决策树实现的基本原理

import numpy as np
import pandas as pd

df = pd.read_csv(‘dtree.csv’)
#刮风的6,3个出去玩,不刮风8,6个出去玩
play_windy_y = 3/6
play_windy_n = 3/6
#a是熵刮风的熵
a = (play_windy_nnp.log2(play_windy_n) + play_windy_ynp.log2(play_windy_y))(6/14)
print(a)
play_windy_f_y = 6/8
play_windy_f_n = 2/8
#b是熵不刮风的熵
b = (play_windy_f_y
np.log2(play_windy_f_y) + play_windy_f_nnp.log2(play_windy_f_n))(8/14)
print(b)

#出去玩的有9,不出去玩的有5个

play = 9/14
n_play = 5/14
#c是熵Play的熵值
c = playnp.log2(play) + n_playnp.log2(n_play)
print©
total = c-(a+b)
print(total)
print(play_false)

相关文章: