hive基本操作与应用
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 input
hdfs dfs -ls /user/hadoop
上传文件至hdfs
hdfs dfs -put ./test.txt input
hdfs dfs -ls /user/hadoop/input
启动Hive
hive
创建原始文档表
create table documents(line string);
导入文件内容到表docs并查看
load data inpath '/user/hadoop/input/test.txt' overwrite into table documents; select * from documents;
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
documents
) word group by word order by word;
查看统计结果
show tables; select * from word_count;