johnynek

groupBy('source) {
  _.sortBy('links)
    .reverse
    .mapStream[(String,Int), (String, Int, Int, Int)]
      (('destination, 'links) -> ('destination, 'links, 'rank, 'gap)) { destLinks =>
        destLinks.scanLeft(None: Option[(String, Int, Int, Int)]) {
          (prevRowOut: Option[(String,Int,Int,Int)], thisRow: (String, Int))  =>
          val (dest, links) = thisRow
          prevRowOut match {
            case None => Some((dest, links, 1, 0)) // rank 1, gap 0 -- not exactly what you wanted...

mushkevych

FROM    ubuntu:precise
MAINTAINER Bohdan Mushkevych

# Installing Oracle JDK
RUN apt-get -y install python-software-properties ;\
	add-apt-repository ppa:webupd8team/java ;\
	apt-get update && apt-get -y upgrade ;\
	echo oracle-java7-installer shared/accepted-oracle-license-v1-1 select true | /usr/bin/debconf-set-selections ;\
	apt-get -y install oracle-java7-installer && apt-get clean ;\
	update-alternatives --display java ;\

terrancesnyder

import java.io.ByteArrayOutputStream;
import java.io.IOException;
import java.io.InputStream;
import java.util.List;
import java.util.Map;
import java.util.Properties;
import java.util.concurrent.ExecutorService;
import java.util.concurrent.Executors;

import org.apache.avro.io.BinaryDecoder;

nipra

# Installing CDH4 on a Single Linux Node in Pseudo-distributed Mode
# https://ccp.cloudera.com/display/CDH4DOC/Installing+CDH4+on+a+Single+Linux+Node+in+Pseudo-distributed+Mode

# Installing CDH4 with MRv1 on a Single Linux Node in Pseudo-distributed mode
# On Ubuntu and other Debian systems
nipra@lambda:Downloads$ wget -cv http://archive.cloudera.com/cdh4/one-click-install/precise/amd64/cdh4-repository_1.0_all.deb
nipra@lambda:Downloads$ sudo dpkg -i cdh4-repository_1.0_all.deb # Adds /etc/apt/sources.list.d/cloudera-cdh4.list ??
nipra@lambda:Downloads$ dpkg -L cdh4-repository                  # To view the files on Ubuntu systems

# Install CDH4