Denis1990

private static String [] MAIL_LIST_PROJECTIONS = {
            MessageProvider.MessageColumns._ID,
            MessageProvider.MessageColumns.SENDER_ADDRESS,
            MessageProvider.MessageColumns.SENDER,
            MessageProvider.MessageColumns.SEND_DATE,
            MessageProvider.MessageColumns.SUBJECT,
            MessageProvider.MessageColumns.PREVIEW,
            MessageProvider.MessageColumns.UNREAD,
    };

Denis1990

2016-09-18 20:29:58 WARN  NativeCodeLoader:62 - Unable to load native-hadoop library for your platform... using builtin-java classes where applicable
 2016-09-18 20:31:34 INFO  deprecation:1173 - session.id is deprecated. Instead, use dfs.metrics.session-id
 2016-09-18 20:31:34 INFO  JvmMetrics:76 - Initializing JVM Metrics with processName=JobTracker, sessionId=
 2016-09-18 20:31:35 WARN  JobResourceUploader:171 - No job jar file set.  User classes may not be found. See Job or Job#setJar(String).
 2016-09-18 20:31:35 INFO  FileInputFormat:283 - Total input paths to process : 0
 2016-09-18 20:31:35 INFO  JobSubmitter:198 - number of splits:0
 2016-09-18 20:31:35 INFO  JobSubmitter:287 - Submitting tokens for job: job_local1137380161_0001
 2016-09-18 20:31:36 INFO  Job:1294 - The url to track the job: http://localhost:8080/
 2016-09-18 20:31:36 INFO  Job:1339 - Running job: job_local1137380161_0001
 2016-09-18 20:31:36 INFO  LocalJobRunner:471 - OutputCommitter set in config null

Denis1990

public class PointVector implements WritableComparable<PointVector> {
    /**
     * Keep the tfIdf values of the terms of a document
     */
    private Vector<Double> data = new Vector<>();

    public PointVector(double [] values) {
        this.data = new Vector<>(values.length);
        this.data.addAll(Doubles.asList(values));
    }

Denis1990

public class KMeansReducer extends Reducer<PointVector, PointVector, Text, Text> {
    private double min_dist = Double.MAX_VALUE;

    @Override
    public void reduce(PointVector center, Iterable<PointVector> points, Context context) throws IOException, InterruptedException {
        EuclideanDistance measure = new EuclideanDistance();
        double distance = 0.0;
        int numOfPoints = 0;
        double centerx = 0;
        double centery = 0;

Denis1990

public class KMeansMapper extends Mapper<LongWritable, Text, PointVector, PointVector> {

    private int clusters;
    private List<ImmutableTriple<Integer, String, PointVector>> centers;

    @Override
    protected void setup(Context context) throws IOException, InterruptedException {
        System.out.println("Inside setup");
        this.clusters = Integer.valueOf(context.getConfiguration().get("clusters"));
        this.centers = new ArrayList<>();

Denis1990

/**
 * Implementation of k-means algorithm using Map Reduce paradigm.
 */
public class KMeans extends Configured implements Tool {
    /**
     * Number of indexed documents
     */
    private int indexedDocuments;
    private List<ImmutableTriple<Integer, String, PointVector>> centers;

Denis1990

[denis@denisArch]$ sudo cp INSTALL.txt  /etc/
[sudo] password for denis: 
/usr/bin/cp INSTALL /etc/

Denis1990

## sudoers file.
##
## This file MUST be edited with the 'visudo' command as root.
## Failure to use 'visudo' may result in syntax or file permission errors
## that prevent sudo from running.
##
## See the sudoers man page for the details on how to write a sudoers file.
##

##

Denis1990

// taken from http://www.mkyong.com/java/how-to-compress-files-in-zip-format/
// and slightly modified to test my hypothesis.

import java.io.File;
import java.io.FileInputStream;
import java.io.FileOutputStream;
import java.io.IOException;
import java.io.FileNotFoundException;
import java.util.ArrayList;
import java.util.List;