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
在数据分析、质量控制、科研实验等场景中,数据波动性(离散程度)的精准衡量是判断数据可靠性、稳定性的核心环节。标准差(Stan ...
2026-01-29在数据分析、质量检测、科研实验等领域,判断数据间是否存在本质差异是核心需求,而t检验、F检验是实现这一目标的经典统计方法。 ...
2026-01-29统计制图(数据可视化)是数据分析的核心呈现载体,它将抽象的数据转化为直观的图表、图形,让数据规律、业务差异与潜在问题一目 ...
2026-01-29箱线图(Box Plot)作为数据分布可视化的核心工具,能清晰呈现数据的中位数、四分位数、异常值等关键统计特征,广泛应用于数据分 ...
2026-01-28在回归分析、机器学习建模等数据分析场景中,多重共线性是高频数据问题——当多个自变量间存在较强的线性关联时,会导致模型系数 ...
2026-01-28数据分析的价值落地,离不开科学方法的支撑。六种核心分析方法——描述性分析、诊断性分析、预测性分析、规范性分析、对比分析、 ...
2026-01-28在机器学习与数据分析领域,特征是连接数据与模型的核心载体,而特征重要性分析则是挖掘数据价值、优化模型性能、赋能业务决策的 ...
2026-01-27关联分析是数据挖掘领域中挖掘数据间潜在关联关系的经典方法,广泛应用于零售购物篮分析、电商推荐、用户行为路径挖掘等场景。而 ...
2026-01-27数据分析的基础范式,是支撑数据工作从“零散操作”走向“标准化落地”的核心方法论框架,它定义了数据分析的核心逻辑、流程与目 ...
2026-01-27在数据分析、后端开发、业务运维等工作中,SQL语句是操作数据库的核心工具。面对复杂的表结构、多表关联逻辑及灵活的查询需求, ...
2026-01-26支持向量机(SVM)作为机器学习中经典的分类算法,凭借其在小样本、高维数据场景下的优异泛化能力,被广泛应用于图像识别、文本 ...
2026-01-26在数字化浪潮下,数据分析已成为企业决策的核心支撑,而CDA数据分析师作为标准化、专业化的数据人才代表,正逐步成为连接数据资 ...
2026-01-26数据分析的核心价值在于用数据驱动决策,而指标作为数据的“载体”,其选取的合理性直接决定分析结果的有效性。选对指标能精准定 ...
2026-01-23在MySQL查询编写中,我们习惯按“SELECT → FROM → WHERE → ORDER BY”的语法顺序组织语句,直觉上认为代码顺序即执行顺序。但 ...
2026-01-23数字化转型已从企业“可选项”升级为“必答题”,其核心本质是通过数据驱动业务重构、流程优化与模式创新,实现从传统运营向智能 ...
2026-01-23CDA持证人已遍布在世界范围各行各业,包括世界500强企业、顶尖科技独角兽、大型金融机构、国企事业单位、国家行政机关等等,“CDA数据分析师”人才队伍遵守着CDA职业道德准则,发挥着专业技能,已成为支撑科技发展的核心力量。 ...
2026-01-22在数字化时代,企业积累的海量数据如同散落的珍珠,而数据模型就是串联这些珍珠的线——它并非简单的数据集合,而是对现实业务场 ...
2026-01-22在数字化运营场景中,用户每一次点击、浏览、交互都构成了行为轨迹,这些轨迹交织成海量的用户行为路径。但并非所有路径都具备业 ...
2026-01-22在数字化时代,企业数据资产的价值持续攀升,数据安全已从“合规底线”升级为“生存红线”。企业数据安全管理方法论以“战略引领 ...
2026-01-22在SQL数据分析与业务查询中,日期数据是高频处理对象——订单创建时间、用户注册日期、数据统计周期等场景,都需对日期进行格式 ...
2026-01-21