def q14():
T = 1
clf = AdaBoost(T, lambda u: DecisionStump(u), lambda dd: dd.err_)
X, y = load_ada_boost_train()
clf.fit(X, y)
print clf.u
print np.sum(clf.u)
print 'AND SEE q13'
def do_boost(x, y, m):
ada_boost = AdaBoost(x, y, m)
accuracy = accuracy_score(ada_boost.predict(x), y)
print("Шаг бустинга:", m)
print("Точность:", accuracy)
print()
draw_boost(x, y, ada_boost)
def draw_dependency(X, Y):
x = []
y = []
for i in range(1, 100):
x.append(i)
ada_boost = AdaBoost(X, Y, i)
y.append(accuracy_score(ada_boost.predict(X), Y))
plt.plot(x, y)
plt.show()
def test(file):
dataset = utils.dataset_reader(file)
X_train, y_train, X_test, y_test = utils.data_process(dataset)
n_estimators = 30
print('AdaBoost Optimal for:', file)
ada_boost = AdaBoost(n_estimators=n_estimators)
ada_boost.fit(X_train, y_train, X_test, y_test)
utils.plot_error_vs_t('local error', ada_boost.local_errs,
ada_boost.n_estimators)
utils.plot_error_vs_t('train error', ada_boost.train_errs,
ada_boost.n_estimators)
utils.plot_error_vs_t('test error', ada_boost.test_errs,
ada_boost.n_estimators)
print('AdaBoost Random for:', file)
ada_boost_random = AdaBoost(n_estimators=n_estimators,
decision_stumps='random')
ada_boost_random.fit(X_train, y_train, X_test, y_test)
utils.plot_error_vs_t('local error', ada_boost_random.local_errs,
ada_boost_random.n_estimators)
utils.plot_error_vs_t('train error', ada_boost_random.train_errs,
ada_boost_random.n_estimators)
utils.plot_error_vs_t('test error', ada_boost_random.test_errs,
ada_boost_random.n_estimators)
def adaBoost():
X, y = make_classification(n_samples=350, n_features=15, n_informative=10,
random_state=1111, n_classes=2,
class_sep=1., n_redundant=0)
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.15,
random_state=1111)
model = AdaBoost(n_estimators=10, max_tree_depth=5,
max_features=8)
model.fit(X_train, y_train)
predictions = model.predict(X_test)
print(predictions)
print(predictions.min())
print(predictions.max())
print('classification, roc auc score: %s'
% roc_auc_score(y_test, predictions))
def train(example_file, out_file, learning_type):
"""
Trains a model basesd on example_data and learning
approach and writes model to serialized object.
:param example_file: training file
:param out_file: hypothesis file
:param learning_type: learning approach
:return:
"""
if learning_type == 'dt':
# print('Trainning Model with decision trees')
decisionModel = DecisionTree(example_file, out_file)
decisionModel.train()
if learning_type == 'ada':
# print('Trainning model with adaboost')
adaModel = AdaBoost(example_file, out_file)
adaModel.train()
def q13():
T = 300
clf = AdaBoost(T, lambda u: DecisionStump(u), lambda dd: dd.err_)
X, y = load_ada_boost_train()
clf.fit(X, y)
print clf.e
print 'Ein:', clf.score(X, y)
print '%f <= U_T <= %f' % (np.min(clf.U), np.max(clf.U))
print 'e_t >= %f' % np.min(clf.e)
X, y = load_ada_boost_test()
print 'Eout:', clf.score(X, y)
print 'U(2):', clf.U[1]
def apply_ada_boost(filename, estimators):
ab = AdaBoost(filename, estimators=estimators, learning_rate=0.1)
#ab.split_data()
ab.start_data()
ab.train_ada_boost()
ab.test_ada_boost()
ab.switch_folds()
ab.train_ada_boost()
ab.test_ada_boost()
