Last active
May 19, 2020 14:59
-
-
Save saisgit/b0ac528d0c136ff2cbaf4732d29eef48 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import org.apache.spark._ | |
import org.apache.spark.SparkConf | |
import org.apache.spark.sql.hive.HiveContext | |
import com.databricks.sparck.csv | |
Object Solution extends App { | |
val conf = new SparkConf().setAppName("Problem_Execution") | |
val sc = new SparkContext(conf) | |
val hiveContext = new HiveContext(sc) | |
val readData = hiveContext.read.format("com.databricks.spark.csv").option("header","true").load("/user/sai/file.csv") | |
readData.registerTempTable("readTable") | |
val formattedData = hiveContext.sql("select Name,`Position Title` as Title, Department, substring(`Employee Annual Salary`,2) as Salary from readTable") | |
formattedData.registerTempTable("formattedTable") | |
val solution = hiveContext.sql("select Name,Title,Department,Salary,rank from (select Name, Title, Department, Salary, | |
dense_rank() over(Partition by Department order by Salary) as rank from formattedTable) temp where rank <= 2") | |
solution.coalesce(1).write.mode("overwrite").option("header"."true").format("com.databricks.spark.csv").option("delimiter","|").save("/user/sai/output.csv") | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment