umbertogriffo

# To execute script launch this command on shell: hbase shell HBaseRestore.rb

include Java

java_import org.apache.hadoop.hbase.HBaseConfiguration
java_import org.apache.hadoop.hbase.client.HBaseAdmin
java_import org.apache.hadoop.hbase.snapshot.ExportSnapshot
java_import org.apache.hadoop.hbase.TableExistsException
java_import org.apache.hadoop.util.ToolRunner

umbertogriffo

import java.util.Queue;
import java.util.concurrent.ConcurrentLinkedQueue;
import java.util.concurrent.Executors;
import java.util.concurrent.ScheduledExecutorService;
import java.util.concurrent.TimeUnit;
import java.util.concurrent.atomic.AtomicInteger;
/**
* @param <T>
*/
public abstract class ObjectPool<T> {

umbertogriffo

public class Method1 {
/*
Adding synchronized to this method will makes it thread-safe. 
When synchronized is added to a static method, the Class object is the object which is locked.
*/
  public static void main(String[] args) throws InterruptedException {

		ProcessingThreadS pt = new ProcessingThreadS();

		Thread t1 = new Thread(pt, "t1");

umbertogriffo

import org.apache.commons.lang.SystemUtils
import org.apache.spark.mllib.random.RandomRDDs._
import org.apache.spark.sql.SQLContext
import org.apache.spark.{SparkConf, SparkContext}

import scala.math.sqrt

/**
  * Created by Umberto on 08/02/2017.
  */

umbertogriffo

import java.util.*;
import java.util.Map.Entry;
import java.util.stream.Collectors;

/**
 * Created by Umberto on 16/05/2017.
 */

public class HashMapUtils {

umbertogriffo

package test.idlike.spark.datastructure;

import org.apache.commons.lang3.SystemUtils;
import org.apache.spark.api.java.JavaDoubleRDD;
import org.apache.spark.api.java.JavaPairRDD;
import org.apache.spark.api.java.JavaRDD;
import org.apache.spark.api.java.JavaSparkContext;
import org.apache.spark.api.java.function.Function;
import org.apache.spark.api.java.function.VoidFunction;
import scala.Tuple2;

umbertogriffo

  def transposeRowMatrix(m: RowMatrix): RowMatrix = {
    val transposedRowsRDD = m.rows.zipWithIndex.map{case (row, rowIndex) => rowToTransposedTriplet(row, rowIndex)}
      .flatMap(x => x) // now we have triplets (newRowIndex, (newColIndex, value))
      .groupByKey
      .sortByKey().map(_._2) // sort rows and remove row indexes
      .map(buildRow) // restore order of elements in each row and remove column indexes
    new RowMatrix(transposedRowsRDD)
  }

  def rowToTransposedTriplet(row: Vector, rowIndex: Long): Array[(Long, (Long, Double))] = {

umbertogriffo

Falsehoods programmers believe about time

This is a compiled list of falsehoods programmers tend to believe about working with time.

Don't re-invent a date time library yourself. If you think you understand everything about time, you're probably doing it wrong.

Falsehoods

• There are always 24 hours in a day.
• February is always 28 days long.
• Any 24-hour period will always begin and end in the same day (or week, or month).

umbertogriffo

package knowledgebase.java.stream;

import java.time.Duration;
import java.util.*;

import static java.util.stream.Collectors.*;

/**
 * Created by Umberto on 15/02/2017.
 * https://dzone.com/articles/a-java-8-streams-cookbook

umbertogriffo

/*
This is a collections of examples about Apache Spark's RDD Api. These examples aim to help me test the RDD functionality.

References:

http://spark.apache.org/docs/latest/programming-guide.html
http://homepage.cs.latrobe.edu.au/zhe/ZhenHeSparkRDDAPIExamples.html
*/
object RddAPI {