def pruning_decision_tree_test():
# load data
X_train, y_train, X_test, y_test = data.sample_decision_tree_pruning()
# build the tree
dTree = decision_tree.DecisionTree()
dTree.train(X_train, y_train)
# print
print('Your decision tree:')
Utils.print_tree(dTree)
print('My decision tree:')
print(
'branch 0{\n\tdeep: 0\n\tnum of samples for each class: 5 : 9 \n\tsplit by dim 0\n\tbranch 0->0{\n\t\tdeep: 1'
'\n\t\tnum of samples for each class: 3 : 2 \n\t\tsplit by dim 1\n\t\tbranch 0->0->0{\n\t\t\tdeep: 2\n\t\t\t'
'num of samples for each class: 3 \n\t\t\tclass:0\n\t\t}\n\t\tbranch 0->0->1{\n\t\t\tdeep: 2\n\t\t\tnum of '
'samples for each class: 2 \n\t\t\tclass:1\n\t\t}\n\t}\n\tbranch 0->1{\n\t\tdeep: 1\n\t\tnum of samples for '
'each class: 4 \n\t\tclass:1\n\t}\n\tbranch 0->2{\n\t\tdeep: 1\n\t\tnum of samples for each class: 2 : 3 '
'\n\t\tsplit by dim 2\n\t\tbranch 0->2->0{\n\t\t\tdeep: 2\n\t\t\tnum of samples for each class: 3 \n\t\t\t'
'class:1\n\t\t}\n\t\tbranch 0->2->1{\n\t\t\tdeep: 2\n\t\t\tnum of samples for each class: 2 \n\t\t\tclass:0'
'\n\t\t}\n\t}\n}')
Utils.reduced_error_prunning(dTree, X_test, y_test)
print('Your decision tree after pruning:')
Utils.print_tree(dTree)
print('My decision tree after pruning:')
print(
'branch 0{\n\tdeep: 0\n\tnum of samples for each class: 5 : 9 \n\tsplit by dim 0\n\tbranch 0->0{\n\t\tdeep: '
'1\n\t\tnum of samples for each class: 3 : 2 \n\t\tsplit by dim 1\n\t\tbranch 0->0->0{\n\t\t\tdeep: 2\n\t\t\t'
'num of samples for each class: 3 \n\t\t\tclass:0\n\t\t}\n\t\tbranch 0->0->1{\n\t\t\tdeep: 2\n\t\t\tnum of '
'samples for each class: 2 \n\t\t\tclass:1\n\t\t}\n\t}\n\tbranch 0->1{\n\t\tdeep: 1\n\t\tnum of samples for '
'each class: 4 \n\t\tclass:1\n\t}\n\tbranch 0->2{\n\t\tdeep: 1\n\t\tnum of samples for each class: 2 : 3 '
'\n\t\tclass:1\n\t}\n}')
def test_big_tree():
# load data
X_train, y_train, X_test, y_test = data.load_decision_tree_data()
# set classifier
dTree = decision_tree.DecisionTree()
# training
dTree.train(X_train.tolist(), y_train.tolist())
# print
# Utils.print_tree(dTree)
# testing
y_est_test = dTree.predict(X_test)
test_accu = accuracy_score(y_est_test, y_test)
print('test_accu', test_accu)
Utils.reduced_error_prunning(dTree, X_test, y_test)
y_est_test = dTree.predict(X_test)
test_accu = accuracy_score(y_est_test, y_test)
print('test_accu', test_accu)
# print
Utils.print_tree(dTree)
def t2():
data = np.loadtxt('car.data',delimiter=',')
x_train = pd.DataFrame(data)
y_train = x_train[0].tolist()
x_train = x_train.drop([0],axis=1)
x_train = np.array(x_train).tolist()
x_test = x_train[1500:]
y_test = y_train[1500:]
x_train = x_train[:1500]
y_train = y_train[:1500]
tree = DecisionTree()
tree.train(x_train,y_train)
p = tree.predict(x_train)
U.print_tree(decisionTree=tree)
U.reduced_error_prunning(decisionTree=tree,X_test=x_test,y_test=y_test)
print('---------------------------')
U.print_tree(decisionTree=tree)
def test_tree():
features, labels = data.sample_decision_tree_data()
# build the tree
dTree = decision_tree.DecisionTree()
dTree.train(features, labels)
# print
Utils.print_tree(dTree)
# data
X_test, y_test = data.sample_decision_tree_test()
# testing
y_est_test = dTree.predict(X_test)
test_accu = accuracy_score(y_est_test, y_test)
print('test_accu', test_accu)
Utils.reduced_error_prunning(dTree, X_test, y_test)
y_est_test = dTree.predict(X_test)
test_accu = accuracy_score(y_est_test, y_test)
print('test_accu', test_accu)
"""
#load data
X_train, y_train, X_test, y_test = data.load_decision_tree_data()
# set classifier
dTree = decision_tree.DecisionTree()
# training
dTree.train(X_train.tolist(), y_train.tolist())
# print
Utils.print_tree(dTree)
import json
# testing
y_est_test = dTree.predict(X_test)
test_accu = accuracy_score(y_est_test, y_test)
print("Before Pruning:")
print('test_accu', test_accu)
print('self-calc-acc', Utils.get_accuracy(y_est_test, y_test))
print()
Utils.reduced_error_prunning(dTree, X_test, y_test)
y_est_test = dTree.predict(X_test)
print()
print("After Pruning:")
test_accu = accuracy_score(y_est_test, y_test)
print('test_accu', test_accu)
print('self-calc-acc', Utils.get_accuracy(y_est_test, y_test))
