def kfold(ds, lab, k=5, regression=False, model=None):
# torch5Fold
from sklearn.model_selection import KFold
kf = KFold(n_splits=k, shuffle=True)
fold = 0
for tr_idx, te_idx in kf.split(lab):
try:
os.mkdir('active%d' % fold)
except FileExistsError:
pass
path = 'active%d' % fold
fold += 1
xtr, ytr, xte, yte = ds[tr_idx], lab[tr_idx], ds[te_idx], lab[te_idx]
if model: pass
else:
if regression: model = NN.FcRegRDKit()
else: model = NN.FcRDKit()
print('start training')
if regression: nn = active.TorchRegressionFold(xtr, ytr, xte, yte, model, 'active', path, ['percent_of_unlabel', 1],
measure='distance', distance='linear')
else: nn = active.TorchFold(xtr, ytr, xte, yte, model, 'active', path, ['percent_of_unlabel', 1])
nn.train()
print('finish training')
def split_train(ds, lab, test_ratio=0.3, regression=False, model=None):
all = len(lab)
splitor = split.TTSplit(all, 'portion', test=test_ratio)
tr_idx, te_idx = splitor.split()
xtr, ytr, xte, yte = ds[tr_idx], lab[tr_idx], ds[te_idx], lab[te_idx]
if model: pass
else:
if regression: model = NN.FcRegRDKit()
else: model = NN.FcRDKit()
print('start training')
if regression: nn = active.TorchRegressionFold(xtr, ytr, xte, yte, model, 'active', path, ['percent_of_unlabel', 1],
measure='distance', distance='linear')
else: nn = active.TorchFold(xtr, ytr, xte, yte, model, 'active', path, ['percent_of_unlabel', 1])
nn.train()
print('finish training')