Java: Data Science Made Easy

Other libraries

Other libraries that we previously covered also have models for solving the regression problem.

For example, in LIBSVM, it is possible to do regression by setting the svm_type parameter to EPSILON_SVR or NU_SVR, and the rest of the code stays almost the same as in the classification case. Likewise, in LIBLINEAR, the regression problem is solved by choosing L2R_L2LOSS_SVR or L2R_L2LOSS_SVR_DUAL models.

It is also possible to solve the regression problem with neural networks, for example, in Encog. The only thing you need to change is the loss function: instead of minimizing a classification loss function (such as logloss) you should use a regression loss function, such as mean-squared error.

Since most of the code is pretty ...