词频统计

#创建表，只有一列，列名line

create table word_count (

line string)

row format delimited fields terminated by '\t'

lines terminated by '\n';

#导入一篇文章到表里

load data local inpath '/home/dip/test/word_count.txt'

#词频统计

select word ,count(*) as cnt

from

(select

explode(split(line ,' ')) as word

from  word_count)t1

group by word

order by cnt desc;