Lecture 26: Pig: Making Hadoop Easy (Some Slides provided by: Alan Gates, Yahoo!Research) Friday, Dec 3, 2010 Dan Suciu -- 444 Spring 2010 1- 2 - What is Pig? • An engine for executing programs on top of Hadoop • It provides a language, Pig Latin, to specify these programs • An Apache open source project http://hadoop.apache.org/pig/- 3 - Map-Reduce • Computation is moved to the data • A simple yet powerful programming model – Map: every record handled individually – Shuffle: records collected by key – Reduce: key and iterator of all associated values • User provides: – input and output (usually files) – map Java function – key to aggregate on – reduce Java function • Opportunities for more control: partitioning, sorting, partial aggregations, etc.- 4 - Map Reduce Illustrated map reduce map reduce Romeo, Romeo, wherefore art thou Romeo? Romeo, 1 Romeo, 1 wherefore, 1 art, 1 thou, 1 Romeo, 1 art, (1, 1) hurt (1), thou (1, 1) art, 2 hurt, 1 thou, 2 What, art thou hurt? What, 1 art, 1 thou, 1 hurt, 1 Romeo, (1, 1, 1) wherefore, (1) what, (1) Romeo, 3 wherefore, 1 what, 1- 5 - Making Parallelism Simple • Sequential reads = good read speeds • In large cluster failures are guaranteed; Map Reduce handles retries • Good fit for batch processing applications that need to touch all your data: – data mining – model tuning • Bad fit for applications that need to find one particular record • Bad fit for applications that need to communicate between processes; oriented around independent units of work- 6 - Why use Pig? Suppose you have user data in one file, website data in another, and you need to find the top 5 most visited sites by users aged 18 - 25. Load Users Load Pages Filter by age Join on name Group on url Count clicks Order by clicks Take top 5- 7 - In Map-Reduce import java.io.IOException; import java.util.ArrayList; import java.util.Iterator; import java.util.List; import org.apache.hadoop.fs.Path; import org.apache.hadoop.io.LongWritable; import org.apache.hadoop.io.Text; import org.apache.hadoop.io.Writable; import org.apache.hadoop.io.WritableComparable; import org.apache.hadoop.mapred.FileInputFormat; import org.apache.hadoop.mapred.FileOutputFormat; import org.apache.hadoop.mapred.JobConf; import org.apache.hadoop.mapred.KeyValueTextInputFormat; import org.apache.hadoop.mapred.Mapper; import org.apache.hadoop.mapred.MapReduceBase; import org.apache.hadoop.mapred.OutputCollector; import org.apache.hadoop.mapred.RecordReader; import org.apache.hadoop.mapred.Reducer; import org.apache.hadoop.mapred.Reporter; import org.apache.hadoop.mapred.SequenceFileInputFormat; import org.apache.hadoop.mapred.SequenceFileOutputFormat; import org.apache.hadoop.mapred.TextInputFormat; import org.apache.hadoop.mapred.jobcontrol.Job; import org.apache.hadoop.mapred.jobcontrol.JobControl; import org.apache.hadoop.mapred.lib.IdentityMapper; public class MRExample { public static class LoadPages extends MapReduceBase implements Mapper<LongWritable, Text, Text, Text> { public void map(LongWritable k, Text val, OutputCollector<Text, Text> oc, Reporter reporter) throws IOException { // Pull the key out String line = val.toString(); int firstComma = line.indexOf(','); String key = line.substring(0, firstComma); String value = line.substring(firstComma + 1); Text outKey = new Text(key); // Prepend an index to the value so we know which file // it came from. Text outVal = new Text("1" + value); oc.collect(outKey, outVal); } } public static class LoadAndFilterUsers extends MapReduceBase implements Mapper<LongWritable, Text, Text, Text> { public void map(LongWritable k, Text val, OutputCollector<Text, Text> oc, Reporter reporter) throws IOException { // Pull the key out String line = val.toString(); int firstComma = line.indexOf(','); String value = line.substring(firstComma + 1); int age = Integer.parseInt(value); if (age < 18 || age > 25) return; String key = line.substring(0, firstComma); Text outKey = new Text(key); // Prepend an index to the value so we know which file // it came from. Text outVal = new Text("2" + value); oc.collect(outKey, outVal); } } public static class Join extends MapReduceBase implements Reducer<Text, Text, Text, Text> { public void reduce(Text key, Iterator<Text> iter, OutputCollector<Text, Text> oc, Reporter reporter) throws IOException { // For each value, figure out which file it's from and store it // accordingly. List<String> first = new ArrayList<String>(); List<String> second = new ArrayList<String>(); while (iter.hasNext()) { Text t = iter.next(); String value = t.toString(); if (value.charAt(0) == '1') first.add(value.substring(1)); else second.add(value.substring(1)); reporter.setStatus("OK"); } // Do the cross product and collect the values for (String s1 : first) { for (String s2 : second) { String outval = key + "," + s1 + "," + s2; oc.collect(null, new Text(outval)); reporter.setStatus("OK"); } } } } public static class LoadJoined extends MapReduceBase implements Mapper<Text, Text, Text, LongWritable> { public void map( Text k, Text val, OutputCollector<Text, LongWritable> oc, Reporter reporter) throws IOException { // Find the url String line = val.toString(); int firstComma = line.indexOf(','); int secondComma = line.indexOf(',', firstComma); String key = line.substring(firstComma, secondComma); // drop the rest of the record, I don't need it anymore, // just pass a 1 for the combiner/reducer to sum instead. Text outKey = new Text(key); oc.collect(outKey, new LongWritable(1L)); } } public static class ReduceUrls extends MapReduceBase implements Reducer<Text, LongWritable, WritableComparable, Writable> { public void reduce( Text key, Iterator<LongWritable> iter, OutputCollector<WritableComparable, Writable> oc, Reporter reporter) throws IOException { // Add up all the values we see long sum = 0; while (iter.hasNext()) { sum += iter.next().get(); reporter.setStatus("OK"); } oc.collect(key, new LongWritable(sum)); } } public static class LoadClicks extends MapReduceBase implements Mapper<WritableComparable, Writable,
View Full Document