KNN调包实现

xzwyb---

于 2022-08-01 23:10:36 发布

阅读量259

点赞数

分类专栏：机器学习文章标签： python 机器学习算法

本文链接：https://blog.csdn.net/weixin_51347879/article/details/126111946

版权

机器学习专栏收录该内容

21 篇文章 2 订阅

订阅专栏

import numpy as np
import pandas as pd
from sklearn import neighbors

T = [
    [3, 104, -1],
    [2, 100, -1],
    [1, 81, -1],
    [101, 10, 1],
    [99, 5, 1],
    [98, 2, 1]]

# 初始化待测样本
x = [[18, 90]]

# 初始化K值
K = 3

data = pd.DataFrame(T, columns=['A', 'B', 'label'])

# print(data)

# 训练数据提取
X_train = data.iloc[:, :-1] 
# print(X_train)
Y_train = data.iloc[:, -1]
# print(Y_train)

# 激活KNN分类，不加权
KNN1 = neighbors.KNeighborsClassifier(n_neighbors=3)

KNN1.fit(X_train, Y_train)
y_predict = KNN1.predict(x)
print(y_predict)

score = KNN01.score(X=X_train, y=Y_train)
print(score)

# 激活KNN，加权
KNN2 = neighbors.KNeighborsClassifier(n_neighbors=3, weights='distance')
KNN2.fit(X_train, Y_train)
y_predict = KNN2.predict(x)
print(y_predict)

print（'---------------------------KNN回归-----------------------------'）

T = [
    [3, 104, 98],
    [2, 100, 93],
    [1, 81, 95],
    [101, 10, 16],
    [99, 5, 8],
    [98, 2, 7]]

# 初始化待测样本
x = [[18, 90]]
# x =[[50, 50]]

# 初始化K值
K = 5

data = pd.DataFrame(T, columns=['A', 'B', 'label'])
# print(data)

X_train = data.iloc[:, :-1]
# print(X_train)
Y_train = data.iloc[:, -1]
# print(Y_train)

# 激活KNN回归，不加权
KNN3 = neighbors.KNeighborsRegressor(n_neighbors=K)
KNN3.fit(X_train, Y_train)
y_predict = KNN3.predict(x)
print(y_predict)

# 激活KNN回归，加权
KNN4 = neighbors.KNeighborsRegressor(n_neighbors=K, weights='distance')
KNN4.fit(X_train, Y_train)
y_predict = KNN4.predict(x)
print(y_predict)