com.intel.analytics.bigdl.ppml.examples.tpch.Q08.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/Q08.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 8
 * Savvas Savvides 
 *
 */
class Q08 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) }
    val isBrazil = udf { (x: String, y: Double) => if (x == "BRAZIL") y else 0 }

    val fregion = region.filter($"r_name" === "AMERICA")
    val forder = order.filter($"o_orderdate" <= "1996-12-31" && $"o_orderdate" >= "1995-01-01")
    val fpart = part.filter($"p_type" === "ECONOMY ANODIZED STEEL")

    val nat = nation.join(supplier, $"n_nationkey" === supplier("s_nationkey"))

    val line = lineitem.select($"l_partkey", $"l_suppkey", $"l_orderkey",
      decrease($"l_extendedprice", $"l_discount").as("volume")).
      join(fpart, $"l_partkey" === fpart("p_partkey"))
      .join(nat, $"l_suppkey" === nat("s_suppkey"))

    nation.join(fregion, $"n_regionkey" === fregion("r_regionkey"))
      .select($"n_nationkey")
      .join(customer, $"n_nationkey" === customer("c_nationkey"))
      .select($"c_custkey")
      .join(forder, $"c_custkey" === forder("o_custkey"))
      .select($"o_orderkey", $"o_orderdate")
      .join(line, $"o_orderkey" === line("l_orderkey"))
      .select(getYear($"o_orderdate").as("o_year"), $"volume",
        isBrazil($"n_name", $"volume").as("case_volume"))
      .groupBy($"o_year")
      .agg(sum($"case_volume") / sum("volume"))
      .sort($"o_year")
  }

}