创建UesrRateBean 的类
package com.cou;
public class UesrRateBean {
private String movie;
private Integer rate;
private String timeStamp;
private String uid;
public String getMovie() {
return movie;
}
public void setMovie(String movie) {
this.movie = movie;
}
public Integer getRate() {
return rate;
}
public void setRate(Integer rate) {
this.rate = rate;
}
public String getTimeStamp() {
return timeStamp;
}
public void setTimeStamp(String timeStamp) {
this.timeStamp = timeStamp;
}
public String getUid() {
return uid;
}
public void setUid(String uid) {
this.uid = uid;
}
@Override
public String toString() {
return "UesrRateBean{" +
"movie='" + movie + '\'' +
", rate=" + rate +
", timeStamp='" + timeStamp + '\'' +
", uid='" + uid + '\'' +
'}';
}
}
创建UseRateDriver测试类
package com.cou;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
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.input.TextInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;
import org.codehaus.jackson.map.ObjectMapper;
import java.io.IOException;
public class UseRateDriver {
public static class UserRateMap extends Mapper<LongWritable, Text,Text, IntWritable>{
ObjectMapper objectMapper = new ObjectMapper();
protected void map(LongWritable key,Text value,Context context) throws IOException, InterruptedException {
String line = value.toString();
//{"movie":"1193","rate":"5","timeStamp":"978300760","uid":"1"}
UesrRateBean userRateBean = objectMapper.readValue(line, UesrRateBean.class);
String movie = userRateBean.getMovie();
Integer rate = userRateBean.getRate();
context.write(new Text(movie),new IntWritable(rate));
}
}
public static class UserRateReduce extends Reducer<Text,IntWritable,Text,IntWritable>{
protected void reduce(Text key, Iterable<IntWritable> values,Context context) throws IOException, InterruptedException {
int sum = 0;
for (IntWritable v:values){
sum = sum + v.get();
}
context.write(key,new IntWritable(sum));
}
}
public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
Configuration conf = new Configuration();
conf.set("yarn resorcemanager.hostname","hadoop01");
conf.set("fs deafutFS","hdfs://hadoop01:9000/");
Job job = Job.getInstance(conf);
job.setJarByClass(UseRateDriver.class);
job.setMapperClass(UserRateMap.class);
job.setReducerClass(UserRateReduce.class);
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(IntWritable.class);
job.setOutputKeyClass(Text.class);
job.setOutputKeyClass(IntWritable.class);
job.setInputFormatClass(TextInputFormat.class);
job.setOutputFormatClass(TextOutputFormat.class);
FileInputFormat.setInputPaths(job,new Path(args[0]));
FileOutputFormat.setOutputPath(job,new Path(args[1]));
job.submit();
boolean b = job.waitForCompletion(true);
System.exit(b ? 0 : 1);
}
}
验证:
rz:将打包好的jar包上传到虚拟机
在jar包所在目录下运行:hadoop jar yann.jar /ynn/input/rating.json /ynn/output