def main():
train, test, L = get_args()
X_train, y_train = decisionStump.load_data(train)
X_train, y_train = np.array(X_train), np.array(y_train)
X_test, y_test = decisionStump.load_data(test)
X_test, y_test = np.array(X_test), np.array(y_test)
ensemble = ada_boosting(X_train, y_train, L)
acc_t,c,i = compute_accuracy(X_train, y_train, ensemble)
acc_te,c,i = compute_accuracy(X_test, y_test, ensemble)
print acc_t, acc_te
def main():
train_file, test_file, T = get_args()
x_train, y_train = decisionStump.load_data(train_file)
x_test, y_test = decisionStump.load_data(test_file)
for t in range(5, T, 5):
bags = [] # "(bestFeature, stump) ..."
for i in range(t):
bestFeature, stump = create_bag(x_train, y_train)
bags.append((bestFeature, stump))
test_acc = []
train_acc = []
for i in range(10000):
acc, c, i = compute_accuracy(x_train, y_train, bags)
train_acc.append(acc)
acc, c, i = compute_accuracy(x_test, y_test, bags)
test_acc.append(acc)
print str(t) + "," + str(scipy.mean(train_acc)) + "," + str(scipy.mean(test_acc))
"""
correct = 0
total = len(y)
for i, example in enumerate(x):
decision = classifier.predict(example)
if decision == y[i]:
correct += 1
accuracy = correct / float(total)
return accuracy, correct, float(total) - correct
data = [[1], [2]]
y = [1,0]
X_train, y_train = decisionStump.load_data(sys.argv[1])
X_test, y_test = decisionStump.load_data(sys.argv[2])
classifier = tree.DecisionTreeClassifier(max_depth=1)
stump = tree.DecisionTreeClassifier(max_depth=1)
trained = classifier.fit(X_train, y_train)
print "Decision stump"
print compute_accuracy(X_train, y_train, classifier)
print compute_accuracy(X_test, y_test, classifier)
print "Bagged results"
bags = ensemble.BaggingClassifier(base_estimator=stump, n_estimators=10, max_samples=40)
bag_trained = bags.fit(X_train, y_train)
print compute_accuracy(X_train, y_train, bag_trained)
print compute_accuracy(X_test, y_test, bag_trained)
