def test_dataset4():
''' (2 points) test dataset4'''
n= 400
X, Y = RF.load_dataset()
assert X.shape == (16,400)
assert Y.shape == (400,)
d = DT()
# train over half of the dataset
t = d.train(X[:,::2],Y[::2])
# test on the other half
Y_predict = DT.predict(t,X[:,1::2])
accuracy0 = sum(Y[1::2]==Y_predict)/float(n)*2.
print('test accuracy of a decision tree:', accuracy0)
b = Bag()
# train over half of the dataset
T = b.train(X[:,::2],Y[::2],21)
# test on the other half
Y_predict = Bag.predict(T,X[:,1::2])
accuracy1 = sum(Y[1::2]==Y_predict)/float(n)*2.
print('test accuracy of a bagging of 21 trees:', accuracy1)
r = RF()
# train over half of the dataset
T = r.train(X[:,::2],Y[::2],21)
# test on the other half
Y_predict = RF.predict(T,X[:,1::2])
accuracy2 = sum(Y[1::2]==Y_predict)/float(n)*2.
print('test accuracy of a random forest of 21 trees:', accuracy2)
assert accuracy1 >= accuracy0
assert accuracy2 >= accuracy0
assert accuracy2 >= accuracy1-.05
def train(self, X, Y, n_tree=11):
'''
Given a training set, train a bagging ensemble of decision trees.
Input:
X: the feature matrix, a numpy matrix of shape p by n.
Each element can be int/float/string.
Here n is the number data instances in the training set, p is the number of attributes.
Y: the class labels, a numpy array of length n.
Each element can be int/float/string.
n_tree: the number of trees in the ensemble
Output:
T: a list of the root of each tree, a list of length n_tree.
'''
#########################################
# INSERT YOUR CODE HERE
T = []
for i in range(n_tree):
X_new, Y_new = Bag.bootstrap(X, Y)
T.append(DT.train(self, X_new, Y_new))
#########################################
return T