通过hadoop上的hive完成WordCount

启动hadoop

cd /usr/local/hadoop./sbin/start-dfs.shcd /usr/local/hive/libservice mysql startstart-all.sh

 

Hdfs上创建文件夹

hdfs dfs -mkdir testhdfs dfs -ls /user/hadoop

 

上传文件至hdfs

hdfs dfs -put ./test.txt testhdfs dfs -ls /user/hadoop/test

 

启动Hive

创建原始文档表

hive create table docs(line string)

 

导入文件内容到表docs并查看

load data inpath '/user/hadoop/tese1/test.txt' overwrite into table docsselect * from docs

 

用HQL进行词频统计，结果放在表word_count里

create table word_count as select word,count(1) as count from (select explode(split(line," ")) as word from docs) word group by word order by word;

 

查看统计结果

show tables;select * from word_count;