覆盖 mapper类的map方法和reducer类的reduce方法
感兴趣的可以一起交流,只是单纯的分享代码,如果需要详细指导可以私聊
package mapreduce;
import java.io.IOException;
import java.util.StringTokenizer;
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;
// word counter main class
public class WordCount {
public static void main(String[] args) throws IOException,ClassNotFoundException,InterruptedException{
Job job = Job.getInstance();
job.setJobName("WordCount");
job.setJarByClass(WordCount.class);
job.setMapperClass(doMapper.class);
job.setReducerClass(doReducer.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(IntWritable.class);
Path in = new Path("hdfs://localhost:9000/mymapreduce1/in/buyer_favorite1");
Path out = new Path("hdfs://localhost:9000/mymapreduce1/out");
FileInputFormat.addInputPath(job, in);
FileOutputFormat.setOutputPath(job, out);
System.exit(job.waitForCompletion(true)? 0: 1);
}
// map
public static class doMapper extends Mapper<Object, Text, Text, IntWritable>{
public static final IntWritable count_one = new IntWritable(1);
public static Text word = new Text();
@Override
protected void map(Object key, Text value, Context context)
throws IOException, InterruptedException{
StringTokenizer st = new StringTokenizer(value.toString(), "\t");
while (st.hasMoreTokens()){
word.set(st.nextToken());
context.write(word, count_one);
}
}
}
// reduce
public static class doReducer extends Reducer<Text, IntWritable, Text, IntWritable>{
private IntWritable result = new IntWritable();
@Override
protected void reduce(Text key, Iterable<IntWritable> values, Context context)
throws IOException, InterruptedException{
int sum = 0;
for(IntWritable value:values){
sum += value.get();
}
result.set(sum);
context.write(key,result);
}
}
}