初学者的疑惑。

[biebersong]

想问一下，在特征工程后选定最优的模型，能否用于Bgolearn，该怎么pre_fit(),没有看懂说明文档？

[biebersong]

还有一个小问题，Bgolearn是否受特征的影响？

[Bin-Cao]

hello, you can use your favourite model in Bgolearn by defining a model class:

class arb_model(object):
            def fit_pre(self,xtrain,ytrain,xtest):
                # instantiated model
                kernel = RBF()
                mdoel = GaussianProcessRegressor(kernel=kernel).fit(xtrain,ytrain)
                # defined the attribute's outputs
                mean,std = mdoel.predict(xtest,return_std=True)
                return mean,std   
Bgolearn.fit(data_matrix=x, Measured_response=y, virtual_samples=vs,  Kriging_model=arb_model)

The second question: of course, the feature set can influence fitting effects of ML models, thus has impact on Bgolearn’s preformance