com.intel.analytics.bigdl.ppml.examples.tpch.Q07.scala Maven / Gradle / Ivy

Go to download
Show more of this group Show more artifacts with this name
Show all versions of bigdl-ppml-spark_3.1.2 Show documentation
The newest version!
// scalastyle:off
/*
 * This file is copied from:
 * https://github.com/ssavvides/tpch-spark/blob/master/src/main/scala/Q07.scala
 *
 * Copyright (c) 2015 Savvas Savvides, [email protected], [email protected]
 *
 * Licensed under the The MIT License:
 *
 * Permission is hereby granted, free of charge, to any person
 * obtaining a copy of this software and associated documentation
 * files (the "Software"), to deal in the Software without
 * restriction, including without limitation the rights to use,
 * copy, modify, merge, publish, distribute, sublicense, and/or sell
 * copies of the Software, and to permit persons to whom the
 * Software is furnished to do so, subject to the following
 * conditions:
 *
 * The above copyright notice and this permission notice shall be
 * included in all copies or substantial portions of the Software.
 *
 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
 * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES
 * OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
 * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT
 * HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY,
 * WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
 * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
 * OTHER DEALINGS IN THE SOFTWARE.
 */
// scalastyle:on

package com.intel.analytics.bigdl.ppml.examples.tpch

import org.apache.spark.sql.DataFrame
import org.apache.spark.SparkContext
import org.apache.spark.sql.functions.sum
import org.apache.spark.sql.functions.udf

import com.intel.analytics.bigdl.ppml.PPMLContext

/**
 * TPC-H Query 7
 * Savvas Savvides 
 *
 */
class Q07 extends TpchQuery {

  override def execute(sc: PPMLContext, schemaProvider: TpchSchemaProvider): DataFrame = {

    // this is used to implicitly convert an RDD to a DataFrame.
    val sqlContext = sc.getSparkSession.sqlContext
    import sqlContext.implicits._
    import schemaProvider._

    val getYear = udf { (x: String) => x.substring(0, 4) }
    val decrease = udf { (x: Double, y: Double) => x * (1 - y) }

    // cache fnation

    val fnation = nation.filter($"n_name" === "FRANCE" || $"n_name" === "GERMANY")
    val fline = lineitem.filter($"l_shipdate" >= "1995-01-01" && $"l_shipdate" <= "1996-12-31")

    val supNation = fnation.join(supplier, $"n_nationkey" === supplier("s_nationkey"))
      .join(fline, $"s_suppkey" === fline("l_suppkey"))
      .select($"n_name".as("supp_nation"), $"l_orderkey", $"l_extendedprice",
        $"l_discount", $"l_shipdate")

    fnation.join(customer, $"n_nationkey" === customer("c_nationkey"))
      .join(order, $"c_custkey" === order("o_custkey"))
      .select($"n_name".as("cust_nation"), $"o_orderkey")
      .join(supNation, $"o_orderkey" === supNation("l_orderkey"))
      .filter($"supp_nation" === "FRANCE" && $"cust_nation" === "GERMANY"
        || $"supp_nation" === "GERMANY" && $"cust_nation" === "FRANCE")
      .select($"supp_nation", $"cust_nation",
        getYear($"l_shipdate").as("l_year"),
        decrease($"l_extendedprice", $"l_discount").as("volume"))
      .groupBy($"supp_nation", $"cust_nation", $"l_year")
      .agg(sum($"volume").as("revenue"))
      .sort($"supp_nation", $"cust_nation", $"l_year")
  }

}