Mehmed B. Duran

``` zir = ZeroInflatedRegressor( classifier=SVC(), regressor=LinearRegression() ) try: zir.fit(X_train, y_train) except ValueError as e: if str(e) =="The predicted training labels are all zero, making the regressor obsolete. Change the classifier...

Exactly @MBrouns . And I think this should be an option given to the user.

@koaning I wish I could, currently struggling with health issues :(