return x * (1 - x) if derivative else 1 / (1 + np.exp(-x))
best_w = sigmoid(best_w)
print()
with np.printoptions(precision=2, suppress=True):
print(best_loss_v)
for l in best_w:
for e in l:
print('%.2f' % e, end=' ')
print()
print()
print(np.sum(best_w, axis=0))
weighted_inp = np.mean(valid_merged, axis=1)
best_th = threshold_search(weighted_inp, valid_ohs)
__best_threshold = best_th
f1_best = get_f1_threshold(weighted_inp, valid_ohs, __best_threshold)
print(__best_threshold)
print('f1_best(all, naive valid)=%.4f' % f1_best)
weighted_inp = np.mean(valid_v, axis=1)
best_th = threshold_search(weighted_inp, valid_ohs_v)
__best_threshold = best_th
f1_best = get_f1_threshold(weighted_inp, valid_ohs_v, __best_threshold)
print(__best_threshold)
print('f1_best(naive valid)=%.4f' % f1_best)
weighted_valid = valid_v * best_w
weighted_valid = np.sum(weighted_valid, axis=1)
weighted_valid = np.clip(weighted_valid, 0.0, 1.0)
# f1_best = get_f1_threshold(weighted_inp, valid_ohs, __best_threshold)
# print(__best_threshold)
# print('f1_best(naive valid)=%.4f' % f1_best)
#
# weighted_inp = np.mean(valid_v, axis=1)
# best_th = threshold_search(weighted_inp, valid_ohs_v)
# __best_threshold = best_th
# __best_threshold_naive = best_th
# f1_best = get_f1_threshold(weighted_inp, valid_ohs_v, __best_threshold)
# print(__best_threshold)
# print('f1_best(naive valid_v)=%.4f' % f1_best)
out = eval_batch(train_v, train_logit_v)
out = out.detach().cpu().numpy()
best_th = threshold_search(out, train_ohs_v)
__best_threshold = best_th
f1_best = get_f1_threshold(out, train_ohs_v, __best_threshold)
print(__best_threshold)
print('f1_best(train_v)=', f1_best)
out = eval_batch(valid_merged, valid_logit)
out = out.detach().cpu().numpy()
f1_best = get_f1_threshold(out, valid_ohs, __best_threshold)
print(__best_threshold)
print('f1_best(valid)=', f1_best)
best_th = threshold_search(out, valid_ohs)
metrics="merror",
seed=100)
print(cvr['train-merror-mean'].tail(1))
print(cvr['test-merror-mean'].tail(1))
print('-----')
print('----- train on subset')
xg_subset_t = xgb.DMatrix(valid_expand_t, label=valid_lbs_t)
xg_subset_v = xgb.DMatrix(valid_expand_v, label=valid_lbs_v)
bst = xgb.train(param,
xg_subset_t,
num_round, [(xg_subset_t, 'train'),
(xg_subset_v, 'valid')],
early_stopping_rounds=early_stop)
xgpred_val = bst.predict(xgb.DMatrix(valid_merged[:split_idx]))
best_th = threshold_search(xgpred_val, valid_ohs[:split_idx])
__best_threshold = best_th
f1_best = get_f1_threshold(xgpred_val, valid_ohs[:split_idx],
__best_threshold)
print(__best_threshold)
print('f1_best=', f1_best)
sys.exit(0)
# print('----------- train')
# bst = xgb.train(param, xg_train, num_round, watchlist, early_stopping_rounds=early_stop)
#
# xgpred_val = bst.predict(xg_train2)
# best_th = threshold_search(xgpred_val, valid_ohs)
# __best_threshold = best_th
# f1_best = get_f1_threshold(xgpred_val, valid_ohs, __best_threshold)
print('test result @ epoch=%d' % best_valid_epoch)
else:
print('load...')
checkpoint = torch.load('asset/%s.best.pt' % C.get()['name'])
model.load_state_dict(checkpoint['model_state_dict'])
print('epoch@%d' % checkpoint['epoch'])
# only for evaluation
tta = True
d_train, d_cvalid, d_tests = get_dataloaders_eval(tta)
model.eval()
# ----- train (sampled) -----
train_result = run_epoch(model, d_train, title='train', aug=tta)
best_th = threshold_search(train_result['prediction'],
train_result['labels'])
__best_threshold = best_th
print('best_th(train)=', __best_threshold)
preds_concat = np.concatenate(train_result['prediction'], axis=0)
ys_concat = np.concatenate(train_result['labels'], axis=0)
f1_train = get_f1_threshold(preds_concat, ys_concat, __best_threshold)
print('f1(train)=', f1_train)
# ----- cvalid -----
cvalid_result = run_epoch(model, d_cvalid, title='valid', aug=tta)
best_th = threshold_search(cvalid_result['prediction'],
cvalid_result['labels'])
__best_threshold = best_th
print('best_th(cvalid)=', __best_threshold)
loss = loss_fn(out, lb)
optimizer.zero_grad()
loss.backward()
optimizer.step()
ma_loss_t = ma_loss_t * 0.9 + loss.item() * 0.1
print()
# net.load_state_dict(best_model)
net.eval()
th_flat = True
weighted_inp = np.mean(train_merged, axis=1)
best_th = threshold_search(weighted_inp, train_ohs, flat=th_flat)
__best_threshold = best_th
f1_best = get_f1_threshold(weighted_inp, train_ohs, __best_threshold)
print(__best_threshold)
print('f1_best(naive train)=%.4f' % f1_best)
weighted_inp = np.mean(train_v, axis=1)
best_th = threshold_search(weighted_inp, train_ohs_v, flat=th_flat)
__best_threshold = best_th
f1_best = get_f1_threshold(weighted_inp, train_ohs_v, __best_threshold)
print(__best_threshold)
print('f1_best(naive train_v)=%.4f' % f1_best)
weighted_inp = np.mean(valid_merged, axis=1)
f1_best = get_f1_threshold(weighted_inp, valid_ohs, __best_threshold)
print('f1_best(naive valid)=%.4f' % f1_best)