def adaboost_avg_run(max_classes, avg_num_of_run, training_set, testing_set):
testing_error_list = []
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)
for cl in range(1, max_classes + 1, 2):
train_error = []
testing_error = []
scikit_error = []
for i in range(avg_num_of_run):
ada_obj = AdaBoost(cl, train_subset_num, THRESHOLD, ETA,
UPPER_BOUND, ETA_WEIGHTS, False)
ada_obj.fit(train_x, train_y)
hypothesis_list = ada_obj.predict(train_x)
mistakes = ada_obj.xor_tuples(train_y, hypothesis_list)
error_rate_train = classifier_error_rate(mistakes)
hypothesis_list = ada_obj.predict(test_x)
mistakes = ada_obj.xor_tuples(test_y, hypothesis_list)
error_rate_test = classifier_error_rate(mistakes)
train_error.append(error_rate_train)
testing_error.append(error_rate_test)
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(train_error) / len(train_error),
sum(testing_error) / len(testing_error),
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))
testing_error_list.append(
(sum(testing_error) / len(testing_error)) * 100)
print("Scikit adaboost avg for %s %s" % (cl, errors.scikit_error))
#return testing_error_list
return all_error_list
