分桶方式改变

src/main/scala/com/aliyun/odps/spark/examples/makedata_ad/makedata_ad_33_bucketData_20240622.scala

@@ -95,8 +95,8 @@ object makedata_ad_33_bucketData_20240622 {
                   }else{
                     if (score > 1E-8) {
                       if (bucketsMap.contains(name)) {
-                        val (_, buckets) = bucketsMap(name)
-                        val scoreNew = 1.0 / (buckets.length + 1) * (ExtractorUtils.findInsertPosition(buckets, score).toDouble + 1.0)
+                        val (bucketsNum, buckets) = bucketsMap(name)
+                        val scoreNew = 1.0 / bucketsNum * (ExtractorUtils.findInsertPosition(buckets, score).toDouble + 1.0)
                         name + ":" + scoreNew.toString
                       } else {
                         name + ":" + score.toString

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

@@ -20,7 +20,7 @@ nohup /opt/apps/SPARK2/spark-2.4.8-hadoop3.2-1.0.8/bin/spark-class2 org.apache.s
 --master yarn --driver-memory 16G --executor-memory 1G --executor-cores 1 --num-executors 16 \
 --conf spark.driver.maxResultSize=16G \
 ./target/spark-examples-1.0.0-SNAPSHOT-shaded.jar \
-readPath:/dw/recommend/model/31_ad_sample_data_v3/2024062[01] \
+readPath:/dw/recommend/model/31_ad_sample_data_v3/2024062[01]* \
 savePath:/dw/recommend/model/32_bucket_file/ \
 fileName:20240703_100_fix sampleRate:1.0 bucketNum:100 \
 > p32_data.log 2>&1 &