KNN参数cross_val_score调参

什么是交叉式验证？

这样所有的数据都进行了验证，所有的数据也都进行了训练，训练了五次也测试了五次，将这五次得到的数据求一个平均值，这样的数据更有说服力







全部代码

#导包，加载数据

import numpy as np

from sklearn.neighbors import KNeighborsClassifier

from sklearn import datasets

#model_selection:模型选择

#cross_val_score  cross：交叉，validation:验证（测试）
#交叉验证

from sklearn.model_selection import cross_val_score

X,y = datasets.load_iris(True)

X.shape

# 参考
150**0.5
# K 选择 1----13

#cross_val_score交叉验证筛选最合适的参数

#演示了交叉验证，如何使用
knn = KNeighborsClassifier()
score = cross_val_score(knn,X,y,scoring='accuracy',cv = 6)
score.mean()

#应用cross_val_score去筛选最合适的邻居数量
erros = []
for k in range(1,14):
    knn = KNeighborsClassifier(n_neighbors=k)
    
    score = cross_val_score(knn,X,y,scoring='accuracy',cv = 6).mean()
    
    #误差越小，说明k选择越合适，越好
    erros.append(1 - score)

import matplotlib.pyplot as plt
%matplotlib inline

#k = 11时，误差最小，说明k = 11对鸢尾花来说，最合适的k值
plt.plot(np.arange(1,14),erros)

weights = ['uniform','distance']

for w in weights:
    knn = KNeighborsClassifier(n_neighbors= 11,weights = w)
    
    print(w,cross_val_score(knn,X,y,scoring='accuracy',cv = 6).mean())
    
#多参数组合使用cross_val_score筛选最合适的参数组合
#模型是如何调参的，参数调节

result = {}
for k in range(1,14):
    for w in weights:
        knn  = KNeighborsClassifier(n_neighbors=k,weights=w)
        sm = cross_val_score(knn,X,y,scoring='accuracy',cv = 6).mean()
        
        result[w + str(k)] = sm
        
result

max(result.values())

np.array(list(result.values())).argmax()

list(result)[20]