A Simple Machine Learning Example in Java

This is a "Hello World" example of machine learning in Java. It simply give you a taste of machine learning in Java.


Java 1.6+ and Eclipse

Step 1: Download Weka library

Download page: http://www.cs.waikato.ac.nz/ml/weka/snapshots/weka_snapshots.html

Download stable.XX.zip, unzip the file, add weka.jar to your library path of Java project in Eclipse.

Step 2: Prepare Data

Create a txt file "weather.txt" by following the following format:

@relation weather

@attribute outlook {sunny, overcast, rainy}
@attribute temperature numeric
@attribute humidity numeric
@attribute windy {TRUE, FALSE}
@attribute play {yes, no}


This dataset is from weka download package. It is located at "/data/weather.numeric.arff". The file extension name is "arff", but we can simply use "txt".

Step 3: Training and Testing by Using Weka

This code example use a set of classifiers provided by Weka. It trains model on the given dataset and test by using 10-split cross validation. I will explain each classifier later as it is a more complicated topic.

import java.io.BufferedReader;
import java.io.FileNotFoundException;
import java.io.FileReader;
import weka.classifiers.Classifier;
import weka.classifiers.Evaluation;
import weka.classifiers.evaluation.NominalPrediction;
import weka.classifiers.rules.DecisionTable;
import weka.classifiers.rules.PART;
import weka.classifiers.trees.DecisionStump;
import weka.classifiers.trees.J48;
import weka.core.FastVector;
import weka.core.Instances;
public class WekaTest {
	public static BufferedReader readDataFile(String filename) {
		BufferedReader inputReader = null;
		try {
			inputReader = new BufferedReader(new FileReader(filename));
		} catch (FileNotFoundException ex) {
			System.err.println("File not found: " + filename);
		return inputReader;
	public static Evaluation classify(Classifier model,
			Instances trainingSet, Instances testingSet) throws Exception {
		Evaluation evaluation = new Evaluation(trainingSet);
		evaluation.evaluateModel(model, testingSet);
		return evaluation;
	public static double calculateAccuracy(FastVector predictions) {
		double correct = 0;
		for (int i = 0; i < predictions.size(); i++) {
			NominalPrediction np = (NominalPrediction) predictions.elementAt(i);
			if (np.predicted() == np.actual()) {
		return 100 * correct / predictions.size();
	public static Instances[][] crossValidationSplit(Instances data, int numberOfFolds) {
		Instances[][] split = new Instances[2][numberOfFolds];
		for (int i = 0; i < numberOfFolds; i++) {
			split[0][i] = data.trainCV(numberOfFolds, i);
			split[1][i] = data.testCV(numberOfFolds, i);
		return split;
	public static void main(String[] args) throws Exception {
		BufferedReader datafile = readDataFile("weather.txt");
		Instances data = new Instances(datafile);
		data.setClassIndex(data.numAttributes() - 1);
		// Do 10-split cross validation
		Instances[][] split = crossValidationSplit(data, 10);
		// Separate split into training and testing arrays
		Instances[] trainingSplits = split[0];
		Instances[] testingSplits = split[1];
		// Use a set of classifiers
		Classifier[] models = { 
				new J48(), // a decision tree
				new PART(), 
				new DecisionTable(),//decision table majority classifier
				new DecisionStump() //one-level decision tree
		// Run for each model
		for (int j = 0; j < models.length; j++) {
			// Collect every group of predictions for current model in a FastVector
			FastVector predictions = new FastVector();
			// For each training-testing split pair, train and test the classifier
			for (int i = 0; i < trainingSplits.length; i++) {
				Evaluation validation = classify(models[j], trainingSplits[i], testingSplits[i]);
				// Uncomment to see the summary for each training-testing pair.
			// Calculate overall accuracy of current classifier on all splits
			double accuracy = calculateAccuracy(predictions);
			// Print current classifier's name and accuracy in a complicated,
			// but nice-looking way.
			System.out.println("Accuracy of " + models[j].getClass().getSimpleName() + ": "
					+ String.format("%.2f%%", accuracy)
					+ "\n---------------------------------");

The package view of your project should look like the following:


1. http://www.cs.umb.edu/~ding/history/480_697_spring_2013/homework/WekaJavaAPITutorial.pdf
2. http://www.cs.ru.nl/P.Lucas/teaching/DM/weka.pdf

Category >> Machine Learning  
If you want someone to read your code, please put the code inside <pre><code> and </code></pre> tags. For example:
String foo = "bar";

  1. Giri on 2014-8-24

    Can you please explain the output /
    / What does this program dp ?

  2. junaid ahmad on 2014-8-27

    it is awesome and works well ………Can you provide me the code for support vector machine like this ……..that you I need it as soon as possible…….

  3. Pratibind Jha on 2014-8-29

    Hi line

    predictions.appendElements(validation.predictions()); throwing error saying validation does not have predictions method

  4. White on 2014-9-24

    Thank you so very much for providing this tutorial, X Wang.. 🙂

  5. Hossein on 2014-11-30

    it was awesome thx, in Weka 3.7 what header should be used instead of “import weka.core.FastVector;”

  6. jadedandbemused on 2015-1-3

    Have you tried Deeplearning4j.org?

  7. Nemo on 2015-2-7

    Thank you very much for sharing.

  8. Rohit Gupta on 2015-3-13

    when i run this code in android emulator it unfortunately stop.We can not run it.
    please suggest some solution

  9. Seetesh Hindlekar on 2015-4-6

    validation’s methods needs to be relooked at for the weka.jar that is available on the net

  10. pritesh on 2015-4-26

    can you please provide me SVM classifier’s java code. I really need that.

  11. sanjaya on 2016-2-25

    Nice work. it is working well

  12. Sujaira Moughawiche on 2016-5-7

    Hello, thanks for the tutorial, I’m having problems understanding the outputs could you explain me please.

  13. Lakshitha Warnakulasuriya on 2017-2-10

    I have an same error in my java code. How to solve this problem

  14. Deeps Srk on 2017-3-10

    did u find the solution for this problem

  15. 이정민 on 2017-4-11

    Can you show me the output of the programs?

  16. Yauheni Dzenisenka on 2017-4-30

    I guess u r importing weka.classifiers.Evaluation instead of weka.classifiers.Evaluation.
    There are 2 classes with the same name and it’s a bit confusing, but with the second one everything works fine.

  17. pranit patil on 2017-8-31

    Great example of machine learning in java . I have been looking for example on this topic and i have found it very good thanks for sharing with us.

  18. nitin bawane on 2017-9-29

    i have used another text data file.
    following is output of above prog….

    Accuracy of J48: 64.29%
    Accuracy of PART: 64.29%
    Accuracy of DecisionTable: 78.57%
    Accuracy of DecisionStump: 64.29%

  19. nitin bawane on 2017-9-29

    Output of the above programme. percentage may vary according to ur dataset.

    Accuracy of J48: 64.29%
    Accuracy of PART: 64.29%
    Accuracy of DecisionTable: 78.57%
    Accuracy of DecisionStump: 64.29%

Leave a comment