vitillo

library(dplyr)
library(reshape)
library(doMC)
library(caret)

trim.leading <- function (x) sub("^\\s+", "", x)
trim.trailing <- function (x) sub("\\s+$", "", x)
trim <- function (x) gsub("^\\s+|\\s+$", "", x)

registerDoMC(8)

vitillo

{
 "metadata": {
  "name": "",
  "signature": "sha256:081b9937ad2575f1768d01c339462ad704226fa0c6551d14934aad2abf212241"
 },
 "nbformat": 3,
 "nbformat_minor": 0,
 "worksheets": [
  {
   "cells": [

vitillo

# BHR hangs distribution and uptime correlation

library(ggplot2)
library(dplyr)

session <- read.csv("session.csv") %.% filter(uptime >= 0)

ggplot(aes(x=hangs), data=session) + 
  geom_histogram(aes(y=..density..), binwidth=1, colour="black", fill="blue") + 
  scale_x_continuous(limits=c(0, 50)) + #~ 90th quantile for sessions

vitillo

//==========================================================================
// A gentle tutorial to Spark and Telemetry
//==========================================================================

// Let's import some Spark classes
import org.apache.spark.SparkContext
import org.apache.spark.SparkContext._
import org.apache.spark.SparkConf

// ... and some json parsing utilities

vitillo

HOME=/home/hadoop
source $HOME/.bashrc

# Error message
error_msg ()
{
	echo 1>&2 "Error: $1"
}

# Parse arguments

vitillo

vitillo

vitillo

vitillo

vitillo