actsasflinn

--- kcthread.cc.orig	2010-04-01 22:59:17.000000000 -0400
+++ kcthread.cc	2010-04-01 23:04:41.000000000 -0400
@@ -178,12 +178,12 @@ Mutex::Mutex(Type type) {
       break;
     }
     case ERRORCHECK: {
-      if (::pthread_mutexattr_settype(&attr, ::PTHREAD_MUTEX_ERRORCHECK) != 0)
+      if (::pthread_mutexattr_settype(&attr, PTHREAD_MUTEX_ERRORCHECK) != 0)
         throw std::runtime_error("pthread_mutexattr_settype");
       break;

actsasflinn

package client;

import org.apache.log4j.AppenderSkeleton;
import org.apache.log4j.Layout;
import org.apache.log4j.Level;
import org.apache.log4j.helpers.CyclicBuffer;
import org.apache.log4j.helpers.LogLog;
import org.apache.log4j.helpers.OptionConverter;
import org.apache.log4j.spi.ErrorCode;
import org.apache.log4j.spi.LoggingEvent;

actsasflinn

function doHash(str, seed) {
  var m = 0x5bd1e995;
  var r = 24;
  var h = seed ^ str.length;
  var length = str.length;
  var currentIndex = 0;
  
  while (length >= 4) {
    var k = UInt32(str, currentIndex);
    

actsasflinn

# Vagrantfile API/syntax version. Don't touch unless you know what you're doing!
VAGRANTFILE_API_VERSION = "2"

Vagrant.configure(VAGRANTFILE_API_VERSION) do |config|
  config.vm.box = "hdp_vm"
  config.vm.box_url = "http://opscode-vm-bento.s3.amazonaws.com/vagrant/virtualbox/opscode_centos-6.7_chef-provisionerless.box"

$script = <<SCRIPT
sudo yum -y install ntp
sudo yum -y install wget

actsasflinn

create table cars_rowid as
select
  regexp_replace(reflect('java.util.UUID','randomUUID'), '-', '') as rowid,
  *
from flinn.cars;
  

create or replace view cars_train as
select
  rowid,

actsasflinn

-----------------------------------------------------------------------------
-- Hivemall: Hive scalable Machine Learning Library
-----------------------------------------------------------------------------

-- CREATE DATABASE IF NOT EXISTS hivemall;
-- USE hivemall;
-- set hivevar:hivemall_jar=hdfs:///apps/hivemall/hivemall-with-dependencies.jar;

DROP FUNCTION IF EXISTS hivemall_version;
CREATE FUNCTION hivemall_version as 'hivemall.HivemallVersionUDF' USING JAR '${hivemall_jar}';

actsasflinn

hadoop fs -mkdir -p /apps/hivemall
hadoop fs -put hivemall-0.3.2-3-with-dependencies.jar /apps/hivemall
curl -L -O https://github.com/myui/hivemall/releases/download/v0.3.2-3/hivemall-0.3.2-3-with-dependencies.jar
curl -L -O https://raw.githubusercontent.com/myui/hivemall/v0.3.2-3/scripts/ddl/define-all-as-permanent.hive

CREATE DATABASE IF NOT EXISTS hivemall0323;
USE hivemall0323;

set hivevar:hivemall_jar=hdfs:///apps/hivemall/hivemall-0.3.2-3-with-dependencies.jar;
source /home/hdfs/define-all-as-permanent.hive;

actsasflinn

import java.io.*;
import org.apache.pdfbox.pdmodel.*;
import org.apache.pdfbox.util.*;
import org.apache.pdfbox.exceptions.*;
import java.util.regex.*;

class Split {
    public static void main(String[] args) throws IOException, COSVisitorException {
        File input = new File("example.pdf");

actsasflinn

require 'java'
require './pdfbox-1.8.13.jar'
require './fontbox-1.8.13.jar'
require './commons-logging-1.2.jar'

input = java.io.File.new("example.pdf")
inputDocument = org.apache.pdfbox.pdmodel.PDDocument::loadNonSeq(input, nil)
stripper = org.apache.pdfbox.util.PDFTextStripper.new
outputDocument = org.apache.pdfbox.pdmodel.PDDocument.new

actsasflinn

library(xgboost)
library(Matrix)

setwd("~/Projects/xgboost_test")
train_file = "train_data"
if (!file.exists(train_file)) {
  download.file("https://archive.ics.uci.edu/ml/machine-learning-databases/adult/adult.data", train_file)
}
test_file = "test_data"
if (!file.exists(test_file)) {