多任务套索回归

MultiTaskLasso Regression是 Lasso 回归的增强版本。 MultiTaskLasso 是 sklearn 提供的一个模型，用于通过估计它们的稀疏系数来解决多个回归问题。所有称为任务的回归问题都有相同的特征。该模型使用混合 l1/l2 范数进行正则化训练。它在许多方面类似于 Lasso 回归。主要区别在于 alpha 参数，其中 alpha 是乘以 l1/l2 范数的常数。

MultiTaskLasso 模型具有以下参数：

alpha: a float value that multiplies l1/l2 norms. by default 1.0 
fit_intercept: decide whether to use intercept for calculations. 
normalize: used to normalize the regressors in the data 
max_itr: number of maximum iteration. by default -1000 
selection: to determine how the updation of the coefficient will take place values – {‘cyclic’, ‘random’} by default cyclic 
tol: tolerance for optimization. 
random_state: A random feature is selected to update.

代码：为了说明 MultiTaskLasso Regression 在Python中的工作

python3

# import linear model library
from sklearn import linear_model
 
# create MultiTaskLasso model
MTL = linear_model.MultiTaskLasso(alpha = 0.5)
 
# fit the model to a data
MTL.fit([[1, 0], [1, 3], [2, 2]], [[0, 2], [1, 4], [2, 4]])
 
# perform prediction and print the result
print("Prediction result: \n", MTL.predict([[0, 1]]), "\n")
 
# print the coefficients
print("Coefficients: \n", MTL.coef_, "\n")
 
# print the intercepts
print("Intercepts: \n", MTL.intercept_, "\n")
 
# print the number of iterations performed
print("Number of Iterations: ", MTL.n_iter_, "\n")

输出：

Prediction result: 
[[0.8245348  3.04089134]] 

Coefficients: 
[[0.         0.26319779]
 [0.         0.43866299]] 

Intercepts:
[0.56133701 2.60222835] 

Number of Iterations: 2