IsolationLevelExperiment.scala

package com.example

import org.apache.spark.sql.functions.avg
import org.apache.spark.sql.SparkSession

object IsolationLevelExperiment {
  def main(args: Array[String]): Unit = {
    // Prepare SparkSession
    val spark = SparkSession
      .builder()
      .appName("Isolation Level Experiment")
      .master("local[*]")
      .getOrCreate()

    import spark.implicits._

    // Read from MySQL
    val dfEmployee = spark
      .read
      .format("jdbc")
      .option("url", "jdbc:mysql://localhost")
      .option("dbtable", "db_name.employees")
      .option("user", "user_name")
      .option("password", "********")
      .option("driver", "com.mysql.cj.jdbc.Driver")
      .load
      .cache

    // Get average salary
    val dfAvg = dfEmployee
      .groupBy($"department_id")
      .agg(avg($"salary").as("avg_salary"))

    // Calculate diff
    val dfResult = dfEmployee
      .as("e")
      .join(
        dfAvg.as("a"),
        $"e.department_id" === $"a.department_id",
        "left_outer"
      )
      .select(
        $"e.id",
        $"e.department_id",
        ($"e.salary" - $"a.avg_salary").as("salary_diff")
      )

    // Output results
    dfResult.show

    spark.stop()
  }
}