如何解决预期的org.apache.hadoop.io.Text，在mapreduce作业中收到org.apache.h

Question

我正在尝试编写一个可以分析YouTube数据集中某些信息的工作。我相信我已经在驱动程序类中正确设置了地图中的输出键，但仍然收到上述错误，我在这里发布代码和异常，

映射器

public class YouTubeDataMapper extends Mapper<LongWritable,Text,Text,IntWritable>{
private static final IntWritable one = new IntWritable(1); 
private Text category = new Text(); 
public void mapper(LongWritable key,Text value,Context context) throws IOException, InterruptedException{
String str[] = value.toString().split("t");
category.set(str[3]);
context.write(category, one);
}
}

减速器类

public class YouTubeDataReducer extends Reducer<Text,IntWritable,Text,IntWritable>{
public void reduce(Text key,Iterable<IntWritable> values,Context context) throws IOException, InterruptedException{
int sum=0;
for(IntWritable count:values){
sum+=count.get();
}
context.write(key, new IntWritable(sum));
}
}

驱动程序类

public class YouTubeDataDriver {
public static void main(String[] args) throws Exception {
Configuration conf = new Configuration();
@SuppressWarnings("deprecation")
Job job = new Job(conf, "categories");
job.setJarByClass(YouTubeDataDriver.class);
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(IntWritable.class);
// job.setNumReduceTasks(0);
job.setOutputKeyClass(Text.class);// Here i have set the output keys
job.setOutputValueClass(IntWritable.class);
job.setMapperClass(YouTubeDataMapper.class);
job.setReducerClass(YouTubeDataReducer.class);
job.setInputFormatClass(TextInputFormat.class);
job.setOutputFormatClass(TextOutputFormat.class);
FileInputFormat.addInputPath(job, new Path(args[0]));
FileOutputFormat.setOutputPath(job, new Path(args[1]));
Path out = new Path(args[1]);
out.getFileSystem(conf).delete(out);
job.waitForCompletion(true);
}
}

我得到的例外

java.io.IOException：映射中的键类型不匹配：预期 org.apache.hadoop.io.Text， received org.apache.hadoop.io.LongWritable 在 org.apache.hadoop.mapred.MapTask$MapOutputBuffer.collect(MapTask.java：1069) 在 org.apache.hadoop.mapred.MapTask$NewOutputCollector.write(MapTask.java：712) 在 org.apache.hadoop.mapreduce.task.TaskInputOutputContextImpl.write(TaskInputOutputContextImpl.java：89) 在 org.apache.hadoop.mapreduce.lib.map.WrappedMapper$Context.write(WrappedMapper.java：112) at org.apache.hadoop.mapreduce.Mapper.map(Mapper.java：124) at org.apache.hadoop.mapreduce.Mapper.run(Mapper.java：145) at org.apache.hadoop.mapred.MapTask.runNewMapper(MapTask.java：784) at org.apache.hadoop.mapred.MapTask.run(MapTask.java：341) at org.apache.hadoop.mapred.YarnChild$2.run(YarnChild.java：168) at java.security.AccessController.doPrivileged(Native Method) at javax.security.auth.Subject.doAs(Subject.java：422) at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java：1642) at org.apache.hadoop.mapred.YarnChild.main(YarnChild.java：163)

我已经在驱动程序类中设置了输出键

job.setOutputKeyClass(Text.class);// Here i have set the output keys
job.setOutputValueClass(IntWritable.class);

但是为什么我仍然收到错误？请帮忙，我是地图还原的新手

Answer 1

将mapper()方法重命名为map()(请参阅官方文档)。

正在发生的事情是映射器实际上没有处理任何数据。它不会进入mapper()方法(因为它正在寻找map()方法)，因此保持映射阶段不变，这意味着映射输出键仍然LongWritable。

顺便说一句，

String str[] = value.toString().split("t");
category.set(str[3]);

是非常危险的。假设所有输入数据至少包含 3 个t字符是有风险的。在处理大量数据时，几乎总会有一些不是您期望的格式，并且您不希望发生这种情况时整个工作都会死亡。考虑执行以下操作：

String valueStr = value.toString();
if (valueStr != null) {
String str[] = valueStr.split("t");
if (str[] != null && str.size > 3) {
category.set(str[3]);
context.write(category, one);
}
}

Answer 2

下面的代码(用对象更新长可写)对我有用 -

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.input.TextInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;
public class YouTubeDataDriver {
public static class YouTubeDataMapper
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 YouTubeDataReducer
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();
@SuppressWarnings("deprecation")
Job job = new Job(conf, "categories");
job.setJarByClass(YouTubeDataDriver.class);
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(IntWritable.class);
// job.setNumReduceTasks(0);
job.setOutputKeyClass(Text.class);// Here i have set the output keys
job.setOutputValueClass(IntWritable.class);
job.setMapperClass(YouTubeDataMapper.class);
job.setReducerClass(YouTubeDataReducer.class);
job.setInputFormatClass(TextInputFormat.class);
job.setOutputFormatClass(TextOutputFormat.class);
FileInputFormat.addInputPath(job, new Path(args[0]));
FileOutputFormat.setOutputPath(job, new Path(args[1]));
Path out = new Path(args[1]);
out.getFileSystem(conf).delete(out);
job.waitForCompletion(true);
}
}