《深度学习Python实践》第13章——审查回归算法

1. 线性回归

1.线性回归算法

from pandas import read_csv
from sklearn.model_selection import KFold
from sklearn.model_selection import cross_val_score
from sklearn.linear_model import LinearRegression

filename='/home/duan/regression-datasets-housing.csv'
names=['CRIM','ZN','INDUS','CHAS','NOX','RM','AGE','DIS','RAD','TAX','PRTATIO','B','LSTAT','MEDV']
data=read_csv(filename,names=names)
array= data.values
X= array[:,0:13]
Y= array[:,13]
num_folds=10
seed=7
kfold=KFold(n_splits=num_folds, random_state=seed)
model=LinearRegression()
scoring='neg_mean_squared_error'
result=cross_val_score(model,X,Y,cv=kfold,scoring=scoring)
print('Linear_Regression:%.3f'%result.mean())

运行结果：

Linear_Regression:-34.942

2.岭回归

from pandas import read_csv
from sklearn.model_selection import KFold
from sklearn.model_selection import cross_val_score
from sklearn.linear_model import Ridge

filename='/home/duan/regression-datasets-housing.csv'
names=['CRIM','ZN','INDUS','CHAS','NOX','RM','AGE','DIS','RAD','TAX','PRTATIO','B','LSTAT','MEDV']
data=read_csv(filename,names=names)
array= data.values
X= array[:,0:13]
Y= array[:,13]
num_folds=10
seed=7
kfold=KFold(n_splits=num_folds, random_state=seed)
model=Ridge()
scoring='neg_mean_squared_error'
result=cross_val_score(model,X,Y,cv=kfold,scoring=scoring)
print('Ridge_Regression:%.3f'%result.mean())

运行结果：

Ridge_Regression:-34.325

3.套索回归算法

#套索回归算法
from pandas import read_csv
from sklearn.model_selection import KFold
from sklearn.model_selection import cross_val_score
from sklearn.linear_model import Lasso

filename='/home/duan/regression-datasets-housing.csv'
names=['CRIM','ZN','INDUS','CHAS','NOX','RM','AGE','DIS','RAD','TAX','PRTATIO','B','LSTAT','MEDV']
data=read_csv(filename,names=names)
array= data.values
X= array[:,0:13]
Y= array[:,13]
num_folds=10
seed=7
kfold=KFold(n_splits=num_folds, random_state=seed)
model=Lasso()
scoring='neg_mean_squared_error'
result=cross_val_score(model,X,Y,cv=kfold,scoring=scoring)
print('Lasso_Regression:%.3f'%result.mean())

运行结果：

Lasso_Regression:-34.614

4.弹性网络回归算法

#弹性网络回归算法
from pandas import read_csv
from sklearn.model_selection import KFold
from sklearn.model_selection import cross_val_score
from sklearn.linear_model import ElasticNet

filename='/home/duan/regression-datasets-housing.csv'
names=['CRIM','ZN','INDUS','CHAS','NOX','RM','AGE','DIS','RAD','TAX','PRTATIO','B','LSTAT','MEDV']
data=read_csv(filename,names=names)
array= data.values
X= array[:,0:13]
Y= array[:,13]
num_folds=10
seed=7
kfold=KFold(n_splits=num_folds, random_state=seed)
model=ElasticNet()
scoring='neg_mean_squared_error'
result=cross_val_score(model,X,Y,cv=kfold,scoring=scoring)
print('ElasticNet_Regression:%.3f'%result.mean())

运行结果：

ElasticNet_Regression:-31.292

2.非线性算法

1.K近邻算法

from pandas import read_csv
from sklearn.model_selection import KFold
from sklearn.model_selection import cross_val_score
from sklearn.neighbors import KNeighborsRegressor

filename='/home/duan/regression-datasets-housing.csv'
names=['CRIM','ZN','INDUS','CHAS','NOX','RM','AGE','DIS','RAD','TAX','PRTATIO','B','LSTAT','MEDV']
data=read_csv(filename,names=names)
array= data.values
X= array[:,0:13]
Y= array[:,13]
num_folds=10
seed=7
kfold=KFold(n_splits=num_folds, random_state=seed)
model=KNeighborsRegressor()
scoring='neg_mean_squared_error'
result=cross_val_score(model,X,Y,cv=kfold,scoring=scoring)
print('KNeighbors_Regression:%.3f'%result.mean())

运行结果：

KNeighbors_Regression:-107.193

2.分类与回归树

##分类树与回归树

from pandas import read_csv
from sklearn.model_selection import KFold
from sklearn.model_selection import cross_val_score
from sklearn.tree import DecisionTreeRegressor

filename='/home/duan/regression-datasets-housing.csv'
names=['CRIM','ZN','INDUS','CHAS','NOX','RM','AGE','DIS','RAD','TAX','PRTATIO','B','LSTAT','MEDV']
data=read_csv(filename,names=names)
array= data.values
X= array[:,0:13]
Y= array[:,13]
num_folds=10
seed=7
kfold=KFold(n_splits=num_folds, random_state=seed)
model=DecisionTreeRegressor()
scoring='neg_mean_squared_error'
result=cross_val_score(model,X,Y,cv=kfold,scoring=scoring)
print('DecisionTree_Regression:%.3f'%result.mean())

运行结果：

DecisionTree_Regression:-32.817

3.支持向量机

from pandas import read_csv
from sklearn.model_selection import KFold
from sklearn.model_selection import cross_val_score
from sklearn.svm import SVR

filename='/home/duan/regression-datasets-housing.csv'
names=['CRIM','ZN','INDUS','CHAS','NOX','RM','AGE','DIS','RAD','TAX','PRTATIO','B','LSTAT','MEDV']
data=read_csv(filename,names=names)
array= data.values
X= array[:,0:13]
Y= array[:,13]
num_folds=10
seed=7
kfold=KFold(n_splits=num_folds, random_state=seed)
model=SVR()
scoring='neg_mean_squared_error'
result=cross_val_score(model,X,Y,cv=kfold,scoring=scoring)
print('SVR_Regression:%.3f'%result.mean())

运行结果：

SVR_Regression:-91.046