scikit-learning k临近算法回归学习

#生成sin散点数据，然后加上扰动，用k临近回归去预测
#进行回归时，找到临近的k个样本，采用普通的算术平均算法或考虑距离差异的加权平均等输出

from sklearn.neighbors import KNeighborsRegressor
import matplotlib.pyplot as plt
import numpy as np
# 生成训练样本
dot_num = 100
x = 10*np.random.rand(dot_num, 1)#(dot_num,1)
#print(x)
y = np.sin(x).ravel()#(1,dot_num)
#print(y)
# 添加[-0.1,0.1]之间的扰动 
y += 0.1*np.random.rand(dot_num)-0.05
#print(y)

# 训练模型
k = 5
#加权平均
knn_Regress1 = KNeighborsRegressor(n_neighbors = k, weights='distance')
#算术平均
knn_Regress2 = KNeighborsRegressor(n_neighbors = k, weights='uniform')

knn_Regress1.fit(x, y)
knn_Regress2.fit(x, y)

#进行预测
pre_dot_num = 200
x_sample = np.linspace(0, 10, pre_dot_num)[:, np.newaxis]#这里要转化成二维(n,1)
#print(x_sample)
y_sample1 = knn_Regress1.predict(x_sample)
y_sample2 = knn_Regress2.predict(x_sample)
#看模型评分
print(knn_Regress1.score(x, y))
print(knn_Regress2.score(x, y))

#数据可视化

#解决中文显示问题
plt.rcParams['font.sans-serif']=['SimHei']
plt.rcParams['axes.unicode_minus'] = False

plt.figure(figsize = (10,10))
plt.scatter(x, y, c='b', label='data', s=50)
plt.plot(x_sample, y_sample1, c='r')
plt.title("加权平均")
plt.show()

plt.figure(figsize = (10,10))
plt.scatter(x, y, c='b', label='data', s=50)
plt.plot(x_sample, y_sample1, c='g')
plt.title(r"算术平均")
plt.show()

输出图片