def gae_for(args):
print("Using {} dataset".format(args.dataset_str))
adj, features = load_data(args.dataset_str)
n_nodes, feat_dim = features.shape
# Store original adjacency matrix (without diagonal entries) for later
adj_orig = adj
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
# Some preprocessing
adj_norm = preprocess_graph(adj)
adj_label = adj_train + sp.eye(adj_train.shape[0])
# adj_label = sparse_to_tuple(adj_label)
adj_label = torch.FloatTensor(adj_label.toarray())
pos_weight = torch.Tensor(
[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)
model = GCNModelVAE(feat_dim, args.hidden1, args.hidden2, args.dropout)
optimizer = optim.Adam(model.parameters(), lr=args.lr)
hidden_emb = None
for epoch in range(args.epochs):
t = time.time()
model.train()
optimizer.zero_grad()
recovered, mu, logvar = model(features, adj_norm)
loss = loss_function(preds=recovered,
labels=adj_label,
mu=mu,
logvar=logvar,
n_nodes=n_nodes,
norm=norm,
pos_weight=pos_weight)
loss.backward()
cur_loss = loss.item()
optimizer.step()
hidden_emb = mu.data.numpy()
roc_curr, ap_curr = get_roc_score(hidden_emb, adj_orig, val_edges,
val_edges_false)
print("Epoch:", '%04d' % (epoch + 1), "train_loss=",
"{:.5f}".format(cur_loss), "val_ap=", "{:.5f}".format(ap_curr),
"time=", "{:.5f}".format(time.time() - t))
print("Optimization Finished!")
roc_score, ap_score = get_roc_score(hidden_emb, adj_orig, test_edges,
test_edges_false)
print('Test ROC score: ' + str(roc_score))
print('Test AP score: ' + str(ap_score))
def gae_for(args):
print("Using {} dataset".format(args.dataset_str))
adj, features, y_test, tx, ty, test_maks, true_labels = load_data(
args.dataset_str)
n_nodes, feat_dim = features.shape
# Store original adjacency matrix (without diagonal entries) for later
adj_orig = adj
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
# Before proceeding further, make the structure for doing deepWalk
if args.dw == 1:
print('Using deepWalk regularization...')
G = load_edgelist_from_csr_matrix(adj_orig, undirected=True)
print("Number of nodes: {}".format(len(G.nodes())))
num_walks = len(G.nodes()) * args.number_walks
print("Number of walks: {}".format(num_walks))
data_size = num_walks * args.walk_length
print("Data size (walks*length): {}".format(data_size))
# Some preprocessing
adj_norm = preprocess_graph(adj)
adj_label = adj_train + sp.eye(adj_train.shape[0])
# adj_label = sparse_to_tuple(adj_label)
adj_label = torch.FloatTensor(adj_label.toarray())
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)
if args.model == 'gcn_vae':
model = GCNModelVAE(feat_dim, args.hidden1, args.hidden2, args.dropout)
else:
model = GCNModelAE(feat_dim, args.hidden1, args.hidden2, args.dropout)
optimizer = optim.Adam(model.parameters(), lr=args.lr)
if args.dw == 1:
sg = SkipGram(args.hidden2, adj.shape[0])
optimizer_dw = optim.Adam(sg.parameters(), lr=args.lr_dw)
# Construct the nodes for doing random walk. Doing it before since the seed is fixed
nodes_in_G = list(G.nodes())
chunks = len(nodes_in_G) // args.number_walks
random.Random().shuffle(nodes_in_G)
hidden_emb = None
for epoch in tqdm(range(args.epochs)):
t = time.time()
model.train()
optimizer.zero_grad()
z, mu, logvar = model(features, adj_norm)
# After back-propagating gae loss, now do the deepWalk regularization
if args.dw == 1:
sg.train()
if args.full_number_walks > 0:
walks = build_deepwalk_corpus(G,
num_paths=args.full_number_walks,
path_length=args.walk_length,
alpha=0,
rand=random.Random(SEED))
else:
walks = build_deepwalk_corpus_iter(
G,
num_paths=args.number_walks,
path_length=args.walk_length,
alpha=0,
rand=random.Random(SEED),
chunk=epoch % chunks,
nodes=nodes_in_G)
for walk in walks:
if args.context == 1:
# Construct the pairs for predicting context node
# for each node, treated as center word
curr_pair = (int(walk[center_node_pos]), [])
for center_node_pos in range(len(walk)):
# for each window position
for w in range(-args.window_size,
args.window_size + 1):
context_node_pos = center_node_pos + w
# make soure not jump out sentence
if context_node_pos < 0 or context_node_pos >= len(
walk
) or center_node_pos == context_node_pos:
continue
context_node_idx = walk[context_node_pos]
curr_pair[1].append(int(context_node_idx))
else:
# first item in the walk is the starting node
curr_pair = (int(walk[0]), [
int(context_node_idx) for context_node_idx in walk[1:]
])
if args.ns == 1:
neg_nodes = []
pos_nodes = set(walk)
while len(neg_nodes) < args.walk_length - 1:
rand_node = random.randint(0, n_nodes - 1)
if rand_node not in pos_nodes:
neg_nodes.append(rand_node)
neg_nodes = torch.from_numpy(np.array(neg_nodes)).long()
# Do actual prediction
src_node = torch.from_numpy(np.array([curr_pair[0]])).long()
tgt_nodes = torch.from_numpy(np.array(curr_pair[1])).long()
optimizer_dw.zero_grad()
log_pos = sg(src_node, tgt_nodes, neg_sample=False)
if args.ns == 1:
loss_neg = sg(src_node, neg_nodes, neg_sample=True)
loss_dw = log_pos + loss_neg
else:
loss_dw = log_pos
loss_dw.backward(retain_graph=True)
cur_dw_loss = loss_dw.item()
optimizer_dw.step()
loss = loss_function(preds=model.dc(z),
labels=adj_label,
mu=mu,
logvar=logvar,
n_nodes=n_nodes,
norm=norm,
pos_weight=pos_weight)
loss.backward()
cur_loss = loss.item()
optimizer.step()
hidden_emb = mu.data.numpy()
roc_curr, ap_curr = get_roc_score(hidden_emb, adj_orig, val_edges,
val_edges_false)
if args.dw == 1:
tqdm.write(
"Epoch: {}, train_loss_gae={:.5f}, train_loss_dw={:.5f}, val_ap={:.5f}, time={:.5f}"
.format(epoch + 1, cur_loss, cur_dw_loss, ap_curr,
time.time() - t))
else:
tqdm.write(
"Epoch: {}, train_loss_gae={:.5f}, val_ap={:.5f}, time={:.5f}".
format(epoch + 1, cur_loss, ap_curr,
time.time() - t))
if (epoch + 1) % 10 == 0:
tqdm.write("Evaluating intermediate results...")
kmeans = KMeans(n_clusters=args.n_clusters,
random_state=0).fit(hidden_emb)
predict_labels = kmeans.predict(hidden_emb)
cm = clustering_metrics(true_labels, predict_labels)
cm.evaluationClusterModelFromLabel(tqdm)
roc_score, ap_score = get_roc_score(hidden_emb, adj_orig,
test_edges, test_edges_false)
tqdm.write('ROC: {}, AP: {}'.format(roc_score, ap_score))
np.save('logs/emb_epoch_{}.npy'.format(epoch + 1), hidden_emb)
tqdm.write("Optimization Finished!")
roc_score, ap_score = get_roc_score(hidden_emb, adj_orig, test_edges,
test_edges_false)
tqdm.write('Test ROC score: ' + str(roc_score))
tqdm.write('Test AP score: ' + str(ap_score))
kmeans = KMeans(n_clusters=args.n_clusters, random_state=0).fit(hidden_emb)
predict_labels = kmeans.predict(hidden_emb)
cm = clustering_metrics(true_labels, predict_labels)
cm.evaluationClusterModelFromLabel(tqdm)
if args.plot == 1:
cm.plotClusters(tqdm, hidden_emb, true_labels)
def gae_for(args):
print("Using {} dataset".format(args.dataset_str))
adj, features = load_corpus(args.dataset_str)
# n_nodes, feat_dim = features.shape
# print(n_nodes, feat_dim)
print(type(features))
print(adj)
# print(adj[0], adj[1])
features = sp.identity(features.shape[0]) # featureless
# print(adj.shape)
# print(features.shape)
# Some preprocessing
features = preprocess_features(features)
adj_norm = preprocess_adj(adj)
num_supports = 1
# model_func = GCN
adj_norm = torch.FloatTensor(adj_norm.toarray())
features = torch.FloatTensor(features.toarray())
n_nodes, feat_dim = features.shape
print(n_nodes, feat_dim)
print(type(features))
print(type(adj_norm))
print(features.shape)
print(adj_norm.shape)
# n_nodes, feat_dim = features.shape
# print(n_nodes, feat_dim)
# Store original adjacency matrix (without diagonal entries) for later
# adj_orig = adj
# adj_orig = adj_orig - sp.dia_matrix((adj_orig.diagonal()[np.newaxis, :], [0]), shape=adj_orig.shape)
# adj_orig.eliminate_zeros()
# modified/added by hollis
# adj_train, train_edges, val_edges, val_edges_false, test_edges, test_edges_false = mask_test_edges(adj)
# Remove diagonal elements
# adj = adj - sp.dia_matrix((adj.diagonal()[np.newaxis, :], [0]), shape=adj.shape)
# adj.eliminate_zeros()
# Check that diag is zero:
# assert np.diag(adj.todense()).sum() == 0
# adj_train = sp.csr_matrix(adj)
# adj_train = adj_train + adj_train.T
# Some preprocessing
# adj_norm = normalize_adj(adj)
# adj_label = adj_train + sp.eye(adj_train.shape[0])
# adj_label = sparse_to_tuple(adj_label)
# adj_label = torch.FloatTensor(adj_label.toarray())
# adj_label = np.array(adj_label, dtype=float)
# adj_label = torch.FloatTensor(adj_label)
pos_weight = float(adj.shape[0] * adj.shape[0] - adj.sum()) / adj.sum()
# added by hollis
# pos_weight = torch.from_numpy(np.array(pos_weight))
norm = adj.shape[0] * adj.shape[0] / float(
(adj.shape[0] * adj.shape[0] - adj.sum()) * 2)
# model = GCNModelVAE(feat_dim, args.hidden1, args.hidden2, args.dropout)
model = GCNModelVAE(feat_dim, args.hidden1, args.dropout)
optimizer = optim.Adam(model.parameters(), lr=args.lr)
hidden_emb = None
for epoch in range(args.epochs):
print("in epoch")
t = time.time()
model.train()
optimizer.zero_grad()
# recovered, mu, logvar = model(features, adj_norm)
print("before model")
recovered, mu, logvar = model(features, adj_norm)
print("before loss")
loss = loss_function(preds=recovered,
labels=adj_norm,
mu=mu,
logvar=logvar,
n_nodes=n_nodes,
norm=norm)
#loss = loss_function(preds=recovered, labels=adj_label,
# mu=mu, logvar=logvar, n_nodes=n_nodes,
# norm=norm, pos_weight=pos_weight)
print("befor backword")
loss.backward()
cur_loss = loss.item()
optimizer.step()
hidden_emb = mu.data.numpy()
hidden_emb = np.array(hidden_emb)
if epoch == 1:
fni = "./result/emb_init.txt"
hidden_emb = np.array(hidden_emb)
np.savetxt(fni, hidden_emb)
if epoch == args.epochs - 1:
fnf = "./result/emb.txt"
hidden_emb = np.array(hidden_emb)
np.savetxt(fnf, hidden_emb)
#roc_curr, ap_curr = get_roc_score(hidden_emb, adj_orig, val_edges, val_edges_false)
print(
"Epoch:",
'%04d' % (epoch + 1),
"train_loss=",
"{:.5f}".format(cur_loss),
# "val_ap=", "{:.5f}".format(ap_curr),
"time=",
"{:.5f}".format(time.time() - t))
print("Optimization Finished!")
def gae_for(args, position):
print("Using {} dataset".format(args.dataset_str))
#qhashes, chashes = load_hashes()
Q, X = load_data()
prebuild = "/media/chundi/3b6b0f74-0ac7-42c7-b76b-00c65f5b3673/revisitop/cnnimageretrieval-pytorch/data/test/matlab_data/GEM_wDis_prebuild.bin"
Q_features = "/media/chundi/3b6b0f74-0ac7-42c7-b76b-00c65f5b3673/revisitop/cnnimageretrieval-pytorch/data/test/matlab_data/roxford5k_GEM_lw_query_feats.npy" #"/media/jason/cc0aeb62-0bc7-4f3e-99a0-3bba3dd9f8fc/landmarks/oxfordRe/evaluation/roxHD_query_fused.npy"
X_features = "/media/chundi/3b6b0f74-0ac7-42c7-b76b-00c65f5b3673/revisitop/cnnimageretrieval-pytorch/data/test/matlab_data/roxford5k_GEM_index.npy"
D_features = "/media/chundi/3b6b0f74-0ac7-42c7-b76b-00c65f5b3673/revisitop/cnnimageretrieval-pytorch/data/test/matlab_data/roxford5k_GEM_Dis.npy"
adj, features, adj_Q, features_Q = load_from_prebuild(prebuild,
Q_features,
X_features,
D_features,
k=5) # ----> 1M
#cut_size = 800000
#adj = adj[:cut_size, :cut_size]
#adj_Q = adj_Q[:, :cut_size]
#features = features[:cut_size]
#Q = np.load("/media/jason/cc0aeb62-0bc7-4f3e-99a0-3bba3dd9f8fc/landmarks/oxfordRe/evaluation/roxHD_query_fused.npy").T.astype(np.float32)
#X = np.load("/media/jason/cc0aeb62-0bc7-4f3e-99a0-3bba3dd9f8fc/landmarks/oxfordRe/evaluation/roxHD_index_fused.npy").T.astype(np.float32)
#D = np.load("/media/jason/cc0aeb62-0bc7-4f3e-99a0-3bba3dd9f8fc/landmarks/revisitop1m/revisitDistractors_fused_3s_cq.npy").T.astype(np.float32)
#X = np.concatenate((X.T,D.T)).T
# load the distractor too, shape should be (2048, 1M)
#adj, features = gen_graph_index(Q, X, k=5, k_qe=3, do_qe=False) #-----> 5k
#adj_Q, features_Q = gen_graph(Q, X, k=5, k_qe=3, do_qe=False) #generate validation/revop evaluation the same way as training ----> 5k
features_all = np.concatenate([features_Q, features])
features_all = torch.from_numpy(features_all)
#adj_Q = adj_Q.todense()
#adj_all = np.concatenate([adj_Q, adj.todense()])
#adj_all = np.pad(adj_all, [[0,0], [Q.shape[1], 0]], "constant")
adj_all = sp.vstack((adj_Q, adj))
zeros = sp.csr_matrix((adj_all.shape[0], Q.shape[1]))
adj_all = sp.hstack((zeros, adj_all))
adj_all = sp.csr_matrix(adj_all)
rows, columns = adj_all.nonzero()
print("Making Symmetry")
for i in range(rows.shape[0]):
if rows[i] < Q.shape[1]:
adj_all[columns[i], rows[i]] = adj_all[rows[i], columns[i]]
else:
break
#adj_all = sp.csr_matrix(adj_all)
print("preprocessing adj_all")
adj_all_norm = preprocess_graph(adj_all)
#adj = add_neighbours_neighbour(adj)
#adj1, features1 = load_data(args.dataset_str)
features = torch.from_numpy(features)
#features_all = torch.from_numpy(features_all)
n_nodes, feat_dim = features.shape
# Store original adjacency matrix (without diagonal entries) for later
adj_orig = adj
adj_orig = adj_orig - sp.dia_matrix(
(adj_orig.diagonal()[np.newaxis, :], [0]), shape=adj_orig.shape)
adj_orig.eliminate_zeros()
adj = adj_orig
#adj_train, train_edges, val_edges, val_edges_false, test_edges, test_edges_false = mask_test_edges(adj)
print("Sampling validation")
adj_train, adj_val, features, features_valid = mask_test_rows(
adj, features)
adj = adj_train
# Some preprocessing
print("preprocessing adj")
adj_norm = preprocess_graph(adj)
#adj_norm_label = preprocess_graph_sp(adj)
adj_label = adj_train + sp.eye(
adj_train.shape[0]
) #adj_norm_label + sp.eye(adj_train.shape[0]) #adj_train + sp.eye(adj_train.shape[0])
#rows, columns = adj_label.nonzero()
#adj_label[columns, rows] = adj_label[rows, columns]
# adj_label = sparse_to_tuple(adj_label)
#adj_label = torch.FloatTensor(adj_label.toarray())
print("adj sum: " + str(adj.sum()))
pos_weight = float(float(adj.shape[0]) * adj.shape[0] -
adj.sum()) / adj.sum()
print("top part: " +
str(float(float(adj.shape[0]) * adj.shape[0] - adj.sum())))
print("pos wieght: " + str(pos_weight))
norm = adj.shape[0] * adj.shape[0] / float(
(adj.shape[0] * adj.shape[0] - adj.sum()) * 2)
# for validation data processing:
zero = sp.csr_matrix((adj_train.shape[0], adj_val.shape[0]))
adj_train_ext = sp.hstack((zero, adj_train))
adj_evaluate = sp.vstack((adj_val, adj_train_ext))
adj_evaluate = sp.csr_matrix(adj_evaluate)
rows, columns = adj_evaluate.nonzero()
val_edges = []
val_edges_false = []
pos = {}
print("getting positive edges")
all_val = [i for i in range(len(rows)) if rows[i] < adj_val.shape[0]]
for i in all_val:
sys.stdout.write("\r sampling edges for validtion: [" + str(i) + "]")
val_edges.append((rows[i], columns[i]))
if rows[i] not in pos:
pos[rows[i]] = []
pos[rows[i]].append(columns[i])
#for i in range(rows.shape[0]):
# sys.stdout.write("\r sampling edges for validtion: [" + str(i) + "/" + str(adj_val.shape[0]) + "]")
# sys.stdout.flush()
# if rows[i] < adj_val.shape[0]:
# val_edges.append((rows[i], columns[i]))
# if rows[i] not in pos:
# pos[rows[i]] = []
# pos[rows[i]].append(columns[i])
# adj_evaluate[columns[i], rows[i]] = adj_evaluate[rows[i], columns[i]]
# else:
# break
step = 0
neg_per_pos = 100
#for r in pos:
# p = pos[r]
#neg_edges = Parallel(n_jobs=40)(delayed(neg_sample)(pos[i], adj_val.shape[1], neg_per_pos, i) for i in pos)
#val_edges_false = [(i, item) for i in range(len(neg_edges)) for item in neg_edges[i]]
#a = np.random.permutation(adj_val.shape[1])
#a = [i for i in a if i not in p]
#a = a[:100]
#for i in a:
# val_edges_false.append((r, i))
##count = 0
##i = 0
#sys.stdout.write("\r sampling neg edges for validtion: [" + str(step) + "/" + str(len(pos)) + "]")
#sys.stdout.flush()
#step += 1
#while count < 100:
# if a[i] not in p:
# val_edges_false.append((r, a[i]))
# count += 1
# i += 1
print("preprocessing adj_evaluate")
adj_evaluate_norm = preprocess_graph(adj_evaluate)
#adj_evaluate_norm_label = preprocess_graph_sp(adj_evaluate)
adj_label_evaluate = adj_evaluate + sp.eye(
adj_evaluate.shape[0]
) #adj_evaluate_norm_label+ sp.eye(adj_evaluate.shape[0]) #adj_evaluate + sp.eye(adj_evaluate.shape[0])
#adj_label_evaluate = torch.FloatTensor(adj_label_evaluate.toarray()) #sparse_mx_to_torch_sparse_tensor(adj_label_evaluate)
features_evaluate = np.concatenate([features, features_valid])
features_evaluate = torch.from_numpy(features_evaluate)
# validation done
if mode == "VAE":
model = GCNModelVAE(feat_dim, args.hidden1, args.hidden2, args.dropout)
adj_label = torch.FloatTensor(adj_label.toarray())
adj_label_evaluate = torch.FloatTensor(adj_label_evaluate.toarray())
elif mode == "AE":
model = GCNModelAE(feat_dim, args.hidden1, args.hidden2, args.dropout)
#adj_label = torch.FloatTensor(adj_label.toarray())
#adj_label_evaluate = torch.FloatTensor(adj_label_evaluate.toarray())
elif mode == "VAE_batch":
model = GCNModelVAE_batch(feat_dim, args.hidden1, args.hidden2,
args.dropout)
elif mode == "AE_batch":
model = GCNModelAE_batch(feat_dim, args.hidden1, args.hidden2,
args.dropout).cuda()
#model = torch.nn.DataParallel(model)
#model = model.cuda()
# train_dataset = GAEDataset(adj_norm, adj_label, features)
# train_loader = DataLoader(dataset=train_dataset, batch_size=args.batch_size,
# shuffle=True, num_workers=8, pin_memory=True)
train_ids = torch.tensor(range(features.shape[0]), dtype=torch.long)
train_dataset = TensorDataset(train_ids)
train_loader = DataLoader(dataset=train_dataset,
batch_size=args.batch_size,
shuffle=True,
num_workers=8,
pin_memory=True)
optimizer = optim.Adam(model.parameters(), lr=args.lr)
#optimizer = pSGLD(model.parameters(), lr=args.lr)
#optimizer = optim.RMSprop(model.parameters(), lr=args.lr)
hidden_emb = None
pos_weight = torch.from_numpy(np.array(0.0, dtype=np.float32))
#ipdb.set_trace()
t = time.time()
best = 0
best_epoch = 0
best_val_cost = 99999
best_val_epoch = 0
best_val_epoch_revop = 0
prev_loss = 0
prev_val_loss = 99999
best_val_roc = 0
best_val_ap = 0
best_val_roc_revop = 0
best_val_ap_revop = 0
torch.set_num_threads(20)
print("NUM THREADS USED")
print(torch.get_num_threads())
for epoch in range(args.epochs):
#t = time.time()
model.train()
lossVal = 0
lossValNorm = 0
backtime = time.time()
for batchID, (inds) in enumerate(train_loader):
z = model(features, adj_norm)
inds = inds[0]
adj = F.relu(torch.mm(z[inds], z[inds].t()))
preds = adj
label_batch = torch.FloatTensor(adj_label[inds, :][:,
inds].toarray())
cost = norm * F.binary_cross_entropy_with_logits(
preds, label_batch, pos_weight=pos_weight)
lossVal += cost.item()
lossValNorm += 1
optimizer.zero_grad()
cost.backward(retain_graph=True)
# if batchID == 0:
# cost.backward(retain_graph=True)
# else:
# cost.backward()
optimizer.step()
if batchID >= 10:
break
backtime_done = time.time() - backtime
sys.stdout.write("\r time taken to do epoch: " + str(backtime_done) +
" opt: " + str(time.time() - backtime) + "\n")
sys.stdout.flush()
#optimizer.step()
# sample rows only: non-square
#for i in range(0, d.shape[0], sample_size):
# selection = random_perm[i:i+sample_size]
# to_keep = selection
# sample_adj_norm = sparse_mx_to_torch_sparse_tensor(sp.coo_matrix(d[to_keep, :]))
# sample_adj = adj[to_keep, :]
# sample_features = features
# recovered, mu, logvar = model(sample_features, sample_adj_norm)
# loss = loss_function(preds=recovered, labels=sample_adj_label,
# mu=mu, logvar=logvar, n_nodes=n_nodes,
# norm=norm, pos_weight=pos_weight)
# loss.backward()
# cur_loss = loss.item()
# optimizer.step()
# sys.stdout.write("\r ")
# sys.stdout.write("\r" + "sampling [" + str(i) + "/" + str(d.shape[0]))
# sys.stdout.flush()
# sample rows + take their postiives and add to rows (make it square)
#for i in range(0, d.shape[0], sample_size):
# selection = random_perm[i:i+sample_size]
# to_keep = np.nonzero(d[selection, :])
# # (array([0, 1, 2, 2]), array([0, 1, 0, 1]))
# the_set = set(list(to_keep[0]) + list(to_keep[1]))
# temp = set(list(to_keep[0]))
# to_keep = list(the_set - column_exclude)
# # column_exclude.union(temp)
# # these ar ethe rows and columns that we need ne select
# sample_adj_norm = sparse_mx_to_torch_sparse_tensor(sp.coo_matrix(d[to_keep, :][:,to_keep]))
# sample_features = features[to_keep, :]
# sample_adj_label = adj_label[to_keep, :][:,to_keep]
# #print(samplei_adj_norm.shape)
# #print(sample_features.shape)
# #print(sample_adj_label.shape)
# #print(sample.shape)
# sample_adj = adj[to_keep, :][:,to_keep]
# pos_weight = float(sample_adj.shape[0] * sample_adj.shape[0] - sample_adj.sum()) / sample_adj.sum()
# pos_weight = torch.from_numpy(np.array(pos_weight))
# norm = sample_adj.shape[0] * sample_adj.shape[0] / float((sample_adj.shape[0] * sample_adj.shape[0] - sample_adj.sum()) * 2)
# n_nodes, feat_dim = sample_features.shape
# if mode == "VAE":
# recovered, mu, logvar = model(sample_features, sample_adj_norm)
# #recovered = recovered[i:i+500]
# #sample_adj_label = sample_adj_label[i:i+500]
# loss = loss_function(preds=recovered, labels=sample_adj_label,
# mu=mu, logvar=logvar, n_nodes=n_nodes,
# norm=norm, pos_weight=pos_weight)
# elif mode == "AE":
# recovered = model(sample_features, sample_adj_norm)
# loss = loss_function_ae(preds=recovered, labels=sample_adj_label,
# norm=norm, pos_weight=pos_weight)
# loss.backward()
# cur_loss = loss.item()
# optimizer.step()
# sys.stdout.write("\r ")
# sys.stdout.write("\r" + "sampling [" + str(i) + "/" + str(d.shape[0]) + "]....size of sample=" + str(len(sample_features)))
# sys.stdout.flush()
sys.stdout.write(
"\r \r"
)
if (epoch + 1) % 1 == 0:
model.eval()
#adj_dense = adj_train.todense()
#adj_val_dense = adj_val.todense()
#adj_train_ext = np.pad(adj_dense, [[0,0], [adj_val_dense.shape[0], 0]], "constant")
#adj_evaluate = np.concatenate([adj_val_dense, adj_train_ext])
#zero = sp.csr_matrix((adj_train.shape[0], adj_val.shape[0]))
#adj_train_ext = sp.hstack((zero, adj_train))
#adj_evaluate = sp.vstack((adj_val, adj_train_ext))
##zeros = sp.csr_matrix((adj_evaluate.shape[0], adj_val.shape[1]))
##adj_evaluate = sp.hstack((zeros, adj_evaluate))
#adj_evaluate = sp.csr_matrix(adj_evaluate)
#rows, columns = adj_evaluate.nonzero()
#for i in range(rows.shape[0]):
# if rows[i] < adj_val.shape[1]:
# adj_evaluate[columns[i], rows[i]] = adj_evaluate[rows[i], columns[i]]
# else:
# break
#adj_evaluate_norm = preprocess_graph(adj_evaluate)
#adj_label_evaluate = adj_evaluate + sp.eye(adj_evaluate.shape[0])
#adj_label_evaluate = torch.FloatTensor(adj_label_evaluate.toarray())
##adj_label_evaluate = sparse_to_tuple(adj_label_evaluate)
#features_evaluate = np.concatenate([features, features_valid])
#features_evaluate = torch.from_numpy(features_evaluate)
just_adj_evaluate = sparse_mx_to_torch_sparse_tensor(adj_evaluate)
#recovered, mu, logvar = model(features_evaluate, just_adj_evaluate.coalesce().indices(), just_adj_evaluate.coalesce().values())
#recovered, mu, logvar = model(features_evaluate, adj_evaluate_norm)
#val_loss = loss_function(preds=recovered, labels=adj_label_evaluate,
# mu=mu, logvar=logvar, n_nodes=n_nodes,
# norm=norm, pos_weight=pos_weight)
# if mode == "VAE":
# recovered, mu, logvar = model(features_evaluate, adj_evaluate_norm)
# val_loss = loss_function(preds=recovered, labels=adj_label_evaluate,
# mu=mu, logvar=logvar, n_nodes=n_nodes,
# norm=norm, pos_weight=pos_weight)
# elif mode == "AE":
# mu = model(features_evaluate, adj_evaluate_norm)
# val_loss = loss_function_ae(preds=recovered, labels=adj_label_evaluate,
# norm=norm, pos_weight=pos_weight)
# elif mode == "VAE_batch":
# recovered, mu, logvar, val_loss = model(features_evaluate, adj_evaluate_norm, labels=adj_label_evaluate, n_nodes=n_nodes, norm=norm, pos_weight=pos_weight, opt=None, training=False)
# elif mode == "AE_batch":
# recovered, mu, val_loss = model(features_evaluate, adj_evaluate_norm, labels=adj_label_evaluate, n_nodes=n_nodes, norm=norm, pos_weight=pos_weight, opt=None, training=False)
# val_emb = mu.data.numpy()
#roc_curr, ap_curr = get_roc_score(val_emb, val_edges, val_edges_false)
# do one q at a time
#revop_map = eval_each_q(model, adj_all, features_all, Q.shape[1])
# hack by appending stuff on top of adj
if mode == "VAE":
_, mu, _ = model(features_all, adj_all_norm)
elif mode == "AE":
mu = model(features_all, adj_all_norm)
elif mode == "VAE_batch":
mu = model(features_all,
adj_all_norm,
None,
None,
None,
None,
None,
just_mu=True,
training=False)
elif mode == "AE_batch":
mu = model(features_all,
adj_all_norm,
None,
None,
None,
None,
None,
just_mu=True,
training=False)
hidden_emb = mu.data.numpy()
## get validation loss
#recovered, mu, logvar = model(features, adj_norm)
#val_loss = loss_function(preds=recovered, labels=adj_label,
# mu=mu, logvar=logvar, n_nodes=n_nodes,
# norm=norm, pos_weight=pos_weight)
revop_map = get_roc_score_matrix(hidden_emb, Q.shape[1])
if best <= revop_map:
emb = hidden_emb
Q_end = Q.shape[1]
best = revop_map
best_epoch = epoch + 1
# write it into a file and do egt on that
#embQ = emb[:Q_end,:].T
#embX = emb[Q_end:,:].T
#np.save("/media/jason/28c9eee1-312e-47d0-88ce-572813ebd6f1/graph/gae-pytorch/best_embedding2.npy",hidden_emb)
#concat = np.concatenate((embQ.T,embX.T))
#revop_inner_prod = np.matmul(concat, concat.T)
#revop_preds = np.argsort(-revop_inner_prod,axis=0)
#if revop_map > 54:
# f = open("best_result.txt", "w")
# for i in range(revop_preds.shape[1]):
# if i < Q_end:
# f.write(qhashes[i] + ",")
# else:
# f.write(chashes[i - Q_end] + ",")
# for j in revop_preds[:,i]:
# if j < Q_end:
# f.write(qhashes[j] + " " + str(int(revop_inner_prod[j,i] * 1000)) + " ")
# else:
# f.write(chashes[j - Q_end] + " " + str(int(revop_inner_prod[j,i] * 1000)) + " ")
# f.write("\n")
# f.flush()
# #for j in range()
# f.close()
if best_val_cost > -99.0: #prev_val_loss - val_loss > 0 and prev_val_loss - val_loss > prev_loss - cur_loss and best_val_cost > val_loss:
best_val_cost = -99.0
best_val_epoch = epoch + 1
best_val_epoch_revop = revop_map
#if best_val_roc < roc_curr:
# best_val_roc = roc_curr
# best_val_roc_revop = revop_map
#if best_val_ap < ap_curr:
# best_val_ap = ap_curr
# best_val_ap_revop = revop_map
print(
"Epoch:",
'%04d' % (epoch + 1),
"train_loss=",
"{:.5f}".format(lossVal / lossValNorm),
"val_loss=",
"{:.5f}".format(-99.0),
#"val_roc_curr=", "{:.5f}".format(roc_curr),
#"val_ap_curr=", "{:.5f}".format(ap_curr),
"revop=",
"{:.5f}".format(revop_map),
"best_revop=",
"{:.5f}".format(best),
"revop_at_best_val=",
"{:.5f}".format(best_val_epoch_revop),
#"revop_at_best_val_roc=", "{:.5f}".format(best_val_roc_revop),
#"revop_at_best_ap_roc=", "{:.5f}".format(best_val_ap_revop),
"time=",
"{:.5f}".format(time.time() - t))
prev_val_loss = -99.0
prev_loss = -99.0
t = time.time()
print("Optimization Finished!")
#roc_score, ap_score = get_roc_score(hidden_emb, adj_orig, test_edges, test_edges_false)
#print('Test ROC score: ' + str(roc_score))
#print('Test AP score: ' + str(ap_score))
return best, best_val_epoch_revop, best_val_roc_revop, best_val_ap_revop
def GAEembedding(z, adj, args):
'''
GAE embedding for clustering
Param:
z,adj
Return:
Embedding from graph
'''
# true_labels = np.asarray(true_labels)
# args.model = 'gcn_vae'
# args.dw = 0
# args.epochs = 200
# args.hidden1 = 32
# args.hidden2 = 16
# args.lr = 0.01
# args.dropout = 0.
# args.dataset_sr = 'cora'
# args.walk_length = 5
# args.window_size = 3
# args.number_walks = 5
# args.full_number_walks =0
# args.lr_dw = 0.001
# args.context = 0
# args.ns = 1
# args.n_clusters = 11
# args.plot = 0
# featrues from z
# Louvain
features = z
# features = torch.DoubleTensor(features)
features = torch.FloatTensor(features)
# Old implementation
# adj, features, y_test, tx, ty, test_maks, true_labels = load_data(args.dataset_str)
n_nodes, feat_dim = features.shape
# Store original adjacency matrix (without diagonal entries) for later
adj_orig = adj
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
# Before proceeding further, make the structure for doing deepWalk
# if args.dw == 1:
# print('Using deepWalk regularization...')
# G = load_edgelist_from_csr_matrix(adj_orig, undirected=True)
# print("Number of nodes: {}".format(len(G.nodes())))
# num_walks = len(G.nodes()) * args.number_walks
# print("Number of walks: {}".format(num_walks))
# data_size = num_walks * args.walk_length
# print("Data size (walks*length): {}".format(data_size))
# Some preprocessing
adj_norm = preprocess_graph(adj)
adj_label = adj_train + sp.eye(adj_train.shape[0])
# adj_label = sparse_to_tuple(adj_label)
# adj_label = torch.DoubleTensor(adj_label.toarray())
adj_label = torch.FloatTensor(adj_label.toarray())
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)
if args.GAEmodel == 'gcn_vae':
model = GCNModelVAE(feat_dim, args.GAEhidden1, args.GAEhidden2,
args.GAEdropout)
else:
model = GCNModelAE(feat_dim, args.GAEhidden1, args.GAEhidden2,
args.GAEdropout)
if args.precisionModel == 'Double':
model = model.double()
optimizer = optim.Adam(model.parameters(), lr=args.GAElr)
# if args.dw == 1:
# sg = SkipGram(args.hidden2, adj.shape[0])
# optimizer_dw = optim.Adam(sg.parameters(), lr=args.lr_dw)
# # Construct the nodes for doing random walk. Doing it before since the seed is fixed
# nodes_in_G = list(G.nodes())
# chunks = len(nodes_in_G) // args.number_walks
# random.Random().shuffle(nodes_in_G)
hidden_emb = None
for epoch in tqdm(range(args.GAEepochs)):
t = time.time()
# mem=resource.getrusage(resource.RUSAGE_SELF).ru_maxrss
# print('Mem consumption before training: '+str(mem))
model.train()
optimizer.zero_grad()
z, mu, logvar = model(features, adj_norm)
# After back-propagating gae loss, now do the deepWalk regularization
# if args.dw == 1:
# sg.train()
# if args.full_number_walks > 0:
# walks = build_deepwalk_corpus(G, num_paths=args.full_number_walks,
# path_length=args.walk_length, alpha=0,
# rand=random.Random(SEED))
# else:
# walks = build_deepwalk_corpus_iter(G, num_paths=args.number_walks,
# path_length=args.walk_length, alpha=0,
# rand=random.Random(SEED),
# chunk=epoch % chunks,
# nodes=nodes_in_G)
# for walk in walks:
# if args.context == 1:
# # Construct the pairs for predicting context node
# # for each node, treated as center word
# curr_pair = (int(walk[center_node_pos]), [])
# for center_node_pos in range(len(walk)):
# # for each window position
# for w in range(-args.window_size, args.window_size + 1):
# context_node_pos = center_node_pos + w
# # make soure not jump out sentence
# if context_node_pos < 0 or context_node_pos >= len(walk) or center_node_pos == context_node_pos:
# continue
# context_node_idx = walk[context_node_pos]
# curr_pair[1].append(int(context_node_idx))
# else:
# # first item in the walk is the starting node
# curr_pair = (int(walk[0]), [int(context_node_idx) for context_node_idx in walk[1:]])
# if args.ns == 1:
# neg_nodes = []
# pos_nodes = set(walk)
# while len(neg_nodes) < args.walk_length - 1:
# rand_node = random.randint(0, n_nodes - 1)
# if rand_node not in pos_nodes:
# neg_nodes.append(rand_node)
# neg_nodes = torch.from_numpy(np.array(neg_nodes)).long()
# # Do actual prediction
# src_node = torch.from_numpy(np.array([curr_pair[0]])).long()
# tgt_nodes = torch.from_numpy(np.array(curr_pair[1])).long()
# optimizer_dw.zero_grad()
# log_pos = sg(src_node, tgt_nodes, neg_sample=False)
# if args.ns == 1:
# loss_neg = sg(src_node, neg_nodes, neg_sample=True)
# loss_dw = log_pos + loss_neg
# else:
# loss_dw = log_pos
# loss_dw.backward(retain_graph=True)
# cur_dw_loss = loss_dw.item()
# optimizer_dw.step()
loss = loss_function(preds=model.dc(z),
labels=adj_label,
mu=mu,
logvar=logvar,
n_nodes=n_nodes,
norm=norm,
pos_weight=pos_weight)
loss.backward()
cur_loss = loss.item()
optimizer.step()
hidden_emb = mu.data.numpy()
# TODO, this is prediction
# roc_curr, ap_curr = get_roc_score(hidden_emb, adj_orig, val_edges, val_edges_false)
ap_curr = 0
# if args.dw == 1:
# tqdm.write("Epoch: {}, train_loss_gae={:.5f}, train_loss_dw={:.5f}, val_ap={:.5f}, time={:.5f}".format(
# epoch + 1, cur_loss, cur_dw_loss,
# ap_curr, time.time() - t))
# else:
tqdm.write(
"Epoch: {}, train_loss_gae={:.5f}, val_ap={:.5f}, time={:.5f}".
format(epoch + 1, cur_loss, ap_curr,
time.time() - t))
# if (epoch + 1) % 10 == 0:
# tqdm.write("Evaluating intermediate results...")
# kmeans = KMeans(n_clusters=args.n_clusters, random_state=0).fit(hidden_emb)
# predict_labels = kmeans.predict(hidden_emb)
# cm = clustering_metrics(true_labels, predict_labels)
# cm.evaluationClusterModelFromLabel(tqdm)
# roc_score, ap_score = get_roc_score(hidden_emb, adj_orig, test_edges, test_edges_false)
# tqdm.write('ROC: {}, AP: {}'.format(roc_score, ap_score))
# np.save('logs/emb_epoch_{}.npy'.format(epoch + 1), hidden_emb)
tqdm.write("Optimization Finished!")
roc_score, ap_score = get_roc_score(hidden_emb, adj_orig, test_edges,
test_edges_false)
tqdm.write('Test ROC score: ' + str(roc_score))
tqdm.write('Test AP score: ' + str(ap_score))
# kmeans = KMeans(n_clusters=args.n_clusters, random_state=0).fit(hidden_emb)
# predict_labels = kmeans.predict(hidden_emb)
# cm = clustering_metrics(true_labels, predict_labels)
# cm.evaluationClusterModelFromLabel(tqdm)
# if args.GAEplot == 1:
# cm.plotClusters(tqdm, hidden_emb, true_labels)
return hidden_emb
def gae_for(args):
print("Using {} dataset".format(args.dataset_str))
adj, features = load_data(args.dataset_str)
n_nodes, feat_dim = features.shape
# Store original adjacency matrix (without diagonal entries) for later
adj_orig = adj
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
# Some preprocessing
adj_norm = preprocess_graph(adj)
adj_label = adj_train + sp.eye(adj_train.shape[0])
# adj_label = sparse_to_tuple(adj_label)
adj_label = torch.FloatTensor(adj_label.toarray())
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)
lst_result = []
for i in range(10):
model = GCNModelVAE(feat_dim, args.hidden1, args.hidden2, args.dropout)
optimizer = optim.Adam(model.parameters(), lr=args.lr)
hidden_emb = None
max_roc_ap = 0
for epoch in range(args.epochs):
t = time.time()
model.train()
optimizer.zero_grad()
recovered, mu, logvar = model(features, adj_norm)
loss = loss_function(preds=recovered,
labels=adj_label,
mu=mu,
logvar=logvar,
n_nodes=n_nodes,
norm=norm,
pos_weight=pos_weight)
loss.backward()
cur_loss = loss.item()
optimizer.step()
hidden_emb = mu.data.numpy()
roc_curr, ap_curr = get_roc_score(hidden_emb, adj_orig, val_edges,
val_edges_false)
roc_ap = roc_curr + ap_curr
if max_roc_ap < roc_ap:
max_roc_ap = roc_ap
h_emb_best_model = hidden_emb
print("Epoch:", '%04d' % (epoch + 1), "train_loss=",
"{:.5f}".format(cur_loss), "val_ap=",
"{:.5f}".format(ap_curr), "time=",
"{:.5f}".format(time.time() - t))
roc_score, ap_score = get_roc_score(hidden_emb, adj_orig,
test_edges, test_edges_false)
print('Test ROC score: ' + str(roc_score))
print('Test AP score: ' + str(ap_score))
print("---------------------------------------")
print("Optimization Finished!: ", i)
roc_score, ap_score = get_roc_score(h_emb_best_model, adj_orig,
test_edges, test_edges_false)
# roc_score, ap_score = get_roc_score(hidden_emb, adj_orig, test_edges, test_edges_false)
lst_result.append([i, roc_score, ap_score])
print('Test ROC score: ' + str(roc_score))
print('Test AP score: ' + str(ap_score))
lst_result = np.array(lst_result)
csv_info = np.append(
lst_result,
[["mean", np.mean(lst_result[:, 1]),
np.mean(lst_result[:, 2])]],
axis=0)
csv_info = np.append(
csv_info,
[["std", np.std(lst_result[:, 1]),
np.std(lst_result[:, 2])]],
axis=0)
t = int(time.time())
folder = Path(os.path.join(os.getcwd(), "csv"))
csv_name = "{}_{}_{}_{}_{}.csv".format(args.dataset_str, args.epochs,
args.hidden1, args.hidden2, t)
df = pd.DataFrame(csv_info, columns=['run', 'ROC', "AP"])
df.to_csv(os.path.join(folder, csv_name))
def GAEembedding(z, adj, args):
'''
GAE embedding for clustering
Param:
z,adj
Return:
Embedding from graph
'''
# featrues from z
# Louvain
features = z
# features = torch.DoubleTensor(features)
features = torch.FloatTensor(features)
# Old implementation
# adj, features, y_test, tx, ty, test_maks, true_labels = load_data(args.dataset_str)
n_nodes, feat_dim = features.shape
# Store original adjacency matrix (without diagonal entries) for later
adj_orig = adj
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
# Some preprocessing
adj_norm = preprocess_graph(adj)
adj_label = adj_train + sp.eye(adj_train.shape[0])
# adj_label = sparse_to_tuple(adj_label)
# adj_label = torch.DoubleTensor(adj_label.toarray())
adj_label = torch.FloatTensor(adj_label.toarray())
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)
if args.GAEmodel == 'gcn_vae':
model = GCNModelVAE(feat_dim, args.GAEhidden1, args.GAEhidden2,
args.GAEdropout)
else:
model = GCNModelAE(feat_dim, args.GAEhidden1, args.GAEhidden2,
args.GAEdropout)
if args.precisionModel == 'Double':
model = model.double()
optimizer = optim.Adam(model.parameters(), lr=args.GAElr)
hidden_emb = None
for epoch in tqdm(range(args.GAEepochs)):
t = time.time()
# mem=resource.getrusage(resource.RUSAGE_SELF).ru_maxrss
# print('Mem consumption before training: '+str(mem))
model.train()
optimizer.zero_grad()
z, mu, logvar = model(features, adj_norm)
loss = loss_function(preds=model.dc(z),
labels=adj_label,
mu=mu,
logvar=logvar,
n_nodes=n_nodes,
norm=norm,
pos_weight=pos_weight)
loss.backward()
cur_loss = loss.item()
optimizer.step()
hidden_emb = mu.data.numpy()
# TODO, this is prediction
# roc_curr, ap_curr = get_roc_score(hidden_emb, adj_orig, val_edges, val_edges_false)
ap_curr = 0
tqdm.write(
"Epoch: {}, train_loss_gae={:.5f}, val_ap={:.5f}, time={:.5f}".
format(epoch + 1, cur_loss, ap_curr,
time.time() - t))
tqdm.write("Optimization Finished!")
roc_score, ap_score = get_roc_score(hidden_emb, adj_orig, test_edges,
test_edges_false)
tqdm.write('Test ROC score: ' + str(roc_score))
tqdm.write('Test AP score: ' + str(ap_score))
return hidden_emb