@Override
public int run(String[] args) throws Exception {
if (args.length != 2) {
System.err.printf(
"Usage: %s [generic options] <input> <output>\n", getClass().getSimpleName());
ToolRunner.printGenericCommandUsage(System.err);
return -1;
}
JobConf conf = new JobConf(getConf(), getClass());
conf.setJobName("Max temperature");
FileInputFormat.addInputPath(conf, new Path(args[0]));
FileOutputFormat.setOutputPath(conf, new Path(args[1]));
conf.setOutputKeyClass(Text.class);
conf.setOutputValueClass(IntWritable.class);
conf.setMapperClass(MaxTemperatureMapper.class);
conf.setCombinerClass(MaxTemperatureReducer.class);
conf.setReducerClass(MaxTemperatureReducer.class);
// vv MaxTemperatureDriverV6
conf.setProfileEnabled(true);
conf.setProfileParams(
"-agentlib:hprof=cpu=samples,heap=sites,depth=6," + "force=n,thread=y,verbose=n,file=%s");
conf.setProfileTaskRange(true, "0-2");
// ^^ MaxTemperatureDriverV6
JobClient.runJob(conf);
return 0;
}
public static void main(String[] args) throws IOException {
/*JobConf conf = new JobConf();
conf.setOutputKeyClass(Text.class);
conf.setOutputValueClass(Text.class);
conf.setInputFormat(TextInputFormat.class);
conf.setOutputFormat(TextOutputFormat.class);
conf.setMapperClass(IpCounterMapper.class);
conf.setCombinerClass(IpCounterReducer.class);
conf.setReducerClass(IpCounterReducer.class);
String inputDir = args[0];
String outputDir = args[1];
FileInputFormat.setInputPaths(conf, inputDir);
FileOutputFormat.setOutputPath(conf, new Path(outputDir));
boolean flag = JobClient.runJob(conf).isSuccessful();
System.out.println(args.length);*/
if (args.length < 2) {
System.out.println("args not right!");
return;
}
JobConf conf = new JobConf(IpCount1.class);
// set output key class
conf.setOutputKeyClass(Text.class);
conf.setOutputValueClass(Text.class);
// set mapper & reducer class
conf.setMapperClass(IpCounterMapper.class);
conf.setCombinerClass(IpCounterReducer.class);
conf.setReducerClass(IpCounterReducer.class);
// set format
conf.setInputFormat(TextInputFormat.class);
conf.setOutputFormat(TextOutputFormat.class);
String inputDir = args[0];
String outputDir = args[1];
// FileInputFormat.setInputPaths(conf, "/user/hadoop/rongxin/locationinput/");
FileInputFormat.setInputPaths(conf, inputDir);
FileOutputFormat.setOutputPath(conf, new Path(outputDir));
boolean flag = JobClient.runJob(conf).isSuccessful();
}
// Main function
public static void main(String[] args) throws Exception {
// TODO Auto-generated method stub
JobConf conf = new JobConf(ProcessUnits.class);
conf.setJobName("max_eletricityunits");
conf.setOutputKeyClass(Text.class);
conf.setOutputValueClass(IntWritable.class);
conf.setMapperClass(EE_Mapper.class);
conf.setCombinerClass(EE_Reducer.class);
conf.setReducerClass(EE_Reducer.class);
conf.setInputFormat(TextInputFormat.class);
conf.setOutputFormat(TextOutputFormat.class);
FileInputFormat.setInputPaths(conf, new Path(args[0]));
FileOutputFormat.setOutputPath(conf, new Path(args[1]));
JobClient.runJob(conf);
}
public static void main(String[] args) throws Exception {
JobConf conf = new JobConf(WordCount.class);
conf.setJobName("wordcount");
conf.setOutputKeyClass(Text.class);
conf.setOutputValueClass(IntWritable.class);
conf.setMapperClass(Map.class);
conf.setCombinerClass(Reduce.class);
conf.setReducerClass(Reduce.class);
conf.setInputFormat(TextInputFormat.class);
conf.setOutputFormat(TextOutputFormat.class);
FileInputFormat.setInputPaths(conf, new Path(args[0]));
FileOutputFormat.setOutputPath(conf, new Path(args[1]));
JobClient.runJob(conf);
}
public static void main(String args[]) throws IOException {
JobConf job = new JobConf(WordCountJob.class);
job.setJobName("Word Count Example");
FileInputFormat.setInputPaths(job, args[0]);
job.setInputFormat(TextInputFormat.class);
job.setMapperClass(MapTask.class);
job.setCombinerClass(ReduceTask.class);
job.setReducerClass(ReduceTask.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(IntWritable.class);
job.setOutputFormat(TextOutputFormat.class);
FileOutputFormat.setOutputPath(job, new Path(args[1]));
JobClient.runJob(job);
}
public static void main(String[] args) throws Exception {
JobConf conf = new JobConf(Main.class);
conf.setJobName("feels-analysis");
conf.setOutputKeyClass(Text.class);
conf.setOutputValueClass(TheOutputClass.class);
conf.setMapperClass(Map.class);
conf.setCombinerClass(Reduce.class);
conf.setReducerClass(Reduce.class);
conf.setNumReduceTasks(1);
conf.setInputFormat(CSVTextInputFormat.class);
conf.setOutputFormat(TextOutputFormat.class);
// TODO: determine whether we need extra output
MultipleOutputs.addMultiNamedOutput(
conf, SECOND_OUTPUT, TextOutputFormat.class, Text.class, TheOutputClass.class);
FileInputFormat.setInputPaths(conf, new Path(args[0]));
FileOutputFormat.setOutputPath(conf, new Path(args[1]));
JobClient.runJob(conf);
}
/**
* The main driver for word count map/reduce program. Invoke this method to submit the map/reduce
* job.
*
* @throws IOException When there is communication problems with the job tracker.
*/
public void testOldJobWithMapAndReducers() throws Exception {
JobConf conf = new JobConf(TestJobCounters.class);
conf.setJobName("wordcount-map-reducers");
// the keys are words (strings)
conf.setOutputKeyClass(Text.class);
// the values are counts (ints)
conf.setOutputValueClass(IntWritable.class);
conf.setMapperClass(WordCount.MapClass.class);
conf.setCombinerClass(WordCount.Reduce.class);
conf.setReducerClass(WordCount.Reduce.class);
conf.setNumMapTasks(3);
conf.setNumReduceTasks(1);
conf.setInt("io.sort.mb", 1);
conf.setInt("io.sort.factor", 2);
conf.set("io.sort.record.percent", "0.05");
conf.set("io.sort.spill.percent", "0.80");
FileSystem fs = FileSystem.get(conf);
Path testDir = new Path(TEST_ROOT_DIR, "countertest");
conf.set("test.build.data", testDir.toString());
try {
if (fs.exists(testDir)) {
fs.delete(testDir, true);
}
if (!fs.mkdirs(testDir)) {
throw new IOException("Mkdirs failed to create " + testDir.toString());
}
String inDir = testDir + File.separator + "genins" + File.separator;
String outDir = testDir + File.separator;
Path wordsIns = new Path(inDir);
if (!fs.mkdirs(wordsIns)) {
throw new IOException("Mkdirs failed to create " + wordsIns.toString());
}
long inputSize = 0;
// create 3 input files each with 5*2k words
File inpFile = new File(inDir + "input5_2k_1");
createWordsFile(inpFile);
inputSize += inpFile.length();
inpFile = new File(inDir + "input5_2k_2");
createWordsFile(inpFile);
inputSize += inpFile.length();
inpFile = new File(inDir + "input5_2k_3");
createWordsFile(inpFile);
inputSize += inpFile.length();
FileInputFormat.setInputPaths(conf, inDir);
Path outputPath1 = new Path(outDir, "output5_2k_3");
FileOutputFormat.setOutputPath(conf, outputPath1);
RunningJob myJob = JobClient.runJob(conf);
Counters c1 = myJob.getCounters();
// 3maps & in each map, 4 first level spills --- So total 12.
// spilled records count:
// Each Map: 1st level:2k+2k+2k+2k=8k;2ndlevel=4k+4k=8k;
// 3rd level=2k(4k from 1st level & 4k from 2nd level & combineAndSpill)
// So total 8k+8k+2k=18k
// For 3 Maps, total = 3*18=54k
// Reduce: each of the 3 map o/p's(2k each) will be spilled in shuffleToDisk()
// So 3*2k=6k in 1st level; 2nd level:4k(2k+2k);
// 3rd level directly given to reduce(4k+2k --- combineAndSpill => 2k.
// So 0 records spilled to disk in 3rd level)
// So total of 6k+4k=10k
// Total job counter will be 54k+10k = 64k
// 3 maps and 2.5k lines --- So total 7.5k map input records
// 3 maps and 10k words in each --- So total of 30k map output recs
validateMapredCounters(c1, 64000, 7500, 30000);
validateMapredFileCounters(c1, inputSize, inputSize, 0, 0, 0);
// create 4th input file each with 5*2k words and test with 4 maps
inpFile = new File(inDir + "input5_2k_4");
createWordsFile(inpFile);
inputSize += inpFile.length();
conf.setNumMapTasks(4);
Path outputPath2 = new Path(outDir, "output5_2k_4");
FileOutputFormat.setOutputPath(conf, outputPath2);
myJob = JobClient.runJob(conf);
c1 = myJob.getCounters();
// 4maps & in each map 4 first level spills --- So total 16.
// spilled records count:
// Each Map: 1st level:2k+2k+2k+2k=8k;2ndlevel=4k+4k=8k;
// 3rd level=2k(4k from 1st level & 4k from 2nd level & combineAndSpill)
// So total 8k+8k+2k=18k
// For 3 Maps, total = 4*18=72k
// Reduce: each of the 4 map o/p's(2k each) will be spilled in shuffleToDisk()
// So 4*2k=8k in 1st level; 2nd level:4k+4k=8k;
// 3rd level directly given to reduce(4k+4k --- combineAndSpill => 2k.
// So 0 records spilled to disk in 3rd level)
// So total of 8k+8k=16k
// Total job counter will be 72k+16k = 88k
// 4 maps and 2.5k words in each --- So 10k map input records
// 4 maps and 10k unique words --- So 40k map output records
validateMapredCounters(c1, 88000, 10000, 40000);
validateMapredFileCounters(c1, inputSize, inputSize, 0, 0, 0);
// check for a map only job
conf.setNumReduceTasks(0);
Path outputPath3 = new Path(outDir, "output5_2k_5");
FileOutputFormat.setOutputPath(conf, outputPath3);
myJob = JobClient.runJob(conf);
c1 = myJob.getCounters();
// 4 maps and 2.5k words in each --- So 10k map input records
// 4 maps and 10k unique words --- So 40k map output records
validateMapredCounters(c1, 0, 10000, 40000);
validateMapredFileCounters(c1, inputSize, inputSize, 0, -1, -1);
} finally {
// clean up the input and output files
if (fs.exists(testDir)) {
fs.delete(testDir, true);
}
}
}
static void checkRecords(Configuration defaults, Path sortInput, Path sortOutput)
throws IOException {
FileSystem inputfs = sortInput.getFileSystem(defaults);
FileSystem outputfs = sortOutput.getFileSystem(defaults);
FileSystem defaultfs = FileSystem.get(defaults);
JobConf jobConf = new JobConf(defaults, RecordStatsChecker.class);
jobConf.setJobName("sortvalidate-recordstats-checker");
int noSortReduceTasks = outputfs.listStatus(sortOutput, sortPathsFilter).length;
jobConf.setInt("sortvalidate.sort.reduce.tasks", noSortReduceTasks);
int noSortInputpaths = inputfs.listStatus(sortInput).length;
jobConf.setInputFormat(NonSplitableSequenceFileInputFormat.class);
jobConf.setOutputFormat(SequenceFileOutputFormat.class);
jobConf.setOutputKeyClass(IntWritable.class);
jobConf.setOutputValueClass(RecordStatsChecker.RecordStatsWritable.class);
jobConf.setMapperClass(Map.class);
jobConf.setCombinerClass(Reduce.class);
jobConf.setReducerClass(Reduce.class);
jobConf.setNumMapTasks(noSortReduceTasks);
jobConf.setNumReduceTasks(1);
FileInputFormat.setInputPaths(jobConf, sortInput);
FileInputFormat.addInputPath(jobConf, sortOutput);
Path outputPath = new Path("/tmp/sortvalidate/recordstatschecker");
if (defaultfs.exists(outputPath)) {
defaultfs.delete(outputPath, true);
}
FileOutputFormat.setOutputPath(jobConf, outputPath);
// Uncomment to run locally in a single process
// job_conf.set("mapred.job.tracker", "local");
Path[] inputPaths = FileInputFormat.getInputPaths(jobConf);
System.out.println(
"\nSortValidator.RecordStatsChecker: Validate sort "
+ "from "
+ inputPaths[0]
+ " ("
+ noSortInputpaths
+ " files), "
+ inputPaths[1]
+ " ("
+ noSortReduceTasks
+ " files) into "
+ FileOutputFormat.getOutputPath(jobConf)
+ " with 1 reducer.");
Date startTime = new Date();
System.out.println("Job started: " + startTime);
JobClient.runJob(jobConf);
Date end_time = new Date();
System.out.println("Job ended: " + end_time);
System.out.println(
"The job took " + (end_time.getTime() - startTime.getTime()) / 1000 + " seconds.");
// Check to ensure that the statistics of the
// framework's sort-input and sort-output match
SequenceFile.Reader stats =
new SequenceFile.Reader(defaultfs, new Path(outputPath, "part-00000"), defaults);
IntWritable k1 = new IntWritable();
IntWritable k2 = new IntWritable();
RecordStatsWritable v1 = new RecordStatsWritable();
RecordStatsWritable v2 = new RecordStatsWritable();
if (!stats.next(k1, v1)) {
throw new IOException("Failed to read record #1 from reduce's output");
}
if (!stats.next(k2, v2)) {
throw new IOException("Failed to read record #2 from reduce's output");
}
if ((v1.getBytes() != v2.getBytes())
|| (v1.getRecords() != v2.getRecords())
|| v1.getChecksum() != v2.getChecksum()) {
throw new IOException(
"("
+ v1.getBytes()
+ ", "
+ v1.getRecords()
+ ", "
+ v1.getChecksum()
+ ") v/s ("
+ v2.getBytes()
+ ", "
+ v2.getRecords()
+ ", "
+ v2.getChecksum()
+ ")");
}
}