#         end_time = time.time()
-#         times.append(end_time-start_time)
-#         print (batch, loss.data[0])
-# 
-#     val_output = graphsage.forward(val) 
-#     print ("Validation F1:", f1_score(labels[val], val_output.data.numpy().argmax(axis=1), average="micro"))
-#     print ("Average batch time:", np.mean(times))
-# =============================================================================
-
 if __name__ == "__main__":
     run_cora()