ceteri

bash-3.2$ ls
README.md		build.gradle		cascading.pattern.ipr	data			model.log		src
build			cascading.pattern.iml	cascading.pattern.iws	dot			output
bash-3.2$ more output/
classify/ measure/  
bash-3.2$ more output/measure/
output/measure/ is a directory
bash-3.2$ more output/measure/part-00000 
label   score   count
0       0       73

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

package example;

import java.util.Properties;

import cascading.flow.Flow;
import cascading.flow.FlowDef;
import cascading.flow.hadoop.HadoopFlowConnector;
import cascading.pipe.CoGroup;
import cascading.pipe.Pipe;
import cascading.pipe.assembly.CountBy;

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

import java.sql.Connection;
import java.sql.DriverManager;
import java.sql.ResultSet;
import java.sql.SQLException;
import java.sql.Statement;

public class JdbcExample
  {
  public static void main( String[] args ) throws Exception
    {

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)

ceteri

bash-3.2$ git show | head
commit d78b48fffff32898a9f76e94923d45a84d7e330e
Author: Paco Nathan <ceteri@gmail.com>
Date:   Sat Mar 16 19:11:46 2013 -0700

    fixed cmd line opts to allow for a different label field, for the confusion matrix calculation

diff --git a/README.md b/README.md
index ed10626..2e8996e 100644
--- a/README.md

ceteri

print(__doc__)

from time import time
import numpy as np
import pylab as pl

from sklearn import metrics
from sklearn.cluster import KMeans
from sklearn.datasets import load_digits
from sklearn.decomposition import PCA