def collect_svc(name, most_similar_name, indices):
svc_results = []
data = dataTools.AuthorshipOneVsOne(name, most_similar_name, ratioTrain,
ratioValid, dataPath)
logging.info('Training SVM on {0} v.s. {1}'.format(name,
most_similar_name))
for split_n in range(NO_OF_SPLITS):
data.get_split(name, most_similar_name, ratioTrain, ratioValid)
data.reduce_dim(indices)
start = time.perf_counter()
svc = linear_class.train_svc(data)
end = time.perf_counter()
svc_result = evaluate_svc(svc, data)
svc_result['time'] = start - end
svc_results.append(svc_result)
logging.info(
'SPLIT {0}: SVM results successfully collected: {1}'.format(
split_n, svc_result))
return svc_results
def collect_gcnn(name, most_similar_name, phi, ind):
gcnn_results = []
data = dataTools.AuthorshipOneVsOne(name, most_similar_name, ratioTrain,
ratioValid, dataPath)
logging.info('Training GCNN on {0} v.s. {1}'.format(
name, most_similar_name))
h_params = ClusterUtils.load_best_hyperparams(name)
for split_n in range(NO_OF_SPLITS):
data.get_split(name, most_similar_name, ratioTrain, ratioValid)
data.reduce_dim(ind)
start = time.perf_counter()
gcnn = train_helper.train_net(data, h_params, phi=phi)
end = time.perf_counter()
gcnn_eval = evaluate_gcnn(gcnn, data)
gcnn_eval['time'] = start - end
gcnn_results.append(gcnn_eval)
logging.info(
'SPLIT {0}: GCNN results successfully collected: {1}'.format(
split_n, gcnn_results[split_n]))
return gcnn_results
def collect_gcnn(name, most_similar_name):
gcnn_results = []
data = dataTools.AuthorshipOneVsOne(name, most_similar_name, ratioTrain, ratioValid, dataPath)
logging.info('Training GCNN on {0} v.s. {1}'.format(name, most_similar_name))
h_params = ClusterUtils.load_best_hyperparams(name)
for split_n in range(NO_OF_SPLITS):
data.get_split(name, most_similar_name, ratioTrain, ratioValid)
gcnn = train_helper.train_net(data, h_params)
gcnn_results.append(evaluate_gcnn(gcnn, data))
logging.info('SPLIT {0}: GCNN results successfully collected: {1}'.format(split_n, gcnn_results[split_n]))
return gcnn_results