|
@@ -108,6 +108,7 @@ make_bucket_feature_to_hive() {
|
|
|
|
|
|
make_bucket_feature_from_origin_to_hive() {
|
|
|
local step_start_time=$(date +%s)
|
|
|
+ neg_sample_rate=${NEG_SAMPLE_RATE:-0.04}
|
|
|
|
|
|
/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_ad.v20240718.makedata_ad_33_bucketDataFromOriginToHive_20250228 \
|
|
@@ -117,7 +118,7 @@ make_bucket_feature_from_origin_to_hive() {
|
|
|
filterNames:_4h_,_5h_,adid_,targeting_conversion_ \
|
|
|
outputTable:${outputTable} \
|
|
|
inputTable:alg_recsys_ad_sample_all \
|
|
|
- negSampleRate:0.04
|
|
|
+ negSampleRate:${neg_sample_rate}
|
|
|
|
|
|
local return_code=$?
|
|
|
check_run_status ${return_code} ${step_start_time} "spark特征分桶任务"
|