Have a project I'm working on and am running into an issue.

Essentially I have lots of data sets with a small amount of data. These data sets represent locations in an area. I have one classification data set (y) with categorical values (number from 1 - 6), the location is in the middle of the rest of the data sets.

The issue with these points is that I don't get a lot of data per point (maybe 100 rows).

My goal was to fit a data set (physically closest to the target classification data set) and generalize it to the rest of data. It doesn't work very well, so now I'm trying to improve the model performance by adding 'k' data sets also close to the class data set.

Initially :

These data sets all share the same features and share the same rows as the classification data set.

With basic sklearn models I'm unable to take multiple inputs to fit, and one input to predict.

Essentially what I'm trying to do is the following : 



Where : All features are numeric (floats) Each X matrix is about 100 points long with a continuous index [0:100].

I only have one test point (with 100 observations) for each group of points, so it's imperative I use as much data close to the test point as possible to improve the model with the goal is to generalize the data to future points.

Is there another model or technique I can use for this? I've done a bit more research into NN models (not familiar so would prefer to avoid), and found that Keras has the ability to take multiple inputs to fit using their functions API, but can I predict with only one input after it has been fitted to multiple?



1 Answer 1


One option is merge nearby data points, aka binning or bucketing. Binning increases the amount data for a specific target and sometimes increases the signal-to-noise ratio. Binning is very useful for location-based data.


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Not the answer you're looking for? Browse other questions tagged or ask your own question.