max_round = 100
if wl_type == 'random_':
max_round = 2000
for ind, c_ecoc in enumerate(best_ecoc[1]):
print('Training function {}...'.format(ind))
# TODO preprocess labels, so that labels match ecoc, {0, 1} -> {-1, 1}
bin_label = util.generate_bin_label_from_ecoc(tr_data[1], c_ecoc)
# TODO prepare distribution
d = util.init_distribution(tr_n)
thresh_cs = None
if wl == ds.DecisionStump:
# TODO precompute thresholds cheat sheet
thresh_cs = util.pre_compute_threshes_8news(tr_data[0], bin_label, threshes)
boost = b.Boosting(d)
training_predict = np.zeros((1, tr_n)).tolist()[0]
round_tr_err = []
round = 0
while round < max_round:
st = time.time() # start ts
round += 1
boost.add_model(wl, tr_data[0], bin_label, threshes, thresh_cs, True)
boost.update_predict(tr_data[0], training_predict)
c_model_err = boost.model[-1].w_err
c_tr_err = util.get_err_from_predict(training_predict, bin_label)
round_tr_err.append(c_tr_err)
c_f_ind = boost.model[-1].f_ind
c_thresh = boost.model[-1].thresh
print('Time used: {}'.format(time.time() - st))
# serialize the best ecoc
with open(ecoc_path, 'wb+') as f:
pickle.dump(best_ecoc, f)
print('Init ecoc done!')
# train 20 boosts
boosts = []
function_tr_err = []
max_round = 10
cs_dict = {}
for ind, c_ecoc in enumerate(best_ecoc[1]):
print('Generating cheat sheet {}...'.format(ind))
# TODO preprocess the labels
# TODO preprocess labels, so that labels match ecoc, {0, 1} -> {-1, 1}
bin_label = copy.deepcopy(tr_data[1])
for i in range(len(c_ecoc)):
for j in range(len(bin_label)):
if bin_label[j] == i:
bin_label[j] = c_ecoc[i] if c_ecoc[i] == 1 else -1
# TODO precompute thresholds cheat sheet
thresh_cs = util.pre_compute_threshes_8news(tr_data[0], tr_data[1], threshes)
cs_dict[ind] = thresh_cs
# early terminating
if ind == 0:
break
with open(thresh_cs_path, 'wb+') as f:
pickle.dump(cs_dict, f)
