Make explain() smarter

[pbiecek]

The explain() function should be more verbose to inform if everything is set up ok.
The explain() function should report what defaults are selected.

[pbiecek]

[pbiecek]

Updated verbose decription:

wine_lm <- explain(wine_lm_model4)
#> Preparation of a new explainer is initiated
#>   -> model label:  lm  (default)
#>   -> data:  4898  rows  5  cols (extracted from model)
#>   -> target variable is not specified! (WARNING)
#>   -> predict function:  yhat.lm  will be used (default)
#>   -> predicted values:  numerical, min =  4.880047 , mean =  5.877909 , max =  7.867825  
#>   -> residual function: difference between y and yhat (default)
#> A new explainer has been created!

wine_lm <- explain(wine_lm_model4, data = wine, label = "model_4v", predict_function = predict)
#> Preparation of a new explainer is initiated
#>   -> model label:  model_4v 
#>   -> data:  4898  rows  12  cols 
#>   -> target variable is not specified! (WARNING)
#>   -> predict function:  predict 
#>   -> predicted values:  numerical, min =  4.880047 , mean =  5.877909 , max =  7.867825  
#>   -> residual function: difference between y and yhat (default)
#> A new explainer has been created!