com.intel.analytics.bigdl.ppml.examples.tpch.Q16.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/Q16.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.countDistinct
import org.apache.spark.sql.functions.udf

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

/**
 * TPC-H Query 16
 * Savvas Savvides 
 *
 */
class Q16 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 decrease = udf { (x: Double, y: Double) => x * (1 - y) }
    val complains = udf { (x: String) => x.matches(".*Customer.*Complaints.*") }
    val polished = udf { (x: String) => x.startsWith("MEDIUM POLISHED") }
    val numbers = udf { (x: Int) => x.toString().matches("49|14|23|45|19|3|36|9") }

    val fparts = part.filter(($"p_brand" !== "Brand#45") && !polished($"p_type") &&
      numbers($"p_size"))
      .select($"p_partkey", $"p_brand", $"p_type", $"p_size")

    supplier.filter(!complains($"s_comment"))
      // .select($"s_suppkey")
      .join(partsupp, $"s_suppkey" === partsupp("ps_suppkey"))
      .select($"ps_partkey", $"ps_suppkey")
      .join(fparts, $"ps_partkey" === fparts("p_partkey"))
      .groupBy($"p_brand", $"p_type", $"p_size")
      .agg(countDistinct($"ps_suppkey").as("supplier_count"))
      .sort($"supplier_count".desc, $"p_brand", $"p_type", $"p_size")
  }

}