
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
,名稱(chēng)自定義即可,如 java-prj
New
-Package
,名稱(chēng)自定義為com.pai.hdfs_demo
New
-Class
,名稱(chēng)自定義為ReadWriteHDFSExample
package 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 新建一個(gè)類(lèi)ReadWriteHDFSExample,編寫(xiě)main函數(shù)如下。main函數(shù)調(diào)用其它函數(shù),創(chuàng)建目錄,寫(xiě)入數(shù)據(jù),添加數(shù)據(jù),然后再讀取數(shù)據(jù)
public static void main(String[] args) throws IOException {
// ReadWriteHDFSExample.checkExists();
ReadWriteHDFSExample.createDirectory();
ReadWriteHDFSExample.writeFileToHDFS();
ReadWriteHDFSExample.appendToHDFSFile();
ReadWriteHDFSExample.readFileFromHDFS();
}
// readFileFromHDFS 該函數(shù)讀取文件內(nèi)容,以字符串形式顯示出來(lái)
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函數(shù)打開(kāi)文件,寫(xiě)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 函數(shù)打開(kāi)文件,添加一行文本。需要注意的是,需要對(duì)Configuration類(lèi)的對(duì)象configuration進(jìn)行適當(dāng)設(shè)置,否則出錯(cuò)
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 函數(shù)創(chuàng)建一個(gè)目錄
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檢查目錄或者文件是否存在。注意如下代碼的最后一個(gè)括號(hào)是ReadWriteHDFSExample類(lèi)的結(jié)束括號(hào)
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());
}
}
}
為了編譯通過(guò)上述Java代碼,需要把如下目錄下的jar包導(dǎo)入Eclipse項(xiàng)目的Build Path
操作序列為 右鍵點(diǎn)擊Eclipse里的Java項(xiàng)目→Properties
→Java Build Path
→Libraries
→Add External Jars
# 添加如下路徑的包
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
就可以愉快地執(zhí)行了,執(zhí)行完畢上述代碼后,在hd-master主機(jī)上可以通過(guò)如下命令,檢查已經(jīng)寫(xiě)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
為了多次進(jìn)行實(shí)驗(yàn)(或者為了調(diào)試代碼),可以把HDFS文件刪除,然后再執(zhí)行或者調(diào)試Java代碼,否則一經(jīng)存在該目錄,執(zhí)行創(chuàng)建目錄的代碼就會(huì)出錯(cuò)
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 {
//定義WordCount類(lèi)的內(nèi)部類(lèi)TokenizerMapper 該類(lèi)實(shí)現(xiàn)了map函數(shù),把從文件讀取的每個(gè)word變成一個(gè)形式為<word,1>的Key Value對(duì),輸出到map函數(shù)的參數(shù)context對(duì)象,由執(zhí)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);
}
}
}
//定義WordCount類(lèi)的內(nèi)部類(lèi)IntSumReducer 該類(lèi)實(shí)現(xiàn)了reduce函數(shù),它收攏所有相同key的、形式為<word,1>的Key-Value對(duì),對(duì)Value部分進(jìn)行累加,輸出一個(gè)計(jì)數(shù)
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類(lèi)的main函數(shù),負(fù)責(zé)配置Job的若干關(guān)鍵的參數(shù),并且啟動(dòng)這個(gè)Job。在main函數(shù)中,conf對(duì)象包含了一個(gè)屬性即“fs.defaultFS”,它的值為“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
數(shù)據(jù)分析咨詢請(qǐng)掃描二維碼
若不方便掃碼,搜微信號(hào):CDAshujufenxi
SQL Server 中 CONVERT 函數(shù)的日期轉(zhuǎn)換:從基礎(chǔ)用法到實(shí)戰(zhàn)優(yōu)化 在 SQL Server 的數(shù)據(jù)處理中,日期格式轉(zhuǎn)換是高頻需求 —— 無(wú)論 ...
2025-09-18MySQL 大表拆分與關(guān)聯(lián)查詢效率:打破 “拆分必慢” 的認(rèn)知誤區(qū) 在 MySQL 數(shù)據(jù)庫(kù)管理中,“大表” 始終是性能優(yōu)化繞不開(kāi)的話題。 ...
2025-09-18CDA 數(shù)據(jù)分析師:表結(jié)構(gòu)數(shù)據(jù) “獲取 - 加工 - 使用” 全流程的賦能者 表結(jié)構(gòu)數(shù)據(jù)(如數(shù)據(jù)庫(kù)表、Excel 表、CSV 文件)是企業(yè)數(shù)字 ...
2025-09-18DSGE 模型中的 Et:理性預(yù)期算子的內(nèi)涵、作用與應(yīng)用解析 動(dòng)態(tài)隨機(jī)一般均衡(Dynamic Stochastic General Equilibrium, DSGE)模 ...
2025-09-17Python 提取 TIF 中地名的完整指南 一、先明確:TIF 中的地名有哪兩種存在形式? 在開(kāi)始提取前,需先判斷 TIF 文件的類(lèi)型 —— ...
2025-09-17CDA 數(shù)據(jù)分析師:解鎖表結(jié)構(gòu)數(shù)據(jù)特征價(jià)值的專(zhuān)業(yè)核心 表結(jié)構(gòu)數(shù)據(jù)(以 “行 - 列” 規(guī)范存儲(chǔ)的結(jié)構(gòu)化數(shù)據(jù),如數(shù)據(jù)庫(kù)表、Excel 表、 ...
2025-09-17Excel 導(dǎo)入數(shù)據(jù)含缺失值?詳解 dropna 函數(shù)的功能與實(shí)戰(zhàn)應(yīng)用 在用 Python(如 pandas 庫(kù))處理 Excel 數(shù)據(jù)時(shí),“缺失值” 是高頻 ...
2025-09-16深入解析卡方檢驗(yàn)與 t 檢驗(yàn):差異、適用場(chǎng)景與實(shí)踐應(yīng)用 在數(shù)據(jù)分析與統(tǒng)計(jì)學(xué)領(lǐng)域,假設(shè)檢驗(yàn)是驗(yàn)證研究假設(shè)、判斷數(shù)據(jù)差異是否 “ ...
2025-09-16CDA 數(shù)據(jù)分析師:掌控表格結(jié)構(gòu)數(shù)據(jù)全功能周期的專(zhuān)業(yè)操盤(pán)手 表格結(jié)構(gòu)數(shù)據(jù)(以 “行 - 列” 存儲(chǔ)的結(jié)構(gòu)化數(shù)據(jù),如 Excel 表、數(shù)據(jù) ...
2025-09-16MySQL 執(zhí)行計(jì)劃中 rows 數(shù)量的準(zhǔn)確性解析:原理、影響因素與優(yōu)化 在 MySQL SQL 調(diào)優(yōu)中,EXPLAIN執(zhí)行計(jì)劃是核心工具,而其中的row ...
2025-09-15解析 Python 中 Response 對(duì)象的 text 與 content:區(qū)別、場(chǎng)景與實(shí)踐指南 在 Python 進(jìn)行 HTTP 網(wǎng)絡(luò)請(qǐng)求開(kāi)發(fā)時(shí)(如使用requests ...
2025-09-15CDA 數(shù)據(jù)分析師:激活表格結(jié)構(gòu)數(shù)據(jù)價(jià)值的核心操盤(pán)手 表格結(jié)構(gòu)數(shù)據(jù)(如 Excel 表格、數(shù)據(jù)庫(kù)表)是企業(yè)最基礎(chǔ)、最核心的數(shù)據(jù)形態(tài) ...
2025-09-15Python HTTP 請(qǐng)求工具對(duì)比:urllib.request 與 requests 的核心差異與選擇指南 在 Python 處理 HTTP 請(qǐng)求(如接口調(diào)用、數(shù)據(jù)爬取 ...
2025-09-12解決 pd.read_csv 讀取長(zhǎng)浮點(diǎn)數(shù)據(jù)的科學(xué)計(jì)數(shù)法問(wèn)題 為幫助 Python 數(shù)據(jù)從業(yè)者解決pd.read_csv讀取長(zhǎng)浮點(diǎn)數(shù)據(jù)時(shí)的科學(xué)計(jì)數(shù)法問(wèn)題 ...
2025-09-12CDA 數(shù)據(jù)分析師:業(yè)務(wù)數(shù)據(jù)分析步驟的落地者與價(jià)值優(yōu)化者 業(yè)務(wù)數(shù)據(jù)分析是企業(yè)解決日常運(yùn)營(yíng)問(wèn)題、提升執(zhí)行效率的核心手段,其價(jià)值 ...
2025-09-12用 SQL 驗(yàn)證業(yè)務(wù)邏輯:從規(guī)則拆解到數(shù)據(jù)把關(guān)的實(shí)戰(zhàn)指南 在業(yè)務(wù)系統(tǒng)落地過(guò)程中,“業(yè)務(wù)邏輯” 是連接 “需求設(shè)計(jì)” 與 “用戶體驗(yàn) ...
2025-09-11塔吉特百貨孕婦營(yíng)銷(xiāo)案例:數(shù)據(jù)驅(qū)動(dòng)下的精準(zhǔn)零售革命與啟示 在零售行業(yè) “流量紅利見(jiàn)頂” 的當(dāng)下,精準(zhǔn)營(yíng)銷(xiāo)成為企業(yè)突圍的核心方 ...
2025-09-11CDA 數(shù)據(jù)分析師與戰(zhàn)略 / 業(yè)務(wù)數(shù)據(jù)分析:概念辨析與協(xié)同價(jià)值 在數(shù)據(jù)驅(qū)動(dòng)決策的體系中,“戰(zhàn)略數(shù)據(jù)分析”“業(yè)務(wù)數(shù)據(jù)分析” 是企業(yè) ...
2025-09-11Excel 數(shù)據(jù)聚類(lèi)分析:從操作實(shí)踐到業(yè)務(wù)價(jià)值挖掘 在數(shù)據(jù)分析場(chǎng)景中,聚類(lèi)分析作為 “無(wú)監(jiān)督分組” 的核心工具,能從雜亂數(shù)據(jù)中挖 ...
2025-09-10統(tǒng)計(jì)模型的核心目的:從數(shù)據(jù)解讀到?jīng)Q策支撐的價(jià)值導(dǎo)向 統(tǒng)計(jì)模型作為數(shù)據(jù)分析的核心工具,并非簡(jiǎn)單的 “公式堆砌”,而是圍繞特定 ...
2025-09-10