def fit(self, X, y):
X = np.asarray(X)
y = np.asarray(y)
self.mean = np.mean(y)
#y = np.asarray([self.mean]*len(y))
#hypothesis = self.learner().fit(X, y)
#self.hypotheses.append(hypothesis)
for round in xrange(self.max_rounds):
residual = [(yn - yl) for yn, yl in zip(y, self.predict(X))]
hypothesis = self.learner().fit(X, residual)
self.hypotheses.append(hypothesis)
self.local_error.append(hw4.compute_mse(residual, hypothesis.predict(X)))
pred_round = self.predict(X)
self.train_score = hw4.compute_mse(pred_round, y)
self.training_error.append(self.train_score)
def q7():
h_test, h_train = utils.load_and_normalize_housing_set()
housingData_test = hw3.pandas_to_data(h_test)
housingData_train = hw3.pandas_to_data(h_train)
y, X = hw4.split_truth_from_data(housingData_train)
y_test, X_test = hw4.split_truth_from_data(housingData_test)
#gb = GradientBoostingRegressor(learning_rate=.1, n_estimators=1, max_depth=1)
gb = gradb.GradientBoostRegressor(learning_rate=.1, n_estimators=100, max_depth=1, learner=lambda: DecisionTreeRegressor(max_depth=1))
gb.fit(X, y)
gb.print_stats()
yhat = gb.predict(X_test)
print y_test[:10]
print yhat[:10]
print 'MSE: {}'.format(hw4.compute_mse(y_test, yhat))