package xxx.DataScience.CompensationStudy

import org.apache.spark._
import org.apache.log4j._

import org.apache.spark.SparkContext
import org.apache.spark.SparkContext._
import org.apache.spark.SparkConf

import org.apache.spark.sql.Row
import org.apache.spark.sql.functions.{col, udf}
import org.apache.spark.sql.types._

import org.apache.spark.SparkContext
import org.apache.spark.sql.SQLContext


object CompensationAnalysis {

  case class GetDF(profil_date:String, profil_pays:String, param_tarif2:String, param_tarif3:String, dt_titre:String, dt_langues:String,
    dt_diplomes:String, dt_experience:String, dt_formation:String, dt_outils:String, comp_applications:String,
    comp_interventions:String, comp_competence:String)

  def main(args: Array[String]) {

    Logger.getLogger("org").setLevel(Level.ERROR)

    val conf = new SparkConf().setAppName("CompensationAnalysis ")
    val sc = new SparkContext(conf)

    val sqlContext = new org.apache.spark.sql.SQLContext(sc)
    import sqlContext.implicits._


    val lines = sc.textFile("C:/Users/../Downloads/CompensationStudy.csv").flatMap { l =>


      l.split(",") match {

        case field: Array[String] if field.size > 13 => Some(field(0), field(1), field(2), field(3), field(4), field(5), field(6), field(7), field(8), field(9), field(10), field(11), field(12))

        case field: Array[String] if field.size == 1 => Some((field(0), "default value"))

        case _ => None
      }


    }

val summary = lines.collect().map(x => GetDF(x("profil_date"), x("profil_pays"), x("param_tarif2"), x("param_tarif3"), x("dt_titre"), x("dt_langues"), x("dt_diplomes"), x("dt_experience"), x("dt_formation"), x("dt_outils"), x("comp_applications"), x("comp_interventions"), x("comp_competence")))

    val sum_df = summary.toDF()

    df.printSchema


  }

}