在Java - Spark中查找DataFrame每天的最大行程

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

SparkSession spark = SparkSession.builder()
        .appName("MaxDistancePerDay")
        .master("local")
        .getOrCreate();

Dataset<Row> df = spark.read()
        .format("csv")
        .option("header", "true")
        .load("path/to/input.csv");

df = df.withColumn("date", functions.to_date(df.col("date"), "yyyy-MM-dd"));

Dataset<Row> maxDistancePerDay = df.groupBy("date")
        .agg(functions.max(df.col("distance")).alias("max_distance"));

maxDistancePerDay.show();