recommend-emr-dataprocess/ad/02_ad_model_update_test.sh

#!/bin/sh
set -x

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

sh_path=$(cd $(dirname $0); pwd)
source ${sh_path}/00_common.sh

source /root/anaconda3/bin/activate py37


# 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
# 特征文件名
feature_file=20240703_ad_feature_name.txt
# 模型本地临时保存路径
model_local_home=/root/zhaohp/XGB/

# 模型HDFS保存路径，测试时修改为其他路径，避免影响线上
MODEL_PATH=/dw/recommend/model/35_ad_model
# 预测结果保存路径，测试时修改为其他路径，避免影响线上
PREDICT_RESULT_SAVE_PATH=/dw/recommend/model/34_ad_predict_data
# 模型OSS保存路径，测试时修改为其他路径，避免影响线上
MODEL_OSS_PATH=oss://art-recommend.oss-cn-hangzhou.aliyuncs.com/zhangbo/
# 线上模型名，测试时修改为其他模型名，避免影响线上
model_name=model_xgb_351_1000_v2
# 线上校准文件名
OSS_CALIBRATION_FILE_NAME=model_xgb_351_1000_v2_calibration


# 本地保存HDFS模型路径文件，测试时修改为其他模型名，避免影响线上
model_path_file=${model_local_home}/online_model_path.txt
# 获取当前是星期几，1表示星期一
current_day_of_week="$(date +"%u")"

# 任务开始时间
start_time=$(date +%s)
# 前一天
today_early_1="$(date -d '1 days ago' +%Y%m%d)"
# 线上模型在HDFS中的路径
online_model_path=`cat ${model_path_file}`
# 训练用的数据路径
train_data_path=""
# 评估用的数据路径
predict_date_path=""
#评估结果保存路径
new_model_predict_result_path=""
# 模型保存路径
model_save_path=""
# 评测结果保存路径，后续需要根据此文件评估是否要更新模型
predict_analyse_file_path=/root/zhaohp/XGB/predict_analyse_file/20241105_351_1000_analyse.txt
# 校准文件保存路径
calibration_file_path=""

# 保存模型评估的分析结果
old_incr_rate_avg=0
new_incr_rate_avg=0

top10_msg=""


calc_model_predict() {
  local count=0
  local max_line=10
  local old_total_diff=0
  local new_total_diff=0
  top10_msg="| CID  | 老模型相对真实CTCVR的变化 | 新模型相对真实CTCVR的变化 |"
  top10_msg+=" \n| ---- | --------- | -------- |"
  while read -r line && [ ${count} -lt ${max_line} ]; do

      # 使用 ! 取反判断，只有当行中不包含 "cid" 时才执行继续的逻辑
      if [[ "${line}" == *"cid"* ]]; then
          continue
      fi

      read -a numbers <<< "${line}"

      # 分数分别保存
      real_score_map[${numbers[0]}]=${numbers[3]}
      old_score_map[${numbers[0]}]=${numbers[6]}
      new_score_map[${numbers[0]}]=${numbers[7]}

      # 拼接Top10详情的飞书消息
      top10_msg="${top10_msg} \n| ${numbers[0]} | ${numbers[6]} | ${numbers[7]} | "

      # 计算top10相对误差绝对值的均值
      old_abs_score=$( echo "if(${numbers[6]} < 0) -${numbers[6]} else ${numbers[6]}" | bc -l )
      new_abs_score=$( echo "if(${numbers[7]} < 0) -${numbers[7]} else ${numbers[7]}" | bc -l )

      old_total_diff=$( echo "${old_total_diff} + ${old_abs_score}" | bc -l )
      new_total_diff=$( echo "${new_total_diff} + ${new_abs_score}" | bc -l )

      count=$((${count} + 1))

  done < "${predict_analyse_file_path}"

  local return_code=$?
  check_run_status $return_code $step_start_time "计算Top10差异" "计算Top10差异异常"

  old_incr_rate_avg=$( echo "scale=6; ${old_total_diff} / ${count}" | bc -l )
  check_run_status $? $step_start_time "计算老模型Top10差异" "计算老模型Top10差异异常"


  new_incr_rate_avg=$( echo "scale=6; ${new_total_diff} / ${count}" | bc -l )
  check_run_status $? $step_start_time "计算新模型Top10差异" "计算新模型Top10差异异常"

  echo "老模型Top10差异平均值: ${old_incr_rate_avg}"
  echo "新模型Top10差异平均值: ${new_incr_rate_avg}"
  echo "新老模型分数对比: "
  for cid in "${!new_score_map[@]}"; do
    echo "\t CID: $cid, 老模型分数: ${old_score_map[$cid]}, 新模型分数: ${new_score_map[$cid]}"
  done
}


calc_model_predict