def main():
for file in [
'data/breast-cancer-assignment5.txt', 'data/german-assignment5.txt'
]:
data, labels, types = load_matrix_from_txt(file)
splices = k_fold_split(10, data, labels)
accuracies = []
for i in range(10):
train_indexes = splices[i][0]
test_indexes = splices[i][1]
train_data = np.copy(data[train_indexes])
train_label = np.copy(labels[train_indexes])
test_data = np.copy(data[test_indexes])
test_label = np.copy(labels[test_indexes])
boost = AdaBoost()
boost.train(train_data, train_label, types)
class_result = boost.test(test_data)
accuracy = compute_accuracy(class_result, test_label)
accuracies.append(accuracy)
print 'accuracy: %f' % accuracy
print('file: {}, mean: {}, std: {}'.format(file, np.mean(accuracies),
np.std(accuracies)))
def do_adaboost(self):
if self.flag == 0:
start = time.time()
adaboost_instance = AdaBoost(self.train)
adaboost_instance.create_and_train_classifiers()
adaboost_instance.write_model(self.model_file)
end = time.time()
print 'Training Time :', (end - start) / 60, 'mins'
else:
start = time.time()
adaboost_instance = AdaBoost(None)
adaboost_instance.load_model(self.model_file)
test_output = adaboost_instance.test(self.test, self.output_file)
print test_output['accuracy'], '%'
end = time.time()
print 'Testing Time :', (end - start) / 60, 'mins'
images_data_vector=data_vector,
all_images_ids=all_image_ids,
images_counter=images_counter,
decision_stumps=30,
)
trained_decision_tree.train()
save_model_to_pickle(obj=trained_decision_tree,
file_name="tree.pkl")
save_model_to_txt(
obj=trained_decision_tree,
file_name="tree_model.txt",
model="adaboost_decision_tree",
)
# Test after train
trained_decision_tree.test(test_file_path="test_file.txt")
else:
# Test
trained_decision_tree = load_model_from_pickle(
file_name="tree.pkl")
trained_decision_tree.test(test_file_path="test_file.txt")
elif model == "nnet":
if train_or_test == "train":
trained_neural_network = start(
layers=[
Dense(300),
Activation("relu"),
Dropout(0.2),
Dense(300),
Activation("relu"),
