jgulum

package example;

import java.io.IOException;

import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;

/* 
 * To define a reduce function for your MapReduce job, subclass 

jgulum

package example;

import java.io.IOException;

import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;

/* 

jgulum

package example;

import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.mapreduce.Job;

/* 

jgulum

<?xml version="1.0" encoding="UTF-8"?>

<project name="empdata_mrjob" default="run" basedir=".">
	<target name="init">
			
		<property name="src.dir" value="java/src" />
		<property name="build.dir" value="java/build" />
		<property name="dist.dir" value="java/dist" />
		<property name="hdfs.output.dir" value="/user/training/empcounts_java" />

jgulum

#!/bin/sh

# Path of Hadoop streaming JAR library
STREAMJAR=/usr/lib/hadoop-0.20-mapreduce/contrib/streaming/hadoop-streaming-*.jar

# Directory in which we'll store job output
OUTPUT=/user/training/empcounts

# Make sure we don't have output from a previous run.
# The -r option removes the directory recursively, and

jgulum

#!/usr/bin/env python

import sys

previous_state = ''
count_for_state = 0

for line in sys.stdin:
   line = line.strip()

jgulum

#!/usr/bin/env python

import sys

for line in sys.stdin:
   line = line.strip()
   (id, fname, lname, addr, city, state, zip, job, email, active, salary) = line.split("\t")

   if int(salary) >= 75000:
      print "%s,1" % state