支持向量机，K近邻模型，回归树在不同配置下的性能比较

1 延续上一篇，还是采用美国波士顿房价测试数据，对支持向量机，K近邻模型以及回归树采用不同的参数配置，进行同一模型在不同配置下的回归预测性能的评估

2 实验代码及结果截图

#导入数据读取器

from sklearn.datasets import load_boston

boston=load_boston()

#数据分割

from sklearn.cross_validation import train_test_split

import numpy as np

X=boston.data

y=boston.target

#随机25%的测试样本数据，其他为训练样本数据

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

#数据的标准化处理

from sklearn.preprocessing import StandardScaler

ss_X=StandardScaler()

ss_y=StandardScaler()

X_train=ss_X.fit_transform(X_train)

X_test=ss_X.fit_transform(X_test)

y_train=ss_y.fit_transform(y_train.reshape(-1,1))

y_test=ss_y.fit_transform(y_test.reshape(-1,1))

from sklearn.svm import SVR

#使用线性核函数配置向量机进行回归训练并预测

linear_svr=SVR(kernel='linear')

linear_svr.fit(X_train, y_train)

linear_svr_y_predict=linear_svr.predict(X_test)

#多项式核函数配置

poly_svr=SVR(kernel='poly')

poly_svr.fit(X_train, y_train)

poly_svr_y_predict=poly_svr.predict(X_test)

#径向基核函数配置

rbf_svr=SVR(kernel='rbf')

rbf_svr.fit(X_train, y_train)

rbf_svr_y_predict=rbf_svr.predict(X_test)

#回归性能的评估

from sklearn.metrics import r2_score,mean_absolute_error,mean_squared_error

print '三种不同配置下的支持向量机的回归分析'

print 'linear SVR'

print 'R-squared:',linear_svr.score(X_test,y_test)

print 'mean_squared:',mean_squared_error(ss_y.inverse_transform(y_test), ss_y.inverse_transform(linear_svr_y_predict))

print 'mean_absolute:',mean_absolute_error(ss_y.inverse_transform(y_test), ss_y.inverse_transform(linear_svr_y_predict))

print 'Poly SVR'

print 'R-squared:',poly_svr.score(X_test,y_test)

print 'mean_squared:',mean_squared_error(ss_y.inverse_transform(y_test), ss_y.inverse_transform(poly_svr_y_predict))

print 'mean_absolute:',mean_absolute_error(ss_y.inverse_transform(y_test), ss_y.inverse_transform(poly_svr_y_predict))

print 'rbf SVR'

print 'R-squared:',rbf_svr.score(
4000
X_test,y_test)

print 'mean_squared:',mean_squared_error(ss_y.inverse_transform(y_test), ss_y.inverse_transform(rbf_svr_y_predict))

print 'mean_absolute:',mean_absolute_error(ss_y.inverse_transform(y_test), ss_y.inverse_transform(rbf_svr_y_predict))



#两种配置下K近邻模型的回归性能分析

#导入K近邻模型

from sklearn.neighbors import KNeighborsRegressor

#初始化，使预测的方式为平均回归:weights='uniform'

uni_knr=KNeighborsRegressor(weights='uniform')

uni_knr.fit(X_train, y_train)

uni_knr_y_predict=uni_knr.predict(X_test)

#初始化预测方式为根据距离加权回归：weight='distance'

dis_knr=KNeighborsRegressor(weights='distance')

dis_knr.fit(X_train, y_train)

dis_knr_y_predict=dis_knr.predict(X_test)

#性能评估

print '两种配置下K近邻模型的回归性能分析'

print '平均回归配置'

print 'R-squared',uni_knr.score(X_test,y_test)

print 'mean_squared',mean_squared_error(ss_y.inverse_transform(y_test), ss_y.inverse_transform(uni_knr_y_predict))

print 'mean_absolute',mean_absolute_error(ss_y.inverse_transform(y_test), ss_y.inverse_transform(uni_knr_y_predict))

print '距离加权回归'

print 'R-squared',dis_knr.score(X_test,y_test)

print 'mean_squared',mean_squared_error(ss_y.inverse_transform(y_test), ss_y.inverse_transform(dis_knr_y_predict))

print 'mean_absolute',mean_absolute_error(ss_y.inverse_transform(y_test), ss_y.inverse_transform(dis_knr_y_predict))



#回归树

#模型导入

from sklearn.tree import DecisionTreeRegressor

dtr=DecisionTreeRegressor()

#构建回归树

dtr.fit(X_train, y_train)

#单一回归树

dtr_y_predict=dtr.predict(X_test)

#评估

print '单一回归树'

print 'R-squared:',dtr.score(X_test,y_test)

print 'mean_squared:',mean_squared_error(ss_y.inverse_transform(y_test), ss_y.inverse_transform(dtr_y_predict))

print 'mean_absolute:',mean_absolute_error(ss_y.inverse_transform(y_test), ss_y.inverse_transform(dtr_y_predict))



#集成模型

#模型导入

from sklearn.ensemble import RandomForestRegressor,ExtraTreesRegressor,GradientBoostingRegressor

#模型训练及预测

rfr=RandomForestRegressor()

rfr.fit(X_train,y_train)

rfr_y_predict=rfr.predict(X_test)

etr=ExtraTreesRegressor()

etr.fit(X_train,y_train)

etr_y_predict=etr.predict(X_test)

gbr=GradientBoostingRegressor()

gbr.fit(X_train, y_train)

gbr_y_predict=gbr.predict(X_test)

print '随机回归森林'

print 'R-squared:',rfr.score(X_test,y_test)

print 'mean_squared:',mean_squared_error(ss_y.inverse_transform(y_test), ss_y.inverse_transform(rfr_y_predict))

print 'mean_absolute:',mean_absolute_error(ss_y.inverse_transform(y_test),ss_y.inverse_transform(rfr_y_predict))

print '极端回归森林'

print 'R-squared:',etr.score(X_test,y_test)

print 'mean_squared:',mean_squared_error(ss_y.inverse_transform(y_test), ss_y.inverse_transform(etr_y_predict))

print 'mean_absolute:',mean_absolute_error(ss_y.inverse_transform(y_test),ss_y.inverse_transform(etr_y_predict))

#每种特征对预测目标的贡献度

print '每种特征对预测目标的贡献度'

print np.sort(zip(etr.feature_importances_,boston.feature_names),axis=0)

#梯度提升回归树

print '梯度提升回归树'

print 'R-squared:',gbr.score(X_test,y_test)

print 'mean_squared:',mean_squared_error(ss_y.inverse_transform(y_test), ss_y.inverse_transform(gbr_y_predict))

print 'mean_absolute:',mean_absolute_error(ss_y.inverse_transform(y_test),ss_y.inverse_transform(gbr_y_predict))