根据用户上网的搜索记录对每天的热点搜索词进行统计,以了解用户所关心的热点话题。
要求完成:统计每天搜索数量前3名的搜索词(同一天中同一用户多次搜索同一个搜索词视为1次)。
数据示例
2019-10-01,tom,小吃街
2019-10-01,jack,谷歌浏览器
2019-10-01,jack,小吃街
2019-10-01,look,小吃街
2019-10-01,steven,烤肉
2019-10-01,lojas,烤肉
2019-10-01,look,小吃街
2019-10-02,marry,安全卫士
2019-10-02,tom,名胜古迹
2019-10-02,marry,安全卫士
2019-10-02,leo,名胜古迹
2019-10-03,tom,名胜古迹
2019-10-03,leo,小吃街
val shuju=spark.read.textFile("hdfs://192.168.10.132:9000/input/keywords.txt")
shuju.show
case class Shuju(date:String,name:String,address:String)
val shujuDataset=shuju.map(line=>{
val fields=line.split(",")
val date=fields(0)
val name=fields(1)
val address=fields(2)
Shuju(date,name,address)})
shujuDataset.show()
val sjdf =shujuDataset.toDF()
sjdf.createTempView("v_shuju")
val result = spark.sql( val result=spark.sql("SELECT date, address, COUNT(*) AS count FROM (SELECT DISTINCT date,name,address FROM v_shuju) GROUP BY date, address")
result.createTempView("v_shuju1")
#降序排列
val result2=spark.sql("select * from v_shuju1 order by date desc")
result2.show
#升序排列
val result3=spark.sql("select * from v_shuju1 order by date ")
result3.show