波士顿房价KNN

 

from sklearn.datasets import load_boston
boston = load_boston()
X =boston.data
y = boston.target
X.shape

 

from sklearn.model_selection import train_test_split
import numpy as np
X_train,X_test,y_train,y_test = train_test_split(X,y,test_size=0.25,random_state=40)
#分析回归目标值的差异
print('The max target value is ',np.max(y))
print ('The min target value is ',np.min(y))
print ('The average target value is ',np.mean(y))

 

#第三步：训练数据和测试数据标准化处理
from sklearn.preprocessing import StandardScaler
#分别初始化对特征值和目标值的标准化器
ss_X = StandardScaler()
#训练数据都是数值型，所以要标准化处理
X_train = ss_X.fit_transform(X_train)
#说明一下：fit_transform与transform都要求操作2D数据，而此时的y_train与y_test都是1D的，因此需要调用reshape(-1,1)，例如：[1,2,3]变成[[1],[2],[3]]
y_train = ss_y.fit_transform(y_train.reshape(-1,1))

#目标数据（房价预测值）也是数值型，所以也要标准化处理
ss_y = StandardScaler()
X_test = ss_X.fit_transform(X_test)
y_test = ss_y.fit_transform(y_test.reshape(-1,1))

#第四步：使用两种不同配置的K近邻回归模型进行训练，并且分别对测试数据进行预测
from sklearn.neighbors import KNeighborsRegressor
#1.初始化k近邻回归器，并且调整配置，使得预测方式为平均回归：weights = 'uniform'
uni_knr = KNeighborsRegressor(weights='uniform')
uni_knr.fit(X_train,y_train)
uni_knr_y_predict = uni_knr.predict(X_test)

#2.初始化k近邻回归器，并且调整配置，使得预测方式为根据距离加权回归：weights = 'distance'
dis_knr = KNeighborsRegressor(weights='distance')
dis_knr.fit(X_train,y_train)
dis_knr_y_predict = dis_knr.predict(X_test)

#使用R-squared、MSE、MAE指标评估
from sklearn.metrics import r2_score,mean_absolute_error,mean_squared_error
#1.预测方式为平均回归的KNR
print ('R-squared value of uniform-weighted KNR is',uni_knr.score(X_test,y_test))
print ('the MSE of uniform-weighted KNR is',mean_squared_error(ss_y.inverse_transform(y_test),ss_y.inverse_transform(uni_knr_y_predict)))
print ('the MAE of uniform-weighted KNR is',mean_absolute_error(ss_y.inverse_transform(y_test),ss_y.inverse_transform(uni_knr_y_predict)))
#2.预测方式为根据加权距离的KNR
print ('R-squared value of distance-weighted KNR is',dis_knr.score(X_test,y_test))
print ('the MSE of distance-weighted KNR is',mean_squared_error(ss_y.inverse_transform(y_test),ss_y.inverse_transform(dis_knr_y_predict)))
print ('the MAE of distance-weighted KNR is',mean_absolute_error(ss_y.inverse_transform(y_test),ss_y.inverse_transform(dis_knr_y_predict)))