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
在业务数据分析中,按天拆分统计夜间时段的数据是高频需求——比如电商夜间订单监测、平台夜间用户活跃度分析、运维系统夜间异常 ...
2026-07-29在机器学习建模与特征工程实践中,判断不同特征对模型预测效果的贡献度,是特征筛选、模型解释、业务归因的核心环节。特征置换重 ...
2026-07-29 很多数据分析师精通Excel单元格操作,但当被问到“表结构数据的基本处理单位是什么”“字段和记录的本质区别”“为什么表结 ...
2026-07-29【核心关键词】岗位、数字化、经验、课程、方法论、决策、企业、大方向、数据分析、销售管理、理论知识、思维方式、分析销售、 ...
2026-07-28在问卷调研、用户分群、效果对比等业务数据分析中,分类变量的关联性与差异性验证是高频需求。卡方检验作为针对离散分类数据的经 ...
2026-07-28 数据分析师八成以上的时间在和数据表格打交道,但许多人拿到Excel后习惯性地先算、先分析,结果回头发现漏了一列关键数据, ...
2026-07-28在Excel数据分析与报表制作中,数据透视表是快速完成多维度汇总、分组统计的核心工具。很多从业者在得到透视表汇总结果后,为了 ...
2026-07-27 很多数据分析师每天与Excel打交道,但当被问到“表格结构数据的基本处理单位是什么”“数据类型误判会引发哪些分析错误”“ ...
2026-07-27当下,我们已然步入数据要素价值全面释放的智能时代。数据不再只是零散的数字记录,更是驱动新质生产力运转的核心动能、滋养人工 ...
2026-07-27【核心关键词】客户、数据分析、指标体系、数据采集、数据指标、业务数据、分析思路、业务需求、分析方法 【专访摘要】本次 CDA ...
2026-07-24在数据分析、业务建模与数字化运营体系中,原始业务数据普遍存在缺失、重复、异常、口径不一致等质量问题,直接用于分析与建模会 ...
2026-07-24 很多数据分析师能熟练计算均值、标准差,但当被问到“如何用一张图让业务方3秒内看懂核心结论”“面对不同数据类型该怎么选 ...
2026-07-24在数据驱动的精细化运营体系中,指标是业务判断、效果复盘、策略优化的核心依据。随着企业数据化程度提升,指标数量持续膨胀,但 ...
2026-07-23在用户运营与产品增长体系中,留存是衡量产品真实价值与用户粘性的核心标尺,也是决定用户生命周期价值、获客投产比的底层因素。 ...
2026-07-23 很多数据分析师精通Excel、SQL、Python等工具,但当被问到“面对一个具体的业务问题,该用什么分析方法”“描述性分析和诊断 ...
2026-07-23【核心关键词】埋点、产品、互联网、数据库、决策、数据分析、产品经理、商业模式、移动互联网、指标体系、运营模块、大数据平 ...
2026-07-22在高并发、大数据量的业务系统中,单表数据量达到千万级甚至亿级后,会出现查询性能骤降、索引维护成本飙升、存储扩容困难等问题 ...
2026-07-22 很多企业团队并非缺乏指标,而是陷入“指标失控”:仪表盘上堆满实时跳动的数据,却无法回答“当前瓶颈在哪、下一步该做什么 ...
2026-07-22在金融风控、企业运营、行业研究等数据分析场景中,大量数据以面板数据形态存在:例如多家分支机构连续多个季度的风险指标、多位 ...
2026-07-21 很多数据分析师每天都在计算指标、制作报表,但当被问到“什么叫指标数据元”“指标数据标准包含哪些核心维度”“指标数据质 ...
2026-07-21