Spark Java Dataset按范围对行进行分类

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

public class SparkJavaExample {
    public static void main(String[] args) {
        SparkSession spark = SparkSession.builder()
                .appName("SparkJavaExample")
                .master("local")
                .getOrCreate();

        // 创建Dataset，假设包含学生的成绩信息
        Dataset<Row> studentScores = spark.read()
                .format("csv")
                .option("header", "true")
                .load("student_scores.csv");

        // 筛选成绩在80到90之间的行
        Dataset<Row> filteredRows = studentScores.filter("score >= 80 and score <= 90");

        // 输出结果
        filteredRows.show();
    }
}

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

public class SparkJavaExample {
    public static void main(String[] args) {
        SparkSession spark = SparkSession.builder()
                .appName("SparkJavaExample")
                .master("local")
                .getOrCreate();

        // 创建Dataset，假设包含学生的成绩信息
        Dataset<Row> studentScores = spark.read()
                .format("csv")
                .option("header", "true")
                .load("student_scores.csv");

        // 筛选成绩在80到90之间的行
        Dataset<Row> filteredRows = studentScores.filter("score >= 80 and score <= 90");

        // 按班级分组
        Dataset<Row> groupedRows = filteredRows.groupBy("class");

        // 输出结果
        groupedRows.show();
    }
}