Created
June 20, 2018 08:12
-
-
Save jiankaiwang/6a35ce56312e04c782b8e9bdabb11ff6 to your computer and use it in GitHub Desktop.
MapReduce example in Hadoop
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
/* | |
************************************************************** | |
Platform | |
************************************************************** | |
jdk: 1.8.x | |
hadoop: 3.1.0 | |
************************************************************** | |
Quick Guide | |
************************************************************** | |
input_dir=/user/input | |
output_dir=/user/output | |
# prepare folder in HDFS | |
hadoop fs -mkdir ${input_dir} | |
hadoop fs -rm -r ${output_dir} | |
hadoop fs -put ~//sample.txt ${input_dir} | |
# compile java | |
javac -classpath hadoop-core-1.2.1.jar -d ../bin WordCount.java | |
jar -cvf WordCount.jar -C ../bin . | |
hadoop jar WordCount.jar WordCount ${input_dir} ${output_dir} | |
# show the result | |
hadoop fs -ls $output_dir | |
hadoop fs -cat $output_dir/part-r-00000 | |
*/ | |
import java.io.IOException; | |
import java.util.StringTokenizer; | |
import org.apache.hadoop.conf.Configuration; | |
import org.apache.hadoop.fs.Path; | |
import org.apache.hadoop.io.IntWritable; | |
import org.apache.hadoop.io.Text; | |
import org.apache.hadoop.mapreduce.Job; | |
import org.apache.hadoop.mapreduce.Mapper; | |
import org.apache.hadoop.mapreduce.Reducer; | |
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat; | |
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat; | |
public class WordCount { | |
public static class TokenizerMapper | |
extends Mapper<Object, Text, Text, IntWritable>{ | |
private final static IntWritable one = new IntWritable(1); | |
private Text word = new Text(); | |
public void map(Object key, Text value, Context context | |
) throws IOException, InterruptedException { | |
StringTokenizer itr = new StringTokenizer(value.toString()); | |
while (itr.hasMoreTokens()) { | |
word.set(itr.nextToken()); | |
context.write(word, one); | |
} | |
} | |
} | |
public static class IntSumReducer | |
extends Reducer<Text,IntWritable,Text,IntWritable> { | |
private IntWritable result = new IntWritable(); | |
public void reduce(Text key, Iterable<IntWritable> values, Context context | |
) throws IOException, InterruptedException { | |
int sum = 0; | |
for (IntWritable val : values) { | |
sum += val.get(); | |
} | |
result.set(sum); | |
context.write(key, result); | |
} | |
} | |
public static void main(String[] args) throws Exception { | |
Configuration conf = new Configuration(); | |
Job job = Job.getInstance(conf, "word count"); | |
job.setJarByClass(WordCount.class); | |
job.setMapperClass(TokenizerMapper.class); | |
job.setCombinerClass(IntSumReducer.class); | |
job.setReducerClass(IntSumReducer.class); | |
job.setOutputKeyClass(Text.class); | |
job.setOutputValueClass(IntWritable.class); | |
FileInputFormat.addInputPath(job, new Path(args[0])); | |
FileOutputFormat.setOutputPath(job, new Path(args[1])); | |
System.exit(job.waitForCompletion(true) ? 0 : 1); | |
} | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment