See the explanation for Step by Step Solution and configuration.
Explanation:
Solution :
Step 1:
hdfs dfs -mkdir sparksql2
hdfs dfs -put product.csv sparksq!2/
hdfs dfs -put supplier.csv sparksql2/
hdfs dfs -put products_suppliers.csv sparksql2/
Step 2 : Now in spark shell
// this Is used to Implicitly convert an RDD to a DataFrame.
import sqlContext.impIicits._
// Import Spark SQL data types and Row.
import org.apache.spark.sql._
// load the data into a new RDD
val products = sc.textFile("sparksql2/product.csv")
val supplier = sc.textFileC'sparksq^supplier.csv")
val prdsup = sc.textFile("sparksql2/products_suppliers.csv"}
// Return the first element in this RDD
products.fi rst()
supplier.first{).
prdsup.first()
//define the schema using a case class
case class Product(productid: Integer, code: String, name: String, quantity:lnteger, price:
Float, supplierid:lnteger)
case class Suplier(supplierid: Integer, name: String, phone: String)
case class PRDSUP(productid: Integer.supplierid: Integer)
// create an RDD of Product objects
val prdRDD = products.map(_.split('\")).map(p =>
Product(p(0).tolnt,p(1),p(2),p(3).tolnt,p(4).toFloat,p(5).toint))
val supRDD = supplier.map(_.split(",")).map(p => Suplier(p(0).tolnt,p(1),p(2))) val prdsupRDD = prdsup.map(_.split(",")).map(p => PRDSUP(p(0).tolnt,p(1}.tolnt}} prdRDD.first() prdRDD.count() supRDD.first() supRDD.count()
prdsupRDD.first() prdsupRDD.count(}
// change RDD of Product objects to a DataFrame
val prdDF = prdRDD.toDF()
val supDF = supRDD.toDF()
val prdsupDF = prdsupRDD.toDF()
// register the DataFrame as a temp table prdDF.registerTempTablef'products") supDF.registerTempTablef'suppliers") prdsupDF.registerTempTablef'productssuppliers"}
//Select product, its price , its supplier name where product price is less than 0.6 val results = sqlContext.sql(......SELECT products.name, price, suppliers.name as sup_name FROM products JOIN suppliers ON products.supplierlD= suppliers.supplierlD
WHERE price < 0.6......]
results. show()