val spark: SparkSession = SparkSession.builder()
      .master("local[*]")
      .appName("exam")
      .getOrCreate()
    val sc: SparkContext = spark.sparkContext
    val lines: RDD[String] = sc.textFile("hdfs://192.168.152.192:9000/app/data/exam/meituan_waimai_meishi.csv")


    val lines1: RDD[Array[String]] = lines.filter(x => x.startsWith("spu_id") == false)
      .map(x => x.split(","))

lines1.map(x => (x(2), 1)).reduceByKey(_ + _).collect().foreach(println)

②统计每个店铺的总销售额。

lines1.map(x => (x(2), Try(x(5).toDouble).toOption.getOrElse(0.0) *
  Try(x(7).toInt).toOption.getOrElse(0))).reduceByKey(_ + _)
  .collect().foreach(println)

③统计每个店铺销售额最高的前三个商品，输出内容包括店铺名，商品名和销售额，其

    //方法一
    lines1.map(x => (x(2), x(4), Try(x(5).toDouble).toOption.getOrElse(0.0) *
      Try(x(7).toInt).toOption.getOrElse(0)))
      .filter(x => x._3 > 0).groupBy(x => x._1)
      .mapValues(value => value.toList.sortBy(x => -x._3).take(3)) //负号(-)降序
      .flatMapValues(x => x)
      .collect().foreach(println)
    //方法二
    lines1.map(x => (x(2), x(4), Try(x(5).toDouble).toOption.getOrElse(0.0) *
      Try(x(7).toInt).toOption.getOrElse(0)))
      .filter(x => x._3 > 0).groupBy(x => x._1)
      .flatMap(x => x._2.toList.sortBy(y => 0 - y._3).take(3))
      .foreach(println)

    //方法三
    lines1.map(x => (x(2), x(4), Try(x(5).toDouble).toOption.getOrElse(0.0) *
      Try(x(7).toInt).toOption.getOrElse(0)))
      .filter(x => x._3 > 0).groupBy(x => x._1)
      .map(x => {
        var shop_name: String = x._1;
        var topThree: List[(String, String, Double)] = x._2.toList.sortBy(item => 0 - item._3).take(3);
        var shopNameAndSumMoney: List[String] = topThree.map(it => it._2 + " " + it._3);
        (shop_name, shopNameAndSumMoney)
      })
      .foreach(println)

Spark SQL操作

    val spark: SparkSession = SparkSession.builder()
      .master("local[*]")
      .appName("exam")
      .getOrCreate()
    val sc: SparkContext = spark.sparkContext
    val spuDF: DataFrame = spark.read.format("csv").option("header", true).load("hdfs://192.168.152.192:9000/app/data/exam/meituan_waimai_meishi.csv")
    
    spuDF.createOrReplaceTempView("sputb")

①统计每个店铺分别有多少商品（SPU）。

spark.sql("select * from sputb").show()

②统计每个店铺的总销售额。

spark.sql("select shop_name,count(shop_name) as num  from sputb group by shop_name").show()

③统计每个店铺销售额最高的前三个商品，输出内容包括店铺名，商品名和销售额，其 中销售额为 0 的商品不进行统计计算，例如：如果某个店铺销售为 0，则不进行统计。

spark.sql("select shop_name, sum(spu_price * month_sales)  as sumMoney  from sputb group by shop_name").show()

创建Hbase数据表

在 HBase 中创建命名空间（namespace）exam，在该命名空间下创建 spu 表，该表下有

create 'exam:spu','result'

create database spu_db;

create external table if not exists  ex_spu (
    spu_id string,
    shop_id string,
    shop_name string,
    category_name string,
    spu_name string,
    spu_price double,
    spu_originprice double,
    month_sales int,
    praise_num int,
    spu_unit string,
    spu_desc string,
    spu_image string
)
row format delimited fields terminated by ","
stored as textfile location "/app/data/exam"
tblproperties ("skip.header.line.count"="1");

create external table if not exists ex_spu_hbase
(
    key string,
    sales double,
    praise int
)
stored by 'org.apache.hadoop.hive.hbase.HBaseStorageHandler' with
serdeproperties ("hbase.columns.mapping"=":key,result:sales,result:praise")
tblproperties ("hbase.table.name"="exam:spu");

insert into ex_spu_hbase
select concat(tb.shop_id,tb.shop_name) as key, tb.sales,tb.praise from
(select shop_id,shop_name,sum(spu_price*month_sales) as sales, sum(praise_num) as praise
from ex_spu group by shop_id,shop_name) tb;

hive > select * from ex_spu_hbase;

hbase(main):007:0> scan 'exam:spu'