使用python语言，实现求特征选择的信息增益，可以同时满足特征中有连续型和二值离散型属性的情况。
师兄让我做一个特征选择的代码，我在网上找了一下，大部分都是用来求离散型属性的信息益益，但是我的数据是同时包含二值离散型和连续型属性的，所以这里实现了一下。
代码块
|
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
|
import numpy as np
import math
class IG():
def __init__(self,X,y):
X = np.array(X)
n_feature = np.shape(X)[1]
n_y = len(y)
orig_H = 0
for i in set(y):
orig_H += -(y.count(i)/n_y)*math.log(y.count(i)/n_y)
condi_H_list = []
for i in range(n_feature):
feature = X[:,i]
sourted_feature = sorted(feature)
threshold = [(sourted_feature[inde-1]+sourted_feature[inde])/2 for inde in range(len(feature)) if inde != 0 ]
thre_set = set(threshold)
if float(max(feature)) in thre_set:
thre_set.remove(float(max(feature)))
if min(feature) in thre_set:
thre_set.remove(min(feature))
pre_H = 0
for thre in thre_set:
lower = [y[s] for s in range(len(feature)) if feature[s] < thre]
highter = [y[s] for s in range(len(feature)) if feature[s] > thre]
H_l = 0
for l in set(lower):
H_l += -(lower.count(l) / len(lower))*math.log(lower.count(l) / len(lower))
H_h = 0
for h in set(highter):
H_h += -(highter.count(h) / len(highter))*math.log(highter.count(h) / len(highter))
temp_condi_H = len(lower)/n_y *H_l+ len(highter)/n_y * H_h
condi_H = orig_H - temp_condi_H
pre_H = max(pre_H,condi_H)
condi_H_list.append(pre_H)
self.IG = condi_H_list
def getIG(self):
return self.IG
if __name__ == "__main__":
X = [[1, 0, 0, 1],
[0, 1, 1, 1],
[0, 0, 1, 0]]
y = [0, 0, 1]
print(IG(X,y).getIG())
|
输出结果为：
[0.17441604792151594, 0.17441604792151594, 0.17441604792151594, 0.6365141682948128]
以上就是本文的全部内容，希望对大家的学习有所帮助，也希望大家多多支持服务器之家。
原文链接：https://blog.csdn.net/fei13971414170/article/details/80010007