大数据实训(三)——MapReduce编程实例:词频统计
#MapReduce#YARN#hdfs#IDEA#JDK1.8
实验三:Mapreduce词频统计
3.1启动hadoop服务,输入命令:
start-all.sh
3.2在export目录下,创建wordcount目录,在里面创建words.txt文件,向words.txt输入下面内容。
[root@bogon~]# mkdir -p /export/wordcount [root@bogon~]# cd /export/wordcount/ [root@bogon~]# vi words.txt [root@bogon~]# cat words.txt
3.3编辑结束,上传文件到HDFS指定目录
创建/wordcount/input目录,执行命令:
hdfs dfs -mkdir -p /wordcount/input
3.4将在本地/export/wordcount/目录下的words.txt文件,上传到HDFS的/wordcount/input目录,输入命令:
hdfs dfs -put /export/wordcount/words.txt /wordcount/input
在Hadoop WebUI界面查看目录是否创建成功
3.5使用IDEA创建Maven项目MRWordCount
在pom.xml文件里添加hadoop和junit依赖,内容为:
org.apache.hadoop hadoop-client 3.3.4 junit junit 4.13.2
3.6创建日志文件:在resources目录里创建log4j.properties文件
log4j.rootLogger=ERROR, stdout, logfile log4j.appender.stdout=org.apache.log4j.ConsoleAppender log4j.appender.stdout.layout=org.apache.log4j.PatternLayout log4j.appender.stdout.layout.ConversionPattern=%d %p [%c] - %m%n log4j.appender.logfile=org.apache.log4j.FileAppender log4j.appender.logfile.File=target/wordcount.log log4j.appender.logfile.layout=org.apache.log4j.PatternLayout log4j.appender.logfile.layout.ConversionPattern=%d %p [%c] - %m%n
3.7创建词频统计映射器类
(1)创建net.army.mr包,在弹出的new package对话框中输入net.army.mr
(2)在net.army.mr包下创建WordCountMapper类
package net.army.mr; import org.apache.hadoop.io.IntWritable; import org.apache.hadoop.io.LongWritable; import org.apache.hadoop.mapreduce.Mapper; import org.apache.hadoop.io.Text; import java.io.IOException; /** * 功能:词频统计映射器类 */ public class WordCountMapper extends Mapper { @Override protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException { // 获取行内容 String line = value.toString(); // 按空格拆分成单词数组 String[] words = line.split(" "); // 遍历单词数组,生成输出键值对 for (String word : words) { context.write(new Text(word), new IntWritable(1)); } } }
3.8创建WordCountReducer类
package net.army.mr; import org.apache.hadoop.io.IntWritable; import org.apache.hadoop.io.NullWritable; import org.apache.hadoop.io.Text; import org.apache.hadoop.mapreduce.Reducer; import java.io.IOException; /** * 功能:词频统计归并类 */ public class WordCountReducer extends Reducer { @Override protected void reduce(Text key, Iterable values, Context context) throws IOException, InterruptedException { // 定义键(单词)出现次数 int count = 0; // 遍历输入值迭代器 for (IntWritable value : values) { count = count + value.get(); // 针对此案例,可以写为count++; } // 生成新的键,格式为(word,count) String newKey = "(" + key.toString() + "," + count + ")"; // 输出新的键值对 context.write(new Text(newKey), NullWritable.get()); } }
3.9创建WordCountDriver类
package net.army.mr; import org.apache.hadoop.conf.Configuration; import org.apache.hadoop.fs.FSDataInputStream; import org.apache.hadoop.fs.FileStatus; import org.apache.hadoop.fs.FileSystem; import org.apache.hadoop.fs.Path; import org.apache.hadoop.io.IOUtils; import org.apache.hadoop.io.IntWritable; import org.apache.hadoop.io.NullWritable; import org.apache.hadoop.io.Text; import org.apache.hadoop.mapreduce.Job; import org.apache.hadoop.mapreduce.lib.input.FileInputFormat; import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat; import java.net.URI; /** * 功能:词频统计驱动器类 */ public class WordCountDriver { public static void main(String[] args) throws Exception { // 创建配置对象 Configuration conf = new Configuration(); // 设置客户端使用数据节点主机名属性 conf.set("dfs.client.use.datanode.hostname", "true"); // 获取作业实例 Job job = Job.getInstance(conf); // 设置作业启动类 job.setJarByClass(WordCountDriver.class); // 设置Mapper类 job.setMapperClass(WordCountMapper.class); // 设置map任务输出键类型 job.setMapOutputKeyClass(Text.class); // 设置map任务输出值类型 job.setMapOutputValueClass(IntWritable.class); // 设置Reducer类 job.setReducerClass(WordCountReducer.class); // 设置reduce任务输出键类型 job.setOutputKeyClass(Text.class); // 设置reduce任务输出值类型 job.setOutputValueClass(NullWritable.class); // 定义uri字符串 String uri = "hdfs://bogon:9000"; // 创建输入目录 Path inputPath = new Path(uri + "/wordcount/input"); // 创建输出目录 Path outputPath = new Path(uri + "/wordcount/output"); // 获取文件系统 FileSystem fs = FileSystem.get(new URI(uri), conf); // 删除输出目录(第二个参数设置是否递归) fs.delete(outputPath, true); // 给作业添加输入目录(允许多个) FileInputFormat.addInputPath(job, inputPath); // 给作业设置输出目录(只能一个) FileOutputFormat.setOutputPath(job, outputPath); // 等待作业完成 job.waitForCompletion(true); // 输出统计结果 System.out.println("======统计结果======"); FileStatus[] fileStatuses = fs.listStatus(outputPath); for (int i = 1; i3.10运行词频统计驱动器类WordCountDriver,查看结果
文章版权声明:除非注明,否则均为主机测评原创文章,转载或复制请以超链接形式并注明出处。