(四)利用Hadoop MapReduce 实现文本单词频率统计
1.Map开发。
package com.aa.mapreduce;
import java.io.IOException;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;
public class WordMapper extends Mapper<LongWritable, Text, Text, LongWritable> {
private LongWritable outValue=new LongWritable(1L);
public void map(LongWritable key,Text value,Context context)throws IOException,InterruptedException{
String[] lst=value.toString().split(" ");
for(String item:lst){
context.write(new Text(item),outValue);
}
}
}
2.Reduce开发。
package com.aa.mapreduce;
import java.io.IOException;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;
public class WordReducer extends Reducer<Text, LongWritable, Text, LongWritable> {
public void reduce(Text key,Iterable<LongWritable> values,Context context)throws IOException,InterruptedException{
long total=0;
for(LongWritable item:values){
total+=item.get();
}
context.write(key,new LongWritable(total));
}
}
3.调度程序开发.
package com.aa.mapreduce;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.lib.input.TextInputFormat;
import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;
public class WordMain {
public static void main(String[] args) throws Exception{
String input_dir="tmp/word/a.txt";
String outputDir="tmp/output";
Configuration conf=new Configuration();
FileSystem fs=FileSystem.get(conf);
fs.deleteOnExit(new Path(outputDir));
fs.close();
Job job=new Job(conf,"WordMain");
job.setMapperClass(WordMapper.class);
job.setReducerClass(WordReducer.class);
///job.setNumReduceTasks(tasks)
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(LongWritable.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(LongWritable.class);
job.setInputFormatClass(TextInputFormat.class);
TextInputFormat.setInputPaths(job, new Path(input_dir));
job.setOutputFormatClass(TextOutputFormat.class);
TextOutputFormat.setOutputPath(job, new Path(outputDir));
job.waitForCompletion(true);
}
}
4.执行日志。
12/04/26 09:55:57 INFO jvm.JvmMetrics: Initializing JVM Metrics with processName=JobTracker, sessionId=
12/04/26 09:55:57 WARN util.NativeCodeLoader: Unable to load native-hadoop library for your platform... using builtin-java classes where applicable
12/04/26 09:55:59 WARN mapred.JobClient: Use GenericOptionsParser for parsing the arguments. Applications should implement Tool for the same.
12/04/26 09:56:00 WARN mapred.JobClient: No job jar file set. User classes may not be found. See JobConf(Class) or JobConf#setJar(String).
12/04/26 09:56:00 INFO input.FileInputFormat: Total input paths to process : 1
12/04/26 09:56:00 WARN snappy.LoadSnappy: Snappy native library not loaded
12/04/26 09:56:02 INFO mapred.JobClient: Running job: job_local_0001
12/04/26 09:56:03 INFO mapred.JobClient: map 0% reduce 0%
12/04/26 09:56:05 INFO mapred.MapTask: io.sort.mb = 100
12/04/26 09:56:05 INFO mapred.MapTask: data buffer = 79691776/99614720
12/04/26 09:56:05 INFO mapred.MapTask: record buffer = 262144/327680
12/04/26 09:56:06 INFO mapred.MapTask: Starting flush of map output
12/04/26 09:56:06 INFO mapred.MapTask: Finished spill 0
12/04/26 09:56:06 INFO mapred.Task: Task:attempt_local_0001_m_000000_0 is done. And is in the process of commiting
12/04/26 09:56:06 INFO mapred.LocalJobRunner:
12/04/26 09:56:06 INFO mapred.Task: Task 'attempt_local_0001_m_000000_0' done.
12/04/26 09:56:06 INFO mapred.LocalJobRunner:
12/04/26 09:56:07 INFO mapred.JobClient: map 100% reduce 0%
12/04/26 09:56:07 INFO mapred.Merger: Merging 1 sorted segments
12/04/26 09:56:07 INFO mapred.Merger: Down to the last merge-pass, with 1 segments left of total size: 349 bytes
12/04/26 09:56:07 INFO mapred.LocalJobRunner:
12/04/26 09:56:07 INFO mapred.Task: Task:attempt_local_0001_r_000000_0 is done. And is in the process of commiting
12/04/26 09:56:07 INFO mapred.LocalJobRunner:
12/04/26 09:56:07 INFO mapred.Task: Task attempt_local_0001_r_000000_0 is allowed to commit now
12/04/26 09:56:07 INFO output.FileOutputCommitter: Saved output of task 'attempt_local_0001_r_000000_0' to tmp/output
12/04/26 09:56:07 INFO mapred.LocalJobRunner: reduce > reduce
12/04/26 09:56:07 INFO mapred.Task: Task 'attempt_local_0001_r_000000_0' done.
12/04/26 09:56:08 INFO mapred.JobClient: map 100% reduce 100%
12/04/26 09:56:08 INFO mapred.JobClient: Job complete: job_local_0001
12/04/26 09:56:08 INFO mapred.JobClient: Counters: 13
12/04/26 09:56:08 INFO mapred.JobClient: FileSystemCounters
12/04/26 09:56:08 INFO mapred.JobClient: FILE_BYTES_READ=889
12/04/26 09:56:08 INFO mapred.JobClient: FILE_BYTES_WRITTEN=93252
12/04/26 09:56:08 INFO mapred.JobClient: Map-Reduce Framework
12/04/26 09:56:08 INFO mapred.JobClient: Reduce input groups=16
12/04/26 09:56:08 INFO mapred.JobClient: Combine output records=0
12/04/26 09:56:08 INFO mapred.JobClient: Map input records=1
12/04/26 09:56:08 INFO mapred.JobClient: Reduce shuffle bytes=0
12/04/26 09:56:08 INFO mapred.JobClient: Reduce output records=16
12/04/26 09:56:08 INFO mapred.JobClient: Spilled Records=46
12/04/26 09:56:08 INFO mapred.JobClient: Map output bytes=301
12/04/26 09:56:08 INFO mapred.JobClient: Combine input records=0
12/04/26 09:56:08 INFO mapred.JobClient: Map output records=23
12/04/26 09:56:08 INFO mapred.JobClient: SPLIT_RAW_BYTES=98
12/04/26 09:56:08 INFO mapred.JobClient: Reduce input records=23