Closed zasdfgbnm closed 5 years ago
@zasdfgbnm could you please add more context on where such metric can be of interest ?
@vfdev-5 This is for regression problem, it characterizes how far the worst point are deviated from ground truth.
@zasdfgbnm in general we can add something like this in the contrib module. Let's see what others think about the importance of this metric.
In general, I think more metrics are definitely welcomed. That being said, for this specific one, I don't now that there is a wide enough use to justify its addition.
I echo @jasonkriss sentiment, that more metrics are welcom. MAE is often used in recommender systems, and other regression tasks to measure performance.
I say go for it, might as well just put it in core as it's pretty simple to implement and I don't envisage much support being needed going forward
@zasdfgbnm can you send a PR?
Sure, I will. @alykhantejani
error = (y_pred - y).abs().max()
Would this be a good thing to add?