Example usage for org.apache.mahout.classifier.df.data DataLoader loadData

Introduction

In this page you can find the example usage for org.apache.mahout.classifier.df.data DataLoader loadData.

Prototype

public static Data loadData(Dataset dataset, FileSystem fs, Path[] pathes) throws IOException 

Source Link

Document

Loads the data from multiple paths specified by pathes

Usage

From source file:bigimp.BuildForest.java

License:Apache License

protected static Data loadData(Configuration conf, Path dataPath, Dataset dataset) throws IOException {
    log.info("Loading the data...");
    FileSystem fs = dataPath.getFileSystem(conf);
    Data data = DataLoader.loadData(dataset, fs, dataPath);
    log.info("Data Loaded");

    return data;/*from   w  w  w.j a  va2  s .com*/
}

---

From source file:javaapplication3.runRandomForest.java

public static void main(String[] args) throws InterruptedException, IOException, ClassNotFoundException {

    String outputFile = "data/lule24";
    String inputFile = "data/DataFraud1MTest.csv";
    String modelFile = "data/forest.seq";
    String infoFile = "data/DataFraud1M.info";

    Path dataPath = new Path(inputFile); // test data path
    Path datasetPath = new Path(infoFile);
    Path modelPath = new Path(modelFile); // path where the forest is stored
    Path outputPath = new Path(outputFile); // path to predictions file, if null do not output the predictions

    Configuration conf = new Configuration();
    FileSystem fs = FileSystem.get(conf);
    /*/*from w w w  .j  a v a 2  s.  c om*/
    p = Runtime.getRuntime().exec("bash /home/ivan/hadoop-1.2.1/bin/start-all.sh");
    p.waitFor();*/

    if (outputPath == null) {
        throw new IllegalArgumentException(
                "You must specify the ouputPath when using the mapreduce implementation");
    }

    Classifier classifier = new Classifier(modelPath, dataPath, datasetPath, outputPath, conf);

    classifier.run();

    double[][] results = classifier.getResults();

    if (results != null) {

        Dataset dataset = Dataset.load(conf, datasetPath);
        Data data = DataLoader.loadData(dataset, fs, dataPath);

        Instance inst;

        for (int i = 0; i < data.size(); i++) {
            inst = data.get(i);

            //System.out.println("Prediction:"+inst.get(7)+" Real value:"+results[i][1]);
            System.out.println(inst.get(0) + " " + inst.get(1) + " " + inst.get(2) + " " + inst.get(3) + " "
                    + inst.get(4) + " " + inst.get(5) + " " + inst.get(6) + " " + inst.get(7) + " ");
        }

        ResultAnalyzer analyzer = new ResultAnalyzer(Arrays.asList(dataset.labels()), "unknown");

        for (double[] res : results) {
            analyzer.addInstance(dataset.getLabelString(res[0]),
                    new ClassifierResult(dataset.getLabelString(res[1]), 1.0));
            System.out.println("Prvi shit:" + res[0] + " Drugi Shit" + res[1]);
        }

        System.out.println(analyzer.toString());

    }

}

---