_post_ml_fitfnwcxsvr_title_

In this chapter two programs are presented: fit_func_esvr.py and fit_func_nusvr.py In fact through the argument --svrparams the user passes a series of hyper-parameters to adjust the behavior of the'underlying SVR algorithm and others to configure its learning phase. In addition to the parameters of the underlying regressor the program supports its own arguments to allow the user to pass the training dataset and on which file to save the trained model. The format of the input datasets is in csv format (with header), with $n m$ columns, of which the first $n$ columns contain the values of the $n$ independent variables and the last $m$ containing the values of the dependent variables. In this chapter the program predict_func.py is presented and which purpose is to make predictions on a test dataset applying it to a previously trained e-SVR or nu-SVR model respectively via the program fit_func_esvr.py or fit_func_nusvr.py,