import matplotlib.pyplot as plt
import numpy as np
from loadData import LoadData
from decisionTree import Node, DecisionTree, Evaluate
from inspection import Inspection
if __name__ == '__main__':
train_input = '../handout/education_train.tsv'
test_input = '../handout/education_test.tsv'
train_output = '../result/education_train.labels'
test_output = '../result/education_test.labels'
ld = LoadData()
dataset = ld.load_data(train_input)
dt = DecisionTree(ld)
tr_err = []
te_err = []
x_arr = []
print(ld.head)
for i in range(len(ld.head)):
root = dt.construct(dataset, i)
# dt.traverse(root)
dt.classify(ld.load_data(train_input), root, train_output)
dt.classify(ld.load_data(test_input), root, test_output)
with open(train_output, 'r') as f:
predcol = f.read().splitlines()
realcol = np.loadtxt(train_input,
dtype=str,
delimiter='\t',
skiprows=1)[:, -1]
self.gi=0
else:
count1 = 0
for item in dataset:
if item[-1]==dataset[0][-1]:
count1+=1
count2 = len(dataset)-count1
self.gi = (count1/len(dataset))*(count2/len(dataset))+(count2/len(dataset))*(count1/len(dataset))
return self.gi
# evaluate with error_rate and gini_impurity
def evaluate(self):
err_rate = self.error_rate(self.ori_dataset)
gini_impurity = self.gini_impurity(self.ori_dataset)
return err_rate,gini_impurity
if __name__ == '__main__':
infile = sys.argv[1]
outfile = sys.argv[2]
ld = LoadData()
ori_dataset = ld.load_data(infile)
ins = Inspection(ori_dataset)
eva = ins.evaluate()
err_rate = eva[0]
gini_impurity = eva[1]
with open(outfile, 'w') as f:
f.writelines("gini_impurity: {}\n".format(gini_impurity))
f.writelines("error: {}\n".format(err_rate))
# print(err_rate)
# print(gini_impurity)
right_branch = self.construct(new_dataset[1], col_index, depth)
node.right = right_branch
# print('col_index:',col_index)
self.col.remove(col_index)
return node
def traverse(self, node):
if node:
# print(node.dataset,'\n')
print(node.depth, '\t', node.attribute)
self.traverse(node.left)
self.traverse(node.right)
if __name__ == '__main__':
ld = LoadData()
dataset = ld.load_data('../handout/small_train.tsv')
dt = DecisionTree(dataset, 0)
ds = dt.divide_dataset(dataset, 1)
# gini = dt.gini_impurity(dataset,1)
giga = dt.gini_gain(dataset, 1)
# col = dt.get_attribute(dataset)
root = dt.construct(dataset)
# print(root.left.left.left.right.depth)
dt.traverse(root)
# print(root.dataset)
# print(dataset)
# print(ds[0])
# print(ds[1])