natbusa

#!/usr/bin/env python
import sys

# input comes from STDIN (standard input)
for line in sys.stdin:
    #clean and split in words
    linechars = [c for c in line.lower() if c.isalpha() or c==' ']
    words     = ''.join(linechars).strip().split()

    #emit the key-balue pairs

natbusa

class ScrubFunction extends BaseOperation implements Function
  {
  public ScrubFunction( Fields fieldDeclaration )
    {
    super( 1, fieldDeclaration );
    }

  public void operate( FlowProcess flowProcess, FunctionCall functionCall )
    {
    TupleEntry argument = functionCall.getArguments();

natbusa

#!/bin/sh

#check if the directory exists on hdfs
$HADOOP_HOME/bin/hadoop fs -ls wordcount-input
if  [ $? -ne 0 ] 
  then $HADOOP_HOME/bin/hadoop fs -mkdir wordcount-input/
fi

#check if the lorem.txt exists on hdfs
$HADOOP_HOME/bin/hadoop fs -ls wordcount-input/lorem.txt

natbusa

A = load 'wordcount-input/lorem.txt' as (line:chararray);
B = foreach A generate FLATTEN(TOKENIZE(line)) as word;
C = foreach B generate LOWER(REPLACE(word,'\\W+','')) as word;
D = group C by word;
E = foreach D generate group, COUNT(C);
store E into 'wordcount-pig-output';

natbusa

class WordCount(args : Args) extends Job(args) {

  TextLine(args("input"))
    .read
    .flatMap('line -> 'word){ line : String => line.split("\\s")}
    .groupBy('word){group => group.size}
    .write(Tsv(args("output")))

}

natbusa

class AnalyticsActor extends Actor {

  def actorRefFactory = context
  val dataActor = actorRefFactory.actorOf(Props[NoSqlActor], "cassandra-client")
  val statActor = actorRefFactory.actorOf(Props[StatActor],  "statistical-engine")

  def receive = {
    case (a: String, c: String, ctx: RequestContext) =>

      val f:Future[Result] =

natbusa

@app.route('/word/<keyword>')
def fetch_word(keyword):
   db = get_cassandra()
    
   pages = []
   results = db.fetchWordResults(keyword)
   for hit in results:
      pages.append(db.fetchPageDetails(hit["url"]))

   return Response(json.dumps(pages), status=200,   

natbusa

var all = {
  //screen
  'screen.width'           : screen.width,
  'screen.height'          : screen.height,
  'screen.availWidth'      : screen.availWidth,
  'screen.availHeight'     : screen.availHeight,
  'screen.colorDepth'      : screen.colorDepth,
  'screen.pixelDepth'      : screen.pixelDepth,
  //location
  'location.href'          : location.href,

natbusa

$> cat data.txt | grep "streming is awesome" > results.txt

natbusa

from httpMethods import *

# Create the graph (profiling tags)

# get (as a http client) every 10 seconds json and emit it on
post('/api/actors',
     {
          "type":"httpclient",
          "trigger": null,      # can also be omitted altogether
          "collect":null,       # can also be omitted altogether