why not default `explain_instance` to 1st top label, rather than 1st label? about lime HOT 3 CLOSED

I am assuming the the most common use case is binary prediction. When the prediction is binary, you want to always explain label 1, as that keeps 0 on the left and 1 on the right in the visualization, even if 0 is the top predicted label.

from lime.

Makes sense. You do know the number of classes, so you could default to label 1 for binary classification and the top label otherwise.

I do think a large percentage of users will want to use this library to explain the prediction their model actually made, and it seems like the default options should facilitate that. You could also add another function that wraps explain_instance, I guess.

from lime.

I will make major changes in the interface to include other explanation methods I've developed soon, so I'll keep the suggestion in mind.
Thanks,

from lime.