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()
from bionev.evaluation import LinkPrediction, NodeClassification
from bionev.embed_train import embedding_training, load_embedding, read_node_labels, split_train_test_graph
from bionev.SVD.model import SVD_embedding
from bionev.utils import *
from utils2
G, G_train, testing_pos_edges, train_graph_filename = split_train_test_graph(train_graph_filename, None, weighted=None)
GSnap, GNx= read_GRaph_SNAP_NX()
g = read_for_SVD(train_graph_filename, weighted=None)
SVD_embedding(g, "SVD_OutputFile", size=100)
embedding_look_up = load_embedding("SVD_OutputFile")
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)
import time
G, G_train, testing_pos_edges, train_graph_filename = split_train_test_graph(train_graph_filename, None, weighted=None)
g = read_for_OpenNE(train_graph_filename, weighted=None)
model = hope.HOPE(g, 100)
model.save_embeddings("HOPE_OutputFile")
embedding_look_up = load_embedding("HOPE_OutputFile")
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)
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