Abhiknoldur

//READ nodetool snapshot documentation in cassandra
//READ stack-overflow-topic gist or directly in stackoverflow -> http://stackoverflow.com/questions/25465904/how-can-i-restore-cassandra-snapshots

//EXPORT the databases schemas
cqlsh -e "DESCRIBE SCHEMA" > my_backup_name.schema

//Create snapshot of the whole server
nodetool snapshot my_backup_name

//Compress the backups

Abhiknoldur

#!/usr/bin/env python
# -*- coding: utf-8 -*-

import io
import os
import sys
from shutil import rmtree

from setuptools import find_packages, setup, Command

Abhiknoldur

vagrant@new-vm:~/new-vm/dummy-project$ ls
files.binary  files.conf  files.data  files.lib  files.log  files.tmp

Abhiknoldur

package com.knoldus

import org.apache.spark.sql.{SaveMode, SparkSession}
import org.apache.spark.sql.functions._
import org.apache.spark.sql.types._

object PowerPlantDemo {
  def main(args: Array[String]): Unit = {

    val spark = SparkSession

Abhiknoldur

scala> val rdd1=sc.parallelize(Seq((1,3.6)))
rdd1: org.apache.spark.rdd.RDD[(Int, Double)] = ParallelCollectionRDD[0] at parallelize at <console>:24

scala> val rdd2=sc.parallelize(Seq((1,1.1)))
rdd2: org.apache.spark.rdd.RDD[(Int, Double)] = ParallelCollectionRDD[1] at parallelize at <console>:24

scala> val jo=rdd1 join rdd2
jo: org.apache.spark.rdd.RDD[(Int, (Double, Double))] = MapPartitionsRDD[4] at join at <console>:27

scala> jo.map(r=>(r._1,(r._2._1-r._2._2)))

Abhiknoldur

{ "car": "supercar",
 "manufacturer": "Porsche", 
 "model": "911", 
 "price": 135000,
 "wiki": "http://en.wikipedia.org/wiki/Porsche_997" 
}

Abhiknoldur

   Queries==============>


1. CREATE TABLE assignment.emp_details (
    emp_id bigint,
    emp_joining_date date,
    emp_city text,
    emp_name text,
    emp_salary float,
    PRIMARY KEY (emp_id, emp_joining_date)

Abhiknoldur

val rdd_1 = sc.parallelize(Seq((1, 3.6)))
  val rdd_2 = sc.parallelize(Seq((1, 1.1)))

  println(s"Wanted Result:", findSubOfVAlues(rdd_1, rdd_2))

  def findSubOfVAlues(value: RDD[(Int, Double)], value1: RDD[(Int, Double)]) = {
    val combordd = value join value1

    val result = combordd.map(r => (r._1, r._2._1 - r._1, r._2._2)).collect