Example usage for org.apache.mahout.classifier.df.data Data Data

Introduction

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

Prototype

public Data(Dataset dataset, List<Instance> instances) 

Source Link

Usage

From source file:com.wsc.myexample.decisionForest.MyDataLoader.java

License:Apache License

/**
 * Loads the data from a file//from   w w w  .j  a  v  a  2  s.  c  o m
 * 
 * @param fs
 *          file system
 * @param fpath
 *          data file path
 * @throws IOException
 *           if any problem is encountered
 */

public static Data loadData(Dataset dataset, String fpath) throws IOException {
    Scanner scanner = new Scanner(new File(fpath));

    List<Instance> instances = Lists.newArrayList();

    DataConverter converter = new DataConverter(dataset);

    while (scanner.hasNextLine()) {
        String line = scanner.nextLine();
        if (line.isEmpty()) {
            log.warn("{}: empty string", instances.size());
            continue;
        }

        Instance instance = converter.convert(line);
        if (instance == null) {
            // missing values found
            log.warn("{}: missing values", instances.size());
            continue;
        }

        instances.add(instance);
    }

    scanner.close();

    return new Data(dataset, instances);
}

---

From source file:com.wsc.myexample.decisionForest.MyDataLoader.java

License:Apache License

/**
 * Loads the data from a String array/*from w  w w.jav  a  2s.c  o m*/
 */
public static Data loadData(Dataset dataset, String[] data) {
    List<Instance> instances = Lists.newArrayList();

    DataConverter converter = new DataConverter(dataset);

    for (String line : data) {
        if (line.isEmpty()) {
            log.warn("{}: empty string", instances.size());
            continue;
        }

        Instance instance = converter.convert(line);
        if (instance == null) {
            // missing values found
            log.warn("{}: missing values", instances.size());
            continue;
        }

        instances.add(instance);
    }

    return new Data(dataset, instances);
}

---