|
@@ -0,0 +1,66 @@
|
|
|
|
+#!/bin/sh
|
|
|
|
+
|
|
|
|
+# 模型训练,预测,计算AUC脚本
|
|
|
|
+
|
|
|
|
+# set -x
|
|
|
|
+
|
|
|
|
+begin_date=$1
|
|
|
|
+end_date=$2
|
|
|
|
+model_name=$3
|
|
|
|
+dim=$4
|
|
|
|
+
|
|
|
|
+PROJECT_HOME=/root/zhaohp/recommend-emr-dataprocess
|
|
|
|
+HADOOP=/opt/apps/HADOOP-COMMON/hadoop-common-current/bin/hadoop
|
|
|
|
+HDFS_TRAIN_DATE_PATH=/dw/recommend/model/33_ad_train_data_v4
|
|
|
|
+MODEL_PATH=${PROJECT_HOME}/model
|
|
|
|
+PREDICT_PATH=${PROJECT_HOME}/predict
|
|
|
|
+
|
|
|
|
+FM_TRAIN=/root/sunmingze/alphaFM/bin/fm_train
|
|
|
|
+FM_PREDICT=/root/sunmingze/alphaFM/bin/fm_predict
|
|
|
|
+
|
|
|
|
+train_date=$begin_date
|
|
|
|
+
|
|
|
|
+# 计算模型的AUC,从训练日期的后一天到参数的end_date
|
|
|
|
+predict_auc() {
|
|
|
|
+ echo -e "\t==================== 开始预测 $train_date 模型 ===================="
|
|
|
|
+
|
|
|
|
+ predict_date=$(date -d "$train_date +1 day" +%Y%m%d)
|
|
|
|
+ predict_end_date=$(date -d "$end_date +1 day" +%Y%m%d)
|
|
|
|
+ while [ "$predict_date" != "$predict_end_date" ]; do
|
|
|
|
+
|
|
|
|
+ $HADOOP fs -text ${HDFS_TRAIN_DATE_PATH}/${predict_date}/* | ${FM_PREDICT} -m ${MODEL_PATH}/${model_name}_${train_date}.txt -dim ${dim} -core 8 -out ${PREDICT_PATH}/${model_name}_${train_date}.txt
|
|
|
|
+ auc=`cat ${PREDICT_PATH}/${model_name}_${train_date}.txt | /root/sunmingze/AUC/AUC`
|
|
|
|
+
|
|
|
|
+ echo "模型训练日期: ${train_date}, 模型预测日期: ${predict_date}, AUC: ${auc}, 模型路径: ${MODEL_PATH}/${model_name}_${train_date}.txt"
|
|
|
|
+
|
|
|
|
+ predict_date=$(date -d "$predict_date +1 day" +%Y%m%d)
|
|
|
|
+
|
|
|
|
+ done
|
|
|
|
+
|
|
|
|
+ echo -e "\n\t==================== 预测 $train_date 模型结束 ===================="
|
|
|
|
+
|
|
|
|
+}
|
|
|
|
+main() {
|
|
|
|
+
|
|
|
|
+ # 增量训练模型
|
|
|
|
+ while [ "$train_date" != "$end_date" ]; do
|
|
|
|
+ echo -e "\n\n\n\n\n\n"
|
|
|
|
+ echo "==================== 开始训练 $train_date 模型 ===================="
|
|
|
|
+
|
|
|
|
+ if [ "$train_date" == "$begin_date" ]; then
|
|
|
|
+ $HADOOP fs -text ${HDFS_TRAIN_DATE_PATH}/${train_date}/* | ${FM_TRAIN} -m ${MODEL_PATH}/${model_name}_${train_date}.txt -dim ${dim} -core 8
|
|
|
|
+ else
|
|
|
|
+ yesterday=$(date -d "$train_date -1 day" +%Y%m%d)
|
|
|
|
+ $HADOOP fs -text ${HDFS_TRAIN_DATE_PATH}/${train_date}/* | ${FM_TRAIN} -m ${MODEL_PATH}/${model_name}_${train_date}.txt -dim ${dim} -core 8 -im ${MODEL_PATH}/${model_name}_${yesterday}.txt
|
|
|
|
+ fi
|
|
|
|
+
|
|
|
|
+ predict_auc
|
|
|
|
+
|
|
|
|
+ train_date=$(date -d "$train_date +1 day" +%Y%m%d)
|
|
|
|
+
|
|
|
|
+ echo "==================== 训练 $train_date 模型结束 ===================="
|
|
|
|
+ done
|
|
|
|
+
|
|
|
|
+}
|
|
|
|
+
|
|
|
|
+main
|