k-NN | machine learning plugin which supports an approximate k

I'm building a predictive model for whether a car is sport car or not. The model works fine, however I would like to join the predicted values back to the unique IDs and visualize the proportion, etc. Basically I have two dataframes:

1. Testing with labelled data - test_cars

1. Unlabelled data to be predicted - cars_new

I've created sound classifier build using Keras from some tutorials in the internet. Here is my model code

We've had great results using a K-NN search with a GiST index with gist_trgm_ops. Pure magic. I've got other situations, with other datatypes like timestamp where distance functions would be quite useful. If I didn't dream it, this is, or was, available through pg_catalog. Looking around, I can't find a way to search on indexes by such properties. I think what I'm after, in this case, is AMPROP_DISTANCE_ORDERABLE under-the-hood.

Just checked, and pg_am did have a lot more attributes than it does now, prior to 9.6.

Is there another way to figure out what options various indexes have with a catalog search?

jjanes' answer inspired me to look at the system information functions some more, and to spend a day in the pg_catalog tables. The catalogs for indexes and operators are complicated. The system information functions are a big help. This piece proved super useful for getting a handle on things:

https://postgrespro.com/blog/pgsql/4161264

I think the conclusion is "no, you can't readily figure out what data types and indexes support proximity searches." The relevant attribute is a property of a column in a specific index. However, it looks like nearest-neighbor searching requires a GiST index, and that there are readily-available index operator classes to add K-NN searching to a huge range of common types. Happy for corrections on these conclusions, or the details below.

https://www.postgresql.org/docs/current/gist-builtin-opclasses.html

From various bits of the docs, it sounds like there are distance (proximity, nearest neighbor, K-NN) operators for GiST indexes on a handful of built-in geometric types.

Blue will be predicted as a result of this case when k is 5 because there are 3 out of 5 blue dots. And, I know how to score the accuracy. But What I want to know is the ratio of each Blue and Red dots like picture below.

Is there any tools to do this in sklearn or tensorflow? or should I make my own k-nn model?

I am trying to implement a k-NN algorithm but it keeps resulting in very low accuracy values. There must be a logic error but I couldn't figure out where it is. The code is below:

I want to visualize 4 test samples of k-NN Classifier. I have searched it but I could not find anything. Can you help me with implementing the code?

Here is my code so far,

I want to plot figures with different value of k for k-nn classifier. My problem is that the figures seem to have same values of k. What I have tried so far, is to change the value of k in each run in the loop:

clf = KNeighborsClassifier(n_neighbors=counter+1) But all the figures seem to be for k=1

I am using matplotlib to draw horizontal plots. I want to add grids and change size of the plot to avoid overleap of the label. My code looks like this:

Hope you guys understand that it is hard to replicate something like this on a generic dataset.

Basically what I'm trying to do is perform K-NN with test and train sets of two different sizes for seven different values of k.

My main problem is that res should be a vector storing all the accuracy values for the same train-set size but it shows one value per iteration and this doesn't allow me to plot accuracy graphs as they appear empty.

Do you know how to fix this problem?

Data is available directly on R for free.