I mentioned the other day that I'd been wrestling with a bug in the predictor. I found a situation where I had generated some new features for my model and they caused a large drop in accuracy. Here's a picture that captures the problem:
The model I'm using here is the standard Ridge Regression model from Scikit-Learn. I'm dubious that any attribute could cause this much inaccuracy, but even so the attribute should have been optimized out of the model. And the fact that this happens with multiple features suggests to me that its a pervasive problem in my data or in the model.
At any rate, I was unable to figure it out and moved on to other things. But I'm still curious about what could be going on here. Maybe there's something obvious I'm missing.