#!/bin/sh
set -x

feature_file=""
year=""
if(($#==2))
then
    feature_file=$1
    year=$2
else
    exit -1
fi

# env
export HADOOP_CONF_DIR=/etc/taihao-apps/hadoop-conf
export JAVA_HOME=/usr/lib/jvm/java-1.8.0

# params
base_data_path=/dw/recommend/model/user_profile/gender/sample/train
model_path=/dw/recommend/model/user_profile/gender/model/model_xgb
minCnt=10
save_path=/dw/recommend/model/user_profile/gender/eval
repartition=4

test_data_path=""
suffix_array=(i m)
for suffix in "${suffix_array[@]}"
do
    one_day_data_path="${base_data_path}/${year}_$suffix"
    if [[ -z $test_data_path ]]
    then
        test_data_path=$one_day_data_path
    else
        test_data_path="$test_data_path,$one_day_data_path"
    fi
done

echo `date` "predict gender sample"
/opt/apps/SPARK3/spark-3.3.1-hadoop3.2-1.0.5/bin/spark-class org.apache.spark.deploy.SparkSubmit \
--class com.tzld.piaoquan.recommend.model.pred_profile_gender_xgb_20251114 \
--master yarn --driver-memory 2G --executor-memory 4G --executor-cores 1 --num-executors 8 \
--conf spark.yarn.executor.memoryoverhead=1024 \
--conf spark.shuffle.service.enabled=true \
--conf spark.shuffle.service.port=7337 \
--conf spark.shuffle.consolidateFiles=true \
--conf spark.shuffle.manager=sort \
--conf spark.storage.memoryFraction=0.4 \
--conf spark.shuffle.memoryFraction=0.5 \
--conf spark.default.parallelism=200 \
--conf spark.debug.maxToStringFields=100 \
--files ${feature_file} \
/mnt/disk1/jch/recommend-model/recommend-model-produce/target/recommend-model-produce-jar-with-dependencies.jar \
modelPath:${model_path} \
testPath:${test_data_path} \
featureFile:${feature_file} \
minCnt:${minCnt} \
savePath:${save_path} \
repartition:${repartition} \