ry",
>>> "1g")
>>> val sc = new SparkContext(conf)
>>> val sqlContext= new SQLContext(sc)
>>>
>>> val hc=new HiveContext(sc)
>>>
>>> hc.sql("CREATE EXTERNAL TABLE IF NOT EXISTS default.TEST (user_name
&
gt;>>> object HiveWordCount {
>>>>
>>>> def main(args: Array[String]): Unit =
>>>> {
>>>> Logger.getLogger("org").setLevel(Level.WARN)
>>>> Logger.getLogger("akka").setLevel(Level.WARN)
>>>>
TS STRING )ROW FORMAT DELIMITED FIELDS TERMINATED BY '001'
>> STORED AS TEXTFILE LOCATION '/data/kali/test' ")
>>
>> val op=hc.sql("select user_name,COLLECT_SET(text) from (select
>> user_name,concat(sub,' ',count(comments)) as text from default.test
>>
from default.test LATERAL
VIEW explode(split(comments,',')) subView AS sub group by user_name,sub)w
group by user_name")
op.collect.foreach(println)
}
Thanks
--
View this message in context:
http://apache-spark-user-list.1001560.n3.nabble.com/word-count-group-by-users
ION '/data/kali/test' ")
>
> val op=hc.sql("select user_name,COLLECT_SET(text) from (select
> user_name,concat(sub,' ',count(comments)) as text from default.test
> LATERAL
> VIEW explode(split(comments,',')) subView AS sub group by user_name,sub)w
> group by user_na