SPARK-SQL - group分组聚合相关的api，groupBy().count()，groupBy().avg()等

准备orders.json文件

{"id":"1", "userId":"1", "userName":"Join", "totalPrice":80.0,"qty":3.0}
{"id":"2", "userId":"1", "userName":"Join", "totalPrice":50.0,"qty":3.0}
{"id":"3", "userId":"2", "userName":"Jeffy", "totalPrice":200.0,"qty":3.0}
{"id":"4", "userId":"99999", "userName":"zombie", "totalPrice":222.0,"qty":3.0}

演示如下api
groupBy().count()
groupBy().avg()
groupBy().max()
groupBy().min()
groupBy().sum()
groupBy().mean()

代码示例

import org.apache.spark.sql.Dataset;
import org.apache.spark.sql.Row;
import org.apache.spark.sql.SparkSession;public class test_28_1 {public static void main(String[] args) {SparkSession spark = SparkSession.builder().config("spark.driver.host", "localhost").appName("GroupApiTest").master("local").getOrCreate();spark.sparkContext().setLogLevel("ERROR");Dataset<Row> ordersDataSet = spark.read().json(Utils.BASE_PATH + "/join/orders.json");ordersDataSet.show();/*+---+---+----------+------+--------+| id|qty|totalPrice|userId|userName|+---+---+----------+------+--------+|  1|3.0|      80.0|     1|    Join||  2|3.0|      50.0|     1|    Join||  3|3.0|     200.0|     2|   Jeffy||  4|3.0|     222.0| 99999|  zombie|+---+---+----------+------+--------+*///1: 基础的聚合函数ordersDataSet.groupBy("userId").count().show();/*+------+-----+|userId|count|+------+-----+|     1|    2|| 99999|    1||     2|    1|+------+-----+*/ordersDataSet.groupBy("userId").avg("totalPrice", "qty").show();/*+------+---------------+--------+|userId|avg(totalPrice)|avg(qty)|+------+---------------+--------+|     1|           65.0|     3.0|| 99999|          222.0|     3.0||     2|          200.0|     3.0|+------+---------------+--------+*/ordersDataSet.groupBy("userId").max("totalPrice", "qty").show();/*+------+---------------+--------+|userId|max(totalPrice)|max(qty)|+------+---------------+--------+|     1|           80.0|     3.0|| 99999|          222.0|     3.0||     2|          200.0|     3.0|+------+---------------+--------+*/ordersDataSet.groupBy("userId").min("totalPrice", "qty").show();/*+------+---------------+--------+|userId|min(totalPrice)|min(qty)|+------+---------------+--------+|     1|           50.0|     3.0|| 99999|          222.0|     3.0||     2|          200.0|     3.0|+------+---------------+--------+*/ordersDataSet.groupBy("userId").sum("totalPrice", "qty").show();/*+------+---------------+--------+|userId|sum(totalPrice)|sum(qty)|+------+---------------+--------+|     1|          130.0|     6.0|| 99999|          222.0|     3.0||     2|          200.0|     3.0|+------+---------------+--------+*///均值ordersDataSet.groupBy("userId").mean("totalPrice", "qty").show();/*+------+---------------+--------+|userId|avg(totalPrice)|avg(qty)|+------+---------------+--------+|     1|           65.0|     3.0|| 99999|          222.0|     3.0||     2|          200.0|     3.0|+------+---------------+--------+*/}
}