source: main/trunk/model-sites-dev/mars/src/java/org/greenstone/mars/WekaFindInstanceKNN.java@ 35228

package org.greenstone.mars;

import weka.core.Instance;
import weka.core.Instances;
import weka.core.converters.ConverterUtils.DataSource;

import weka.core.neighboursearch.LinearNNSearch;
import weka.core.neighboursearch.NearestNeighbourSearch;
//import weka.core.neighboursearch.KDTree;

// Based on StackOverflow:
//   https://stackoverflow.com/questions/31350506/how-to-calculate-the-nearest-neighbors-using-weka-from-the-command-line

public class WekaCLFindNN 
{
    public static void findNearestNN(NearestNeighbourSearch knn, Instance sample_instance, int k_nearest)
    {
    try {
        Instances nearest_instances= knn.kNearestNeighbours(sample_instance, k_nearest);
        
        //cycle through the instances and printout the nearestneighbors
        
        System.out.println("\n" + sample_instance);
        for(int i =0; i<k_nearest; i++) {
        System.out.println("\t" + nearest_instances.instance(i));        
        }   
    }
    catch (Exception e) {
        e.printStackTrace();
    }
        
    }


    public static void main(String[] args) throws Exception {
    
    if (args.length != 2) {
        System.err.println("Usage: k-nearest-num file.{arff,csv}");
        System.exit(1);
    }
    String k_nearest_str     = args[0];
    String input_filename = args[1];
    
    int k_nearest = Integer.parseInt(k_nearest_str);
     
    System.out.println("Weka Command Line Find Nearest " + k_nearest_str
               + " Neighbors for each Instance in "  + input_filename);
    
    DataSource source = new DataSource(input_filename);
    Instances instances = source.getDataSet();
    
    LinearNNSearch knn = new LinearNNSearch(instances);
    //KDTree knn = new KDTree(instances);
    
    //cycle through the dataset and get instances for the nearestneighbors
    
    int num_instances = instances.numInstances();
    for(int j=0; j<num_instances; j++) {
        Instances nearestInstances= knn.kNearestNeighbours(instances.instance(j), k_nearest);
        
        Instance sample_instance = instances.instance(j);
        findNearestNN(knn,sample_instance,k_nearest);
    }    
    }
}