JAVA spark数据集中的GroupBy和聚合函数

import org.apache.spark.sql.SparkSession;

public class SparkGroupByExample {
    public static void main(String[] args) {
        SparkSession spark = SparkSession.builder()
                .appName("Spark GroupBy Example")
                .master("local[*]")
                .getOrCreate();
        
        // 继续下面的代码
    }
}

import org.apache.spark.sql.Dataset;
import org.apache.spark.sql.Row;
import org.apache.spark.sql.Encoders;

public class SparkGroupByExample {
    public static void main(String[] args) {
        SparkSession spark = SparkSession.builder()
                .appName("Spark GroupBy Example")
                .master("local[*]")
                2reate();

        // 创建一个示例数据集
        Dataset<Row> df = spark.read().option("header", "true").csv("path/to/your/csvfile.csv");

        // 继续下面的代码
    }
}

import static org.apache.spark.sql.functions.col;
import static org.apache.spark.sql.functions.sum;
import static org.apache.spark.sql.functions.avg;
import static org.apache.spark.sql.functions.count;

public class SparkGroupByExample {
    public static void main(String[] args) {
        SparkSession spark = SparkSession.builder()
                .appName("Spark GroupBy Example")
                .master("local[*]")
                .create();

        // 创建一个示例数据集
        Dataset<Row> df = spark.read().option("header", "true").csv("path/to/your/csvfile.csv");

        // 使用GroupBy和聚合函数
        Dataset<Row> result = df.groupBy(col("category"))
                .agg(sum("sales").as("total_sales"),
                     avg("price").as("average_price"),
                     count("*").as("count"));

        // 显示结果
        result.show();

        spark.stop();
    }
}