/*
* Cloud9: A Hadoop toolkit for working with big data
*
* Licensed under the Apache License, Version 2.0 (the "License"); you
* may not use this file except in compliance with the License. You may
* obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
* implied. See the License for the specific language governing
* permissions and limitations under the License.
*/
package edu.umd.cloud9.example.cooccur;
import java.io.IOException;
import java.util.Arrays;
import java.util.Iterator;
import org.apache.commons.cli.CommandLine;
import org.apache.commons.cli.CommandLineParser;
import org.apache.commons.cli.GnuParser;
import org.apache.commons.cli.HelpFormatter;
import org.apache.commons.cli.OptionBuilder;
import org.apache.commons.cli.Options;
import org.apache.commons.cli.ParseException;
import org.apache.hadoop.conf.Configured;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.Partitioner;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;
import org.apache.log4j.Logger;
import tl.lin.data.pair.PairOfStrings;
/**
* <p>
* Implementation of the "pairs" algorithm for computing co-occurrence matrices from a large text
* collection. This algorithm is described in Chapter 3 of "Data-Intensive Text Processing with
* MapReduce" by Lin & Dyer, as well as the following paper:
* </p>
*
* <blockquote>Jimmy Lin. <b>Scalable Language Processing Algorithms for the Masses: A Case Study in
* Computing Word Co-occurrence Matrices with MapReduce.</b> <i>Proceedings of the 2008 Conference
* on Empirical Methods in Natural Language Processing (EMNLP 2008)</i>, pages 419-428.</blockquote>
*
* @author Jimmy Lin
*/
public class ComputeCooccurrenceMatrixPairs extends Configured implements Tool {
private static final Logger LOG = Logger.getLogger(ComputeCooccurrenceMatrixPairs.class);
private static class MyMapper extends Mapper<LongWritable, Text, PairOfStrings, IntWritable> {
private static final PairOfStrings PAIR = new PairOfStrings();
private static final IntWritable ONE = new IntWritable(1);
private int window = 2;
@Override
public void setup(Context context) {
window = context.getConfiguration().getInt("window", 2);
}
@Override
public void map(LongWritable key, Text line, Context context)
throws IOException, InterruptedException {
String text = line.toString();
String[] terms = text.split("\\s+");
for (int i = 0; i < terms.length; i++) {
String term = terms[i];
// skip empty tokens
if (term.length() == 0)
continue;
for (int j = i - window; j < i + window + 1; j++) {
if (j == i || j < 0)
continue;
if (j >= terms.length)
break;
// skip empty tokens
if (terms[j].length() == 0)
continue;
PAIR.set(term, terms[j]);
context.write(PAIR, ONE);
}
}
}
}
private static class MyReducer extends
Reducer<PairOfStrings, IntWritable, PairOfStrings, IntWritable> {
private final static IntWritable SUM = new IntWritable();
@Override
public void reduce(PairOfStrings key, Iterable<IntWritable> values, Context context)
throws IOException, InterruptedException {
Iterator<IntWritable> iter = values.iterator();
int sum = 0;
while (iter.hasNext()) {
sum += iter.next().get();
}
SUM.set(sum);
context.write(key, SUM);
}
}
protected static class MyPartitioner extends Partitioner<PairOfStrings, IntWritable> {
@Override
public int getPartition(PairOfStrings key, IntWritable value, int numReduceTasks) {
return (key.getLeftElement().hashCode() & Integer.MAX_VALUE) % numReduceTasks;
}
}
/**
* Creates an instance of this tool.
*/
public ComputeCooccurrenceMatrixPairs() {}
private static final String INPUT = "input";
private static final String OUTPUT = "output";
private static final String WINDOW = "window";
private static final String NUM_REDUCERS = "numReducers";
/**
* Runs this tool.
*/
@SuppressWarnings({ "static-access" })
public int run(String[] args) throws Exception {
Options options = new Options();
options.addOption(OptionBuilder.withArgName("path").hasArg()
.withDescription("input path").create(INPUT));
options.addOption(OptionBuilder.withArgName("path").hasArg()
.withDescription("output path").create(OUTPUT));
options.addOption(OptionBuilder.withArgName("num").hasArg()
.withDescription("window size").create(WINDOW));
options.addOption(OptionBuilder.withArgName("num").hasArg()
.withDescription("number of reducers").create(NUM_REDUCERS));
CommandLine cmdline;
CommandLineParser parser = new GnuParser();
try {
cmdline = parser.parse(options, args);
} catch (ParseException exp) {
System.err.println("Error parsing command line: " + exp.getMessage());
return -1;
}
if (!cmdline.hasOption(INPUT) || !cmdline.hasOption(OUTPUT)) {
System.out.println("args: " + Arrays.toString(args));
HelpFormatter formatter = new HelpFormatter();
formatter.setWidth(120);
formatter.printHelp(this.getClass().getName(), options);
ToolRunner.printGenericCommandUsage(System.out);
return -1;
}
String inputPath = cmdline.getOptionValue(INPUT);
String outputPath = cmdline.getOptionValue(OUTPUT);
int reduceTasks = cmdline.hasOption(NUM_REDUCERS) ?
Integer.parseInt(cmdline.getOptionValue(NUM_REDUCERS)) : 1;
int window = cmdline.hasOption(WINDOW) ? Integer.parseInt(cmdline.getOptionValue(WINDOW)) : 2;
LOG.info("Tool: " + ComputeCooccurrenceMatrixPairs.class.getSimpleName());
LOG.info(" - input path: " + inputPath);
LOG.info(" - output path: " + outputPath);
LOG.info(" - window: " + window);
LOG.info(" - number of reducers: " + reduceTasks);
Job job = Job.getInstance(getConf());
job.setJobName(ComputeCooccurrenceMatrixPairs.class.getSimpleName());
job.setJarByClass(ComputeCooccurrenceMatrixPairs.class);
// Delete the output directory if it exists already.
Path outputDir = new Path(outputPath);
FileSystem.get(getConf()).delete(outputDir, true);
job.getConfiguration().setInt("window", window);
job.setNumReduceTasks(reduceTasks);
FileInputFormat.setInputPaths(job, new Path(inputPath));
FileOutputFormat.setOutputPath(job, new Path(outputPath));
job.setMapOutputKeyClass(PairOfStrings.class);
job.setMapOutputValueClass(IntWritable.class);
job.setOutputKeyClass(PairOfStrings.class);
job.setOutputValueClass(IntWritable.class);
job.setMapperClass(MyMapper.class);
job.setCombinerClass(MyReducer.class);
job.setReducerClass(MyReducer.class);
job.setPartitionerClass(MyPartitioner.class);
long startTime = System.currentTimeMillis();
job.waitForCompletion(true);
System.out.println("Job Finished in " + (System.currentTimeMillis() - startTime) / 1000.0 + " seconds");
return 0;
}
/**
* Dispatches command-line arguments to the tool via the {@code ToolRunner}.
*/
public static void main(String[] args) throws Exception {
ToolRunner.run(new ComputeCooccurrenceMatrixPairs(), args);
}
}