1

What approach should I use to sort the following into naturally occurring "bins". 

   double[] x = { 18, 18, 18, 18, 19, 20, 20, 20, 21, 22, 22, 23, 24,  
      26, 27, 32, 33, 49, 52, 56,900,1200, 1200, 1500, 2000, 2000,2200,2200 };

I've looked at various code for "outliers", "quintiles" and not sure about what approach to take.

If it makes it easier, I'm using C# and might leverage Linq or some other approach to do this.

In my case I want to create two "bins" of drastically different number sets such as:

  • NumbersLessThan56
  • NumbersGreaterThan900

The thing I want to mathematically compute is that there is a large "multiple of x" gap between Bin1 and Bin2.

I'm experimenting with MathNet to find derivative inflection points, but still figuring this out

TLDR
  • 1,198
  • 1
  • 12
  • 31

1 Answers1

0

You may want to look into "Jenks natural breaks optimization" for this type of problem, cf. 1D Number Array Clustering.

monomeric
  • 48
  • 5