def adaboost_avg_run_new(max_classes, avg_num_of_run, training_set,
testing_set):
all_error_list = []
# because datasets sometimes place the class attribute at the end or even
# at the beginning or the middle, we'll separate the attribute vector from
# the class-label. also note that this is the way scikit-learn does it.
# train_x: the attribute vector; train_y: the class_label
(train_x, train_y) = split_attribute_and_label(training_set)
(test_x, test_y) = split_attribute_and_label(testing_set)
# print(len(train_x))
train_subset_num = int(len(train_y) * 0.2)
our_ada_training_errors = {}
our_ada_testing_errors = {}
# init dict of num classifier to error list
for i in range(1, max_classes + 1):
our_ada_training_errors[i] = []
our_ada_testing_errors[i] = []
# run ada num_runs times
for i in range(avg_num_of_run):
ada_obj = AdaBoost(max_classes, train_subset_num, THRESHOLD, ETA,
UPPER_BOUND, ETA_WEIGHTS, False)
ada_obj.fit_with_errors(train_x, train_y, test_x, test_y)
for j in range(max_classes):
our_ada_training_errors[j + 1].append(ada_obj.training_error[j])
our_ada_testing_errors[j + 1].append(ada_obj.testing_error[j])
for cl in range(1, max_classes + 1):
scikit_error = []
for i in range(avg_num_of_run):
pada = perceptron.Perceptron(max_iter=UPPER_BOUND,
verbose=0,
random_state=None,
fit_intercept=True,
eta0=ETA)
bdt = AdaBoostClassifier(pada, algorithm="SAMME", n_estimators=cl)
bdt.fit(train_x, train_y)
result_list = bdt.predict(test_x)
scikit_error.append(calculate_error(test_y, result_list))
errors = ErrorWrapper(
cl,
sum(our_ada_training_errors[cl]) /
len(our_ada_training_errors[cl]),
sum(our_ada_testing_errors[cl]) / len(our_ada_testing_errors[cl]),
sum(scikit_error) / len(scikit_error))
all_error_list.append(errors)
print("Train avg for %s %s" % (cl, errors.train_error))
print("Testing avg for %s %s" % (cl, errors.test_error))
print("Scikit adaboost avg for %s %s" % (cl, errors.scikit_error))
return all_error_list
