diff --git a/02-HelloRDD/build.sbt b/02-HelloRDD/build.sbt
index 219b4f4..54486a2 100644
--- a/02-HelloRDD/build.sbt
+++ b/02-HelloRDD/build.sbt
@@ -1,8 +1,13 @@
-ThisBuild / version := "0.1.0-SNAPSHOT"
+name := "HelloRDD"
+organization := "com.spark.learnings"
+version := "0.1.0-SNAPSHOT"
+scalaVersion := "2.12.10"
+autoScalaLibrary := false
+val sparkVersion = "3.0.0-preview2"
 
-ThisBuild / scalaVersion := "2.12.10"
+val sparkDependencies = Seq(
+  "org.apache.spark" %% "spark-core" % sparkVersion
+)
+
+libraryDependencies ++= sparkDependencies
 
-lazy val root = (project in file("."))
-  .settings(
-    name := "02-HelloRDD"
-  )
diff --git a/02-HelloRDD/data/sample.csv b/02-HelloRDD/data/sample.csv
new file mode 100644
index 0000000..1fc06ad
--- /dev/null
+++ b/02-HelloRDD/data/sample.csv
@@ -0,0 +1,9 @@
+2014-08-27 11:29:31,37,"Female","United States","IL",NA,"No","Yes","Often","6-25","No","Yes","Yes","Not sure","No","Yes","Yes","Somewhat easy","No","No","Some of them","Yes","No","Maybe","Yes","No",NA
+2014-08-27 11:29:37,44,"M","United States","IN",NA,"No","No","Rarely","More than 1000","No","No","Don't know","No","Don't know","Don't know","Don't know","Don't know","Maybe","No","No","No","No","No","Don't know","No",NA
+2014-08-27 11:29:44,32,"Male","Canada",NA,NA,"No","No","Rarely","6-25","No","Yes","No","No","No","No","Don't know","Somewhat difficult","No","No","Yes","Yes","Yes","Yes","No","No",NA
+2014-08-27 11:29:46,31,"Male","United Kingdom",NA,NA,"Yes","Yes","Often","26-100","No","Yes","No","Yes","No","No","No","Somewhat difficult","Yes","Yes","Some of them","No","Maybe","Maybe","No","Yes",NA
+2014-08-27 11:30:22,31,"Male","United States","TX",NA,"No","No","Never","100-500","Yes","Yes","Yes","No","Don't know","Don't know","Don't know","Don't know","No","No","Some of them","Yes","Yes","Yes","Don't know","No",NA
+2014-08-27 11:31:22,33,"Male","United States","TN",NA,"Yes","No","Sometimes","6-25","No","Yes","Yes","Not sure","No","Don't know","Don't know","Don't know","No","No","Yes","Yes","No","Maybe","Don't know","No",NA
+2014-08-27 11:31:50,35,"Female","United States","MI",NA,"Yes","Yes","Sometimes","1-5","Yes","Yes","No","No","No","No","No","Somewhat difficult","Maybe","Maybe","Some of them","No","No","No","Don't know","No",NA
+2014-08-27 11:32:05,39,"M","Canada",NA,NA,"No","No","Never","1-5","Yes","Yes","No","Yes","No","No","Yes","Don't know","No","No","No","No","No","No","No","No",NA
+2014-08-27 11:32:39,42,"Female","United States","IL",NA,"Yes","Yes","Sometimes","100-500","No","Yes","Yes","Yes","No","No","No","Very difficult","Maybe","No","Yes","Yes","No","Maybe","No","No",NA
\ No newline at end of file
diff --git a/02-HelloRDD/src/main/scala/com/spark/scala/learning/examples/HelloRDD.scala b/02-HelloRDD/src/main/scala/com/spark/scala/learning/examples/HelloRDD.scala
new file mode 100644
index 0000000..50c7fe4
--- /dev/null
+++ b/02-HelloRDD/src/main/scala/com/spark/scala/learning/examples/HelloRDD.scala
@@ -0,0 +1,37 @@
+package com.spark.scala.learning.examples
+
+import org.apache.log4j.{Level, Logger}
+import org.apache.spark.{SparkConf, SparkContext}
+
+object HelloRDD extends  Serializable {
+
+  def main(args: Array[String]): Unit ={
+    @transient lazy val logger: Logger = Logger.getLogger(getClass.getName)
+    Logger.getLogger("org").setLevel(Level.OFF)
+    Logger.getLogger("akka").setLevel(Level.OFF)
+    //Create Spark Context
+    val sparkConf =new SparkConf().setAppName("HelloRDD").setMaster("local[2]")
+    val sparkContext = new SparkContext(sparkConf)
+    //Read CSV file
+    val lineRDD = sparkContext.textFile(args(0))
+
+    //Give it a structure and select 4 columns
+    case class SurveyRecord(Age: Int, Gender: String, Country: String, State: String)
+    var colsRDD = lineRDD.map(line => {
+      val cols = line.split(",").map(_.trim)
+      SurveyRecord(cols(1).toInt, cols(2), cols(3), cols(4))
+    })
+
+    //Apply filter
+    val filteredRDD =  colsRDD.filter(r=> r.Age < 40)
+    filteredRDD.collect().foreach(println)
+
+    ///manually implement the GroupBy
+    val kvRDD = filteredRDD.map(r=> (r.Country, 1))
+    val countRDD = kvRDD.reduceByKey((v1, v2) => v1 + v2)
+    countRDD.collect().foreach(println)
+
+    sparkContext.stop()
+
+  }
+}