hive进行词频统计

统计文件信息：

$ /opt/cdh-5.3.6/hadoop-2.5.0/bin/hdfs dfs -text /user/hadoop/wordcount/input/wc.input
hadoop spark
spark hadoop
oracle mysql postgresql
postgresql oracle mysql
mysql mongodb
hdfs yarn mapreduce
yarn hdfs
zookeeper

针对于以上文件使用hive做词频统计：

create table docs (line string);

load data inpath ‘/user/hadoop/wordcount/input/wc.input‘ into table docs;

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

分段解释：

--使用split函数对表中行按空格进行分隔：

select split(line,‘ ‘) from docs；
["hadoop","spark",""]
["spark","hadoop"]
["oracle","mysql","postgresql"]
["postgresql","oracle","mysql"]
["mysql","mongodb"]
["hdfs","yarn","mapreduce"]
["yarn","hdfs"]
["zookeeper"]

--使用explode函数对split的结果集进行行拆列：

select explode(split(line,‘ ‘)) as word from docs；
word
hadoop
spark

spark
hadoop
oracle
mysql
postgresql
postgresql
oracle
mysql
mysql
mongodb
hdfs
yarn
mapreduce
yarn
hdfs
zookeeper

--以上输出内容已经满足对其做统计分析，这时通过sql对其进行分析：

select word,count(1) as count from
(select explode(split(line,‘ ‘)) as word from docs) word
group by word
order by word;

word    count
     1
hadoop    2
hdfs    2
mapreduce    1
mongodb    1
mysql    3
oracle    2
postgresql    2
spark    2
yarn    2
zookeeper    1