com.intel.analytics.bigdl.ppml.examples.tpch.Q02.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/Q02.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.min

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

/**
 * TPC-H Query 2
 * Savvas Savvides 
 *
 */
class Q02 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 europe = region.filter($"r_name" === "EUROPE")
      .join(nation, $"r_regionkey" === nation("n_regionkey"))
      .join(supplier, $"n_nationkey" === supplier("s_nationkey"))
      .join(partsupp, supplier("s_suppkey") === partsupp("ps_suppkey"))
    // .select($"ps_partkey", $"ps_supplycost", $"s_acctbal", $"s_name",
    // $"n_name", $"s_address", $"s_phone", $"s_comment")

    val brass = part.filter(part("p_size") === 15 && part("p_type").endsWith("BRASS"))
      .join(europe, europe("ps_partkey") === $"p_partkey")
    // .cache

    val minCost = brass.groupBy(brass("ps_partkey"))
      .agg(min("ps_supplycost").as("min"))

    brass.join(minCost, brass("ps_partkey") === minCost("ps_partkey"))
      .filter(brass("ps_supplycost") === minCost("min"))
      .select("s_acctbal", "s_name", "n_name", "p_partkey", "p_mfgr",
        "s_address", "s_phone", "s_comment")
      .sort($"s_acctbal".desc, $"n_name", $"s_name", $"p_partkey")
      .limit(100)
  }

}