recommend-emr-dataprocess/qiaojialiang/check_auc.sh

#!/bin/sh
set -ex

source /root/anaconda3/bin/activate py37

#  nohup sh handle_rov.sh > "$(date +%Y%m%d_%H%M%S)_handle_rov.log" 2>&1 &

# 原始数据table name
table='alg_recsys_sample_all'
today="$(date +%Y%m%d)"
today_early_3="$(date -d '3 days ago' +%Y%m%d)"
#table='alg_recsys_sample_all_test'
# 处理分区配置 推荐数据间隔一天生产，所以5日0点使用3日0-23点数据生产new模型数据
begin_early_2_Str="$(date -d '2 days ago' +%Y%m%d)"
end_early_2_Str="$(date -d '2 days ago' +%Y%m%d)"
beginHhStr=00
endHhStr=23
max_hour=05
max_minute=00
# 各节点产出hdfs文件绝对路径
# 源数据文件
originDataPath=/dw/recommend/model/13_sample_data/
# 特征值
valueDataPath=/dw/recommend/model/14_feature_data/
# 特征分桶
bucketDataPath=/dw/recommend/model/16_train_data/
# 模型数据路径
MODEL_PATH=/root/joe/recommend-emr-dataprocess/model
# 预测路径
PREDICT_PATH=/root/joe/recommend-emr-dataprocess/predict
# 历史线上正在使用的模型数据路径
LAST_MODEL_HOME=/root/joe/model_online
# 模型数据文件前缀
model_name=akaqjl8
# fm模型
FM_HOME=/root/sunmingze/alphaFM/bin
# hadoop
HADOOP=/opt/apps/HADOOP-COMMON/hadoop-common-current/bin/hadoop



 0 对比AUC 前置对比2日模型数据 与 线上模型数据效果对比，如果2日模型优于线上，更新线上模型
echo "$(date +%Y-%m-%d_%H-%M-%S)----------step0------------开始对比，新：${MODEL_PATH}/${model_name}_${today_early_3}.txt，与线上online模型数据auc效果"
#$HADOOP fs -text ${bucketDataPath}/${begin_early_2_Str}/* | ${FM_HOME}/bin/fm_predict -m ${LAST_MODEL_HOME}/model_online.txt -dim 8 -core 8 -out ${PREDICT_PATH}/${model_name}_${today}_online.txt
#$HADOOP fs -text ${bucketDataPath}/${begin_early_2_Str}/* | ${FM_HOME}/bin/fm_predict -m ${MODEL_PATH}/${model_name}_${today_early_3}.txt -dim 8 -core 8 -out ${PREDICT_PATH}/${model_name}_${today}_new.txt

$HADOOP fs -text ${bucketDataPath}/20240703/* | ${FM_HOME}/bin/fm_predict -m ${LAST_MODEL_HOME}/model_online.txt -dim 8 -core 8 -out ${PREDICT_PATH}/${model_name}_${today}_online.txt
$HADOOP fs -text ${bucketDataPath}/20240703/* | ${FM_HOME}/bin/fm_predict -m ${MODEL_PATH}/${model_name}_20240703.txt -dim 8 -core 8 -out ${PREDICT_PATH}/${model_name}_${today}_new.txt


online_auc=`cat ${PREDICT_PATH}/${model_name}_${today}_online.txt | /root/sunmingze/AUC/AUC`
if [ $? -ne 0 ]; then
   echo "推荐线上模型AUC计算失败"
#   /root/anaconda3/bin/python ad/ad_monitor_util.py "线上模型AUC计算失败"
   exit 1
fi

new_auc=`${PREDICT_PATH}/${model_name}_${today}_new.txt | /root/sunmingze/AUC/AUC`
if [ $? -ne 0 ]; then
   echo "推荐新模型AUC计算失败"
#   /root/anaconda3/bin/python ad/ad_monitor_util.py "新模型AUC计算失败"
   exit 1
fi


# 1 对比auc数据判断是否更新线上模型
if [ "$online_auc" \< "$new_auc" ]; then
    echo "新模型优于线上模型: 线上模型AUC: ${online_auc}, 新模型AUC: ${new_auc}"
    # todo 模型格式转换

    # todo 模型文件上传OSS

    # todo 本地保存最新的线上使用的模型，用于下一次的AUC验证
#    /root/anaconda3/bin/python ad/ad_monitor_util.py "新模型优于线上模型: 线上模型AUC: ${online_auc}, 新模型AUC: ${new_auc}"
else
    echo "新模型不如线上模型: 线上模型AUC: ${online_auc}, 新模型AUC: ${new_auc}"
#    /root/anaconda3/bin/python ad/ad_monitor_util.py "新模型不如线上模型: 线上模型AUC: ${online_auc}, 新模型AUC: ${new_auc}"
fi