def sim3():
filename = '../dataset/dataset3.csv'
dataset = load_csv(filename)
dataset = dataset_to_float(dataset)
plot_2D_dataset(dataset, "Simulation n.3")
tree = build_tree(dataset, 5, 1)
print("-" * 10 + " Sim.3 TREE " + "-" * 10)
print_tree(tree.root, ['x', 'y'])
print_tree_separating_2D(tree.root)
show_plot()
def sim4():
filename = '../dataset/dataset3.csv'
dataset = load_csv(filename)
dataset = dataset_to_float(dataset)
train_accuracy = list()
nodes_numbers = list()
for i in range(1, 21):
tree_size, predicted, expected = decision_tree_prediction_and_size(
dataset, dataset, i, 1)
acc = accuracy_metric(expected, predicted)
train_accuracy.append(acc)
nodes_numbers.append(tree_size)
x = range(1, 21)
plt.figure("Simulation n.4")
line1, = plt.plot(x, train_accuracy, 'r', label='Train accuracy')
line2, = plt.plot(x, nodes_numbers, 'g', label='Tree complexity(# nodes)')
plt.legend(handles=[line1, line2], loc=4)
plt.xticks(x)
plt.xlabel('Maximum Tree Depth')
plt.draw()
def parkinson_main(n_folds_outer_cross_val, n_folds_inner_cross_val, max_depth, min_size):
if n_folds_outer_cross_val < 2 or n_folds_inner_cross_val < 2:
raise ValueError("Illegal value parameter")
filename = '../dataset/parkinson_recording_data.csv'
dataset = load_csv(filename)
dataset = dataset_to_float(dataset)
folds = cross_validation_split(dataset,n_folds_outer_cross_val)
scores = list()
outer_fold_number = 0
# Outer k-fold cross validation
for fold in folds:
outer_fold_number += 1
# Prepare train and test set
train_set = list(folds)
train_set.remove(fold)
train_set = sum(train_set, [])
test_set = list()
for row in fold:
row_copy = list(row)
test_set.append(row_copy)
row_copy[-1] = None
# Inner k-fold cross validation ( grid search )
best_couple, inner_accuracy = two_grid_search_with_accuracy_return(decision_tree, n_folds_inner_cross_val, train_set, max_depth, min_size)
# Evaluate results on outer cross validation test set
predictions = decision_tree(train_set, test_set, best_couple[0], best_couple[1])
actual = [row[-1] for row in fold]
outer_accuracy = accuracy_metric(actual, predictions)
print("-" * 10 + " Outer Fold n. " + str(outer_fold_number) + " " + "-" * 10)
print("Best params selected by inner cross validation (max_depth,min_size): "+str(best_couple[0])+" "+str(best_couple[1]))
print("Best params mean accuracy in the inner cross validation: " + str(inner_accuracy))
print("Best params accuracy in the outer cross validation: " + str(outer_accuracy))
scores.append(outer_accuracy)
print("-" * 10 + " Final Results " + " " + "-" * 10)
print("Total Accuracy mean: " + str(mean(scores)))
print("Total Accuracy std dev: " + str(stdev(scores)))
return scores
def banknote_main(tr_percentages, number_repetitions, n_folds_2grid_search,
max_depth, min_size):
if number_repetitions < 2 or n_folds_2grid_search < 2:
raise ValueError("Illegal value parameter")
filename = '../dataset/data_banknote_authentication.csv'
dataset = load_csv(filename)
dataset = dataset_to_float(dataset)
mean_accuracies = list()
std_devs = list()
# For each percentage of training split
for percentage in tr_percentages:
accuracies = list()
# Repeat number_repetions times the random split and test validation for each split
for run in range(1, number_repetitions + 1):
train, test = random_training_test_split(dataset, percentage)
result = two_grid_search(decision_tree, n_folds_2grid_search,
train, max_depth, min_size)
predictions = decision_tree(train, test, result[0], result[1])
actual = [row[-1] for row in test]
accuracy = accuracy_metric(actual, predictions)
accuracies.append(accuracy)
print("-" * 10 + " training split %" + str(percentage) + " " +
"-" * 10)
print("Accuracies of training split %" + str(percentage) + " : " +
str(accuracies))
mean_acc = mean(accuracies)
std_dev = stdev(accuracies)
print("Accuracy mean: " + str(mean_acc))
print("Accuracy std dev: " + str(std_dev))
mean_accuracies.append(mean_acc)
std_devs.append(std_dev)
plt.figure("BankNote dataset")
plot_results(tr_percentages, mean_accuracies, std_devs)
plt.show()