List of usage examples for org.apache.hadoop.mapreduce Job setCombinerClass
public void setCombinerClass(Class<? extends Reducer> cls) throws IllegalStateException
From source file:crunch.MaxTemperature.java
License:Apache License
@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;
}/* w ww. j a v a 2 s. co m*/
Job job = new Job(getConf(), "Max temperature");
job.setJarByClass(getClass());
FileInputFormat.addInputPath(job, new Path(args[0]));
FileOutputFormat.setOutputPath(job, new Path(args[1]));
job.setMapperClass(MaxTemperatureMapper.class);
job.setCombinerClass(MaxTemperatureReducer.class);
job.setReducerClass(MaxTemperatureReducer.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(IntWritable.class);
return job.waitForCompletion(true) ? 0 : 1;
}
From source file:crunch.MaxTemperature.java
License:Apache License
@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;
}/*from ww w. j av a2s .c om*/
//vv MaxTemperatureDriverV6
Configuration conf = getConf();
conf.setBoolean("mapred.task.profile", true);
conf.set("mapred.task.profile.params",
"-agentlib:hprof=cpu=samples," + "heap=sites,depth=6,force=n,thread=y,verbose=n,file=%s");
conf.set("mapred.task.profile.maps", "0-2");
conf.set("mapred.task.profile.reduces", ""); // no reduces
Job job = new Job(conf, "Max temperature");
//^^ MaxTemperatureDriverV6
// Following alternative is only available in 0.21 onwards
// conf.setBoolean(JobContext.TASK_PROFILE, true);
// conf.set(JobContext.TASK_PROFILE_PARAMS, "-agentlib:hprof=cpu=samples," +
// "heap=sites,depth=6,force=n,thread=y,verbose=n,file=%s");
// conf.set(JobContext.NUM_MAP_PROFILES, "0-2");
// conf.set(JobContext.NUM_REDUCE_PROFILES, "");
job.setJarByClass(getClass());
FileInputFormat.addInputPath(job, new Path(args[0]));
FileOutputFormat.setOutputPath(job, new Path(args[1]));
job.setMapperClass(MaxTemperatureMapper.class);
job.setCombinerClass(MaxTemperatureReducer.class);
job.setReducerClass(MaxTemperatureReducer.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(IntWritable.class);
return job.waitForCompletion(true) ? 0 : 1;
}
From source file:crunch.MaxTemperature.java
License:Apache License
@Override
public int run(String[] args) throws Exception {
if (args.length != 3) {
JobBuilder.printUsage(this, "<ncdc input> <metoffice input> <output>");
return -1;
}// w w w .ja v a2 s . c o m
Job job = new Job(getConf(), "Max temperature with multiple input formats");
job.setJarByClass(getClass());
Path ncdcInputPath = new Path(args[0]);
Path metOfficeInputPath = new Path(args[1]);
Path outputPath = new Path(args[2]);
// vv MaxTemperatureWithMultipleInputs
MultipleInputs.addInputPath(job, ncdcInputPath, TextInputFormat.class, MaxTemperatureMapper.class);
MultipleInputs.addInputPath(job, metOfficeInputPath, TextInputFormat.class,
MetOfficeMaxTemperatureMapper.class);
// ^^ MaxTemperatureWithMultipleInputs
FileOutputFormat.setOutputPath(job, outputPath);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(IntWritable.class);
job.setCombinerClass(MaxTemperatureReducer.class);
job.setReducerClass(MaxTemperatureReducer.class);
return job.waitForCompletion(true) ? 0 : 1;
}
From source file:crunch.MaxTemperature.java
License:Apache License
@Override
public int run(String[] args) throws Exception {
Job job = JobBuilder.parseInputAndOutput(this, getConf(), args);
if (job == null) {
return -1;
}/*from w ww . j a va 2 s .c om*/
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(IntWritable.class);
job.setMapperClass(StationTemperatureMapper.class);
job.setCombinerClass(MaxTemperatureReducer.class);
job.setReducerClass(MaxTemperatureReducerWithStationLookup.class);
return job.waitForCompletion(true) ? 0 : 1;
}
From source file:crunch.MaxTemperature.java
License:Apache License
@Override
public int run(String[] args) throws Exception {
Job job = JobBuilder.parseInputAndOutput(this, getConf(), args);
if (job == null) {
return -1;
}/*from w w w . ja va 2s .c o m*/
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(IntWritable.class);
job.setMapperClass(MaxTemperatureMapperWithCounters.class);
job.setCombinerClass(MaxTemperatureReducer.class);
job.setReducerClass(MaxTemperatureReducer.class);
return job.waitForCompletion(true) ? 0 : 1;
}
From source file:crunch.MaxTemperature.java
License:Apache License
@Override
public int run(String[] args) throws Exception {
Job job = JobBuilder.parseInputAndOutput(this, getConf(), args);
if (job == null) {
return -1;
}//from w ww. j a v a 2s.c o m
job.setMapperClass(TemperatureCountMapper.class);
job.setCombinerClass(LongSumReducer.class);
job.setReducerClass(LongSumReducer.class);
job.setOutputKeyClass(IntWritable.class);
job.setOutputValueClass(LongWritable.class);
return job.waitForCompletion(true) ? 0 : 1;
}
From source file:csc555.ebratt.depaul.edu.AverageScoreDriver.java
License:Open Source License
/** * /*w w w. ja va2 s .c om*/ * Runs the driver by creating a new hadoop Job based on the configuration. * Defines the path in/out based on the first two arguments. Allows for an * optional combiner based on the 4th argument. * * @param args * [0] the input directory on HDFS * @param args * [1] the output directory on HDFS * @param args * [2] tells the system whether or not to use a combiner ("yes") * and, if so, it will use the AverageScoreReducer.class as the * combiner. * @throws Exception * if there is an issue with any of the arguments * */ @Override public int run(String[] args) throws Exception { Job job = new Job(getConf()); String groupBy = getConf().get("groupBy"); StringBuffer sb = new StringBuffer(); sb.append("average score by: "); sb.append(groupBy); job.setJobName(sb.toString()); Path in = new Path(args[0]); Path out = new Path(args[1]); FileInputFormat.setInputPaths(job, in); FileOutputFormat.setOutputPath(job, out); // testing -- ensure each node gets 2 reducers JobConf jobConf = new JobConf(getConf(), AverageScoreDriver.class); JobClient jobClient = new JobClient(jobConf); ClusterStatus cluster = jobClient.getClusterStatus(); job.setNumReduceTasks(cluster.getTaskTrackers() * 2); // Mapper and Reducer Classes to use job.setMapperClass(AverageScoreMapper.class); job.setReducerClass(AverageScoreReducer.class); // Mapper output classes job.setMapOutputKeyClass(Text.class); job.setMapOutputValueClass(DoubleWritable.class); // Input format class job.setInputFormatClass(TextInputFormat.class); // Reducer output classes job.setOutputKeyClass(Text.class); job.setOutputValueClass(DoubleWritable.class); // Output format class job.setOutputFormatClass(TextOutputFormat.class); // Combiner if (args[2].equals("yes")) { job.setCombinerClass(AverageScoreReducer.class); } // The Jar file to run job.setJarByClass(AverageScoreDriver.class); boolean success = job.waitForCompletion(true); System.exit(success ? 0 : 1); return 0; }
From source file:csc555.ebratt.depaul.edu.AverageScoreRankerDriver.java
License:Open Source License
/** * /*from w w w . j a va 2s .c o m*/ * Runs the driver by creating a new hadoop Job based on the configuration. * Defines the path in/out based on the first two arguments. Allows for an * optional combiner based on the 4th argument. * * @param args * [0] the input directory on HDFS * @param args * [1] the output directory on HDFS * @param args * [2] tells the system whether or not to use a combiner ("yes") * and, if so, it will use the AverageScoreRankerReducer.class as the * combiner. * @throws Exception * if there is an issue with any of the arguments * */ @Override public int run(String[] args) throws Exception { Job job = new Job(getConf()); job.setJobName("average score ranked"); Path in = new Path(args[0]); Path out = new Path(args[1]); FileInputFormat.setInputPaths(job, in); FileOutputFormat.setOutputPath(job, out); job.setNumReduceTasks(1); // Mapper and Reducer Classes to use job.setMapperClass(AverageScoreRankerMapper.class); job.setReducerClass(AverageScoreRankerReducer.class); // Mapper output classes job.setMapOutputKeyClass(DoubleWritable.class); job.setMapOutputValueClass(Text.class); // Input format class job.setInputFormatClass(TextInputFormat.class); // Reducer output classes job.setOutputKeyClass(DoubleWritable.class); job.setOutputValueClass(Text.class); // Output format class job.setOutputFormatClass(TextOutputFormat.class); // Combiner if (args[2].equals("yes")) { job.setCombinerClass(AverageScoreRankerReducer.class); } // sort in descending order job.setSortComparatorClass(DoubleWritableDescendingComparator.class); // The Jar file to run job.setJarByClass(AverageScoreRankerDriver.class); boolean success = job.waitForCompletion(true); System.exit(success ? 0 : 1); return 0; }
From source file:csc555.ebratt.depaul.edu.GildedCountDriver.java
License:Open Source License
/** * /*from w ww . jav a2s.c o m*/ * Runs the driver by creating a new hadoop Job based on the configuration. * Defines the path in/out based on the first two arguments. Allows for an * optional combiner based on the 4th argument. * * @param args * [0] the input directory on HDFS * @param args * [1] the output directory on HDFS * @param args * [2] tells the system whether or not to use a combiner ("yes") * and, if so, it will use the GildedCountReducer.class as the * combiner. * @throws Exception * if there is an issue with any of the arguments * */ @Override public int run(String[] args) throws Exception { Job job = new Job(getConf()); String groupBy = getConf().get("groupBy"); StringBuffer sb = new StringBuffer(); sb.append("count of gilded comments grouped by: "); sb.append(groupBy); job.setJobName(sb.toString()); Path in = new Path(args[0]); Path out = new Path(args[1]); FileInputFormat.setInputPaths(job, in); FileOutputFormat.setOutputPath(job, out); // testing -- ensure each node gets 2 reducers JobConf jobConf = new JobConf(getConf(), GildedCountDriver.class); JobClient jobClient = new JobClient(jobConf); ClusterStatus cluster = jobClient.getClusterStatus(); job.setNumReduceTasks(cluster.getTaskTrackers() * 2); // Mapper and Reducer Classes to use job.setMapperClass(GildedCountMapper.class); job.setReducerClass(LongSumReducer.class); // Mapper output classes job.setMapOutputKeyClass(Text.class); job.setMapOutputValueClass(LongWritable.class); // Input format class job.setInputFormatClass(TextInputFormat.class); // Reducer output classes job.setOutputKeyClass(Text.class); job.setOutputValueClass(LongWritable.class); // Output format class job.setOutputFormatClass(TextOutputFormat.class); // Combiner if (args[2].equals("yes")) { job.setCombinerClass(LongSumReducer.class); } // The Jar file to run job.setJarByClass(GildedCountDriver.class); boolean success = job.waitForCompletion(true); System.exit(success ? 0 : 1); return 0; }
From source file:csc555.ebratt.depaul.edu.GildedSorterDriver.java
License:Open Source License
/** * //from w w w. jav a2s. c o m * Runs the driver by creating a new hadoop Job based on the configuration. * Defines the path in/out based on the first two arguments. Allows for an * optional combiner based on the 4th argument. * * @param args * [0] the input directory on HDFS * @param args * [1] the output directory on HDFS * @param args * [2] tells the system whether or not to use a combiner ("yes") * and, if so, it will use the GildedSorterReducer.class as the * combiner. * @throws Exception * if there is an issue with any of the arguments * */ @Override public int run(String[] args) throws Exception { Job job = new Job(getConf()); StringBuffer sb = new StringBuffer(); sb.append("sorted gild counts"); job.setJobName(sb.toString()); Path in = new Path(args[0]); Path out = new Path(args[1]); FileInputFormat.setInputPaths(job, in); FileOutputFormat.setOutputPath(job, out); // to ensure output is sorted job.setNumReduceTasks(1); // Mapper and Reducer Classes to use job.setMapperClass(GildedSorterMapper.class); job.setReducerClass(GildedSorterReducer.class); // Mapper output classes job.setMapOutputKeyClass(LongWritable.class); job.setMapOutputValueClass(Text.class); // Input format class job.setInputFormatClass(TextInputFormat.class); // Reducer output classes job.setOutputKeyClass(LongWritable.class); job.setOutputValueClass(Text.class); // Output format class job.setOutputFormatClass(TextOutputFormat.class); // Combiner if (args[2].equals("yes")) { job.setCombinerClass(GildedSorterReducer.class); } // sort in descending order job.setSortComparatorClass(LongWritable.DecreasingComparator.class); // The Jar file to run job.setJarByClass(GildedSorterDriver.class); boolean success = job.waitForCompletion(true); System.exit(success ? 0 : 1); return 0; }