nohup /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_dssm.makedata_i2i_01_originData_20241127 \
--master yarn --driver-memory 2G --executor-memory 2G --executor-cores 1 --num-executors 16 \
./target/spark-examples-1.0.0-SNAPSHOT-shaded.jar \
beginStr:2024113000 endStr:2024113023 negCnt:20 \
tablePart:64 savePath:/dw/recommend/model/51_dssm_i2i_sample/ > p51_2.log 2>&1 &

nohup /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_dssm.makedata_i2i_02_joinFeatureData_20241128 \
--master yarn --driver-memory 2G --executor-memory 2G --executor-cores 1 --num-executors 32 \
./target/spark-examples-1.0.0-SNAPSHOT-shaded.jar \
beginStr:2024113000 endStr:2024113023 \
tablePart:64 \
readPath:/dw/recommend/model/51_dssm_i2i_sample/ \
savePath:/dw/recommend/model/52_dssm_i2i_joinfeature/ > p52_2.log 2>&1 &

nohup /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_dssm.makedata_i2i_03_onehotFile_20241128 \
--master yarn --driver-memory 16G --executor-memory 1G --executor-cores 1 --num-executors 32 \
./target/spark-examples-1.0.0-SNAPSHOT-shaded.jar \
dt:20241201 \
tablePart:64 \
readPath:/dw/recommend/model/53_dssm_i2i_onehot/after_20241201_file \
savePath:/dw/recommend/model/53_dssm_i2i_onehot/after_20241201_file > p53.log 2>&1 &




数据量:3544265打印各个特征多少枚举值：vid       3534920
video_style     7382
captions_color  782
valid_time      754
audience_age_group      80
cate2   67
audience_value_type     65
font_size       49
audience_gender 47
cover_persons_num       45
cate1   42
sentiment_tendency      11
video_type      8
background_music_type   6
captions        3
has_end_credit_guide    2
timeliness      2

nohup /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_dssm.makedata_i2i_04_bucketFile_20241128 \
--master yarn --driver-memory 16G --executor-memory 2G --executor-cores 1 --num-executors 32 \
./target/spark-examples-1.0.0-SNAPSHOT-shaded.jar \
readPath:/dw/recommend/model/52_dssm_i2i_joinfeature/20241126* \
savePath:/dw/recommend/model/54_dssm_i2i_bucketfile/ \
fileName:47_rate_v2  bucketNum:100 > p54.log 2>&1 &

nohup /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_dssm.makedata_i2i_05_trainData_20241129 \
--master yarn --driver-memory 2G --executor-memory 4G --executor-cores 1 --num-executors 32 \
./target/spark-examples-1.0.0-SNAPSHOT-shaded.jar \
beginStr:2024113000 endStr:2024113023 \
readPath:/dw/recommend/model/52_dssm_i2i_joinfeature/ \
savePath:/dw/recommend/model/55_dssm_i2i_traindata/ \
onehotPath:/dw/recommend/model/53_dssm_i2i_onehot/after_20241201_file \
bucketFile:20241128_recsys_i2i_bucket_47_v2.txt > p55_2.log 2>&1 &

nohup /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_dssm.makedata_i2i_06_itemPred_20241206 \
--master yarn --driver-memory 2G --executor-memory 2G --executor-cores 1 --num-executors 16 \
./target/spark-examples-1.0.0-SNAPSHOT-shaded.jar \
onehotPath:/dw/recommend/model/53_dssm_i2i_onehot/after_20241201_file \
bucketFile:20241128_recsys_i2i_bucket_47_v2.txt repartition:100 \
dt:20241206 \
savePath:/dw/recommend/model/56_dssm_i2i_itempredData/ \
> p56.log 2>&1 &