feat:修改工具类

src/main/scala/com/aliyun/odps/spark/examples/makedata_ad/makedata_ad_31_originData_20240718.scala

@@ -3,8 +3,7 @@ package com.aliyun.odps.spark.examples.makedata_ad
 import com.alibaba.fastjson.{JSON, JSONObject}
 import com.aliyun.odps.TableSchema
 import com.aliyun.odps.data.Record
-import com.aliyun.odps.spark.common.AdUtil
-import com.aliyun.odps.spark.examples.myUtils.{MyDateUtils, MyHdfsUtils, ParamUtils, env}
+import com.aliyun.odps.spark.examples.myUtils.{DataTimeUtil, MyDateUtils, MyHdfsUtils, ParamUtils, env}
 import examples.extractor.RankExtractorFeature_20240530
 import org.apache.hadoop.io.compress.GzipCodec
 import org.apache.spark.sql.SparkSession
@@ -93,10 +92,10 @@ object makedata_ad_31_originData_20240718 {
               featureMap.put("targeting_conversion_" + b1.getString("targeting_conversion"), idDefaultValue)
             }
 
-            val hour = AdUtil.getHourByTimestamp(ts)
+            val hour = DataTimeUtil.getHourByTimestamp(ts)
             featureMap.put("hour_" + hour, 0.1)
 
-            val dayOfWeek = AdUtil.getDayOrWeekByTimestamp(ts)
+            val dayOfWeek = DataTimeUtil.getDayOrWeekByTimestamp(ts)
             featureMap.put("dayOfWeek_" + dayOfWeek, 0.1);
 
             if (b1.containsKey("cpa")) {

src/main/scala/com/aliyun/odps/spark/examples/myUtils/DataTimeUtil.java

@@ -0,0 +1,21 @@
+package com.aliyun.odps.spark.examples.myUtils;
+
+import java.time.Instant;
+import java.time.LocalDateTime;
+import java.time.ZoneId;
+
+public class DataTimeUtil {
+
+    public static int getHourByTimestamp(long timestamp) {
+        return LocalDateTime
+                .ofInstant(Instant.ofEpochSecond(timestamp), ZoneId.systemDefault())
+                .getHour();
+    }
+
+    public static int getDayOrWeekByTimestamp(long timestamp) {
+        return LocalDateTime
+                .ofInstant(Instant.ofEpochSecond(timestamp), ZoneId.systemDefault())
+                .getDayOfWeek()
+                .getValue();
+    }
+}

src/main/scala/com/aliyun/odps/spark/zhp/makedata_ad/makedata_ad_31_originDataCheck_20240620.scala

@@ -3,7 +3,7 @@ package com.aliyun.odps.spark.zhp.makedata_ad
 import com.alibaba.fastjson.{JSON, JSONObject}
 import com.aliyun.odps.TableSchema
 import com.aliyun.odps.data.Record
-import com.aliyun.odps.spark.common.AdUtil
+import com.aliyun.odps.spark.examples.myUtils.DataTimeUtil
 import examples.extractor.RankExtractorFeature_20240530
 import org.xm.Similarity
 
@@ -21,7 +21,7 @@ object makedata_ad_31_originDataCheck_20240620 {
 
     val idDefaultValue = 0.01;
 
-    List(AdUtil.keyReplace(metaFeatureJson)).map(record => {
+    List(DataTimeUtil.keyReplace(metaFeatureJson)).map(record => {
       val ts = record.getString("ts").toInt
       val cid = record.getString("cid")
 

src/main/scala/com/aliyun/odps/spark/common/AdUtil.java → src/main/scala/com/aliyun/odps/spark/zhp/utils/AdUtil.java

@@ -1,10 +1,7 @@
-package com.aliyun.odps.spark.common;
+package com.aliyun.odps.spark.zhp.utils;
 
 import com.alibaba.fastjson.JSONObject;
 
-import java.time.Instant;
-import java.time.LocalDateTime;
-import java.time.ZoneId;
 import java.util.HashMap;
 import java.util.Map;
 
@@ -40,17 +37,4 @@ public class AdUtil {
 
         return newJson;
     }
-
-    public static int getHourByTimestamp(long timestamp) {
-        return LocalDateTime
-                .ofInstant(Instant.ofEpochSecond(timestamp), ZoneId.systemDefault())
-                .getHour();
-    }
-
-    public static int getDayOrWeekByTimestamp(long timestamp) {
-        return LocalDateTime
-                .ofInstant(Instant.ofEpochSecond(timestamp), ZoneId.systemDefault())
-                .getDayOfWeek()
-                .getValue();
-    }
 }

src/main/scala/com/aliyun/odps/spark/zhp/临时记录的脚本-广告

@@ -2,14 +2,14 @@
 
 // 模型特征生产
 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_ad.makedata_ad_31_originData_20240620 \
+--class com.aliyun.odps.spark.examples.makedata_ad.makedata_ad_31_originData_20240718 \
 --master yarn --driver-memory 1G --executor-memory 2G --executor-cores 1 --num-executors 16 \
 ./target/spark-examples-1.0.0-SNAPSHOT-shaded.jar \
 tablePart:64 repartition:32 \
-beginStr:2024062008 endStr:2024062223 \
-savePath:/dw/recommend/model/31_ad_sample_data_fix/ \
+beginStr:2024071200 endStr:2024071209 \
+savePath:/dw/recommend/model/33_ad_train_data_v4/ \
 table:alg_recsys_ad_sample_all \
-> p31_2024062008.log 2>&1 &
+> logs/p31_2024062008.log 2>&1 &