机器学习实战之knn算法pandas，供大家参考，具体内容如下
开始学习机器学习实战这本书，打算看完了再回头看 周志华的 机器学习。机器学习实战的代码都是用numpy写的，有些麻烦，所以考虑用pandas来实现代码，也能回顾之前学的 用python进行数据分析。感觉目前章节的测试方法太渣，留着以后学了更多再回头写。
|
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
|
# coding: gbk
import pandas as pd
import numpy as np
def getdata(path):
data = pd.read_csv(path, header=none, sep='\t')
character = data.iloc[:, :-1]
label = data.iloc[:, -1]
chara_max = character.max()
chara_min = character.min()
chara_range = chara_max - chara_min
normal_chara = (character - chara_min) / chara_range
return normal_chara, label # 获得归一化特征值和标记
def knn(inx, normal_chara, label, k):
data_sub = normal_chara - inx
data_square = data_sub.applymap(np.square)
data_sum = data_square.sum(axis=1)
data_sqrt = data_sum.map(np.sqrt)
dis_sort = data_sqrt.argsort()
k_label = label[dis_sort[:k]]
label_sort = k_label.value_counts()
res_label = label_sort.index[0]
return res_label # knn算法分类
|
小编为大家分享一段代码：机器学习--knn基本实现
|
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
|
# _*_ coding _*_
import numpy as np
import math
import operator
def get_data(dataset):
x = dataset[:,:-1].astype(np.float)
y = dataset[:,-1]
return x,y
# def cal_dis(a,b):
# x1,y1 = a[:]
# x2,y2 = b[:]
# dist = math.sqrt(math.pow(2,x2)-math.pow(2,x1))
def knnclassifer(dataset,predict,k=3):
x,y = get_data(dataset)
dic = {}
distince = np.sum((predict-x)**2,axis=1)**0.5
sorted_dict = np.argsort(distince)#[2 1 0 3 4]
countlabel = {}
for i in range(k):
label = y[sorted_dict[i]]
# print(i,sorted_dict[i],label)
countlabel[label] = countlabel.get(label,0)+1
new_dic = sorted(countlabel,key=operator.itemgetter(0),reverse=true)
return new_dic[0][0]
if __name__ == '__main__':
dataset = np.loadtxt("dataset.txt",dtype=np.str,delimiter=",")
predict = [2,2]
label = knnclassifer(dataset,predict,3)
print(label)
|
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/weixin_38204423/article/details/74640625