新样本数据生产

src/main/scala/com/aliyun/odps/spark/examples/makedata/makedata_12_rosData_v3.scala

@@ -71,7 +71,7 @@ object makedata_12_rosData_v3 {
               val ts = r.split(":")(1).toLong / 1000
               (midReturn, ts)
             }).sortBy(_._2)
-            val midSet = Set()
+            var midSet = scala.collection.mutable.HashSet[String]()
             for ((midReturn, tsReturn) <- return_mid_ts_list){
               if (!midSet.contains(midReturn)){
                 midSet.add(midReturn)

src/main/scala/com/aliyun/odps/spark/examples/临时记录的脚本

@@ -1,8 +1,8 @@
 nohup /opt/apps/SPARK2/spark-2.4.8-hadoop3.2-1.0.8/bin/spark-class2 org.apache.spark.deploy.SparkSubmit \
 --class com.aliyun.odps.spark.examples.makedata.makedata_10_originData_v3 \
---master yarn --driver-memory 1G --executor-memory 2G --executor-cores 1 --num-executors 32 \
+--master yarn --driver-memory 1G --executor-memory 1G --executor-cores 1 --num-executors 64 \
 ./target/spark-examples-1.0.0-SNAPSHOT-shaded.jar \
-tablePart:32 savePath:/dw/recommend/model/10_sample_data_v3/ beginStr:20240226 endStr:20240226 > p10.log 2>&1 &
+tablePart:64 savePath:/dw/recommend/model/10_sample_data_v3/ beginStr:20240226 endStr:20240226 > p10.log 2>&1 &