python实现K近邻回归，采用等权重和不等权重

最新推荐文章于 2024-02-17 10:39:44 发布

原创最新推荐文章于 2024-02-17 10:39:44 发布 · 2.2k 阅读

1 ·

CC 4.0 BY-SA版权

机器学习--ML 专栏收录该内容

36 篇文章

订阅专栏

本文通过使用sklearn库中的波士顿房价数据集，进行了数据预处理并采用标准化方法，之后利用K近邻回归算法进行房价预测。实验比较了均匀权重和距离权重下模型的表现，并评估了模型的决定系数（R-squared）、均方误差（MSE）及平均绝对误差（MAE）。

from sklearn.datasets import load_boston

boston = load_boston()

from sklearn.cross_validation import train_test_split

import numpy as np;

X = boston.data
y = boston.target

X_train, X_test, y_train, y_test = train_test_split(X, y, random_state = 33, test_size = 0.25)

print 'The max target value is: ', np.max(boston.target)
print 'The min target value is: ', np.min(boston.target)
print 'The average terget value is: ', np.mean(boston.target)

from sklearn.preprocessing import StandardScaler

ss_X = StandardScaler()
ss_y = StandardScaler()

X_train = ss_X.fit_transform(X_train)
X_test = ss_X.transform(X_test)
y_train = ss_y.fit_transform(y_train)
y_test = ss_y.transform(y_test)

from sklearn.neighbors import KNeighborsRegressor

uni_knr = KNeighborsRegressor(weights = 'uniform')
uni_knr.fit(X_train, y_train)
uni_knr_y_predict = uni_knr.predict(X_test)

dis_knr = KNeighborsRegressor(weights = 'distance')
dis_knr.fit(X_train, y_train)
dis_knr_y_predict = dis_knr.predict(X_test)

from sklearn.metrics import r2_score, mean_squared_error, mean_absolute_error

print 'R-squared value of uniform weights KNeighorRegressor is: ', uni_knr.score(X_test, y_test)
print 'The mean squared error of uniform weights KNeighorRegressor is: ', mean_squared_error(ss_y.inverse_transform(y_test), ss_y.inverse_transform(uni_knr_y_predict))
print 'The mean absolute error of uniform weights KNeighorRegressor is: ', mean_absolute_error(ss_y.inverse_transform(y_test), ss_y.inverse_transform(uni_knr_y_predict))

print 'R-squared of distance weights KNeighorRegressor is: ', dis_knr.score(X_test, y_test)
print 'the value of mean squared error of distance weights KNeighorRegressor is: ', mean_squared_error(ss_y.inverse_transform(y_test), ss_y.inverse_transform(dis_knr_y_predict))
print 'the value of mean ssbsolute error of distance weights KNeighorRegressor is: ', mean_absolute_error(ss_y.inverse_transform(y_test), ss_y.inverse_transform(dis_knr_y_predict))