Commands

#creating the dataframe (making instance of SparkSQL with the .json file)
# val sqlcontext= new org.apache.spark.sql.SQLContext(sc)

val a=spark.read.format("json").load("/home/nikhil/abcd.json")

#to show the data
a.show

#To pront the schema 
a.pritnSchema

#to show id
a.select("id").show()

#select the name and incerement the id by 1
a.select(a("name"), a("id")+1).show()

# select the people greater than id 10
a.filter(a("id")>10).show()

#count people by age
a.groupBy("age").count().show()

#to create  dataframe in csv file
val t=spark.read.format("csv").option("header" , "true").load("/home/nikhil/sql.csv")


case class Employee(g: String, name: String) //schema

val op=sc,textFile("/home/nikhil/new.txt).map(_.split(",")).map(e=> Employee(e(0),e(1))).toDF() //map is transformation

op.registerTempTable("employee")

val allrecords=sqlcontext.sql("SELECT * FROM employee") // sql query not dataframe query to run this code first imprt sqlcontext