public static void main(String[] args) throws Exception {
Configuration conf = new Configuration();
String[] remainArgs = new GenericOptionsParser(conf, args).getRemainingArgs();
if (remainArgs.length != 2) {
System.err.println("Usage: wordcount <input> <output>");
System.exit(1);
}
Job job = new Job(conf, "wordcount");
job.setJarByClass(WordCount.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(IntWritable.class);
job.setMapperClass(Map.class);
job.setCombinerClass(Reduce.class);
job.setReducerClass(Reduce.class);
job.setNumReduceTasks(4);
job.setInputFormatClass(TextInputFormat.class);
job.setOutputFormatClass(TextOutputFormat.class);
FileSystem.get(conf).delete(new Path(remainArgs[1]), true);
FileInputFormat.setInputPaths(job, new Path(remainArgs[0]));
FileOutputFormat.setOutputPath(job, new Path(remainArgs[1]));
System.exit(job.waitForCompletion(true) ? 0 : 1);
}
public static void main(String[] args) throws Exception {
String inputDirectory = "/home/cs246/Desktop/HW2/input";
String outputDirectory = "/home/cs246/Desktop/HW2/output";
String centroidDirectory = "/home/cs246/Desktop/HW2/config";
int iterations = 20;
for (int i = 1; i <= iterations; i++) {
Configuration conf = new Configuration();
String cFile = centroidDirectory + "/c" + i + ".txt";
String nextCFile = centroidDirectory + "/c" + (i + 1) + ".txt";
conf.set("CFILE", cFile);
conf.set("NEXTCFILE", nextCFile);
String cFile = centroidDirectory + "/c" + i + ".txt";
String nextCFile = centroidDirectory + "/c" + (i + 1) + ".txt";
conf.set("CFILE", cFile);
conf.set("NEXTCFILE", nextCFile);
Job job = new Job(conf, "HW2_Q4." + i);
job.setJarByClass(HW2_Q4.class);
job.setOutputKeyClass(IntWritable.class);
job.setOutputValueClass(Text.class);
job.setMapperClass(Map1.class);
job.setReducerClass(Reduce1.class);
job.setInputFormatClass(TextInputFormat.class);
job.setOutputFormatClass(TextOutputFormat.class);
FileInputFormat.addInputPath(job, new Path(inputDirectory));
FileOutputFormat.setOutputPath(job, new Path(outputDirectory + "/output" + i));
job.waitForCompletion(true);
}
}
@Override
public int run(String[] arg0) throws Exception {
// config a job and start it
Configuration conf = getConf();
Job job = new Job(conf, "Index construction..");
job.setJarByClass(IndexConstructorDriver.class);
job.setMapperClass(IndexConstructorMapper.class);
job.setReducerClass(IndexConstructorReducer.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(InvertedListWritable.class);
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(Text.class);
job.setInputFormatClass(SequenceFileInputFormat.class);
job.setOutputFormatClass(SequenceFileOutputFormat.class);
// can add the dir by the config
FileSystem fs = FileSystem.get(conf);
String workdir = conf.get("org.joy.crawler.dir", "crawler/");
fs.delete(new Path(workdir + "indexOutput/"), true);
FileInputFormat.addInputPath(job, new Path(workdir + "content/"));
FileOutputFormat.setOutputPath(job, new Path(workdir + "indexOutput/"));
System.out.println(
"indexer starts to work, it begins to construct the index, please wait ...\n");
return job.waitForCompletion(true) ? 0 : 1;
}
public static void main(String args[]) throws Exception {
Configuration c = new Configuration();
if (args.length != 2) {
System.out.println("provide sufficient arguments");
System.exit(-1);
}
Job job = Job.getInstance(c, "Wordcount");
job.setJarByClass(Wordcount.class);
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(IntWritable.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(Text.class);
job.setMapperClass(Map.class);
job.setReducerClass(Reduce.class);
job.setInputFormatClass(TextInputFormat.class);
job.setOutputFormatClass(TextOutputFormat.class);
FileInputFormat.addInputPath(job, new Path(args[0]));
FileOutputFormat.setOutputPath(job, new Path(args[1]));
// job.submit();
job.waitForCompletion(true);
}
public static void main(String[] args) throws Exception {
Job job = new Job();
job.setJarByClass(Sort.class);
job.setJobName("Sort");
FileInputFormat.addInputPath(job, new Path("hdfs://localhost:9000/input/"));
FileOutputFormat.setOutputPath(job, new Path("hdfs://localhost:9000/output/"));
job.setMapperClass(Map.class);
// job.setCombinerClass(Reduce.class);
job.setReducerClass(Reduce.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(IntWritable.class);
job.setNumReduceTasks(2);
System.exit(job.waitForCompletion(true) ? 0 : 1);
}
public int run(String[] args) throws Exception {
Job job = new Job(getConf());
job.setJarByClass(HadoopNBFilter.class);
job.setJobName("hadoopnbfilter");
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(IntWritable.class);
job.setMapperClass(Map.class);
job.setReducerClass(Reduce.class);
job.setInputFormatClass(TextInputFormat.class);
job.setOutputFormatClass(TextOutputFormat.class);
job.setNumReduceTasks(Integer.parseInt(args[2]));
FileInputFormat.setInputPaths(job, new Path(args[0]));
FileOutputFormat.setOutputPath(job, new Path(args[1]));
boolean jobCompleted = job.waitForCompletion(true);
return jobCompleted ? 0 : 1;
}
public static void main(String[] args) throws Exception {
Configuration conf = new Configuration();
Job job = new Job(conf, "wordcount");
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(IntWritable.class);
job.setMapperClass(TopMapper.class);
job.setReducerClass(TopReducer.class);
job.setInputFormatClass(TextInputFormat.class);
job.setOutputFormatClass(TextOutputFormat.class);
job.setNumReduceTasks(1);
job.setJarByClass(WordCount_e3.class);
FileInputFormat.addInputPath(job, new Path(args[0]));
FileOutputFormat.setOutputPath(job, new Path(args[1]));
job.waitForCompletion(true);
}
@Override
public int run(String[] args) throws Exception {
Job job = new Job(getConf());
job.setJarByClass(ElimiateRepeat.class);
job.setJobName("ElimiateRepeat");
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(IntWritable.class);
job.setMapperClass(Map.class);
job.setReducerClass(Reduce.class);
job.setInputFormatClass(TextInputFormat.class);
job.setOutputFormatClass(TextOutputFormat.class);
FileInputFormat.setInputPaths(job, new Path("file0*"));
FileOutputFormat.setOutputPath(job, new Path("elimiateRepeat"));
boolean success = job.waitForCompletion(true);
return success ? 0 : 1;
}
public int run(String args[]) throws Exception {
Configuration conf = getConf();
/* creates a new job with given job name */
Job job = Job.getInstance(conf, "Mat_vect_mul");
job.setJarByClass(Mat_vect_mul.class);
/* adds input-vector file to the cache */
DistributedCache.addCacheFile(new Path(args[1]).toUri(), job.getConfiguration());
/* set the key class and value class for the job output */
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(Text.class);
/* set mapper and reducer for the job */
job.setMapperClass(Map1.class);
job.setReducerClass(Reduce1.class);
/* set the input foramt and output format for the job */
job.setInputFormatClass(TextInputFormat.class);
job.setOutputFormatClass(TextOutputFormat.class);
/* add path to the list of inputs for the map-reduce job */
FileInputFormat.addInputPath(job, new Path(args[0]));
/* set path of the output diretcory for the map-reduce job*/
FileOutputFormat.setOutputPath(job, new Path(args[2]));
/* Submit the job, then poll for progress until the job is complete */
boolean succ = job.waitForCompletion(true);
if (!succ) {
System.out.println("Job failed, exiting");
return -1;
}
return 0;
}