Spark專案智慧城市車流量分析專案之固定卡口下車輛的行車軌跡
資料集
- 日期 卡口ID 攝像頭編號 車牌號 拍攝時間
- date monitor_id camera_id car action_time
車速 道路ID 區域ID
speed road_id area_id
資料集
模擬資料
2018-06-27 0007 00536 京R66884 2018-06-27 11:30:25 30 41 08
2018-06-27 0005 01726 閔P89564 2018-06-27 09:34:03 19 7 03
2018-06-27 0005 01272 閔P89564 2018-06-27 09:50:39 187 19 05
2018-06-27 0002 00082 閔P89564 2018-06-27 09:34:47 1 28 05
2018-06-27 0003 08417 閔P89564 2018-06-27 09:23:05 171 42 02
2018-06-27 0003 02757 閔P89564 2018-06-27 09:52:35 32 50 04
2018-06-27 0000 03759 滬W87972 2018-06-27 20:02:43 243 25 05
2018-06-27 0002 08652 滬W87972 2018-06-27 20:05:10 51 11 05
程式碼邏輯
本地模擬程式碼
package test; import org.apache.spark.SparkConf; import org.apache.spark.api.java.JavaPairRDD; import org.apache.spark.api.java.JavaRDD; import org.apache.spark.api.java.JavaSparkContext; import org.apache.spark.api.java.function.Function; import org.apache.spark.api.java.function.PairFunction; import org.apache.spark.api.java.function.VoidFunction; import org.apache.spark.broadcast.Broadcast; import scala.Tuple2; import java.util.*; public class Carlearn { public static void main(String[] args) { SparkConf conf = new SparkConf(); conf.setMaster("local").setAppName("Carlearn"); JavaSparkContext sc = new JavaSparkContext(conf); JavaRDD<String> lineRDD = sc.textFile("monitor_flow_action"); //mapToPair 形成一個tuple<卡扣id,車牌號> JavaPairRDD<String, String> rdd2 = lineRDD.mapToPair(new PairFunction<String, String, String>() { @Override public Tuple2<String, String> call(String s) throws Exception { String[] split = s.split("\t"); return new Tuple2<>(split[1], split[3]); } }); //過濾只留下一個卡扣id為001的資訊 JavaPairRDD<String, String> rdd3 = rdd2.filter(new Function<Tuple2<String, String>, Boolean>() { @Override public Boolean call(Tuple2<String, String> tuple2) throws Exception { return tuple2._1.equals("0001"); } }); //map 形成一個個的car JavaRDD<String> rdd4 = rdd3.map(new Function<Tuple2<String, String>, String>() { @Override public String call(Tuple2<String, String> tuple2) throws Exception { return tuple2._2; } }); //去重 JavaRDD<String> rdd5 = rdd4.distinct(); //轉換成集合 List<String> result = rdd5.collect(); //廣播變數 final Broadcast<List<String>> broadcast = sc.broadcast(result); /** * mapToPair轉換成Tuple<車牌號,一行的值> */ JavaPairRDD<String, String> rddA = lineRDD.mapToPair(new PairFunction<String, String, String>() { @Override public Tuple2<String, String> call(String s) throws Exception { String[] split = s.split("\t"); return new Tuple2<>(split[3], s); } }); //過濾掉只留下卡扣id為001資訊的車, JavaPairRDD<String, Iterable<String>> rddC = rddA.filter(new Function<Tuple2<String, String>, Boolean>() { @Override public Boolean call(Tuple2<String, String> tuple2) throws Exception { List<String> carList = broadcast.value(); String carId = tuple2._2.split("\t")[3]; return carList.contains(carId); } }).groupByKey(); rddC.foreach(new VoidFunction<Tuple2<String, Iterable<String>>>() { @Override public void call(Tuple2<String, Iterable<String>> tuple2) throws Exception { Iterator<String> iterator = tuple2._2.iterator(); List<Tuple2<String, String>> map = new ArrayList<>(); //將時間和卡扣號封裝成一個list while (iterator.hasNext()) { String next = iterator.next(); String time = next.split("\t")[4]; String kakouId = next.split("\t")[1]; Tuple2<String, String> time_kakou = new Tuple2<>(time, kakouId); map.add(time_kakou); } //通過時間排序,整理出汽車的行車軌跡 Collections.sort(map, new Comparator<Tuple2<String, String>>() { @Override public int compare(Tuple2<String, String> o1, Tuple2<String, String> o2) { return o1._1.compareTo(o2._1); } }); //列印下行車軌跡 String chepai = tuple2._1; System.out.println("汽車號:"+chepai); for (Tuple2<String, String> s : map) { System.out.print("時間:"+s._1+"卡扣:"+s._2+"===>"); } System.out.println(); } }); } }
結果
06-27 22:39:26卡扣:0005===>時間:2018-06-27 22:40:31卡扣:0008===>時間:2018-06-27 22:41:37卡扣:0005===>時間:2018-06-27 22:42:02卡扣:0000===>時間:2018-06-27 22:43:07卡扣:0002===>時間:2018-06-27 22:44:28卡扣:0004===>時間:2018-06-27 22:45:49卡扣:0001===>時間:2018-06-27 22:51:40卡扣:0005===>時間:2018-06-27 22:53:26卡扣:0008===>時間:2018-06-27 22:54:06卡扣:0007===>時間:2018-06-27 22:57:26卡扣:0004===>時間:2018-06-27 22:57:56卡扣:0005===>時間:2018-06-27 22:58:07卡扣:0006===>時間:2018-06-27 23:00:40卡扣:0006===>時間:2018-06-27 23:01:56卡扣:0008===>時間:2018-06-27 23:04:27卡扣:0004===>時間:2018-06-27 23:04:43卡扣:0003===>時間:2018-06-27 23:05:38卡扣:0001===>時間:2018-06-27 23:09:03卡扣:0007===>時間:2018-06-27 23:09:06卡扣:0005===>時間:2018-06-27 23:09:37卡扣:0004===>時間:2018-06-27 23:11:11卡扣:0007===>時間:2018-06-27 23:12:06卡扣:0001===>時間:2018-06-27 23:12:12卡扣:0008===>時間:2018-06-27 23:14:31卡扣:0002===>時間:2018-06-27 23:16:25卡扣:0007===>時間:2018-06-27 23:23:47卡扣:0000===>時間:2018-06-27 23:24:03卡扣:0008===>時間:2018-06-27 23:26:27卡扣:0003===>時間:2018-06-27 23:29:44卡扣:0001===>時間:2018-06-27 23:30:23卡扣:0003===>時間:2018-06-27 23:33:27卡扣:0007===>時間:2018-06-27 23:34:18卡扣:0002===>時間:2018-06-27 23:34:28卡扣:0002===>時間:2018-06-27 23:34:39卡扣:0001===>時間:2018-06-27 23:39:59卡扣:0005===>時間:2018-06-27 23:45:13卡扣:0001===>時間:2018-06-27 23:48:47卡扣:0004===>
汽車號:京D44143
時間:2018-06-27 02:00:01卡扣:0007===>時間:2018-06-27 02:00:59卡扣:0001===>時間:2018-06-27 02:02:11卡扣:0008===>時間:2018-06-27 02:02:29卡扣:0001===>時間:2018-06-27 02:02:31卡扣:0001===>時間:2018-06-27 02:04:11卡扣:0005===>時間:2018-06-27 02:06:20卡扣:0000===>時間:2018-06-27 02:07:36卡扣:0007===>時間:2018-06-27 02:14:36卡扣:0004===>時間:2018-06-27 02:14:58卡扣:0005===>時間:2018-06-27 02:15:01卡扣:0007===>時間:2018-06-27 02:15:14卡扣:0003===>時間:2018-06-27 02:17:16卡扣:0005===>時間:2018-06-27 02:20:59卡扣:0001===>時間:2018-06-27 02:21:26卡扣:0008===>時間:2018-06-27 02:21:27卡扣:0000===>時間:2018-06-27 02:22:19卡扣:0004===>時間:2018-06-27 02:26:20卡扣:0007===>時間:2018-06-27 02:35:02卡扣:0002===>時間:2018-06-27 02:35:28卡扣:0006===>時間:2018-06-27 02:37:23卡扣:0001===>時間:2018-06-27 02:38:13卡扣:0005===>時間:2018-06-27 02:38:33卡扣:0002===>時間:2018-06-27 02:39:15卡扣:0000===>時間:2018-06-27 02:39:42卡扣:0008===>時間:2018-06-27 02:41:53卡扣:0001===>時間:2018-06-27 02:46:54卡扣:0007===>時間:2018-06-27 02:47:23卡扣:0008===>時間:2018-06-27 02:52:27卡扣:0001===>時間:2018-06-27 02:53:31卡扣:0006===>時間:2018-06-27 03:08:55卡扣:0007===>
汽車號:京R34631
時間:2018-06-27 14:01:24卡扣:0004===>時間:2018-06-27 14:03:36卡扣:0005===>時間:2018-06-27 14:05:04卡扣:0006===>時間:2018-06-27 14:08:40卡扣:0007===>時間:2018-06-27 14:09:29卡扣:0002===>時間:2018-06-27 14:09:51卡扣:0008===>時間:2018-06-27 14:13:40卡扣:0008===>時間:2018-06-27 14:18:55卡扣:0005===>時間:2018-06-27 14:26:54卡扣:0001===>時間:2018-06-27 14:27:20卡扣:0000===>時間:2018-06-27 14:34:02卡扣:0001===>時間:2018-06-27 14:34:39卡扣:0006===>時間:2018-06-27 14:36:10卡扣:0003===>時間:2018-06-27 14:37:08卡扣:0006===>時間:2018-06-27 14:37:30卡扣:0003===>時間:2018-06-27 14:39:25卡扣:0005===>時間:2018-06-27 14:41:00卡扣:0007===>時間:2018-06-27 14:42:03卡扣:0001===>時間:2018-06-27 14:47:36卡扣:0001===>時間:2018-06-27 14:48:16卡扣:0003===>時間:2018-06-27 14:53:22卡扣:0001===>時間:2018-06-27 14:53:34卡扣:0005===>時間:2018-06-27 14:53:54卡扣:0001===>時間:2018-06-27 14:53:56卡扣:0002===>時間:2018-06-27 14:54:14卡扣:0003===>時間:2018-06-27 14:55:44卡扣:0003===>時間:2018-06-27 14:57:27卡扣:0006===>時間:2018-06-27 14:57:53卡扣:0000===>時間:2018-06-27 14:58:12卡扣:0008===>時間:2018-06-27 14:59:11卡扣:0008===>
汽車號:滬V82625