def main(args):
print('#' * 70)
print('Embedding Method: %s, Evaluation Task: %s' %
(args.method, args.task))
print('#' * 70)
if args.task == 'link-prediction':
G, G_train, testing_pos_edges, train_graph_filename = split_train_test_graph(
args.input, args.seed, weighted=args.weighted)
time1 = time.time()
embedding_training(args, train_graph_filename)
embed_train_time = time.time() - time1
print('Embedding Learning Time: %.2f s' % embed_train_time)
embedding_look_up = load_embedding(args.output)
time1 = time.time()
print('Begin evaluation...')
result = LinkPrediction(embedding_look_up, G, G_train,
testing_pos_edges, args.seed)
eval_time = time.time() - time1
print('Prediction Task Time: %.2f s' % eval_time)
os.remove(train_graph_filename)
elif args.task == 'node-classification':
if not args.label_file:
raise ValueError("No input label file. Exit.")
node_list, labels = read_node_labels(args.label_file)
train_graph_filename = args.input
time1 = time.time()
embedding_training(args, train_graph_filename)
embed_train_time = time.time() - time1
print('Embedding Learning Time: %.2f s' % embed_train_time)
embedding_look_up = load_embedding(args.output, node_list)
time1 = time.time()
print('Begin evaluation...')
result = NodeClassification(embedding_look_up, node_list, labels,
args.testingratio, args.seed)
eval_time = time.time() - time1
print('Prediction Task Time: %.2f s' % eval_time)
else:
train_graph_filename = args.input
time1 = time.time()
embedding_training(args, train_graph_filename)
embed_train_time = time.time() - time1
print('Embedding Learning Time: %.2f s' % embed_train_time)
if args.eval_result_file and result:
_results = dict(
input=args.input,
task=args.task,
method=args.method,
dimension=args.dimensions,
user=getpass.getuser(),
date=datetime.datetime.now().strftime('%Y-%m-%d-%H%M%S'),
seed=args.seed,
)
if args.task == 'link-prediction':
##### ADDED: variables to store prediction and ROC results
auc_roc, auc_pr, accuracy, f1, prediction, fpr, tpr = result
_results['results'] = dict(auc_roc=auc_roc,
auc_pr=auc_pr,
accuracy=accuracy,
f1=f1
#pred=prediction,
#fpr=fpr,
#tpr=tpr
)
else:
accuracy, f1_micro, f1_macro = result
_results['results'] = dict(
accuracy=accuracy,
f1_micro=f1_micro,
f1_macro=f1_macro,
)
with open(args.eval_result_file, 'a+') as wf:
print(json.dumps(_results, sort_keys=True), file=wf)
##### ADDED: Write predictions to predictions output file #####
with open(args.predictions, 'w') as pf:
np.savetxt(pf, prediction, fmt='%s', delimiter=',')
pf.close()
##### ADDED: Write FPR and TPR to ROC output file #####
fpr = list(fpr)
tpr = list(tpr)
roc = [fpr, tpr]
with open(args.roc, 'w') as rf:
writer = csv.writer(rf)
writer.writerows(roc)
rf.close()
def main(args):
print('#' * 70)
print('Embedding Method: %s, Evaluation Task: %s' %
(args.method, args.task))
print('#' * 70)
if args.task == 'link-prediction':
G, G_train, testing_pos_edges, train_graph_filename = split_train_test_graph(
args.input, args.seed, weighted=args.weighted)
time1 = time.time()
embedding_training(args, train_graph_filename)
embed_train_time = time.time() - time1
print('Embedding Learning Time: %.2f s' % embed_train_time)
embedding_look_up = load_embedding(args.output)
time1 = time.time()
print('Begin evaluation...')
result = LinkPrediction(embedding_look_up, G, G_train,
testing_pos_edges, args.seed)
eval_time = time.time() - time1
print('Prediction Task Time: %.2f s' % eval_time)
os.remove(train_graph_filename)
elif args.task == 'node-classification':
if not args.label_file:
raise ValueError("No input label file. Exit.")
node_list, labels = read_node_labels(args.label_file)
train_graph_filename = args.input
time1 = time.time()
embedding_training(args, train_graph_filename)
embed_train_time = time.time() - time1
print('Embedding Learning Time: %.2f s' % embed_train_time)
embedding_look_up = load_embedding(args.output, node_list)
time1 = time.time()
print('Begin evaluation...')
result = NodeClassification(embedding_look_up, node_list, labels,
args.testingratio, args.seed)
eval_time = time.time() - time1
print('Prediction Task Time: %.2f s' % eval_time)
else:
train_graph_filename = args.input
time1 = time.time()
embedding_training(args, train_graph_filename)
embed_train_time = time.time() - time1
print('Embedding Learning Time: %.2f s' % embed_train_time)
if args.eval_result_file and result:
_results = dict(
input=args.input,
task=args.task,
method=args.method,
dimension=args.dimensions,
user=getpass.getuser(),
date=datetime.datetime.now().strftime('%Y-%m-%d-%H%M%S'),
seed=args.seed,
)
if args.task == 'link-prediction':
auc_roc, auc_pr, accuracy, f1 = result
_results['results'] = dict(
auc_roc=auc_roc,
auc_pr=auc_pr,
accuracy=accuracy,
f1=f1,
)
else:
accuracy, f1_micro, f1_macro = result
_results['results'] = dict(
accuracy=accuracy,
f1_micro=f1_micro,
f1_macro=f1_macro,
)
with open(args.eval_result_file, 'a+') as wf:
print(json.dumps(_results, sort_keys=True), file=wf)
vectors[word] = word2vec.wv[word]
del word2vec
filename="C:/git/BioNEV/src/node2vec Embeddings.txt"
fout = open(filename, 'w')
node_num = len(vectors.keys())
fout.write("{} {}\n".format(node_num, 100))
for node, vec in vectors.items():
fout.write("{} {}\n".format(node,
' '.join([str(x) for x in vec])))
fout.close()
############################################################################################
_results = dict()
G, G_train, testing_pos_edges, train_graph_filename = split_train_test_graph(train_graph_filename, None, weighted=None)
g = read_for_SVD(train_graph_filename, weighted=None)
EMBED="C:/git/BioNEV/embeddings/SVD_OutputFile"
SVD_embedding(g, EMBED, size=100)
embedding_look_up = load_embedding(EMBED)
result = LinkPrediction(embedding_look_up, G, G_train, testing_pos_edges,0)
auc_roc, auc_pr, accuracy, f1 = result
_results['results'] = dict(
auc_roc=auc_roc,
auc_pr=auc_pr,
accuracy=accuracy,
f1=f1,
)
print(_results)
)
train_graph_filename= "C:/git/BioNEV/data/DrugBank_DDI/DrugBank_DDI.edgelist"
train_graph_filename= "C:/git/BioNEV/data/DrugBank_DDI/Karate.edgelist"
G2=Graph()
#G..read_weighted_edgelist(train_graph_filename)
G1 = nx.read_weighted_edgelist(train_graph_filename)
G2.read_g(G1)
from bionev.OpenNE import node2vec
from bionev.OpenNE import gf, grarep, hope, lap, line, node2vec, sdne
from bionev.utils import *
G, G_train, testing_pos_edges, train_graph_filename = split_train_test_graph(args.input, args.seed, weighted=args.weighted)
G, G_train, testing_pos_edges, train_graph_filename = split_train_test_graph(train_graph_filename, None, weighted=False)
model = node2vec.Node2vec(graph=G_, path_length=args.walk_length,
num_paths=args.number_walks, dim=args.dimensions,
workers=args.workers, p=args.p, q=args.q, window=args.window_size)
g1 = read_for_OpenNE(train_graph_filename, weighted=False)
model = node2vec.Node2vec(g1,path_length=64,num_paths=32,dim=100, workers=8,p=1,q=1,window=10)
print("test")
model = node2vecmodel.fit(window=10,min_count=1)
# Save embeddings for later use
def main(trials=None):
args = parse_args()
if trials is not None:
params = {
'C': trials.suggest_loguniform('C', 1e-10, 1e10),
'window_size': trials.suggest_int('window_size', 1, 20),
'pro_steps': trials.suggest_int('pro_steps', 1, 20),
'pro_mu': trials.suggest_uniform('pro_mu', -1.0, 1.0),
'pro_theta': trials.suggest_uniform('pro_theta', -1.0, 1.0),
'output': "%s_trial_%s" % (args.output, str(trials.number))
}
dargs = vars(args)
dargs.update(params)
print(args)
seed = args.seed
random.seed(seed)
np.random.seed(seed)
print('#' * 70)
print('Embedding Method: %s, Evaluation Task: %s' %
(args.method, args.task))
print('#' * 70)
if args.task == 'link-prediction':
G, G_train, testing_pos_edges, train_graph_filename = split_train_test_graph(
args.input,
args.seed,
weighted=args.weighted,
trial_number=trials.number)
time1 = time.time()
embedding_training(args, train_graph_filename)
embed_train_time = time.time() - time1
print('Embedding Learning Time: %.2f s' % embed_train_time)
embedding_look_up = load_embedding(args.output)
time1 = time.time()
print('Begin evaluation...')
result = LinkPrediction(embedding_look_up,
G,
G_train,
testing_pos_edges,
args.seed,
C=args.C)
eval_time = time.time() - time1
print('Prediction Task Time: %.2f s' % eval_time)
os.remove(train_graph_filename)
elif args.task == 'node-classification':
if not args.label_file:
raise ValueError("No input label file. Exit.")
node_list, labels = read_node_labels(args.label_file)
train_graph_filename = args.input
time1 = time.time()
embedding_training(args, train_graph_filename)
embed_train_time = time.time() - time1
print('Embedding Learning Time: %.2f s' % embed_train_time)
embedding_look_up = load_embedding(args.output, node_list)
time1 = time.time()
print('Begin evaluation...')
result = NodeClassification(embedding_look_up,
node_list,
labels,
args.testingratio,
args.seed,
C=args.C)
eval_time = time.time() - time1
print('Prediction Task Time: %.2f s' % eval_time)
else:
train_graph_filename = args.input
time1 = time.time()
embedding_training(args, train_graph_filename)
embed_train_time = time.time() - time1
print('Embedding Learning Time: %.2f s' % embed_train_time)
if args.eval_result_file and result:
_results = dict(
input=args.input,
task=args.task,
method=args.method,
dimension=args.dimensions,
user=getpass.getuser(),
date=datetime.datetime.now().strftime('%Y-%m-%d-%H%M%S'),
seed=args.seed,
)
if args.task == 'link-prediction':
auc_roc, auc_pr, accuracy, f1 = result
_results['results'] = dict(
auc_roc=auc_roc,
auc_pr=auc_pr,
accuracy=accuracy,
f1=f1,
)
else:
accuracy, f1_micro, f1_macro = result
_results['results'] = dict(
accuracy=accuracy,
f1_micro=f1_micro,
f1_macro=f1_macro,
)
with open(args.eval_result_file, 'a+') as wf:
print(json.dumps(_results, sort_keys=True), file=wf)
if args.task == 'link-prediction':
return auc_roc
else:
return accuracy