京公网安备 11010802034615号
经营许可证编号:京B2-20210330
rm -rf /opt/linuxsir/hadoop/logs/*.*
ssh root@192.168.31.132 rm -rf /opt/linuxsir/hadoop/logs/*.*
ssh root@192.168.31.133 rm -rf /opt/linuxsir/hadoop/logs/*.*
clear
cd /opt/linuxsir/hadoop/sbin
./start-dfs.sh
./start-yarn.sh
clear
jps
ssh root@192.168.31.132 jps
ssh root@192.168.31.133 jps
在eclipse里面操作如下:
New-Java Project,名称自定义即可,如 java-prjNew-Package,名称自定义为com.pai.hdfs_demoNew-Class,名称自定义为ReadWriteHDFSExamplepackage com.pai.hdfs_demo;
import org.apache.commons.io.IOUtils;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FSDataInputStream;
import org.apache.hadoop.fs.FSDataOutputStream;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import java.io.*;
import java.nio.charset.StandardCharsets;
public class ReadWriteHDFSExample {
// main 新建一个类ReadWriteHDFSExample,编写main函数如下。main函数调用其它函数,创建目录,写入数据,添加数据,然后再读取数据
public static void main(String[] args) throws IOException {
// ReadWriteHDFSExample.checkExists();
ReadWriteHDFSExample.createDirectory();
ReadWriteHDFSExample.writeFileToHDFS();
ReadWriteHDFSExample.appendToHDFSFile();
ReadWriteHDFSExample.readFileFromHDFS();
}
// readFileFromHDFS 该函数读取文件内容,以字符串形式显示出来
public static void readFileFromHDFS() throws IOException {
Configuration configuration = new Configuration();
configuration.set("fs.defaultFS", "hdfs://192.168.31.131:9000");
FileSystem fileSystem = FileSystem.get(configuration);
// Create a path
String fileName = "read_write_hdfs_example.txt";
Path hdfsReadPath = new Path("/javareadwriteexample/" + fileName);
// initialize input stream
FSDataInputStream inputStream = fileSystem.open(hdfsReadPath);
// Classical input stream usage
String out = IOUtils.toString(inputStream, "UTF-8");
System.out.println(out);
// BufferedReader bufferedReader = new BufferedReader(
// new InputStreamReader(inputStream, StandardCharsets.UTF_8));
// String line = null;
// while ((line=bufferedReader.readLine())!=null){
// System.out.println(line);
// }
inputStream.close();
fileSystem.close();
}
// writeFileToHDFS writeFileToHDFS函数打开文件,写入一行文本
public static void writeFileToHDFS() throws IOException {
Configuration configuration = new Configuration();
configuration.set("fs.defaultFS", "hdfs://192.168.31.131:9000");
FileSystem fileSystem = FileSystem.get(configuration);
// Create a path
String fileName = "read_write_hdfs_example.txt";
Path hdfsWritePath = new Path("/javareadwriteexample/" + fileName);
FSDataOutputStream fsDataOutputStream = fileSystem.create(hdfsWritePath, true);
BufferedWriter bufferedWriter = new BufferedWriter(
new OutputStreamWriter(fsDataOutputStream, StandardCharsets.UTF_8));
bufferedWriter.write("Java API to write data in HDFS");
bufferedWriter.newLine();
bufferedWriter.close();
fileSystem.close();
}
// appendToHDFSFile 函数打开文件,添加一行文本。需要注意的是,需要对Configuration类的对象configuration进行适当设置,否则出错
public static void appendToHDFSFile() throws IOException {
Configuration configuration = new Configuration();
configuration.set("fs.defaultFS", "hdfs://192.168.31.131:9000");
//configuration.setBoolean("dfs.client.block.write.replace-datanode-on-failure.enabled", true);
configuration.set("dfs.client.block.write.replace-datanode-on-failure.policy","NEVER");
configuration.set("dfs.client.block.write.replace-datanode-on-failure.enable","true");
FileSystem fileSystem = FileSystem.get(configuration);
// Create a path
String fileName = "read_write_hdfs_example.txt";
Path hdfsWritePath = new Path("/javareadwriteexample/" + fileName);
FSDataOutputStream fsDataOutputStream = fileSystem.append(hdfsWritePath);
BufferedWriter bufferedWriter = new BufferedWriter(
new OutputStreamWriter(fsDataOutputStream, StandardCharsets.UTF_8));
bufferedWriter.write("Java API to append data in HDFS file");
bufferedWriter.newLine();
bufferedWriter.close();
fileSystem.close();
}
// createDirectory 函数创建一个目录
public static void createDirectory() throws IOException {
Configuration configuration = new Configuration();
configuration.set("fs.defaultFS", "hdfs://192.168.31.131:9000");
FileSystem fileSystem = FileSystem.get(configuration);
String directoryName = "/javareadwriteexample";
Path path = new Path(directoryName);
fileSystem.mkdirs(path);
}
// checkExists checkExists检查目录或者文件是否存在。注意如下代码的最后一个括号是ReadWriteHDFSExample类的结束括号
public static void checkExists() throws IOException {
Configuration configuration = new Configuration();
configuration.set("fs.defaultFS", "hdfs://192.168.31.131:9000");
FileSystem fileSystem = FileSystem.get(configuration);
String directoryName = "/javareadwriteexample";
Path path = new Path(directoryName);
if (fileSystem.exists(path)) {
System.out.println("File/Folder Exists : " + path.getName());
} else {
System.out.println("File/Folder does not Exists : " + path.getName());
}
}
}
为了编译通过上述Java代码,需要把如下目录下的jar包导入Eclipse项目的Build Path
操作序列为 右键点击Eclipse里的Java项目→Properties→Java Build Path →Libraries→Add External Jars
# 添加如下路径的包
D:hadoop-2.7.3sharehadoopcommonlib
D:hadoop-2.7.3sharehadoopcommon
D:hadoop-2.7.3sharehadoophdfs
D:hadoop-2.7.3sharehadoophdfslib
D:hadoop-2.7.3sharehadoopmapreducelib
D:hadoop-2.7.3sharehadoopmapreduce
D:hadoop-2.7.3sharehadoopyarnlib
D:hadoop-2.7.3sharehadoopyarn
就可以愉快地执行了,执行完毕上述代码后,在hd-master主机上可以通过如下命令,检查已经写入的文件
[root@hd-master bin]# cd /opt/linuxsir/hadoop/bin
[root@hd-master bin]# ./hdfs dfs -ls /javareadwriteexample/read_write_hdfs_example.txt
-rw-r--r-- 3 root supergroup 70 2024-10-10 04:47 /javareadwriteexample/read_write_hdfs_example.txt
[root@hd-master bin]# ./hdfs dfs -cat /javareadwriteexample/read_write_hdfs_example.txt
Java API to write data in HDFS
Java API to append data in HDFS file
为了多次进行实验(或者为了调试代码),可以把HDFS文件删除,然后再执行或者调试Java代码,否则一经存在该目录,执行创建目录的代码就会出错
cd /opt/linuxsir/hadoop/bin
./hdfs dfs -rm /javareadwriteexample/*
./hdfs dfs -rmdir /javareadwriteexample
cd /opt/linuxsir/hadoop/sbin
./stop-yarn.sh
./stop-dfs.sh
jps
ssh root@192.168.31.132 jps
ssh root@192.168.31.133 jps
package mywordcount;
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.output.FileOutputFormat;
import org.apache.hadoop.util.GenericOptionsParser;
public class WordCount {
//定义WordCount类的内部类TokenizerMapper 该类实现了map函数,把从文件读取的每个word变成一个形式为<word,1>的Key Value对,输出到map函数的参数context对象,由执行引擎完成Shuffle
public static class TokenizerMapper 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);
}
}
}
//定义WordCount类的内部类IntSumReducer 该类实现了reduce函数,它收拢所有相同key的、形式为<word,1>的Key-Value对,对Value部分进行累加,输出一个计数
public static class IntSumReducer 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);
String thekey = key.toString();
int thevalue = sum;
}
}
// WordCount类的main函数,负责配置Job的若干关键的参数,并且启动这个Job。在main函数中,conf对象包含了一个属性即“fs.defaultFS”,它的值为“hdfs://192.168.31.131:9000”,使得WordCount程序知道如何存取HDFS
public static void main(String[] args) throws Exception {
Configuration conf = new Configuration();
String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();
if (otherArgs.length != 2) {
System.err.println("Usage: wordcount <in> <out>");
System.exit(2);
}
conf.set("fs.defaultFS", "hdfs://192.168.31.131:9000");
Job job = new Job(conf, "word count");
job.setJarByClass(WordCount.class);
job.setMapperClass(TokenizerMapper.class);
job.setCombinerClass(IntSumReducer.class);
job.setReducerClass(IntSumReducer.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(IntWritable.class);
FileInputFormat.addInputPath(job, new Path(otherArgs[0]));
FileOutputFormat.setOutputPath(job, new Path(otherArgs[1]));
System.exit(job.waitForCompletion(true) ? 0 : 1);
}
}
[root@hd-master bin]# ./hdfs dfs -ls /output1
Found 2 items
-rw-r--r-- 3 root supergroup 0 2024-10-10 05:17 /output1/_SUCCESS
-rw-r--r-- 3 root supergroup 89 2024-10-10 05:17 /output1/part-r-00000
[root@hd-master bin]# ./hdfs dfs -cat /output1/part-r-00000
I 1
apache 1
cloudera 1
google 1
hadoop 8
hortonworks 1
ibm 1
intel 1
like 1
microsoft 1
数据分析咨询请扫描二维码
若不方便扫码,搜微信号:CDAshujufenxi
在数据处理的全流程中,数据呈现与数据分析是两个紧密关联却截然不同的核心环节。无论是科研数据整理、企业业务复盘,还是日常数 ...
2026-03-06在数据分析、数据预处理场景中,dat文件是一种常见的二进制或文本格式数据文件,广泛应用于科研数据、工程数据、传感器数据等领 ...
2026-03-06在数据驱动决策的时代,CDA(Certified Data Analyst)数据分析师的核心价值,早已超越单纯的数据清洗与统计分析,而是通过数据 ...
2026-03-06在教学管理、培训数据统计、课程体系搭建等场景中,经常需要对课时数据进行排序并实现累加计算——比如,按课程章节排序,累加各 ...
2026-03-05在数据分析场景中,环比是衡量数据短期波动的核心指标——它通过对比“当前周期与上一个相邻周期”的数据,直观反映指标的月度、 ...
2026-03-05数据治理是数字化时代企业实现数据价值最大化的核心前提,而CDA(Certified Data Analyst)数据分析师作为数据全生命周期的核心 ...
2026-03-05在实验检测、质量控制、科研验证等场景中,“方法验证”是确保检测/分析结果可靠、可复用的核心环节——无论是新开发的检测方法 ...
2026-03-04在数据分析、科研实验、办公统计等场景中,我们常常需要对比两组数据的整体差异——比如两种营销策略的销售额差异、两种实验方案 ...
2026-03-04在数字化转型进入深水区的今天,企业对数据的依赖程度日益加深,而数据治理体系则是企业实现数据规范化、高质量化、价值化的核心 ...
2026-03-04在深度学习,尤其是卷积神经网络(CNN)的实操中,转置卷积(Transposed Convolution)是一个高频应用的操作——它核心用于实现 ...
2026-03-03在日常办公、数据分析、金融理财、科研统计等场景中,我们经常需要计算“平均值”来概括一组数据的整体水平——比如计算月度平均 ...
2026-03-03在数字化转型的浪潮中,数据已成为企业最核心的战略资产,而数据治理则是激活这份资产价值的前提——没有规范、高质量的数据治理 ...
2026-03-03在Excel办公中,数据透视表是汇总、分析繁杂数据的核心工具,我们常常通过它快速得到销售额汇总、人员统计、业绩分析等关键结果 ...
2026-03-02在日常办公和数据分析中,我们常常需要探究两个或多个数据之间的关联关系——比如销售额与广告投入是否正相关、员工出勤率与绩效 ...
2026-03-02在数字化运营中,时间序列数据是CDA(Certified Data Analyst)数据分析师最常接触的数据类型之一——每日的营收、每小时的用户 ...
2026-03-02在日常办公中,数据透视表是Excel、WPS等表格工具中最常用的数据分析利器——它能快速汇总繁杂数据、挖掘数据关联、生成直观报表 ...
2026-02-28有限元法(Finite Element Method, FEM)作为工程数值模拟的核心工具,已广泛应用于机械制造、航空航天、土木工程、生物医学等多 ...
2026-02-28在数字化时代,“以用户为中心”已成为企业运营的核心逻辑,而用户画像则是企业读懂用户、精准服务用户的关键载体。CDA(Certifi ...
2026-02-28在Python面向对象编程(OOP)中,类方法是构建模块化、可复用代码的核心载体,也是实现封装、继承、多态特性的关键工具。无论是 ...
2026-02-27在MySQL数据库优化中,索引是提升查询效率的核心手段—— 面对千万级、亿级数据量,合理创建索引能将查询时间从秒级压缩到毫秒级 ...
2026-02-27