distances = []
for x_train in X_train:d=sqrt(np.sum((x_train-x)**2))distances.append(d)

寻找最好的k,调参
best_score = 0.0
besk_k = -1
for k in range(1,11):knn_clf = KNeighborsClassifier(n_neighbors=k)knn_clf.fit(X_train,y_train)score = knn_clf.score(X_test,y_test)if score>best_score:best_k=kbest_score=scoreprint('best_k=',best_k)
print('best_score=',best_score)考虑距离？
best_method = ''
best_score = 0.0
besk_k = -1
for method in ['uniform','distance']:for k in range(1,11):knn_clf = KNeighborsClassifier(n_neighbors=k,weights=method)knn_clf.fit(X_train,y_train)score = knn_clf.score(X_test,y_test)if score>best_score:best_k=kbest_score=scorebest_method = method
print('best_k=',best_k)
print('best_score=',best_score)
print('best_method',best_method)搜索明可夫斯基距离相应的p
%%time
best_p = -1
best_score = 0.0
besk_k = -1
for k in range(1,11):for p in range(1,6):knn_clf = KNeighborsClassifier(n_neighbors=k,weights='distance',p = p)knn_clf.fit(X_train,y_train)score = knn_clf.score(X_test,y_test)if score>best_score:best_k=kbest_score=scorebest_p=p
print('best_k=',best_k)
print('best_score=',best_score)
print('best_p=',best_p)

# coding=utf-8
import numpy as np
from sklearn import datasets
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.neighbors import KNeighborsClassifier
from sklearn.metrics import accuracy_score  # 分类的准确度
from sklearn.model_selection import GridSearchCViris = datasets.load_iris()
X = iris.data
y = iris.target
X_train, X_test, y_train, y_test = train_test_split(iris.data, iris.target, test_size=0.2, random_state=666)
standardScaler = StandardScaler()  # 创建实例
standardScaler.fit(X_train)
# standardScaler.mean_
# standardScaler.scale_
X_train = standardScaler.transform(X_train)  # 使用transform方法进行归一化
X_test_standard = standardScaler.transform(X_test)# 寻找最好的参数K
# param_grid = [
#     {#         'weights': ['uniform'],
#         'n_neighbors': [i for i in range(1, 11)]
#     },
#     {#         'weights': ['distance'],
#         'n_neighbors': [i for i in range(1, 11)],
#         'p': [i for i in range(1, 6)]
#     }
# ]
# knn_clf = KNeighborsClassifier()
# grid_search = GridSearchCV(knn_clf, param_grid)
# grid_search.fit(X_train, y_train)
# print(grid_search.best_estimator_, grid_search.best_params_, grid_search.best_score_)
# knn_clf.predict(X_test)
# knn_clf.score(X_test, y_test)knn_clf = KNeighborsClassifier(n_neighbors=3)
knn_clf.fit(X_train, y_train)  # X_train已经进行了归一化
print(knn_clf.score(X_test_standard, y_test))
# 或者
y_predict = knn_clf.predict(X_test_standard)
print(accuracy_score(y_test, y_predict))
knn_clf.score(X_test_standard, y_test)