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 decision_tree_test():
features, labels = data.sample_decision_tree_data()
# build the tree
dTree = decision_tree.ID3()
dTree.train(features, labels)
# print
print('Your decision tree: ')
Utils.printTree(dTree)
# 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)
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)
from utils import NormalizationScaler, MinMaxScaler
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)