|
@@ -2,7 +2,8 @@
|
|
|
set -ex
|
|
|
|
|
|
# 原始数据table name
|
|
|
-table='alg_recsys_sample_all'
|
|
|
+#table='alg_recsys_sample_all'
|
|
|
+table='alg_recsys_sample_all_test'
|
|
|
# 处理分区配置
|
|
|
beginStr="$(date -d '1 days ago' +%Y%m%d)"
|
|
|
endStr="$(date -d '1 days ago' +%Y%m%d)"
|
|
@@ -36,9 +37,9 @@ echo "----------step2------------开始根据${table}生产原始数据"
|
|
|
/opt/apps/SPARK2/spark-2.4.8-hadoop3.2-1.0.8/bin/spark-class2 org.apache.spark.deploy.SparkSubmit \
|
|
|
--class com.aliyun.odps.spark.examples.makedata_qiao.makedata_13_originData_20240705 \
|
|
|
--master yarn --driver-memory 1G --executor-memory 2G --executor-cores 1 --num-executors 16 \
|
|
|
-./target/spark-examples-1.0.0-SNAPSHOT-shaded.jar \
|
|
|
+../target/spark-examples-1.0.0-SNAPSHOT-shaded.jar \
|
|
|
tablePart:64 repartition:32 \
|
|
|
-beginStr:${beginStr} endStr:${endStr} \
|
|
|
+beginStr:${beginStr}${beginHhStr} endStr:${endStr}${endHhStr} \
|
|
|
savePath:/dw/recommend/model/13_sample_data/ \
|
|
|
table:${table}
|
|
|
if [ $? -ne 0 ]; then
|
|
@@ -53,7 +54,7 @@ fi
|
|
|
/opt/apps/SPARK2/spark-2.4.8-hadoop3.2-1.0.8/bin/spark-class2 org.apache.spark.deploy.SparkSubmit \
|
|
|
--class com.aliyun.odps.spark.examples.makedata_qiao.makedata_14_valueData_20240705 \
|
|
|
--master yarn --driver-memory 1G --executor-memory 3G --executor-cores 1 --num-executors 32 \
|
|
|
-./target/spark-examples-1.0.0-SNAPSHOT-shaded.jar \
|
|
|
+../target/spark-examples-1.0.0-SNAPSHOT-shaded.jar \
|
|
|
readPath:/dw/recommend/model/13_sample_data/ \
|
|
|
savePath:/dw/recommend/model/14_feature_data/ \
|
|
|
beginStr:${beginStr} endStr:${endStr} repartition:1000
|
|
@@ -69,7 +70,7 @@ echo "----------step3------------根据特征分桶生产重打分特征数据"
|
|
|
/opt/apps/SPARK2/spark-2.4.8-hadoop3.2-1.0.8/bin/spark-class2 org.apache.spark.deploy.SparkSubmit \
|
|
|
--class com.aliyun.odps.spark.examples.makedata_qiao.makedata_16_bucketData_20240705 \
|
|
|
--master yarn --driver-memory 2G --executor-memory 4G --executor-cores 1 --num-executors 16 \
|
|
|
-./target/spark-examples-1.0.0-SNAPSHOT-shaded.jar \
|
|
|
+../target/spark-examples-1.0.0-SNAPSHOT-shaded.jar \
|
|
|
beginStr:${beginStr} endStr:${endStr} repartition:1000
|
|
|
if [ $? -ne 0 ]; then
|
|
|
echo "Spark特征分桶处理任务执行失败"
|