标签:编号 exception spl 将不 height 方式 ros 功能 one
MapReduce:其实就是把数据分开处理后再将数据合在一起.
MapReduce中定义了如下的Map和Reduce两个抽象的编程接口,由用户去编程实现.Map和Reduce,
MapReduce处理的数据类型是
MapReduce 的开发一共有八个步骤, 其中 Map 阶段分为 2 个步骤,Shuwle 阶段 4 个步
骤,Reduce 阶段分为 2 个步骤
Map 阶段 2 个步骤
Shuwle 阶段 4 个步骤
Reduce 阶段 2 个步骤
常用Maven依赖
<packaging>jar</packaging>
<dependencies>
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-common</artifactId>
<version>2.7.5</version>
</dependency>
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-client</artifactId>
<version>2.7.5</version>
</dependency>
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-hdfs</artifactId>
<version>2.7.5</version>
</dependency>
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-mapreduce-client-core</artifactId>
<version>2.7.5</version>
</dependency>
<dependency>
<groupId>junit</groupId>
<artifactId>junit</artifactId>
<version>RELEASE</version>
</dependency>
</dependencies>
<build>
<plugins>
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-compiler-plugin</artifactId>
<version>3.1</version>
<configuration>
<source>1.8</source>
<target>1.8</target>
<encoding>UTF-8</encoding>
<!-- <verbal>true</verbal>-->
</configuration>
</plugin>
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-shade-plugin</artifactId>
<version>2.4.3</version>
<executions>
<execution>
<phase>package</phase>
<goals>
<goal>shade</goal>
</goals>
<configuration>
<minimizeJar>true</minimizeJar>
</configuration>
</execution>
</executions>
</plugin>
</plugins>
</build>
入门---统计
结构
/*
四个泛型解释:
KEYIN :K1的类型
VALUEIN: V1的类型
KEYOUT: K2的类型
VALUEOUT: V2的类型
*/
public class WordCountMapper extends Mapper<LongWritable,Text, Text , LongWritable> {
//map方法就是将K1和V1 转为 K2和V2
/*
参数:
key : K1 行偏移量(默认几乎一直固定为LongWritable)
value : V1 每一行的文本数据
context :表示上下文对象
*/
/*
如何将K1和V1 转为 K2和V2
K1 V1
0 hello,world,hadoop
15 hdfs,hive,hello
---------------------------
K2 V2
hello 1
world 1
hdfs 1
hadoop 1
hello 1
*/
@Override
protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
Text text = new Text();
LongWritable longWritable = new LongWritable();
//1:将一行的文本数据进行拆分
String[] split = value.toString().split(",");
//2:遍历数组,组装 K2 和 V2
for (String word : split) {
//3:将K2和V2写入上下文
text.set(word);
longWritable.set(1);
context.write(text, longWritable);
}
}
}
/*
四个泛型解释:
KEYIN: K2类型
VALULEIN: V2类型
KEYOUT: K3类型
VALUEOUT:V3类型
*/
public class WordCountReducer extends Reducer<Text,LongWritable,Text,LongWritable> {
//reduce方法作用: 将新的K2和V2转为 K3和V3 ,将K3和V3写入上下文中
/*
参数:
key : 新K2
values: 集合 新 V2
context :表示上下文对象
----------------------
如何将新的K2和V2转为 K3和V3
新 K2 V2
hello <1,1,1>
world <1,1>
hadoop <1>
------------------------
K3 V3
hello 3
world 2
hadoop 1
*/
@Override
protected void reduce(Text key, Iterable<LongWritable> values, Context context) throws IOException, InterruptedException {
long count = 0;
//1:遍历集合,将集合中的数字相加,得到 V3
for (LongWritable value : values) {
count += value.get();
}
//2:将K3和V3写入上下文中
context.write(key, new LongWritable(count));
}
}
public class JobMain extends Configured implements Tool {
//该方法用于指定一个job任务
@Override
public int run(String[] args) throws Exception {
//1:创建一个job任务对象
Job job = Job.getInstance(super.getConf(), "wordcount");
//如果打包运行出错,则需要加该配置
job.setJarByClass(JobMain.class);
//2:配置job任务对象(八个步骤)
//第一步:指定文件的读取方式和读取路径
job.setInputFormatClass(TextInputFormat.class);
TextInputFormat.addInputPath(job, new Path("hdfs://node01:8020/wordcount"));
//TextInputFormat.addInputPath(job, new Path("file:///D:\\mapreduce\\input"));
//第二步:指定Map阶段的处理方式和数据类型
job.setMapperClass(WordCountMapper.class);
//设置Map阶段K2的类型
job.setMapOutputKeyClass(Text.class);
//设置Map阶段V2的类型
job.setMapOutputValueClass(LongWritable.class);
//第三,四,五,六 采用默认的方式
//第七步:指定Reduce阶段的处理方式和数据类型
job.setReducerClass(WordCountReducer.class);
//设置K3的类型
job.setOutputKeyClass(Text.class);
//设置V3的类型
job.setOutputValueClass(LongWritable.class);
//第八步: 设置输出类型
job.setOutputFormatClass(TextOutputFormat.class);
//设置输出的路径
Path path = new Path("hdfs://node01:8020/wordcount_out");
TextOutputFormat.setOutputPath(job, path);
//TextOutputFormat.setOutputPath(job, new Path("file:///D:\\mapreduce\\output"));
//获取FileSystem
FileSystem fileSystem = FileSystem.get(new URI("hdfs://node01:8020"), new Configuration());
//判断目录是否存在
boolean bl2 = fileSystem.exists(path);
if(bl2){
//删除目标目录
fileSystem.delete(path, true);
}
//等待任务结束
boolean bl = job.waitForCompletion(true);
return bl ? 0:1;
}
public static void main(String[] args) throws Exception {
Configuration configuration = new Configuration();
//启动job任务
int run = ToolRunner.run(configuration, new JobMain(), args);
System.exit(run);
}
}
分区实则目的是按照我们的需求,将不同类型的数据分开处理,最终分开获取
代码实现
结构
public class MyPartitioner extends Partitioner<Text,NullWritable> {
/*
1:定义分区规则
2:返回对应的分区编号
*/
@Override
public int getPartition(Text text, NullWritable nullWritable, int i) {
//1:拆分行文本数据(K2),获取中奖字段的值
String[] split = text.toString().split("\t");
String numStr = split[5];
//2:判断中奖字段的值和15的关系,然后返回对应的分区编号
if(Integer.parseInt(numStr) > 15){
return 1;
}else{
return 0;
}
}
}
//第三步,指定分区类
job.setPartitionerClass(MyPartitioner.class);
//第四, 五,六步
//设置ReduceTask的个数
job.setNumReduceTasks(2);
MapReduce 中的计数器
计数器是收集作业统计信息的有效手段之一,用于质量控制或应用级统计
可辅助诊断系统故障
看能否用一个计数器值来记录某一特定事件的发生 ,比分析一堆日志文件容易
通过enum枚举类型来定义计数器 统计reduce端数据的输入的key有多少个
public class PartitionerReducer extends Reducer<Text,NullWritable,Text,NullWritable> {
public static enum Counter{
MY_INPUT_RECOREDS,MY_INPUT_BYTES
}
@Override
protected void reduce(Text key, Iterable<NullWritable> values, Context context) throws IOException, InterruptedException {
//方式2:使用枚枚举来定义计数器
context.getCounter(Counter.MY_INPUT_RECOREDS).increment(1L);
context.write(key, NullWritable.get());
}
}
public class SortBean implements WritableComparable<SortBean>{
private String word;
private int num;
public String getWord() {
return word;
}
public void setWord(String word) {
this.word = word;
}
public int getNum() {
return num;
}
public void setNum(int num) {
this.num = num;
}
@Override
public String toString() {
return word + "\t"+ num ;
}
//实现比较器,指定排序的规则
/*
规则:
第一列(word)按照字典顺序进行排列 // aac aad
第一列相同的时候, 第二列(num)按照升序进行排列
*/
@Override
public int compareTo(SortBean sortBean) {
//先对第一列排序: Word排序
int result = this.word.compareTo(sortBean.word);
//如果第一列相同,则按照第二列进行排序
if(result == 0){
return this.num - sortBean.num;
}
return result;
}
//实现序列化
@Override
public void write(DataOutput out) throws IOException {
out.writeUTF(word);
out.writeInt(num);
}
//实现反序列
@Override
public void readFields(DataInput in) throws IOException {
this.word = in.readUTF();
this.num = in.readInt();
}
}
public class SortMapper extends Mapper<LongWritable,Text,SortBean,NullWritable> {
/*
map方法将K1和V1转为K2和V2:
K1 V1
0 a 3
5 b 7
----------------------
K2 V2
SortBean(a 3) NullWritable
SortBean(b 7) NullWritable
*/
@Override
protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
//1:将行文本数据(V1)拆分,并将数据封装到SortBean对象,就可以得到K2
String[] split = value.toString().split("\t");
SortBean sortBean = new SortBean();
sortBean.setWord(split[0]);
sortBean.setNum(Integer.parseInt(split[1]));
//2:将K2和V2写入上下文中
context.write(sortBean, NullWritable.get());
}
}
public class SortReducer extends Reducer<SortBean,NullWritable,SortBean,NullWritable> {
//reduce方法将新的K2和V2转为K3和V3
@Override
protected void reduce(SortBean key, Iterable<NullWritable> values, Context context) throws IOException, InterruptedException {
context.write(key, NullWritable.get());
}
}
job略
在三大阶段的第一阶段map处理完后,可能数据过多,利用分布式思想,抢在reduce前先做一次合并,后再由reduce合并,目的是:提高网络IO 性能
实现步骤
//第三(分区),四 (排序)
//第五步: 规约(Combiner)
job.setCombinerClass(MyCombiner.class);
//第六步 分布
案例:流量统计(key相同则++++++++)
public class FlowBean implements Writable {
private Integer upFlow; //上行数据包数
private Integer downFlow; //下行数据包数
private Integer upCountFlow; //上行流量总和
private Integer downCountFlow;//下行流量总和
//下略get set 序列化 反序列化
public class FlowCountMapper extends Mapper<LongWritable,Text,Text,FlowBean> {
/*
将K1和V1转为K2和V2:
K1 V1
0 1363157985059 13600217502 00-1F-64-E2-E8-B1:CMCC 120.196.100.55 www.baidu.com 综合门户 19 128 1177 16852 200
------------------------------
K2 V2
13600217502 FlowBean(19 128 1177 16852)
*/
@Override
protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
//1:拆分行文本数据,得到手机号--->K2
String[] split = value.toString().split("\t");
String phoneNum = split[1];
//2:创建FlowBean对象,并从行文本数据拆分出流量的四个四段,并将四个流量字段的值赋给FlowBean对象
FlowBean flowBean = new FlowBean();
flowBean.setUpFlow(Integer.parseInt(split[6]));
flowBean.setDownFlow(Integer.parseInt(split[7]));
flowBean.setUpCountFlow(Integer.parseInt(split[8]));
flowBean.setDownCountFlow(Integer.parseInt(split[9]));
//3:将K2和V2写入上下文中
context.write(new Text(phoneNum), flowBean);
}
}
public class FlowCountReducer extends Reducer<Text,FlowBean,Text,FlowBean> {
@Override
protected void reduce(Text key, Iterable<FlowBean> values, Context context) throws IOException, InterruptedException {
//1:遍历集合,并将集合中的对应的四个字段累计
Integer upFlow = 0; //上行数据包数
Integer downFlow = 0; //下行数据包数
Integer upCountFlow = 0; //上行流量总和
Integer downCountFlow = 0;//下行流量总和
for (FlowBean value : values) {
upFlow += value.getUpFlow();
downFlow += value.getDownFlow();
upCountFlow += value.getUpCountFlow();
downCountFlow += value.getDownCountFlow();
}
//2:创建FlowBean对象,并给对象赋值 V3
FlowBean flowBean = new FlowBean();
flowBean.setUpFlow(upFlow);
flowBean.setDownFlow(downFlow);
flowBean.setUpCountFlow(upCountFlow);
flowBean.setDownCountFlow(downCountFlow);
//3:将K3和V3下入上下文中
context.write(key, flowBean);
}
}
public class JobMain extends Configured implements Tool {
//该方法用于指定一个job任务
@Override
public int run(String[] args) throws Exception {
//1:创建一个job任务对象
Job job = Job.getInstance(super.getConf(), "mapreduce_flowcount");
//如果打包运行出错,则需要加该配置
job.setJarByClass(JobMain.class);
//2:配置job任务对象(八个步骤)
//第一步:指定文件的读取方式和读取路径
job.setInputFormatClass(TextInputFormat.class);
//TextInputFormat.addInputPath(job, new Path("hdfs://node01:8020/wordcount"));
TextInputFormat.addInputPath(job, new Path("file:///D:\\input\\flowcount_input"));
//第二步:指定Map阶段的处理方式和数据类型
job.setMapperClass(FlowCountMapper.class);
//设置Map阶段K2的类型
job.setMapOutputKeyClass(Text.class);
//设置Map阶段V2的类型
job.setMapOutputValueClass(FlowBean.class);
//第三(分区),四 (排序)
//第五步: 规约(Combiner)
//第六步 分组
//第七步:指定Reduce阶段的处理方式和数据类型
job.setReducerClass(FlowCountReducer.class);
//设置K3的类型
job.setOutputKeyClass(Text.class);
//设置V3的类型
job.setOutputValueClass(FlowBean.class);
//第八步: 设置输出类型
job.setOutputFormatClass(TextOutputFormat.class);
//设置输出的路径
TextOutputFormat.setOutputPath(job, new Path("file:///D:\\out\\flowcount_out"));
//等待任务结束
boolean bl = job.waitForCompletion(true);
return bl ? 0:1;
}
public static void main(String[] args) throws Exception {
Configuration configuration = new Configuration();
//启动job任务
int run = ToolRunner.run(configuration, new JobMain(), args);
System.exit(run);
}
}
如增加需求:
上行流量倒序排序
public class FlowBean implements WritableComparable<FlowBean> {
//指定排序的规则
@Override
public int compareTo(FlowBean flowBean) {
// return this.upFlow.compareTo(flowBean.getUpFlow()) * -1;
return flowBean.upFlow - this.upFlow ;
}
}
需求:手机号码分区
public class FlowCountPartition extends Partitioner<Text,FlowBean> {
/*
该方法用来指定分区的规则:
135 开头数据到一个分区文件
136 开头数据到一个分区文件
137 开头数据到一个分区文件
其他分区
参数:
text : K2 手机号
flowBean: V2
i : ReduceTask的个数
*/
@Override
public int getPartition(Text text, FlowBean flowBean, int i) {
//1:获取手机号
String phoneNum = text.toString();
//2:判断手机号以什么开头,返回对应的分区编号(0-3)
if(phoneNum.startsWith("135")){
return 0;
}else if(phoneNum.startsWith("136")){
return 1;
}else if(phoneNum.startsWith("137")){
return 2;
}else{
return 3;
}
}
}
//第三(分区),四 (排序)
job.setPartitionerClass(FlowCountPartition.class);
//第五步: 规约(Combiner)
//第六步 分组
//设置reduce个数
job.setNumReduceTasks(4);
标签:编号 exception spl 将不 height 方式 ros 功能 one
原文地址:https://www.cnblogs.com/leccoo/p/11337386.html