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 decision_tree_test():
features, labels = data.sample_decision_tree_data()
# build the tree
dTree = decision_tree.DecisionTree()
dTree.train(features, labels)
# 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: 2 : 2 \n\tsplit by dim 0\n\tbranch 0->0{\n\t\tdeep: '
'1\n\t\tnum of samples for each class: 1 \n\t\tclass:0\n\t}\n\tbranch 0->1{\n\t\tdeep: 1\n\t\tnum of '
'samples for each class: 1 : 1 \n\t\tsplit by dim 0\n\t\tbranch 0->1->0{\n\t\t\tdeep: 2\n\t\t\tnum of '
'samples for each class: 1 \n\t\t\tclass:0\n\t\t}\n\t\tbranch 0->1->1{\n\t\t\tdeep: 2\n\t\t\tnum of '
'samples for each class: 1 \n\t\t\tclass:1\n\t\t}\n\t}\n\tbranch 0->2{\n\t\tdeep: 1\n\t\tnum of '
'samples for each class: 1 \n\t\tclass:1\n\t}\n}')
# data
X_test, y_test = data.sample_decision_tree_test()
# testing
y_est_test = dTree.predict(X_test)
print('Your estimate test: ', y_est_test)
print('My estimate test: ', [0, 0, 1])
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 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)
scaling_classes = {
'min_max_scale': MinMaxScaler,
'normalize': NormalizationScaler,
}
#best_model, best_k, best_function, best_scaler = model_selection_with_transformation(distance_funcs, scaling_classes, Xtrain, ytrain, Xval, yval)
import data
import hw1_dt as decision_tree
import utils as Utils
from sklearn.metrics import accuracy_score
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)
"""
def reduced_error_prunning(decisionTree, X_test, y_test):
if not decisionTree.root_node.splittable:
return
"""
predict = node.predict()
"""
if decisionTree.root_node.splittable:
labels =y_test
to_split = decisionTree.root_node.feature_uniq_split
cut = decisionTree.root_node.dim_split
dr=[]
dl=[]
for m in to_split:
res = []
l = []
for i in range(len(X_test)):
if m == X_test[i][cut]:
l.append(labels[i])
a = list(X_test[i])
a.remove(m)
res.append(a)
dl.append(l)
dr.append(res)
for i in range(len(decisionTree.root_node.children)):
a=hw.DecisionTree()
a.root_node = decisionTree.root_node.children[i]
if i<=(len(dr)-1) and i<=(len(dl)-1):
reduced_error_prunning(a,dr[i],dl[i])
error1=0
error2=0
if a.predict(dr[i])and dl[i]:
for x in range(len(a.predict(dr[i]))):
if a.predict(dr[i])[x]==dl[i][x]:
error1+=1
for y in dl[i]:
if y==a.root_node.cls_max:
error2+=1
if error1<=error2:
a.root_node.splittable=False
a.root_node.children=[]
a.root_node.feature_uniq_split=None
a.root_node.dim_split=None
else:
a.root_node.splittable=False
a.root_node.children=[]
a.root_node.feature_uniq_split=None
a.root_node.dim_split=None
else:
a.root_node.splittable=False
a.root_node.children=[]
a.root_node.feature_uniq_split=None
a.root_node.dim_split=None
else:
decisionTree.splittable=False
decisionTree.children=[]
decisionTree.feature_uniq_split=None
decisionTree.dim_split=None
return