recommend-emr-dataprocess/ad/00_test.sh

#!/bin/sh
set -x

sh_path=$(cd $(dirname $0); pwd)

source /root/anaconda3/bin/activate py37

# 模型保存路径
model_save_path=/dw/recommend/model/35_ad_model/model_xgb_351_1000_v2_1009_1015
MODEL_OSS_PATH=oss://art-recommend.oss-cn-hangzhou.aliyuncs.com/zhangbo/
model_name=model_xgb_351_1000_v2
predict_analyse_file_path=/root/zhaohp/XGB/predict_analyse_file/20241014_351_1000_analyse.txt

start_time=$(date +%s)

# 保存模型评估的分析结果
old_incr_rate_avg=0
new_incr_rate_avg=0
declare -A old_score_map
declare -A new_score_map

count=0
max_line=10
old_total_diff=0
new_total_diff=0
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
    old_score_map[${numbers[0]}]=${numbers[6]}
    new_score_map[${numbers[0]}]=${numbers[7]}

    old_total_diff=$( echo "${old_total_diff} + ${numbers[6]}" | bc -l )
    new_total_diff=$( echo "${new_total_diff} + ${numbers[7]}" | bc -l )

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

done < "${predict_analyse_file_path}"

old_incr_rate_avg=$( echo "scale=6; ${old_total_diff} / ${count}" | bc -l )
new_incr_rate_avg=$( echo "scale=6; ${new_total_diff} / ${count}" | bc -l )

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

msg=" 广告模型文件更新完成"
msg+="\n\t - 老模型Top10差异平均值: ${old_incr_rate_avg}"
msg+="\n\t - 新模型Top10差异平均值: ${new_incr_rate_avg}"
msg+="\n\t - 模型在HDFS中的路径: ${model_save_path}"
msg+="\n\t - 模型上传路径: ${MODEL_OSS_PATH}/${model_name}.tar.gz"


top10_msg = "| CID  | 老模型    | 新模型    | \n| ---- | -------- | -------- | "
for cid in "${!new_score_map[@]}"; do
    top10_msg="${top10_msg} \n| ${cid} | ${old_score_map[$cid]} | ${new_score_map[$cid]} | "
done


/root/anaconda3/bin/python ${sh_path}/ad_monitor_util.py --level info --msg "${msg}" --start "${start_time}" --elapsed "10000" --top10 "${top10_msg}"