recommend-emr-dataprocess/scripts/nor/nor_train.sh

#!/bin/sh
set -x

export HADOOP_CONF_DIR=/etc/taihao-apps/hadoop-conf
export JAVA_HOME=/usr/lib/jvm/java-1.8.0

# params
FEATURE_FILE=20250303_recsys_nor_name.txt
BASE_TRAIN_DATA_PATH=/dw/recommend/model/82_recsys_nor_train_data
PREDICT_RESULT_PATH=/dw/recommend/model/82_recsys_nor_predict_data
MODEL_SAVE_PATH=/dw/recommend/model/82_recsys_nor_model/model_xgb

start_date=20250221
end_date=20250228
train_data_path=""
for((i=0; i<=21; i++))
do
  data_date=$(date -d "$start_date $i day" +"%Y%m%d")
  if [ "$data_date" -le "$end_date" ]
  then
    one_day_data_path="${BASE_TRAIN_DATA_PATH}/${data_date}"
    if [[ -z $train_data_path ]]
    then
      train_data_path=$one_day_data_path
    else
      train_data_path="$train_data_path,$one_day_data_path"
    fi
  fi
done

## ******* train *******
/opt/apps/SPARK3/spark-3.3.1-hadoop3.2-1.0.5/bin/spark-class org.apache.spark.deploy.SparkSubmit \
--class com.tzld.piaoquan.recommend.model.train_recsys_61_xgb_nor_20241209 \
--master yarn --driver-memory 4G --executor-memory 10G --executor-cores 1 --num-executors 32 \
--conf spark.yarn.executor.memoryoverhead=2048 \
--conf spark.shuffle.service.enabled=true \
--conf spark.shuffle.service.port=7337 \
--conf spark.shuffle.consolidateFiles=true \
--conf spark.shuffle.manager=sort \
--conf spark.storage.memoryFraction=0.4 \
--conf spark.shuffle.memoryFraction=0.5 \
--conf spark.default.parallelism=200 \
--conf spark.sql.debug.maxToStringFields=100 \
/mnt/disk1/jch/recommend-model/recommend-model-produce/target/recommend-model-produce-jar-with-dependencies.jar \
featureFile:${FEATURE_FILE} \
trainPath:${train_data_path} \
savePath:${PREDICT_RESULT_PATH} \
modelPath:${MODEL_SAVE_PATH} \
labelLogType:0 \
labelLogBase:1.5 \
eta:0.06 gamma:0.0 max_depth:5 num_round:1000 num_worker:32 repartition:20