各种坑
没有导入包
Caused by: java.lang.ClassNotFoundException: org.apache.hadoop.yarn.exceptions.YarnException org.apache.hadoop.conf.Configuration
把yarn的包都导入了
连不上IP
Failed to connect to /127.0.0.1:9866 for block BP-1097528271-127.0.1.1-1619346840026:blk_1073741829_1005, add to deadNodes and continue.
伪分布式安装没装好,修改配置/usr/local/hadoop/etc/hadoop/core-site.xml
将
<name>fs.defaultFS</name>
<value>hdfs://localhost:9000</value>
中的localhost改成虚拟机的IP
End of File Exception between local host is: “Nick/192.168.137.1”; destination host is: “192.168.2.128”:9200; :
修改后连接的IP要修改
目录不存在
Exception in thread “main” org.apache.hadoop.mapreduce.lib.input.InvalidInputException: Input path does not exist: hdfs://192.168.2.128:9000/user/hadoop/input
实验内容
先将文件上传
hdfs dfs -mkdir -p /user/hadoop/input
hdfs dfs -put A.txt /user/hadoop/input
删除output目录
hdfs dfs -rm -r /user/hadoop/output
一 编程实现文件合并和去重操作
代码
import java.io.IOException;
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.util.GenericOptionsParser;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
public class Merge {
/**
* @param args
* 对A,B两个文件进行合并,并剔除其中重复的内容,得到一个新的输出文件C
*/
//在这重载map函数,直接将输入中的value复制到输出数据的key上 注意在map方法中要抛出异常:throws IOException,InterruptedException
public static class Map extends Mapper<Object, Text, Text, Text> {
private static Text text = new Text();
public void map(Object key, Text value, Context content) throws IOException, InterruptedException {
text = value;
content.write(text, new Text(""));
}
}
//在这重载reduce函数,直接将输入中的key复制到输出数据的key上 注意在reduce方法上要抛出异常:throws IOException,InterruptedException
public static class Reduce extends Reducer<Text, Text, Text, Text> {
public void reduce(Text key, Iterable<Text> values, Context context) throws IOException, InterruptedException {
context.write(key, new Text(""));
}
}
public static void main(String[] args) throws Exception{
// TODO Auto-generated method stub
Configuration conf = new Configuration();
conf.set("fs.defaultFS","hdfs://192.168.2.182:9000");
String[] otherArgs = new String[]{"input","output"}; /* 直接设置输入参数 */
if (otherArgs.length != 2) {
System.err.println("Usage: wordcount <in> <out>");
System.exit(2);
}
Job job = Job.getInstance(conf,"Merge and duplicate removal");
job.setJarByClass(Merge.class);
job.setMapperClass(Map.class);
job.setCombinerClass(Reduce.class);
job.setReducerClass(Reduce.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(Text.class);
FileInputFormat.addInputPath(job, new Path(otherArgs[0]));
FileOutputFormat.setOutputPath(job, new Path(otherArgs[1]));
System.exit(job.waitForCompletion(true) ? 0 : 1);
}
}
运行结果
hdfs dfs -cat /user/hadoop/output/part-r-00000
二 编程实现对输入文件的排序
代码
import java.io.IOException;
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.Partitioner;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.util.GenericOptionsParser;
public class MergeSort {
/**
* @param args
* 输入多个文件,每个文件中的每行内容均为一个整数
* 输出到一个新的文件中,输出的数据格式为每行两个整数,第一个数字为第二个整数的排序位次,第二个整数为原待排列的整数
*/
//map函数读取输入中的value,将其转化成IntWritable类型,最后作为输出key
public static class Map extends Mapper<Object, Text, IntWritable, IntWritable>{
private static IntWritable data = new IntWritable();
public void map(Object key, Text value, Context context) throws IOException,InterruptedException{
/********** Begin **********/
String line = value.toString();
data.set(Integer.parseInt(line));
context.write(data, new IntWritable(1));
/********** End **********/
}
}
//reduce函数将map输入的key复制到输出的value上,然后根据输入的value-list中元素的个数决定key的输出次数,定义一个全局变量line_num来代表key的位次
public static class Reduce extends Reducer<IntWritable, IntWritable, IntWritable, IntWritable>{
private static IntWritable line_num = new IntWritable(1);
public void reduce(IntWritable key, Iterable<IntWritable> values, Context context) throws IOException,InterruptedException{
/********** Begin **********/
for(IntWritable num : values) {
context.write(line_num, key);
line_num = new IntWritable(line_num.get() + 1);
}
/********** End **********/
}
}
//自定义Partition函数,此函数根据输入数据的最大值和MapReduce框架中Partition的数量获取将输入数据按照大小分块的边界,然后根据输入数值和边界的关系返回对应的Partiton ID
public static class Partition extends Partitioner<IntWritable, IntWritable>{
public int getPartition(IntWritable key, IntWritable value, int num_Partition){
/********** Begin **********/
int Maxnumber = 65223;//int型的最大数值
int bound = Maxnumber / num_Partition + 1;
int Keynumber = key.get();
for(int i = 0; i < num_Partition; i++){
if(Keynumber < bound * i && Keynumber >= bound * (i - 1)) {
return i - 1;
}
}
return -1 ;
/********** End **********/
}
}
public static void main(String[] args) throws Exception{
// TODO Auto-generated method stub
Configuration conf = new Configuration();
conf.set("fs.defaultFS","hdfs://192.168.2.128:9000");
String[] otherArgs = new String[]{"input2","output2"}; /* 直接设置输入参数 */
if (otherArgs.length != 2) {
System.err.println("Usage: wordcount <in> <out>");
System.exit(2);
}
Job job = Job.getInstance(conf,"Merge and Sort");
job.setJarByClass(MergeSort.class);
job.setMapperClass(Map.class);
job.setReducerClass(Reduce.class);
job.setPartitionerClass(Partition.class);
job.setOutputKeyClass(IntWritable.class);
job.setOutputValueClass(IntWritable.class);
System.out.println(new Path(otherArgs[0]));
FileInputFormat.addInputPath(job, new Path(otherArgs[0]));
FileOutputFormat.setOutputPath(job, new Path(otherArgs[1]));
System.exit(job.waitForCompletion(true) ? 0 : 1);
}
}
三 对给定的表格进行信息挖掘
child parent
Steven Lucy
Steven Jack
Jone Lucy
Jone Jack
Lucy Mary
Lucy Frank
Jack Alice
Jack Jesse
David Alice
David Jesse
Philip David
Philip Alma
Mark David
Mark Alma
hdfs dfs -put /home/hadoop/child-parent.txt /user/hadoop/input3
import java.io.IOException;
import java.util.*;
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.output.FileOutputFormat;
import org.apache.hadoop.util.GenericOptionsParser;
public class child_parent {
public static int time = 0;
/**
* @param args
* 输入一个child-parent的表格
* 输出一个体现grandchild-grandparent关系的表格
*/
//Map将输入文件按照空格分割成child和parent,然后正序输出一次作为右表,反序输出一次作为左表,需要注意的是在输出的value中必须加上左右表区别标志
public static class Map extends Mapper<Object, Text, Text, Text>{
public void map(Object key, Text value, Context context) throws IOException,InterruptedException{
String child_name = new String();
String parent_name = new String();
String relation_type = new String();
String line = value.toString();
int i = 0;
while(line.charAt(i) != ' '){
i++;
}
String[] values = {line.substring(0,i),line.substring(i+1)};
if(values[0].compareTo("child") != 0){
child_name = values[0];
parent_name = values[1];
relation_type = "1";//左右表区分标志
context.write(new Text(values[1]), new Text(relation_type+"+"+child_name+"+"+parent_name));
//左表
relation_type = "2";
context.write(new Text(values[0]), new Text(relation_type+"+"+child_name+"+"+parent_name));
//右表
}
}
}
public static class Reduce extends Reducer<Text, Text, Text, Text>{
public void reduce(Text key, Iterable<Text> values,Context context) throws IOException,InterruptedException{
if(time == 0){ //输出表头
context.write(new Text("grand_child"), new Text("grand_parent"));
time++;
}
int grand_child_num = 0;
String grand_child[] = new String[10];
int grand_parent_num = 0;
String grand_parent[]= new String[10];
Iterator ite = values.iterator();
while(ite.hasNext()){
String record = ite.next().toString();
int len = record.length();
int i = 2;
if(len == 0) continue;
char relation_type = record.charAt(0);
String child_name = new String();
String parent_name = new String();
//获取value-list中value的child
while(record.charAt(i) != '+'){
child_name = child_name + record.charAt(i);
i++;
}
i=i+1;
//获取value-list中value的parent
while(i<len){
parent_name = parent_name+record.charAt(i);
i++;
}
//左表,取出child放入grand_child
if(relation_type == '1'){
grand_child[grand_child_num] = child_name;
grand_child_num++;
}
else{//右表,取出parent放入grand_parent
grand_parent[grand_parent_num] = parent_name;
grand_parent_num++;
}
}
if(grand_parent_num != 0 && grand_child_num != 0 ){
for(int m = 0;m<grand_child_num;m++){
for(int n=0;n<grand_parent_num;n++){
context.write(new Text(grand_child[m]), new Text(grand_parent[n]));
//输出结果
}
}
}
}
}
public static void main(String[] args) throws Exception{
// TODO Auto-generated method stub
Configuration conf = new Configuration();
conf.set("fs.default.name","hdfs://192.168.2.128:9000");
String[] otherArgs = new String[]{"input3","output3"}; /* 直接设置输入参数 */
if (otherArgs.length != 2) {
System.err.println("Usage: wordcount <in><out>");
System.exit(2);
}
Job job = Job.getInstance(conf,"Single table join");
job.setJarByClass(child_parent.class);
job.setMapperClass(Map.class);
job.setReducerClass(Reduce.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(Text.class);
FileInputFormat.addInputPath(job, new Path(otherArgs[0]));
FileOutputFormat.setOutputPath(job, new Path(otherArgs[1]));
System.exit(job.waitForCompletion(true) ? 0 : 1);
}
}
代码参考: 林子雨编著《大数据基础编程、实验和案例教程(第2版)》教材附录A的代码
http://dblab.xmu.edu.cn/blog/2808-2/
合并文件
one.txt
yongpeng weidong weinan
sanfeng luozong xiaoming
two.txt
longlong fanfan
mazong kailun yuhang yixin
longlong fanfan
mazong kailun yuhang yixin
three.txt
shuaige changmo zhenqiang
dongli lingu xuanxuan
代码:
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FSDataInputStream;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.BytesWritable;
import org.apache.hadoop.io.IOUtils;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.*;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.input.FileSplit;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.mapreduce.lib.output.SequenceFileOutputFormat;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FSDataInputStream;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.BytesWritable;
import org.apache.hadoop.io.IOUtils;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.InputSplit;
import org.apache.hadoop.mapreduce.RecordReader;
import org.apache.hadoop.mapreduce.TaskAttemptContext;
import org.apache.hadoop.mapreduce.lib.input.FileSplit;
import java.io.IOException;
/**
* @program: test2_java1
* @ClassName :Combine
* @Description:
* @Author :Nick
* @Date :2021-06-21 22:48
**/
public class Combine {
public static void main(String[] args) throws Exception {
// 输入输出路径需要根据自己电脑上实际的输入输出路径设置
String inputDir = "/inputdata";
String outputDir = "/output";
process(inputDir, outputDir);
}
/**
* 执行hdfs
* @param inputDir 输入文件夹地址
* @param outputDir 输出文件夹地址
* @throws IOException
* @throws InterruptedException
* @throws ClassNotFoundException
*/
private static void process(String inputDir, String outputDir) throws IOException, InterruptedException, ClassNotFoundException {
// 1 获取job对象
Configuration conf = new Configuration();
// 设置可以读子目录
conf.set("mapreduce.input.fileinputformat.input.dir.recursive", "true");
conf.set("fs.default.name","hdfs://192.168.2.128:9000");
Job job = Job.getInstance(conf);
// 2 设置jar包存储位置、关联自定义的mapper和reducer
job.setJarByClass(Combine.class);
job.setMapperClass(CombineFileMapper.class);
job.setReducerClass(CombineFileReducer.class);
// 7设置输入的inputFormat
job.setInputFormatClass(CombineFileInputformat.class);
// 8设置输出的outputFormat
job.setOutputFormatClass(SequenceFileOutputFormat.class);
// 3 设置map输出端的kv类型
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(BytesWritable.class);
// 4 设置最终输出端的kv类型
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(BytesWritable.class);
// 5 设置输入输出路径
FileInputFormat.setInputPaths(job, new Path(inputDir));
FileOutputFormat.setOutputPath(job, new Path(outputDir));
// 6 提交job
boolean result = job.waitForCompletion(true);
System.exit(result ? 0 : 1);
}
}
// 定义类继承FileInputFormat
class CombineFileInputformat extends FileInputFormat<Text, BytesWritable> {
@Override
protected boolean isSplitable(JobContext context, Path filename) {
return false;
}
@Override
public RecordReader<Text, BytesWritable> createRecordReader(InputSplit split, TaskAttemptContext context) throws IOException, InterruptedException {
CombineFileRecordReader recordReader = new CombineFileRecordReader();
recordReader.initialize(split, context);
return recordReader;
}
}
/**
* <b>合并小文件 Mapper<br>
* </b>
* Text, BytesWritable, Text, BytesWritable
* 输入Key类型,输入Value类型,输出Key类型,输出Value类型
*/
class CombineFileMapper extends Mapper<Text, BytesWritable, Text, BytesWritable> {
@Override
protected void map(Text key, BytesWritable value, Context context) throws IOException, InterruptedException {
context.write(key, value);
}
}
class CombineFileRecordReader extends RecordReader<Text, BytesWritable> {
private Configuration configuration;
private FileSplit split;
private boolean isProgress = true;
private BytesWritable value = new BytesWritable();
private Text k = new Text();
@Override
public void initialize(InputSplit split, TaskAttemptContext context) throws IOException, InterruptedException {
this.split = (FileSplit) split;
configuration = context.getConfiguration();
}
@Override
public boolean nextKeyValue() throws IOException, InterruptedException {
if (isProgress) {
// 1 定义缓存区
byte[] contents = new byte[(int) split.getLength()];
FileSystem fs = null;
FSDataInputStream fis = null;
try {
// 2 获取文件系统
Path path = split.getPath();
fs = path.getFileSystem(configuration);
// 3 读取数据
fis = fs.open(path);
// 4 读取文件内容
IOUtils.readFully(fis, contents, 0, contents.length);
// 5 输出文件内容
value.set(contents, 0, contents.length);
// 6 获取文件路径及名称
String name = split.getPath().toString();
// 7 设置输出的key值
k.set(name);
} catch (Exception e) {
} finally {
IOUtils.closeStream(fis);
}
isProgress = false;
return true;
}
return false;
}
@Override
public Text getCurrentKey() throws IOException, InterruptedException {
return k;
}
@Override
public BytesWritable getCurrentValue() throws IOException, InterruptedException {
return value;
}
@Override
public float getProgress() throws IOException, InterruptedException {
return 0;
}
@Override
public void close() throws IOException {
}
}
/**
* <b>合并小文件 Reducer<br>
* </b>
* Text, BytesWritable, Text, BytesWritable
* 输入Key类型,输入Value类型,输出Key类型,输出Value类型
*/
class CombineFileReducer extends Reducer<Text, BytesWritable, Text, BytesWritable> {
@Override
protected void reduce(Text key, Iterable<BytesWritable> values, Context context) throws IOException, InterruptedException {
context.write(key, values.iterator().next());
}
}