23_str_train_data_make.sh 832 B

1234567891011121314151617181920
  1. #!/bin/sh
  2. set -x
  3. dts=('20250224' '20250225' '20250226' '20250227' '20250228' '20250301' '20250302')
  4. for dt in "${dts[@]}"; do
  5. echo "开始处理: ${dt}"
  6. # STR负样本采样
  7. /opt/apps/SPARK2/spark-2.4.8-hadoop3.2-1.0.8/bin/spark-class2 org.apache.spark.deploy.SparkSubmit \
  8. --class com.aliyun.odps.spark.examples.makedata_recsys.v20250218.makedata_recsys_41_data_fu_sample_20250218 \
  9. --master yarn --driver-memory 4G --executor-memory 8G --executor-cores 1 --num-executors 20 \
  10. --conf spark.driver.maxResultSize=2g \
  11. ./target/spark-examples-1.0.0-SNAPSHOT-shaded.jar \
  12. readPath:/dw/recommend/model/41_recsys_origin_date/${dt}*/* \
  13. savePath:/dw/recommend/model/41_recsys_str_train_data/${dt} \
  14. fuSampleRate:0.05 whatLabel:is_share repartition:64
  15. echo "${dt} 负样本采样完成"
  16. done