X_train, X_test, Y_train, Y_test = train_test_split(X,
Y,
test_size=0.25,
random_state=1)
folds = 5
alphas = np.logspace(1, 5, 3)
l1_ratios = np.linspace(0, 1, 2, endpoint=True)
models = MultiTaskElasticNetCV(l1_ratio=l1_ratios,
alphas=alphas,
verbose=1,
cv=folds,
n_jobs=-1)
models.fit(X_train, Y_train)
models.score(X_test, Y_test)
print "Alpha: ", models.alpha_
print "L1 ratio: ", models.l1_ratio_
print "Score of Elastic-net on test data: ", models.score(X_test, Y_test)
model_EN = ElasticNet(l1_ratio=models.l1_ratio_, alpha=models.alpha_)
model_EN.fit(np.concatenate((X_train, X_test)),
np.concatenate((Y_train, Y_test)))
test = np.rint(models.predict(X_test)).astype('int16')
coeff = model_EN.coef_.T
# coeff = models.coef_.T
# high=1.0
# low=0.0
# 在初始化MultiTaskElasticNetCV类时, 提供一组备选的α值, MultiTaskElasticNetCV类会帮我们选择一个合适的α值.
multiTaskElasticNetCV = MultiTaskElasticNetCV(
alphas=[0.01, 0.1, 0.5, 1, 3, 5, 7, 10, 20, 100], cv=5)
# 拟合训练集
multiTaskElasticNetCV.fit(train_X, train_Y)
# 打印最优的α值
print "最优的alpha值: ", multiTaskElasticNetCV.alpha_
# 打印模型的系数
print "系数:", multiTaskElasticNetCV.coef_
print "截距:", multiTaskElasticNetCV.intercept_
print '训练集R2: ', r2_score(train_Y, multiTaskElasticNetCV.predict(train_X))
# 对于线性回归模型, 一般使用均方误差(Mean Squared Error,MSE)或者
# 均方根误差(Root Mean Squared Error,RMSE)在测试集上的表现来评该价模型的好坏.
test_Y_pred = multiTaskElasticNetCV.predict(test_X)
print "测试集得分:", multiTaskElasticNetCV.score(test_X, test_Y)
print "测试集MSE:", mean_squared_error(test_Y, test_Y_pred)
print "测试集RMSE:", np.sqrt(mean_squared_error(test_Y, test_Y_pred))
print "测试集R2:", r2_score(test_Y, test_Y_pred)
tss, rss, ess, r2 = xss(Y, multiTaskElasticNetCV.predict(X))
print "TSS(Total Sum of Squares): ", tss
print "RSS(Residual Sum of Squares): ", rss
print "ESS(Explained Sum of Squares): ", ess
print "R^2: ", r2
print "\n**********测试BayesianRidge类**********"
bayesianRidge = BayesianRidge()
# 拟合训练集
bayesianRidge.fit(train_X, train_Y.values.ravel())
# 打印模型的系数
