IT虾米网

MapReduce之WordCount单词计数

lxf 2022年06月12日 大数据 179 0
一 代码
Wordcount.java
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.LongWritable;
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.input.TextInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;
 
public class WordCount {
public static class WordCountMap extends
Mapper<LongWritable, Text, Text, IntWritable> {
private final IntWritable one = new IntWritable(1);
private Text word = new Text();
 
public void map(LongWritable key, Text value, Context context)
throws IOException, InterruptedException {
String line = value.toString();
StringTokenizer token = new StringTokenizer(line);
while (token.hasMoreTokens()) {
word.set(token.nextToken());
context.write(word, one);
}
}
}
 
public static class WordCountReduce extends
Reducer<Text, IntWritable, Text, IntWritable> {
public void reduce(Text key, Iterable<IntWritable> values,
Context context) throws IOException, InterruptedException {
int sum = 0;
for (IntWritable val : values) {
sum += val.get();
}
context.write(key, new IntWritable(sum));
}
}
 
public static void main(String[] args) throws Exception {
Configuration conf = new Configuration();
Job job = new Job(conf);
job.setJarByClass(WordCount.class);
job.setJobName("wordcount");
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(IntWritable.class);
job.setMapperClass(WordCountMap.class);
job.setReducerClass(WordCountReduce.class);
job.setInputFormatClass(TextInputFormat.class);
job.setOutputFormatClass(TextOutputFormat.class);
FileInputFormat.addInputPath(job, new Path(args[0]));
FileOutputFormat.setOutputPath(job, new Path(args[1]));
job.waitForCompletion(true);
}
}
 
二 构建运行
1、编译
[root@localhost word_count]# ll
total 4
drwxr-xr-x. 2 root root 101 Aug 20 14:27 word_count_class
-rwxr-xr-x. 1 root root 2132 Aug 20 14:22 WordCount.java
[root@localhost word_count]# javac -classpath /opt/hadoop-1.2.1/hadoop-core-1.2.1.jar:/opt/hadoop-1.2.1/lib/commons-cli-1.2.jar -d word_count_class/ WordCount.java
[root@localhost word_count]# cd word_count_class/
[root@localhost word_count_class]# ls
WordCount.class WordCount$WordCountMap.class WordCount$WordCountReduce.class
2、打包
[root@localhost word_count_class]# jar -cvf wordcount.jar *.class
added manifest
adding: WordCount.class(in = 1539) (out= 772)(deflated 49%)
adding: WordCount$WordCountMap.class(in = 1829) (out= 767)(deflated 58%)
adding: WordCount$WordCountReduce.class(in = 1645) (out= 687)(deflated 58%)
[root@localhost word_count_class]# ls
WordCount.class wordcount.jar WordCount$WordCountMap.class WordCount$WordCountReduce.class
3、准备输入文件file1和输入文件file2
[root@localhost input]# ls
file1 file2
file1的内容:
hello world
hello hadoop
hadoop file system
hadoop java api
hello java
file2的内容:
new file
hadoop file
hadoop new world
hadoop free home
hadoop free school
4、将输入文件提交HDFS
[root@localhost word_count]# hadoop fs -mkdir input_wordcount
Warning: $HADOOP_HOME is deprecated.
 
[root@localhost word_count]# hadoop fs -put input/* input_wordcount/
Warning: $HADOOP_HOME is deprecated.
[root@localhost word_count]# hadoop fs -ls
Warning: $HADOOP_HOME is deprecated.
 
Found 2 items
drwxr-xr-x - root supergroup 0 2017-08-20 12:44 /user/root/input
drwxr-xr-x - root supergroup 0 2017-08-20 14:41 /user/root/input_wordcount
[root@localhost word_count]# hadoop fs -ls input_wordcount
Warning: $HADOOP_HOME is deprecated.
 
Found 2 items
-rw-r--r-- 3 root supergroup 71 2017-08-20 14:41 /user/root/input_wordcount/file1
-rw-r--r-- 3 root supergroup 74 2017-08-20 14:41 /user/root/input_wordcount/file2
[root@localhost word_count]# hadoop fs -cat input_wordcount/file1
Warning: $HADOOP_HOME is deprecated.
 
hello world
hello hadoop
hadoop file system
hadoop java api
hello java
5、任务提交
[root@localhost word_count]# hadoop jar word_count_class/wordcount.jar WordCount input_wordcount output_wordcount
Warning: $HADOOP_HOME is deprecated.
 
17/08/20 14:50:30 WARN mapred.JobClient: Use GenericOptionsParser for parsing the arguments. Applications should implement Tool for the same.
17/08/20 14:50:31 INFO input.FileInputFormat: Total input paths to process : 2
17/08/20 14:50:31 INFO util.NativeCodeLoader: Loaded the native-hadoop library
17/08/20 14:50:31 WARN snappy.LoadSnappy: Snappy native library not loaded
17/08/20 14:50:33 INFO mapred.JobClient: Running job: job_201708201140_0001
17/08/20 14:50:34 INFO mapred.JobClient: map 0% reduce 0%
17/08/20 14:51:20 INFO mapred.JobClient: map 100% reduce 0%
17/08/20 14:51:45 INFO mapred.JobClient: map 100% reduce 100%
17/08/20 14:51:51 INFO mapred.JobClient: Job complete: job_201708201140_0001
17/08/20 14:51:52 INFO mapred.JobClient: Counters: 29
17/08/20 14:51:52 INFO mapred.JobClient: Job Counters
17/08/20 14:51:52 INFO mapred.JobClient: Launched reduce tasks=1
17/08/20 14:51:52 INFO mapred.JobClient: SLOTS_MILLIS_MAPS=81389
17/08/20 14:51:52 INFO mapred.JobClient: Total time spent by all reduces waiting after reserving slots (ms)=0
17/08/20 14:51:52 INFO mapred.JobClient: Total time spent by all maps waiting after reserving slots (ms)=0
17/08/20 14:51:52 INFO mapred.JobClient: Launched map tasks=2
17/08/20 14:51:52 INFO mapred.JobClient: Data-local map tasks=2
17/08/20 14:51:52 INFO mapred.JobClient: SLOTS_MILLIS_REDUCES=24253
17/08/20 14:51:52 INFO mapred.JobClient: File Output Format Counters
17/08/20 14:51:52 INFO mapred.JobClient: Bytes Written=83
17/08/20 14:51:52 INFO mapred.JobClient: FileSystemCounters
17/08/20 14:51:52 INFO mapred.JobClient: FILE_BYTES_READ=301
17/08/20 14:51:52 INFO mapred.JobClient: HDFS_BYTES_READ=381
17/08/20 14:51:52 INFO mapred.JobClient: FILE_BYTES_WRITTEN=156847
17/08/20 14:51:52 INFO mapred.JobClient: HDFS_BYTES_WRITTEN=83
17/08/20 14:51:52 INFO mapred.JobClient: File Input Format Counters
17/08/20 14:51:52 INFO mapred.JobClient: Bytes Read=145
17/08/20 14:51:52 INFO mapred.JobClient: Map-Reduce Framework
17/08/20 14:51:52 INFO mapred.JobClient: Map output materialized bytes=307
17/08/20 14:51:52 INFO mapred.JobClient: Map input records=10
17/08/20 14:51:52 INFO mapred.JobClient: Reduce shuffle bytes=307
17/08/20 14:51:52 INFO mapred.JobClient: Spilled Records=50
17/08/20 14:51:52 INFO mapred.JobClient: Map output bytes=245
17/08/20 14:51:52 INFO mapred.JobClient: Total committed heap usage (bytes)=246751232
17/08/20 14:51:52 INFO mapred.JobClient: CPU time spent (ms)=5290
17/08/20 14:51:52 INFO mapred.JobClient: Combine input records=0
17/08/20 14:51:52 INFO mapred.JobClient: SPLIT_RAW_BYTES=236
17/08/20 14:51:52 INFO mapred.JobClient: Reduce input records=25
17/08/20 14:51:52 INFO mapred.JobClient: Reduce input groups=11
17/08/20 14:51:52 INFO mapred.JobClient: Combine output records=0
17/08/20 14:51:52 INFO mapred.JobClient: Physical memory (bytes) snapshot=382996480
17/08/20 14:51:52 INFO mapred.JobClient: Reduce output records=11
17/08/20 14:51:52 INFO mapred.JobClient: Virtual memory (bytes) snapshot=2590666752
17/08/20 14:51:52 INFO mapred.JobClient: Map output records=25
6、查看结果
[root@localhost word_count]# hadoop fs -ls output_wordcount
Warning: $HADOOP_HOME is deprecated.
 
Found 3 items
-rw-r--r-- 3 root supergroup 0 2017-08-20 14:51 /user/root/output_wordcount/_SUCCESS
drwxr-xr-x - root supergroup 0 2017-08-20 14:50 /user/root/output_wordcount/_logs
-rw-r--r-- 3 root supergroup 83 2017-08-20 14:51 /user/root/output_wordcount/part-r-00000
[root@localhost word_count]# hadoop fs -cat output_wordcount/part-r-00000
Warning: $HADOOP_HOME is deprecated.
 
api 1
file 3
free 2
hadoop 7
hello 3
home 1
java 2
new 2
school 1
system 1
world 2
 
 

评论关闭
IT虾米网

微信公众号号:IT虾米 (左侧二维码扫一扫)欢迎添加!

MapReduce之WordCount单词计数(上)