educoder中网约车大数据综合项目 —— 数据分析Spark

第1关： 统计撤销订单中撤销理由最多的前 10 种理由

import org.apache.log4j.Level;
import org.apache.log4j.Logger;
import org.apache.spark.sql.Dataset;
import org.apache.spark.sql.Row;
import org.apache.spark.sql.SaveMode;
import org.apache.spark.sql.SparkSession;
public class CancelReasonTop10 {
    public static void main(String[] args) {
        /********** Begin **********/
        Logger.getLogger("org").setLevel(Level.ERROR);
        SparkSession spark = SparkSession.builder().master("local").appName("CancelReasonTop10").getOrCreate();
        Dataset<Row> moviesData = spark.read().option("delimiter", "|").csv("/data/workspace/myshixun/data/canceldata.txt")
                .toDF("companyid", "address", "districtname", "orderid", "ordertime", "canceltime", "operator", "cancelt