我使用了这里提供的代码： https ://towardsdatascience.com/ridge-and-lasso-regression-a-complete-guide-with-python-scikit-learn-e20e34bcbf0b
唯一的区别是我在下面给出的数据上使用了 StandardScalar：
from sklearn.preprocessing import StandardScaler
sc = StandardScaler()
X_train = sc.fit_transform(X_train)
X_test = sc.transform (X_test)
print len(X_test), len(y_test)
这是我的岭回归结果：
linear regression train score: 1.0
linear regression test score: -0.07550729376673715
ridge regression train score low alpha: 0.9999999970240117
ridge regression test score low alpha: -0.07532716978805554
ridge regression train score high alpha: 0.8659167364307487
ridge regression test score high alpha: 0.013702748149851396
我的套索结果：
training score: 0.48725444995774625
test score: -0.3393210376146986
number of features used: 4
training score for alpha=0.01: 0.9998352085084429
test score for alpha =0.01: -0.6995903332119675
number of features used: for alpha =0.01: 24
training score for alpha=0.0001: 0.9999999830932269
test score for alpha =0.0001: -0.7189894474663594
number of features used: for alpha =0.0001: 25
LR training score: 1.0
LR test score: -0.7217224228737649
我无法理解为什么我会得到这样的结果！非常感谢任何帮助。
编辑：代码如下
#Importing modules
import sys
import math
import itertools
import numpy as np
import pandas as pd
from numpy import genfromtxt
from matplotlib import style
import matplotlib.pyplot as plt
from sklearn import linear_model
from matplotlib import style, figure
from sklearn.linear_model import Lasso
from sklearn.linear_model import Ridge
from sklearn.linear_model import LinearRegression
from sklearn.cross_validation import train_test_split
#Importing data
df = np.genfromtxt('/Users/pfc.csv', delimiter=',')
X = df[0:,1:298]
y = df[0:,0]
print (X).shape
print (y).shape
display (X)
display (y)
print (y)
#print type(newY)# pandas core frame
X_train,X_test,y_train,y_test=train_test_split(X,y,test_size=0.2,random_state=4)
#Apply StandardScaler for feature scaling
from sklearn.preprocessing import StandardScaler
sc = StandardScaler()
X_train = sc.fit_transform(X_train)
X_test = sc.transform (X_test)
print len(X_test), len(y_test)
lr = LinearRegression()
lr.fit(X_train, y_train)
rr = Ridge(alpha=0.01) # higher the alpha value, more restriction on the coefficients; low alpha > more generalization, coefficients are barely restricted and in this case linear and ridge regression resembles
from sklearn.metrics import mean_squared_error
from math import sqrt
rr.fit(X_train, y_train)
rr100 = Ridge(alpha=115.5) # comparison with alpha value
rr100.fit(X_train, y_train)
train_score=lr.score(X_train, y_train)
test_score=lr.score(X_test, y_test)
Ridge_train_score = rr.score(X_train,y_train)
Ridge_test_score = rr.score(X_test, y_test)
Ridge_train_score100 = rr100.score(X_train,y_train)
Ridge_test_score100 = rr100.score(X_test, y_test)
print "linear regression train score:", train_score
print "linear regression test score:", test_score
print "ridge regression train score low alpha:", Ridge_train_score
print "ridge regression test score low alpha:", Ridge_test_score
print "ridge regression train score high alpha:", Ridge_train_score100
print "ridge regression test score high alpha:", Ridge_test_score100
plt.figure (figsize= (12.8,9.6), dpi =100)
plt.plot(rr.coef_,alpha=0.7,linestyle='none',marker='*',markersize=5,color='red',label=r'Ridge; $\alpha = 0.01$',zorder=7) # zorder for ordering the markers
plt.plot(rr100.coef_,alpha=0.5,linestyle='none',marker='d',markersize=6,color='blue',label=r'Ridge; $\alpha = 100$') # alpha here is for transparency
plt.plot(lr.coef_,alpha=0.4,linestyle='none',marker='o',markersize=7,color='green',label='Linear Regression')
plt.xlabel('Coefficient Index',fontsize=16)
plt.ylabel('Coefficient Magnitude',fontsize=16)
plt.legend(fontsize=13,loc=4)
plt.show()
# difference of lasso and ridge regression is that some of the coefficients can be zero i.e. some of the features are
# completely neglected
lasso = Lasso()
lasso.fit(X_train,y_train)
train_score=lasso.score(X_train,y_train)
test_score=lasso.score(X_test,y_test)
coeff_used = np.sum(lasso.coef_!=0)
print "training score:", train_score
print "test score: ", test_score
print "number of features used: ", coeff_used
lasso001 = Lasso(alpha=0.01, max_iter=10e5)
lasso001.fit(X_train,y_train)
train_score001=lasso001.score(X_train,y_train)
test_score001=lasso001.score(X_test,y_test)
coeff_used001 = np.sum(lasso001.coef_!=0)
print "training score for alpha=0.01:", train_score001
print "test score for alpha =0.01: ", test_score001
print "number of features used: for alpha =0.01:", coeff_used001
lasso00001 = Lasso(alpha=0.0001, max_iter=10e5)
lasso00001.fit(X_train,y_train)
train_score00001=lasso00001.score(X_train,y_train)
test_score00001=lasso00001.score(X_test,y_test)
coeff_used00001 = np.sum(lasso00001.coef_!=0)
print "training score for alpha=0.0001:", train_score00001
print "test score for alpha =0.0001: ", test_score00001
print "number of features used: for alpha =0.0001:", coeff_used00001
lr = LinearRegression()
lr.fit(X_train,y_train)
lr_train_score=lr.score(X_train,y_train)
lr_test_score=lr.score(X_test,y_test)
print "LR training score:", lr_train_score
print "LR test score: ", lr_test_score
plt.figure (figsize= (12.8,9.6), dpi =100)
plt.subplot(1,2,1)
plt.plot(lasso.coef_,alpha=0.7,linestyle='none',marker='*',markersize=5,color='red',label=r'Lasso; $\alpha = 1$',zorder=7) # alpha here is for transparency
plt.plot(lasso001.coef_,alpha=0.5,linestyle='none',marker='d',markersize=6,color='blue',label=r'Lasso; $\alpha = 0.01$') # alpha here is for transparency
plt.xlabel('Coefficient Index',fontsize=16)
plt.ylabel('Coefficient Magnitude',fontsize=16)
plt.legend(fontsize=13,loc=4)
plt.subplot(1,2,2)
plt.plot(lasso.coef_,alpha=0.7,linestyle='none',marker='*',markersize=5,color='red',label=r'Lasso; $\alpha = 1$',zorder=7) # alpha here is for transparency
plt.plot(lasso001.coef_,alpha=0.5,linestyle='none',marker='d',markersize=6,color='blue',label=r'Lasso; $\alpha = 0.01$') # alpha here is for transparency
plt.plot(lasso00001.coef_,alpha=0.8,linestyle='none',marker='v',markersize=6,color='black',label=r'Lasso; $\alpha = 0.00001$') # alpha here is for transparency
plt.plot(lr.coef_,alpha=0.7,linestyle='none',marker='o',markersize=5,color='green',label='Linear Regression',zorder=2)
plt.xlabel('Coefficient Index',fontsize=16)
plt.ylabel('Coefficient Magnitude',fontsize=16)
plt.legend(fontsize=13,loc=4)
plt.tight_layout()
plt.show()
PS：请忽略缩进。