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);
}
}
void checkFormat(Job job) throws Exception {
TaskAttemptContext attemptContext =
new TaskAttemptContext(job.getConfiguration(), new TaskAttemptID("123", 0, false, 1, 2));
MyClassMessagePackBase64LineInputFormat format = new MyClassMessagePackBase64LineInputFormat();
FileInputFormat.setInputPaths(job, workDir);
List<InputSplit> splits = format.getSplits(job);
for (int j = 0; j < splits.size(); j++) {
RecordReader<LongWritable, MyClassWritable> reader =
format.createRecordReader(splits.get(j), attemptContext);
reader.initialize(splits.get(j), attemptContext);
int count = 0;
try {
while (reader.nextKeyValue()) {
LongWritable key = reader.getCurrentKey();
MyClassWritable val = reader.getCurrentValue();
MyClass mc = val.get();
assertEquals(mc.v, count);
assertEquals(mc.s, Integer.toString(count));
count++;
}
} finally {
reader.close();
}
}
}
public int run(String[] args) throws Exception {
Path tempDir = new Path("/user/akhfa/temp");
Configuration conf = new Configuration();
Job job = Job.getInstance(conf, "word count");
job.setJarByClass(AuthorCounter.class);
job.setMapperClass(TokenizerMapper.class);
job.setCombinerClass(IntSumReducer.class);
job.setReducerClass(IntSumReducer.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(LongWritable.class);
job.setOutputFormatClass(SequenceFileOutputFormat.class);
FileInputFormat.addInputPath(job, new Path(args[0]));
FileOutputFormat.setOutputPath(job, tempDir);
System.exit(job.waitForCompletion(true) ? 0 : 1);
return 0;
}
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 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);
}
/**
* @param args
* @throws IOException
* @throws ClassNotFoundException
* @throws InterruptedException
*/
public static void main(String[] args)
throws IOException, InterruptedException, ClassNotFoundException {
// TODO Auto-generated method stub
Configuration conf = new Configuration();
// conf.set("inParameter", args[0]);
Job job = new Job(conf, "MovieGenreIdentifier");
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(IntWritable.class);
job.setJarByClass(UserIdForAge.class);
job.setMapperClass(Map.class);
job.setCombinerClass(Reduce.class);
job.setReducerClass(Reduce.class);
job.setInputFormatClass(TextInputFormat.class);
job.setOutputFormatClass(TextOutputFormat.class);
FileInputFormat.addInputPath(job, new Path(args[1]));
FileOutputFormat.setOutputPath(job, new Path(args[2]));
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;
}
@Override
public int run(String[] args) throws Exception {
String locatorHost = args[0];
int locatorPort = Integer.parseInt(args[1]);
String hdfsHomeDir = args[2];
System.out.println(
"KnownKeysMRv2 invoked with args (locatorHost = "
+ locatorHost
+ " locatorPort = "
+ locatorPort
+ " hdfsHomeDir = "
+ hdfsHomeDir);
Configuration conf = getConf();
conf.set(GFInputFormat.INPUT_REGION, "partitionedRegion");
conf.set(GFInputFormat.HOME_DIR, hdfsHomeDir);
conf.setBoolean(GFInputFormat.CHECKPOINT, false);
conf.set(GFOutputFormat.REGION, "validationRegion");
conf.set(GFOutputFormat.LOCATOR_HOST, locatorHost);
conf.setInt(GFOutputFormat.LOCATOR_PORT, locatorPort);
Job job = Job.getInstance(conf, "knownKeysMRv2");
job.setInputFormatClass(GFInputFormat.class);
job.setOutputFormatClass(GFOutputFormat.class);
job.setMapperClass(KnownKeysMRv2Mapper.class);
job.setMapOutputKeyClass(GFKey.class);
job.setMapOutputValueClass(PEIWritable.class);
job.setReducerClass(KnownKeysMRv2Reducer.class);
// job.setOutputKeyClass(String.class);
// job.setOutputValueClass(ValueHolder.class);
return job.waitForCompletion(false) ? 0 : 1;
}
public static void main(String[] args)
throws IOException, ClassNotFoundException, InterruptedException {
Configuration conf = new Configuration();
Job job = new Job(conf, "job");
job.setJarByClass(PVidConvert.class);
job.setMapperClass(Map1.class);
job.setReducerClass(Reduce1.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(Text.class);
FileInputFormat.addInputPath(job, new Path(args[0]));
FileOutputFormat.setOutputPath(job, new Path("/tmp/temporary_execution/"));
job.waitForCompletion(true);
Configuration conf1 = new Configuration();
Job job1 = new Job(conf1, "job1");
job1.setJarByClass(PVidConvert.class);
job1.setMapperClass(Map2.class);
job1.setReducerClass(Reduce2.class);
job1.setOutputKeyClass(Text.class);
job1.setOutputValueClass(Text.class);
FileInputFormat.addInputPath(job1, new Path("/tmp/temporary_execution/"));
FileOutputFormat.setOutputPath(job1, new Path(args[1]));
job1.waitForCompletion(true);
}
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 runJob(String mysqlJar, String output) throws Exception {
Configuration conf = new Configuration();
JobHelper.addJarForJob(conf, mysqlJar);
DBConfiguration.configureDB(
conf,
"com.mysql.jdbc.Driver",
"jdbc:mysql://localhost/sqoop_test" + "?user=hip_sqoop_user&password=password");
Job job = new Job(conf);
job.setJarByClass(DBImportExportMapReduce.class);
job.setMapperClass(Map.class);
job.setReducerClass(Reduce.class);
job.setInputFormatClass(DBInputFormat.class);
job.setOutputFormatClass(DBOutputFormat.class);
job.setMapOutputKeyClass(StockRecord.class);
job.setMapOutputValueClass(NullWritable.class);
job.setOutputKeyClass(StockRecord.class);
job.setOutputValueClass(NullWritable.class);
job.getConfiguration().setInt("mapred.map.tasks", 4);
job.setNumReduceTasks(4);
DBInputFormat.setInput(
job, StockRecord.class, "select * from stocks", "SELECT COUNT(id) FROM stocks");
DBOutputFormat.setOutput(job, "stocks_export", StockRecord.fields);
Path outputPath = new Path(output);
FileOutputFormat.setOutputPath(job, outputPath);
outputPath.getFileSystem(conf).delete(outputPath, true);
job.waitForCompletion(true);
}
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 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 X(String input, String output, Configuration config, FileSystem hdfs) throws Exception {
Job job = new Job(config);
job.setJarByClass(codesquare.badges.badge_21_22_23.Pass2.class);
job.setJobName("");
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(Text.class);
job.setMapperClass(Map.class);
job.setReducerClass(Reduce.class);
job.setNumReduceTasks(1);
job.setInputFormatClass(TextInputFormat.class);
job.setOutputFormatClass(TextOutputFormat.class);
FileInputFormat.addInputPath(job, new Path("/user/interns/Extras/bossList.txt"));
FileOutputFormat.setOutputPath(job, new Path(output));
try {
job.waitForCompletion(true);
} catch (IOException e) {
System.out.println("No Input Paths to run this MapReduce on!");
}
}
@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 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;
}
public static void main(String[] args) throws Exception {
final String NAME_NODE = "hdfs://sandbox.hortonworks.com:8020";
Configuration conf = new Configuration();
Job job = Job.getInstance(conf);
job.setJarByClass(WordCount.class);
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(IntWritable.class);
job.setOutputKeyClass(IntWritable.class);
job.setOutputValueClass(NullWritable.class);
if (args.length > 2) {
job.setNumReduceTasks(Integer.parseInt(args[2]));
}
job.setMapperClass(CountMapper.class);
job.setReducerClass(CountReducer.class);
job.setJarByClass(WordCount.class);
job.setNumReduceTasks(1);
FileInputFormat.addInputPath(job, new Path(args[0] + "data/plot_summaries.txt"));
FileSystem fs = FileSystem.get(conf);
// handle (e.g. delete) existing output path
Path outputDestination = new Path(args[0] + args[1]);
if (fs.exists(outputDestination)) {
fs.delete(outputDestination, true);
}
// set output path & start job1
FileOutputFormat.setOutputPath(job, outputDestination);
int jobCompletionStatus = job.waitForCompletion(true) ? 0 : 1;
}
