import numpy as np
import pandas as pd 
from sklearn.neighbors import KNeighborsClassifier # 导入knn学习包
  • 1.
  • 2.
  • 3.
salary = pd.read\_csv("./adults.txt")
salary.head()  
![](https://img2020.cnblogs.com/blog/1781001/202008/1781001-20200806150826624-1480880366.png)
  • 1.
  • 2.
  • 3.
#样本数据的提取
y = salary\['salary'\]
X \= salary.iloc\[:,\[0,1,3,5,6,8,9,-2,-3\]\]
X.head()  
![](https://img2020.cnblogs.com/blog/1781001/202008/1781001-20200806150903415-786323650.png)
  • 1.
  • 2.
  • 3.
  • 4.
  • 5.
# 数据去重 用于下面函数的理解
u = X\['occupation'\].unique()
u  
![](https://img2020.cnblogs.com/blog/1781001/202008/1781001-20200806150926044-2070200122.png)
  • 1.
  • 2.
  • 3.
  • 4.
# np.argwhere此方法找到对应名称的索引
np.argwhere(u == "Exec-managerial")\[0,0\]  # np.argwhere  
  
X.columns\[2:-1\]  
![](https://img2020.cnblogs.com/blog/1781001/202008/1781001-20200806151003147-1450558348.png)
  • 1.
  • 2.
  • 3.
  • 4.
  • 5.
# 2:-1列的所有数据映射
for col in X.columns\[1:-1\]:  # 遍历所有类名
    
    u \= X\[col\].unique()  #  类似上面的u = X\['occupation'\].unique()  得出每个分类下面的种类名称
#     print(col)

    def convert(x):  # 将上面得出的u 进行索引映射
#         print(x)
        return np.argwhere(u == x)\[0,0\]  #  将上面得出的u 进行索引映射
    
    X\[col\] \= X\[col\].map(convert)  # 将上面得出的u 进行索引映射
    
X.head()  
  
![](https://img2020.cnblogs.com/blog/1781001/202008/1781001-20200806151032358-1833361325.png)
  • 1.
  • 2.
  • 3.
  • 4.
  • 5.
  • 6.
  • 7.
  • 8.
  • 9.
  • 10.
  • 11.
  • 12.
  • 13.
  • 14.
  • 15.
# 切分训练集跟测试集
from sklearn.model\_selection import train\_test\_split

X\_train,X\_test,y\_train,y\_test \= train\_test\_split(X,y,test\_size = 0.2)  # 切分
print(X\_train.shape,X\_test.shape,y\_train.shape,y\_test.shape)

![](https://img2020.cnblogs.com/blog/1781001/202008/1781001-20200806151157621-1006853718.png)
  • 1.
  • 2.
  • 3.
  • 4.
  • 5.
  • 6.
  • 7.
# 预测测试
knn = KNeighborsClassifier(n\_neighbors=8)

knn.fit(X\_train,y\_train)  # 计算公式
y\_ \= knn.predict(X\_test) # 预测值

from sklearn.metrics import accuracy\_score # 计算分类预测的准确率

# 求出预测准确率
accuracy = accuracy\_score(y\_test, y\_)

print("预测准确率: ", accuracy)  
![](https://img2020.cnblogs.com/blog/1781001/202008/1781001-20200806151210088-802068279.png)
  • 1.
  • 2.
  • 3.
  • 4.
  • 5.
  • 6.
  • 7.
  • 8.
  • 9.
  • 10.
  • 11.
  • 12.
  • 13.

总结：难度在于数据的预处理