一,背景
气象站分析一批复杂的数据,演示需要分析的数据
0043011990999991950051518004+68750+023550FM-12+038299999V0203201N00261220001CN9999999N9-00111+99999999999
存放在input.txt中。
其中包含了年份 和 温度数据
需要把这个年份和温度数据提取出来
二,具体执行
1,下载 hadoop-0.20.1
cd hadoop-020.1/conf/ 配置:
core-site.xml
<?xml version="1.0"?>
<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
<!-- Put site-specific property overrides in this file. -->
<configuration>
<property>
<name>fs.default.name</name>
<value>hdfs://localhost:9000</value>
</property>
</configuration>
hdfs-site.xml
<?xml version="1.0"?>
<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
<!-- Put site-specific property overrides in this file. -->
<configuration>
<property>
<name>dfs.replication</name>
<value>1</value>
</property>
</configuration>
mapred-site.xml
<?xml version="1.0"?>
<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
<!-- Put site-specific property overrides in this file. -->
<configuration>
<property>
<name>mapred.job.tracker</name>
<value>localhost:9001</value>
</property>
</configuration>
配置完毕
cd bin
./hadoop namenode -format
./start-all.sh
2,我的pom.xml
<?xml version="1.0" encoding="UTF-8"?>
<project
xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd"
xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance">
<modelVersion>4.0.0</modelVersion>
<parent>
<artifactId>balance</artifactId>
<groupId>com.yajun</groupId>
<version>1.0-SNAPSHOT</version>
</parent>
<groupId>com.yajun.hadoop</groupId>
<artifactId>balance.hadoop</artifactId>
<version>1.0-SNAPSHOT</version>
<name>balance.hadoop</name>
<url>http://maven.apache.org</url>
<dependencies>
<dependency>
<groupId>junit</groupId>
<artifactId>junit</artifactId>
<version>4.7</version>
<scope>test</scope>
</dependency>
<dependency>
<groupId>org.mockito</groupId>
<artifactId>mockito-core</artifactId>
<version>1.8.2</version>
<scope>test</scope>
</dependency>
<dependency>
<groupId>org.apache.mahout.hadoop</groupId>
<artifactId>hadoop-core</artifactId>
<version>0.20.1</version>
</dependency>
<dependency>
<groupId>commons-logging</groupId>
<artifactId>commons-logging</artifactId>
<version>1.1.1</version>
</dependency>
<dependency>
<groupId>commons-httpclient</groupId>
<artifactId>commons-httpclient</artifactId>
<version>3.0</version>
</dependency>
<dependency>
<groupId>commons-cli</groupId>
<artifactId>commons-cli</artifactId>
<version>1.2</version>
</dependency>
</dependencies>
</project>
使用以上pom,用maven 构建eclipse开发环境
3,写代码
分析代码 (Map部分)
package com.yajun.hadoop.temperature;
import java.io.IOException;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapred.MapReduceBase;
import org.apache.hadoop.mapred.Mapper;
import org.apache.hadoop.mapred.OutputCollector;
import org.apache.hadoop.mapred.Reporter;
/**
* hadoop 书上的例子,提取年份,温度数据
*
* @author txy
*/
public class MaxTemperatureMapper extends MapReduceBase implements
Mapper<LongWritable, Text, Text, IntWritable> {
public void map(LongWritable key, Text value, OutputCollector<Text, IntWritable> output,
Reporter reporter) throws IOException {
String line = value.toString();
// 提取年份
String year = line.substring(15, 19);
// 提取温度
String temp = line.substring(87, 92);
if (!missing(temp)) {
int airTemperature = Integer.parseInt(temp);
output.collect(new Text(year), new IntWritable(airTemperature));
}
}
/**
* 如果提取出来的温度达到9999,认为是提取不到数据
*
* @param temp
* @return 是否能正确提取温度数据
*/
private boolean missing(String temp) {
return temp.equals("+9999");
}
}
输出结果代码(Reduce部分)
package com.yajun.hadoop.temperature;
import java.io.IOException;
import java.util.Iterator;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapred.MapReduceBase;
import org.apache.hadoop.mapred.OutputCollector;
import org.apache.hadoop.mapred.Reducer;
import org.apache.hadoop.mapred.Reporter;
/**
* 输出当年最高温度
*
* @author txy
*/
public class MaxTemperatureReducer extends MapReduceBase implements
Reducer<Text, IntWritable, Text, IntWritable> {
public void reduce(Text key, Iterator<IntWritable> values,
OutputCollector<Text, IntWritable> output, Reporter reporter)
throws IOException {
int maxValue = Integer.MIN_VALUE;
while (values.hasNext()) {
maxValue = Math.max(maxValue, values.next().get());
}
output.collect(key, new IntWritable(maxValue));
}
}
运行整个JOB的代码
package com.yajun.hadoop.temperature;
import org.apache.hadoop.conf.Configured;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapred.FileInputFormat;
import org.apache.hadoop.mapred.FileOutputFormat;
import org.apache.hadoop.mapred.JobClient;
import org.apache.hadoop.mapred.JobConf;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;
public class MaxTemperatureDriver extends Configured implements Tool {
@Override
public int run(String[] args) throws Exception {
if (args.length != 2) {
System.err.printf("Usage: %s [generic options] <input> <output>\n", getClass()
.getSimpleName());
ToolRunner.printGenericCommandUsage(System.err);
return -1;
}
JobConf conf = new JobConf(getConf(), getClass());
conf.setJobName("Max temperature");
FileInputFormat.addInputPath(conf, new Path(args[0]));
FileOutputFormat.setOutputPath(conf, new Path(args[1]));
conf.setOutputKeyClass(Text.class);
conf.setOutputValueClass(IntWritable.class);
conf.setMapperClass(MaxTemperatureMapper.class);
conf.setCombinerClass(MaxTemperatureReducer.class);
conf.setReducerClass(MaxTemperatureReducer.class);
JobClient.runJob(conf);
return 0;
}
public static void main(String[] args) throws Exception {
int exitCode = ToolRunner.run(new MaxTemperatureDriver(), args);
System.exit(exitCode);
}
}
4,eclipse环境的hadoop插件配置好(如果没有安装这个插件也很简单:https://issues.apache.org/jira/browse/MAPREDUCE-1262
上面下载,扔到eclipse 的dropins目录里面搞定)
与hadoop的配置一样
5,运行代码
现将input.txt拷贝到 hdfs中去
./hadoop fs -put /home/txy/work/balanceofworld/balance/balance.hadoop/src/main/resources/temperature/input.txt /user/txy/src/main/resources/temperature/input.txt
设置运行 MaxTemperatureDriver 的时候需要两个命令行参数
1,输入文件:src/main/resources/temperature/input.txt (对应到HDFS里面的
/user/txy/src/main/resources/temperature/input.txt
)
2,输出文件:src/main/resources/temperature/output.txt(对应到HDFS里面的
/user/txy/src/main/resources/temperature/output.txt
)
然后就在eclipse 里右键在hadoop上运行吧,哈哈。
- 大小: 39.8 KB
分享到:
相关推荐
赠送源代码:hadoop-yarn-client-2.6.5-sources.jar; 赠送Maven依赖信息文件:hadoop-yarn-client-2.6.5.pom; 包含翻译后的API文档:hadoop-yarn-client-2.6.5-javadoc-API文档-中文(简体)版.zip; Maven坐标:org...
为了方便开发者在Eclipse或MyEclipse这样的集成开发环境中高效地进行Hadoop应用开发,Hadoop-Eclipse-Plugin应运而生。这个插件允许开发者直接在IDE中对Hadoop集群进行操作,如创建、编辑和运行MapReduce任务,极大...
赠送源代码:hadoop-mapreduce-client-jobclient-2.6.5-sources.jar; 赠送Maven依赖信息文件:hadoop-mapreduce-client-jobclient-2.6.5.pom; 包含翻译后的API文档:hadoop-mapreduce-client-jobclient-2.6.5-...
赠送源代码:hadoop-yarn-common-2.6.5-sources.jar 包含翻译后的API文档:hadoop-yarn-common-2.6.5-javadoc-API文档-中文(简体)版.zip 对应Maven信息:groupId:org.apache.hadoop,artifactId:hadoop-yarn-...
Eclipse集成Hadoop2.10.0的插件,使用`ant`对hadoop的jar包进行打包并适应Eclipse加载,所以参数里有hadoop和eclipse的目录. 必须注意对于不同的hadoop版本,` HADDOP_INSTALL_PATH/share/hadoop/common/lib`下的jar包...
标题中的"apache-hadoop-3.1.0-winutils-master.zip"是一个针对Windows用户的Hadoop工具包,它包含了运行Hadoop所需的特定于Windows的工具和配置。`winutils.exe`是这个工具包的关键组件,它是Hadoop在Windows上的一...
赠送源代码:hadoop-mapreduce-client-common-2.6.5-sources.jar; 赠送Maven依赖信息文件:hadoop-mapreduce-client-common-2.6.5.pom; 包含翻译后的API文档:hadoop-mapreduce-client-common-2.6.5-javadoc-API...
赠送源代码:hadoop-auth-2.5.1-sources.jar; 赠送Maven依赖信息文件:hadoop-auth-2.5.1.pom; 包含翻译后的API文档:hadoop-auth-2.5.1-javadoc-API文档-中文(简体)版.zip; Maven坐标:org.apache.hadoop:hadoop...
Hadoop-Eclipse-Plugin-3.1.1是一款专为Eclipse集成开发环境设计的插件,用于方便地在Hadoop分布式文件系统(HDFS)上进行开发和调试MapReduce程序。这款插件是Hadoop生态系统的组成部分,它使得Java开发者能够更加...
Hadoop权威指南----读书笔记
在Flink-shaded-hadoop-3-uber-jar中,Flink的开发人员对Hadoop的相关类进行了阴影处理,使得Flink可以在不修改源代码的情况下,与Hadoop 3.x进行无缝对接。 总结起来,"flink-shaded-hadoop-3-uber-3.1.1.7.1.1.0-...
hadoop-eclipse-plugin-2.7.3和2.7.7的jar包 hadoop-eclipse-plugin-2.7.3和2.7.7的jar包 hadoop-eclipse-plugin-2.7.3和2.7.7的jar包 hadoop-eclipse-plugin-2.7.3和2.7.7的jar包
`hadoop-common-2.6.0-bin-master.zip` 是一个针对Hadoop 2.6.0版本的压缩包,特别适用于在Windows环境下进行本地开发和测试。这个版本的Hadoop包含了对Windows系统的优化,比如提供了`winutils.exe`,这是在Windows...
hadoop-annotations-3.1.1.jar hadoop-common-3.1.1.jar hadoop-mapreduce-client-core-3.1.1.jar hadoop-yarn-api-3.1.1.jar hadoop-auth-3.1.1.jar hadoop-hdfs-3.1.1.jar hadoop-mapreduce-client-hs-3.1.1.jar ...
《Hadoop-Eclipse-Plugin-2.6.4.jar:Eclipse中的Hadoop开发利器》 在大数据处理领域,Hadoop作为一个开源的分布式计算框架,因其高效、可扩展的特性而备受青睐。为了方便开发者在Eclipse环境中进行Hadoop应用程序...
Ubuntu虚拟机HADOOP集群搭建eclipse环境 hadoop-eclipse-plugin-3.3.1.jar
赠送源代码:hadoop-yarn-server-resourcemanager-2.6.0-sources.jar; 赠送Maven依赖信息文件:hadoop-yarn-server-resourcemanager-2.6.0.pom; 包含翻译后的API文档:hadoop-yarn-server-resourcemanager-2.6.0-...
赠送源代码:hadoop-mapreduce-client-core-2.5.1-sources.jar; 赠送Maven依赖信息文件:hadoop-mapreduce-client-core-2.5.1.pom; 包含翻译后的API文档:hadoop-mapreduce-client-core-2.5.1-javadoc-API文档-...
《Hadoop-eclipse-plugin-2.7.2:在Eclipse中轻松开发Hadoop应用》 在大数据处理领域,Hadoop作为一个开源的分布式计算框架,因其高效、可扩展的特性而备受青睐。然而,对于开发者而言,有效地集成开发环境至关重要...
赠送源代码:hadoop-yarn-api-2.5.1-sources.jar; 赠送Maven依赖信息文件:hadoop-yarn-api-2.5.1.pom; 包含翻译后的API文档:hadoop-yarn-api-2.5.1-javadoc-API文档-中文(简体)版.zip; Maven坐标:org.apache....