用Spark完成复杂TopN计算的两种逻辑

如果有商品品类的数据pairRDD(categoryId,clickCount_orderCount_payCount)，用Spark完成Top5,你会怎么做?

这里假设使用Java语言进行编写，那么你有两种思路：

1.简化成RDD(categoryObject)，其中categoryObject实现了java.lang.Comparable.然后使用top(5)获得topN

2.转换成PairRDD(categoryKey,info)，其中categoryKey实现了scala.math.Ordered。然后进行sortByKey之后再take(5).

注意:

1)top(n)函数在Java的Spark API中内部调用的比较器是java.lang.Comparable进行比较.

2)而sortByKey函数在Java的Spark API中依然调用scala.math.Ordered进行比较.

相比之下，思路2的空间和时间都不如思路1，但是如果我们需要sort结果的过程中顺便获得topN,则使用思路2更好一些。

思路1实现:

CategoryObject:

package com.stan.core.spark.userAction;

import java.io.Serializable;

public class ComparableCategoryObject
    implements Comparable<ComparableCategoryObject>, Serializable {
    String categoryId;
    Long clickCategoryCount;
    Long orderCategoryCount;
    Long defrayCategoryCount;

    @Override
    public int compareTo(ComparableCategoryObject o) {
        long compareNum =
                (this.defrayCategoryCount - o.defrayCategoryCount) * 10000
                        +
                        (this.orderCategoryCount - o.orderCategoryCount) * 100
                        +
                        (this.clickCategoryCount - o.clickCategoryCount) * 1;
        return (int)(compareNum%1000);
    }

    @Override
    public String toString() {
        return "ComparableCategoryObject{" +
                "categoryId='" + categoryId + '\'' +
                ", clickCategoryCount=" + clickCategoryCount +
                ", orderCategoryCount=" + orderCategoryCount +
                ", defrayCategoryCount=" + defrayCategoryCount +
                '}';
    }

    public String getCategoryId() {
        return categoryId;
    }

    public void setCategoryId(String categoryId) {
        this.categoryId = categoryId;
    }

    public Long getClickCategoryCount() {
        return clickCategoryCount;
    }

    public void setClickCategoryCount(Long clickCategoryCount) {
        this.clickCategoryCount = clickCategoryCount;
    }

    public Long getOrderCategoryCount() {
        return orderCategoryCount;
    }

    public void setOrderCategoryCount(Long orderCategoryCount) {
        this.orderCategoryCount = orderCategoryCount;
    }

    public Long getDefrayCategoryCount() {
        return defrayCategoryCount;
    }

    public void setDefrayCategoryCount(Long defrayCategoryCount) {
        this.defrayCategoryCount = defrayCategoryCount;
    }
}

具体调用方法:

        // 1.封装
        JavaRDD<ComparableCategoryObject> comparableCategoryObjectJavaRDD =
                categoryId2allCount.map(
                        new Function<Tuple2<String, String>, ComparableCategoryObject>() {
                            @Override
                            public ComparableCategoryObject call(Tuple2<String, String> stringStringTuple2) throws Exception {
                                String categoryId = stringStringTuple2._1;
                                String allCount = stringStringTuple2._2;
                                String[] tmpAllCountSplited = allCount.split("_");
                                Long clickCount = Long.valueOf(tmpAllCountSplited[0]);
                                Long orderCount = Long.valueOf(tmpAllCountSplited[1]);
                                Long defrayCount = Long.valueOf(tmpAllCountSplited[2]);
                                ComparableCategoryObject comparableCategoryObject =
                                        new ComparableCategoryObject();
                                comparableCategoryObject.setCategoryId(categoryId);
                                comparableCategoryObject.setClickCategoryCount(clickCount);
                                comparableCategoryObject.setOrderCategoryCount(orderCount);
                                comparableCategoryObject.setDefrayCategoryCount(defrayCount);
                                return comparableCategoryObject;
                            }
                        }
                );
         // 2.top(5)
        List<ComparableCategoryObject> top10Categorys = comparableCategoryObjectJavaRDD.top(5);

思路2实现:

CategoryKey：

package com.stan.core.spark.userAction;

import scala.Serializable;
import scala.math.Ordered;

/**
 * 用于按照
 * (clickCategoryCount,orderCategoryCount,defrayCategoryCount)的优先级排序
 */
public class ComparableCategoryKey
        // scala中可比较，以便于进行RDD排序
        implements Ordered<ComparableCategoryKey>, Serializable {
    String categoryId;
    Long clickCategoryCount;
    Long orderCategoryCount;
    Long defrayCategoryCount;

    /**
     * 计算比较数
     *
     * 因为优先级为 : 先比较支付量，若支付量相同，则比较下单量，若下单量相同，则继续比较点击量
     * 所以我在进行比较的时候直接使用 比较值 = 支付量差 * 10000 + 下单量差 * 100 + 点击量差
     * 若比较值小于 0 ，则小于，若比较值大于0 ， 则大于，若比较值等于0，则等于
     * @param comparableCategoryWithAllCount
     * @return
     */
    public long computeCompareNum(ComparableCategoryKey comparableCategoryWithAllCount){
        long compareNum =
                (this.defrayCategoryCount - comparableCategoryWithAllCount.defrayCategoryCount) * 10000
                        +
                        (this.orderCategoryCount - comparableCategoryWithAllCount.orderCategoryCount) * 100
                        +
                        (this.clickCategoryCount - comparableCategoryWithAllCount.clickCategoryCount) * 1;
        return compareNum;
    }

    @Override
    public int compare(ComparableCategoryKey comparableCategoryWithAllCount) {
        return (int)(computeCompareNum(comparableCategoryWithAllCount)%1000);
    }

    @Override
    public boolean $less(ComparableCategoryKey comparableCategoryWithAllCount) {
        return computeCompareNum(comparableCategoryWithAllCount) < 0;
    }

    @Override
    public boolean $greater(ComparableCategoryKey comparableCategoryWithAllCount) {
        return computeCompareNum(comparableCategoryWithAllCount) > 0;
    }

    @Override
    public boolean $less$eq(ComparableCategoryKey comparableCategoryWithAllCount) {
        return computeCompareNum(comparableCategoryWithAllCount) <= 0;
    }

    @Override
    public boolean $greater$eq(ComparableCategoryKey comparableCategoryWithAllCount) {
        return computeCompareNum(comparableCategoryWithAllCount) >= 0;
    }

    @Override
    public int compareTo(ComparableCategoryKey comparableCategoryWithAllCount) {
        return (int)(computeCompareNum(comparableCategoryWithAllCount)%1000);
    }

    public String getCategoryId() {
        return categoryId;
    }

    public void setCategoryId(String categoryId) {
        this.categoryId = categoryId;
    }

    public Long getClickCategoryCount() {
        return clickCategoryCount;
    }

    public void setClickCategoryCount(Long clickCategoryCount) {
        this.clickCategoryCount = clickCategoryCount;
    }

    public Long getOrderCategoryCount() {
        return orderCategoryCount;
    }

    public void setOrderCategoryCount(Long orderCategoryCount) {
        this.orderCategoryCount = orderCategoryCount;
    }

    public Long getDefrayCategoryCount() {
        return defrayCategoryCount;
    }

    public void setDefrayCategoryCount(Long defrayCategoryCount) {
        this.defrayCategoryCount = defrayCategoryCount;
    }

    @Override
    public String toString() {
        return "ComparableCategoryKey{" +
                "categoryId='" + categoryId + '\'' +
                ", clickCategoryCount=" + clickCategoryCount +
                ", orderCategoryCount=" + orderCategoryCount +
                ", defrayCategoryCount=" + defrayCategoryCount +
                '}';
    }
}

具体的调用过程:

// 1.封装成(categoryKey,info)
JavaPairRDD<ComparableCategoryKey,String> comparableCategory2AllCountRDD =
                categoryId2allCount.mapToPair(
                new PairFunction<Tuple2<String, String>, ComparableCategoryKey,String>() {
                    @Override
                    public Tuple2<ComparableCategoryKey,String> call(Tuple2<String, String> stringStringTuple2) throws Exception {
                        String categoryId = stringStringTuple2._1;
                        String allCount = stringStringTuple2._2;
                        String[] tmpAllCountSplited = allCount.split("_");
                        Long clickCount = Long.valueOf(tmpAllCountSplited[0]);
                        Long orderCount = Long.valueOf(tmpAllCountSplited[1]);
                        Long defrayCount = Long.valueOf(tmpAllCountSplited[2]);
                        ComparableCategoryKey comparableCategoryWithAllCount =
                                new ComparableCategoryKey();
                        comparableCategoryWithAllCount.setCategoryId(categoryId);
                        comparableCategoryWithAllCount.setClickCategoryCount(clickCount);
                        comparableCategoryWithAllCount.setOrderCategoryCount(orderCount);
                        comparableCategoryWithAllCount.setDefrayCategoryCount(defrayCount);
                        return new Tuple2<>(comparableCategoryWithAllCount,allCount);
                    }
                }
        );
        // 2.sortByKey 排序
        comparableCategory2AllCountRDD.sortByKey();

        // 3.获取前五
        List<Tuple2<ComparableCategoryKey,String>> top10Categorys =  comparableCategory2AllCountRDD.take(5);