通过hadoop上的hive完成WordCount

启动hadoop

start-all.sh

 

Hdfs上创建文件夹

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

 

上传文件至hdfs

hdfs dfs -put ./1.txt wcinputhdfs dfs -ls /user/hadoop/wcinput

 

启动Hive

hive

 

创建原始文档表

create table docs(line string);

 

导入文件内容到表docs并查看

load data inpath '/user/hadoop/wcinput/1.txt' overwrite into table docs;select * 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 (se lect 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;