recommend-emr-dataprocess/ad/01_ad_model_update.sh

#!/bin/sh
set -x

# source /root/anaconda3/bin/activate py37
sh_path=$(dirname $0)
source ${sh_path}/00_common.sh

export SPARK_HOME=/opt/apps/SPARK2/spark-2.4.8-hadoop3.2-1.0.8
export PATH=$SPARK_HOME/bin:$PATH
export HADOOP_CONF_DIR=/etc/taihao-apps/hadoop-conf
export JAVA_HOME=/usr/lib/jvm/java-1.8.0

# 全局常量
HADOOP=/opt/apps/HADOOP-COMMON/hadoop-common-current/bin/hadoop

TRAIN_PATH=/dw/recommend/model/31_ad_sample_data_v4/
BUCKET_FEATURE_PATH=/dw/recommend/model/33_ad_train_data_v4/
TABLE=alg_recsys_ad_sample_all

# 训练用的数据路径
train_data_path=""

# 评估用的数据路径
predict_date_path=""

init() {

  local today_early_1="$(date -d '1 days ago' +%Y%m%d)"

  predict_date_path=${BUCKET_FEATURE_PATH}/${today_early_1}

  local count=1

  local current_data="$(date -d '2 days ago' +%Y%m%d)"
  # 循环获取前 n 天的非节日日期
  while [[ $count -lt 8 ]]; do
    date_key=$(date -d "$current_data" +%Y%m%d)
    # 判断是否是节日，并拼接训练数据路径
    if [ $(is_not_holidays $date_key) -eq 1 ]; then
      if [[ -z ${train_data_path} ]]; then
        train_data_path="${BUCKET_FEATURE_PATH}/${date_key}"
      else
        train_data_path="${BUCKET_FEATURE_PATH}/${date_key},${train_data_path}"
      fi 
      count=$((count + 1))
    else
      echo "日期: ${date_key}是节日，跳过"
    fi
    current_data=$(date -d "$current_date -1 day" +%Y-%m-%d)
  done

  echo "train_data_path: ${train_data_path}"
  echo "predict_date_path: ${predict_date_path}"
}

# xgb_train() {

# }


# 主方法
main() {
  init
}


main