前提:
? 安装hadoop、IDEA、maven
具体操作:(1)准备数据 wc.txt(格式-12345年份12345温度12345,放在hdfs中的/input/中):
123452015123453012345
123452015123453212345
123452016123453812345
123452016123453812345
123452021123453612345
123452021123453812345
123452021123453612345
(2)Java代码、pom:
POM:
<dependencies>
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-common</artifactId>
<version>2.6.5</version>
</dependency>
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-client</artifactId>
<version>2.6.5</version>
</dependency>
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-hdfs</artifactId>
<version>2.6.5</version>
</dependency>
</dependencies>
Mapper:
package com.demo.mapper;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;
import java.io.IOException;
public class MaxTemperatureMapper extends Mapper<LongWritable, Text, Text, IntWritable> {
@Override
protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
String line = value.toString();
String year = line.substring(5, 9);
int airTemperature = Integer.valueOf(line.substring(14, 16));
context.write(new Text(year), new IntWritable(airTemperature));
}
}
Reducer:
package com.demo.reduer;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;
import java.io.IOException;
public class MaxTemperatureReducer extends Reducer<Text, IntWritable, Text, IntWritable> {
@Override
protected void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException {
int maxValue = Integer.MIN_VALUE;
for (IntWritable value : values) {
maxValue = Math.max(maxValue, value.get());
}
context.write(key, new IntWritable(maxValue));
}
}
(3)执行与结果
hadoop jar newWordCount.jar com.demo.MaxTemperature /input/wc.txt /output/
2015 32
2016 38
2021 38
|