ceteri

bash-3.2$ java -version
java version "1.6.0_33"
Java(TM) SE Runtime Environment (build 1.6.0_33-b03-424-11M3720)
Java HotSpot(TM) 64-Bit Server VM (build 20.8-b03-424, mixed mode)
bash-3.2$ hadoop -version
Warning: $HADOOP_HOME is deprecated.

java version "1.6.0_33"
Java(TM) SE Runtime Environment (build 1.6.0_33-b03-424-11M3720)
Java HotSpot(TM) 64-Bit Server VM (build 20.8-b03-424, mixed mode)

ceteri

import com.twitter.scalding._

class Example3(args : Args) extends Job(args) {
  Tsv(args("doc"), ('doc_id, 'text), skipHeader = true)
    .read
    .flatMap('text -> 'token) { text : String => text.split("[ \\[\\]\\(\\),.]") }
    .mapTo('token -> 'token) { token : String => scrub(token) }
    .filter('token) { token : String => token.length > 0 }
    .groupBy('token) { _.size('count) }
    .write(Tsv(args("wc"), writeHeader = true))

ceteri

bash-3.2$ lein repl
Listening for transport dt_socket at address: 51539
nREPL server started on port 51542
REPL-y 0.1.0-beta10
Clojure 1.4.0
    Exit: Control+D or (exit) or (quit)
Commands: (user/help)
    Docs: (doc function-name-here)
          (find-doc "part-of-name-here")
  Source: (source function-name-here)

ceteri

bash-3.2$ pwd
/Users/ceteri/src/concur/pattern
bash-3.2$ java -version
java version "1.6.0_43"
Java(TM) SE Runtime Environment (build 1.6.0_43-b01-447-11M4203)
Java HotSpot(TM) 64-Bit Server VM (build 20.14-b01-447, mixed mode)
bash-3.2$ hadoop version
Warning: $HADOOP_HOME is deprecated.

Hadoop 1.0.3

ceteri

bash-3.2$ lein version
Leiningen 2.0.0-preview10 on Java 1.6.0_43 Java HotSpot(TM) 64-Bit Server VM
bash-3.2$ hadoop version
Warning: $HADOOP_HOME is deprecated.

Hadoop 1.0.3
Subversion https://svn.apache.org/repos/asf/hadoop/common/branches/branch-1.0 -r 1335192
Compiled by hortonfo on Tue May  8 20:31:25 UTC 2012
From source with checksum e6b0c1e23dcf76907c5fecb4b832f3be
bash-3.2$ lein clean

ceteri

bash-3.2$ lein do sub install, deps, compile, repl
Could not find artifact lein-newnew:lein-newnew:pom:0.3.5 in central (http://repo1.maven.org/maven2)
Retrieving lein-newnew/lein-newnew/0.3.5/lein-newnew-0.3.5.pom (3k)
    from https://clojars.org/repo/
Could not find artifact stencil:stencil:pom:0.3.0 in central (http://repo1.maven.org/maven2)
Retrieving stencil/stencil/0.3.0/stencil-0.3.0.pom (3k)
    from https://clojars.org/repo/
Retrieving org/clojure/clojure/1.3.0/clojure-1.3.0.pom (5k)
    from http://repo1.maven.org/maven2/
Retrieving org/sonatype/oss/oss-parent/5/oss-parent-5.pom (4k)

drewlanenga

<?xml version="1.0"?>
<PMML version="4.1" xmlns="http://www.dmg.org/PMML-4_1" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.dmg.org/PMML-4_1 http://www.dmg.org/v4-1/pmml-4-1.xsd">
 <Header copyright="Copyright (c) 2014 lanenga" description="Linear Regression Model">
  <Extension name="user" value="lanenga" extender="Rattle/PMML"/>
  <Application name="Rattle/PMML" version="1.4"/>
  <Timestamp>2014-01-07 15:33:34</Timestamp>
 </Header>
 <DataDictionary numberOfFields="4">
  <DataField name="sepal_width" optype="continuous" dataType="double"/>
  <DataField name="sepal_length" optype="continuous" dataType="double"/>

ccsevers

package cascading.avro.examples;

import java.util.Properties;

import cascading.flow.Flow;
import cascading.flow.FlowDef;
import cascading.flow.hadoop.HadoopFlowConnector;
import cascading.operation.aggregator.Count;
import cascading.operation.regex.RegexFilter;
import cascading.operation.regex.RegexSplitGenerator;

porterjamesj

import logging
import uuid
import time

from mesos.interface import Scheduler
from mesos.native import MesosSchedulerDriver
from mesos.interface import mesos_pb2

logging.basicConfig(level=logging.INFO)

jakevdp