Merge branch 'feature/zhangbo_makedata_v2' into feature_zhaohaipeng

src/main/scala/com/aliyun/odps/spark/examples/makedata_ad/makedata_ad_31_originData_20240620.scala

@@ -32,7 +32,8 @@ object makedata_ad_31_originData_20240620 {
     val project = param.getOrElse("project", "loghubods")
     val table = param.getOrElse("table", "alg_recsys_ad_sample_all")
     val repartition = param.getOrElse("repartition", "100").toInt
-
+    val filterHours = param.getOrElse("filterHours", "00,01,02,03,04,05,06,07").split(",").toSet
+    val idDefaultValue = param.getOrElse("idDefaultValue", "1.0").toDouble
     // 2 读取odps+表信息
     val odpsOps = env.getODPS(sc)
 
@@ -42,323 +43,335 @@ object makedata_ad_31_originData_20240620 {
       val dt = dt_hh.substring(0, 8)
       val hh = dt_hh.substring(8, 10)
       val partition = s"dt=$dt,hh=$hh"
-      println("开始执行partiton:" + partition)
-      val odpsData = odpsOps.readTable(project = project,
-        table = table,
-        partition = partition,
-        transfer = func,
-        numPartition = tablePart)
-        .map(record => {
-
-
-          val ts = record.getString("ts").toInt
-          val cid = record.getString("cid")
-
-
-          val featureMap = new JSONObject()
-
-          val b1: JSONObject = if (record.isNull("b1_feature")) new JSONObject() else
-            JSON.parseObject(record.getString("b1_feature"))
-          val b2: JSONObject = if (record.isNull("b2_feature")) new JSONObject() else
-            JSON.parseObject(record.getString("b2_feature"))
-          val b3: JSONObject = if (record.isNull("b3_feature")) new JSONObject() else
-            JSON.parseObject(record.getString("b3_feature"))
-          val b4: JSONObject = if (record.isNull("b4_feature")) new JSONObject() else
-            JSON.parseObject(record.getString("b4_feature"))
-          val b5: JSONObject = if (record.isNull("b5_feature")) new JSONObject() else
-            JSON.parseObject(record.getString("b5_feature"))
-          val b6: JSONObject = if (record.isNull("b6_feature")) new JSONObject() else
-            JSON.parseObject(record.getString("b6_feature"))
-          val b7: JSONObject = if (record.isNull("b7_feature")) new JSONObject() else
-            JSON.parseObject(record.getString("b7_feature"))
-          val b8: JSONObject = if (record.isNull("b8_feature")) new JSONObject() else
-            JSON.parseObject(record.getString("b8_feature"))
-          val b9: JSONObject = if (record.isNull("b9_feature")) new JSONObject() else
-            JSON.parseObject(record.getString("b9_feature"))
-
-
-          featureMap.put("cid_" + cid, 1.0)
-          if (b1.containsKey("adid") && b1.getString("adid").nonEmpty) {
-            featureMap.put("adid_" + b1.getString("adid"), 1.0)
-          }
-          if (b1.containsKey("adverid") && b1.getString("adverid").nonEmpty) {
-            featureMap.put("adverid_" + b1.getString("adverid"), 1.0)
-          }
-          if (b1.containsKey("targeting_conversion") && b1.getString("targeting_conversion").nonEmpty) {
-            featureMap.put("targeting_conversion_" + b1.getString("targeting_conversion"), 1.0)
-          }
-
-
-          if (b1.containsKey("cpa")) {
-            featureMap.put("cpa", b1.getString("cpa").toDouble)
-          }
-
-          for ((bn, prefix1) <- List(
-            (b2, "b2"), (b3, "b3"),(b4, "b4"),(b5, "b5"),(b8, "b8")
-          )){
-            for (prefix2 <- List(
-              "3h", "6h", "12h", "1d", "3d", "7d"
-            )){
-              val view = if (bn.isEmpty) 0D else bn.getIntValue("ad_view_" + prefix2).toDouble
-              val click = if (bn.isEmpty) 0D else bn.getIntValue("ad_click_" + prefix2).toDouble
-              val conver = if (bn.isEmpty) 0D else bn.getIntValue("ad_conversion_" + prefix2).toDouble
-              val income = if (bn.isEmpty) 0D else bn.getIntValue("ad_income_" + prefix2).toDouble
-              val f1 = RankExtractorFeature_20240530.calDiv(click, view)
-              val f2 = RankExtractorFeature_20240530.calDiv(conver, view)
-              val f3 = RankExtractorFeature_20240530.calDiv(conver, click)
-              val f4 = conver
-              val f5 = RankExtractorFeature_20240530.calDiv(income*1000, view)
-              featureMap.put(prefix1 + "_" + prefix2 + "_" + "ctr", f1)
-              featureMap.put(prefix1 + "_" + prefix2 + "_" + "ctcvr", f2)
-              featureMap.put(prefix1 + "_" + prefix2 + "_" + "cvr", f3)
-              featureMap.put(prefix1 + "_" + prefix2 + "_" + "conver", f4)
-              featureMap.put(prefix1 + "_" + prefix2 + "_" + "ecpm", f5)
+      if (filterHours.nonEmpty && filterHours.contains(hh)){
+        println("不执行partiton:" + partition)
+      }else{
+        println("开始执行partiton:" + partition)
+        val odpsData = odpsOps.readTable(project = project,
+            table = table,
+            partition = partition,
+            transfer = func,
+            numPartition = tablePart)
+          .map(record => {
+
+
+            val ts = record.getString("ts").toInt
+            val cid = record.getString("cid")
+
+
+            val featureMap = new JSONObject()
+
+            val b1: JSONObject = if (record.isNull("b1_feature")) new JSONObject() else
+              JSON.parseObject(record.getString("b1_feature"))
+            val b2: JSONObject = if (record.isNull("b2_feature")) new JSONObject() else
+              JSON.parseObject(record.getString("b2_feature"))
+            val b3: JSONObject = if (record.isNull("b3_feature")) new JSONObject() else
+              JSON.parseObject(record.getString("b3_feature"))
+            val b4: JSONObject = if (record.isNull("b4_feature")) new JSONObject() else
+              JSON.parseObject(record.getString("b4_feature"))
+            val b5: JSONObject = if (record.isNull("b5_feature")) new JSONObject() else
+              JSON.parseObject(record.getString("b5_feature"))
+            val b6: JSONObject = if (record.isNull("b6_feature")) new JSONObject() else
+              JSON.parseObject(record.getString("b6_feature"))
+            val b7: JSONObject = if (record.isNull("b7_feature")) new JSONObject() else
+              JSON.parseObject(record.getString("b7_feature"))
+            val b8: JSONObject = if (record.isNull("b8_feature")) new JSONObject() else
+              JSON.parseObject(record.getString("b8_feature"))
+            val b9: JSONObject = if (record.isNull("b9_feature")) new JSONObject() else
+              JSON.parseObject(record.getString("b9_feature"))
+
+
+            featureMap.put("cid_" + cid, idDefaultValue)
+            if (b1.containsKey("adid") && b1.getString("adid").nonEmpty) {
+              featureMap.put("adid_" + b1.getString("adid"), idDefaultValue)
+            }
+            if (b1.containsKey("adverid") && b1.getString("adverid").nonEmpty) {
+              featureMap.put("adverid_" + b1.getString("adverid"), idDefaultValue)
+            }
+            if (b1.containsKey("targeting_conversion") && b1.getString("targeting_conversion").nonEmpty) {
+              featureMap.put("targeting_conversion_" + b1.getString("targeting_conversion"), idDefaultValue)
             }
-          }
 
-          for ((bn, prefix1) <- List(
-            (b6, "b6"), (b7, "b7")
-          )) {
-            for (prefix2 <- List(
-              "7d", "14d"
-            )) {
-              val view = if (bn.isEmpty) 0D else bn.getIntValue("ad_view_" + prefix2).toDouble
-              val click = if (bn.isEmpty) 0D else bn.getIntValue("ad_click_" + prefix2).toDouble
-              val conver = if (bn.isEmpty) 0D else bn.getIntValue("ad_conversion_" + prefix2).toDouble
-              val income = if (bn.isEmpty) 0D else bn.getIntValue("ad_income_" + prefix2).toDouble
-              val f1 = RankExtractorFeature_20240530.calDiv(click, view)
-              val f2 = RankExtractorFeature_20240530.calDiv(conver, view)
-              val f3 = RankExtractorFeature_20240530.calDiv(conver, click)
-              val f4 = conver
-              val f5 = RankExtractorFeature_20240530.calDiv(income * 1000, view)
-              featureMap.put(prefix1 + "_" + prefix2 + "_" + "ctr", f1)
-              featureMap.put(prefix1 + "_" + prefix2 + "_" + "ctcvr", f2)
-              featureMap.put(prefix1 + "_" + prefix2 + "_" + "cvr", f3)
-              featureMap.put(prefix1 + "_" + prefix2 + "_" + "conver", f4)
-              featureMap.put(prefix1 + "_" + prefix2 + "_" + "ecpm", f5)
+
+            if (b1.containsKey("cpa")) {
+              featureMap.put("cpa", b1.getString("cpa").toDouble)
             }
-          }
-
-          val c1: JSONObject = if (record.isNull("c1_feature")) new JSONObject() else
-            JSON.parseObject(record.getString("c1_feature"))
-
-          val midActionList = if (c1.containsKey("action") && c1.getString("action").nonEmpty){
-            c1.getString("action").split(",").map(r=>{
-              val rList = r.split(":")
-              (rList(0), (rList(1).toInt, rList(2).toInt, rList(3).toInt, rList(4).toInt, rList(5)))
-            }).sortBy(-_._2._1).toList
-          }else {
-            new ArrayBuffer[(String, (Int, Int, Int, Int, String))]().toList
-          }
-          // u特征
-          val viewAll = midActionList.size.toDouble
-          val clickAll = midActionList.map(_._2._2).sum.toDouble
-          val converAll = midActionList.map(_._2._3).sum.toDouble
-          val incomeAll = midActionList.map(_._2._4).sum.toDouble
-          featureMap.put("viewAll", viewAll)
-          featureMap.put("clickAll", clickAll)
-          featureMap.put("converAll", converAll)
-          featureMap.put("incomeAll", incomeAll)
-          featureMap.put("ctr_all", RankExtractorFeature_20240530.calDiv(clickAll, viewAll))
-          featureMap.put("ctcvr_all", RankExtractorFeature_20240530.calDiv(converAll, viewAll))
-          featureMap.put("cvr_all", RankExtractorFeature_20240530.calDiv(clickAll, converAll))
-          featureMap.put("ecpm_all", RankExtractorFeature_20240530.calDiv(incomeAll * 1000, viewAll))
-
-          // ui特征
-          val midTimeDiff = scala.collection.mutable.Map[String, Double]()
-          midActionList.foreach{
-            case (cid, (ts_history, click, conver, income, title)) =>
-              if (!midTimeDiff.contains("timediff_view_" + cid)){
-                midTimeDiff.put("timediff_view_" + cid, 1.0 / ((ts - ts_history).toDouble/3600.0/24.0))
-              }
-              if (!midTimeDiff.contains("timediff_click_" + cid) && click > 0) {
-                midTimeDiff.put("timediff_click_" + cid, 1.0 / ((ts - ts_history).toDouble / 3600.0 / 24.0))
+
+            for ((bn, prefix1) <- List(
+              (b2, "b2"), (b3, "b3"), (b4, "b4"), (b5, "b5"), (b8, "b8")
+            )) {
+              for (prefix2 <- List(
+                "3h", "6h", "12h", "1d", "3d", "7d"
+              )) {
+                val view = if (bn.isEmpty) 0D else bn.getIntValue("ad_view_" + prefix2).toDouble
+                val click = if (bn.isEmpty) 0D else bn.getIntValue("ad_click_" + prefix2).toDouble
+                val conver = if (bn.isEmpty) 0D else bn.getIntValue("ad_conversion_" + prefix2).toDouble
+                val income = if (bn.isEmpty) 0D else bn.getIntValue("ad_income_" + prefix2).toDouble
+                val f1 = RankExtractorFeature_20240530.calDiv(click, view)
+                val f2 = RankExtractorFeature_20240530.calDiv(conver, view)
+                val f3 = RankExtractorFeature_20240530.calDiv(conver, click)
+                val f4 = conver
+                val f5 = RankExtractorFeature_20240530.calDiv(income * 1000, view)
+                featureMap.put(prefix1 + "_" + prefix2 + "_" + "ctr", f1)
+                featureMap.put(prefix1 + "_" + prefix2 + "_" + "ctcvr", f2)
+                featureMap.put(prefix1 + "_" + prefix2 + "_" + "cvr", f3)
+                featureMap.put(prefix1 + "_" + prefix2 + "_" + "conver", f4)
+                featureMap.put(prefix1 + "_" + prefix2 + "_" + "ecpm", f5)
+
+                featureMap.put(prefix1 + "_" + prefix2 + "_" + "click", click)
+                featureMap.put(prefix1 + "_" + prefix2 + "_" + "conver*log(view)", conver * RankExtractorFeature_20240530.calLog(view))
+                featureMap.put(prefix1 + "_" + prefix2 + "_" + "conver*ctcvr", conver * f2)
               }
-              if (!midTimeDiff.contains("timediff_conver_" + cid) && conver > 0) {
-                midTimeDiff.put("timediff_conver_" + cid, 1.0 / ((ts - ts_history).toDouble / 3600.0 / 24.0))
+            }
+
+            for ((bn, prefix1) <- List(
+              (b6, "b6"), (b7, "b7")
+            )) {
+              for (prefix2 <- List(
+                "7d", "14d"
+              )) {
+                val view = if (bn.isEmpty) 0D else bn.getIntValue("ad_view_" + prefix2).toDouble
+                val click = if (bn.isEmpty) 0D else bn.getIntValue("ad_click_" + prefix2).toDouble
+                val conver = if (bn.isEmpty) 0D else bn.getIntValue("ad_conversion_" + prefix2).toDouble
+                val income = if (bn.isEmpty) 0D else bn.getIntValue("ad_income_" + prefix2).toDouble
+                val f1 = RankExtractorFeature_20240530.calDiv(click, view)
+                val f2 = RankExtractorFeature_20240530.calDiv(conver, view)
+                val f3 = RankExtractorFeature_20240530.calDiv(conver, click)
+                val f4 = conver
+                val f5 = RankExtractorFeature_20240530.calDiv(income * 1000, view)
+                featureMap.put(prefix1 + "_" + prefix2 + "_" + "ctr", f1)
+                featureMap.put(prefix1 + "_" + prefix2 + "_" + "ctcvr", f2)
+                featureMap.put(prefix1 + "_" + prefix2 + "_" + "cvr", f3)
+                featureMap.put(prefix1 + "_" + prefix2 + "_" + "conver", f4)
+                featureMap.put(prefix1 + "_" + prefix2 + "_" + "ecpm", f5)
+
+                featureMap.put(prefix1 + "_" + prefix2 + "_" + "click", click)
+                featureMap.put(prefix1 + "_" + prefix2 + "_" + "conver*log(view)", conver * RankExtractorFeature_20240530.calLog(view))
+                featureMap.put(prefix1 + "_" + prefix2 + "_" + "conver*ctcvr", conver * f2)
               }
-          }
-
-          val midActionStatic = scala.collection.mutable.Map[String, Double]()
-          midActionList.foreach {
-            case (cid, (ts_history, click, conver, income, title)) =>
-              midActionStatic.put("actionstatic_view_" + cid, 1.0 + midActionStatic.getOrDefault("actionstatic_view_" + cid, 0.0))
-              midActionStatic.put("actionstatic_click_" + cid, click + midActionStatic.getOrDefault("actionstatic_click_" + cid, 0.0))
-              midActionStatic.put("actionstatic_conver_" + cid, conver + midActionStatic.getOrDefault("actionstatic_conver_" + cid, 0.0))
-              midActionStatic.put("actionstatic_income_" + cid, income + midActionStatic.getOrDefault("actionstatic_income_" + cid, 0.0))
-          }
-
-          if (midTimeDiff.contains("timediff_view_" + cid)){
-            featureMap.put("timediff_view", midTimeDiff.getOrDefault("timediff_view_" + cid, 0.0))
-          }
-          if (midTimeDiff.contains("timediff_click_" + cid)) {
-            featureMap.put("timediff_click", midTimeDiff.getOrDefault("timediff_click_" + cid, 0.0))
-          }
-          if (midTimeDiff.contains("timediff_conver_" + cid)) {
-            featureMap.put("timediff_conver", midTimeDiff.getOrDefault("timediff_conver_" + cid, 0.0))
-          }
-          if (midActionStatic.contains("actionstatic_view_" + cid)) {
-            featureMap.put("actionstatic_view", midActionStatic.getOrDefault("actionstatic_view_" + cid, 0.0))
-          }
-          if (midActionStatic.contains("actionstatic_click_" + cid)) {
-            featureMap.put("actionstatic_click", midActionStatic.getOrDefault("actionstatic_click_" + cid, 0.0))
-          }
-          if (midActionStatic.contains("actionstatic_conver_" + cid)) {
-            featureMap.put("actionstatic_conver", midActionStatic.getOrDefault("actionstatic_conver_" + cid, 0.0))
-          }
-          if (midActionStatic.contains("actionstatic_income_" + cid)) {
-            featureMap.put("actionstatic_income", midActionStatic.getOrDefault("actionstatic_income_" + cid, 0.0))
-          }
-          if (midActionStatic.contains("actionstatic_view_" + cid) && midActionStatic.contains("actionstatic_click_" + cid)) {
-            featureMap.put("actionstatic_ctr", RankExtractorFeature_20240530.calDiv(
-              midActionStatic.getOrDefault("actionstatic_click_" + cid, 0.0),
-              midActionStatic.getOrDefault("actionstatic_view_" + cid, 0.0)
-            ))
-          }
-          if (midActionStatic.contains("actionstatic_view_" + cid) && midActionStatic.contains("actionstatic_conver_" + cid)) {
-            featureMap.put("actionstatic_ctcvr", RankExtractorFeature_20240530.calDiv(
-              midActionStatic.getOrDefault("actionstatic_conver_" + cid, 0.0),
-              midActionStatic.getOrDefault("actionstatic_view_" + cid, 0.0)
-            ))
-          }
-          if (midActionStatic.contains("actionstatic_conver_" + cid) && midActionStatic.contains("actionstatic_click_" + cid)) {
-            featureMap.put("actionstatic_cvr", RankExtractorFeature_20240530.calDiv(
-              midActionStatic.getOrDefault("actionstatic_click_" + cid, 0.0),
-              midActionStatic.getOrDefault("actionstatic_conver_" + cid, 0.0)
-            ))
-          }
-
-          val e1: JSONObject = if (record.isNull("e1_feature")) new JSONObject() else
-            JSON.parseObject(record.getString("e1_feature"))
-          val e2: JSONObject = if (record.isNull("e2_feature")) new JSONObject() else
-            JSON.parseObject(record.getString("e2_feature"))
-          val title = b1.getOrDefault("cidtitle", "").toString
-          if (title.nonEmpty){
-            for ((en, prefix1) <- List((e1, "e1"), (e2, "e2"))){
-              for (prefix2 <- List("tags_3d", "tags_7d", "tags_14d")){
-                if (en.nonEmpty && en.containsKey(prefix2) && en.getString(prefix2).nonEmpty) {
-                  val (f1, f2, f3, f4) = funcC34567ForTags(en.getString(prefix2), title)
-                  featureMap.put(prefix1 + "_" + prefix2 + "_matchnum", f1)
-                  featureMap.put(prefix1 + "_" + prefix2 + "_maxscore", f3)
-                  featureMap.put(prefix1 + "_" + prefix2 + "_avgscore", f4)
+            }
+
+            val c1: JSONObject = if (record.isNull("c1_feature")) new JSONObject() else
+              JSON.parseObject(record.getString("c1_feature"))
 
+            val midActionList = if (c1.containsKey("action") && c1.getString("action").nonEmpty) {
+              c1.getString("action").split(",").map(r => {
+                val rList = r.split(":")
+                (rList(0), (rList(1).toInt, rList(2).toInt, rList(3).toInt, rList(4).toInt, rList(5)))
+              }).sortBy(-_._2._1).toList
+            } else {
+              new ArrayBuffer[(String, (Int, Int, Int, Int, String))]().toList
+            }
+            // u特征
+            val viewAll = midActionList.size.toDouble
+            val clickAll = midActionList.map(_._2._2).sum.toDouble
+            val converAll = midActionList.map(_._2._3).sum.toDouble
+            val incomeAll = midActionList.map(_._2._4).sum.toDouble
+            featureMap.put("viewAll", viewAll)
+            featureMap.put("clickAll", clickAll)
+            featureMap.put("converAll", converAll)
+            featureMap.put("incomeAll", incomeAll)
+            featureMap.put("ctr_all", RankExtractorFeature_20240530.calDiv(clickAll, viewAll))
+            featureMap.put("ctcvr_all", RankExtractorFeature_20240530.calDiv(converAll, viewAll))
+            featureMap.put("cvr_all", RankExtractorFeature_20240530.calDiv(clickAll, converAll))
+            featureMap.put("ecpm_all", RankExtractorFeature_20240530.calDiv(incomeAll * 1000, viewAll))
+
+            // ui特征
+            val midTimeDiff = scala.collection.mutable.Map[String, Double]()
+            midActionList.foreach {
+              case (cid, (ts_history, click, conver, income, title)) =>
+                if (!midTimeDiff.contains("timediff_view_" + cid)) {
+                  midTimeDiff.put("timediff_view_" + cid, 1.0 / ((ts - ts_history).toDouble / 3600.0 / 24.0))
+                }
+                if (!midTimeDiff.contains("timediff_click_" + cid) && click > 0) {
+                  midTimeDiff.put("timediff_click_" + cid, 1.0 / ((ts - ts_history).toDouble / 3600.0 / 24.0))
+                }
+                if (!midTimeDiff.contains("timediff_conver_" + cid) && conver > 0) {
+                  midTimeDiff.put("timediff_conver_" + cid, 1.0 / ((ts - ts_history).toDouble / 3600.0 / 24.0))
+                }
+            }
+
+            val midActionStatic = scala.collection.mutable.Map[String, Double]()
+            midActionList.foreach {
+              case (cid, (ts_history, click, conver, income, title)) =>
+                midActionStatic.put("actionstatic_view_" + cid, 1.0 + midActionStatic.getOrDefault("actionstatic_view_" + cid, 0.0))
+                midActionStatic.put("actionstatic_click_" + cid, click + midActionStatic.getOrDefault("actionstatic_click_" + cid, 0.0))
+                midActionStatic.put("actionstatic_conver_" + cid, conver + midActionStatic.getOrDefault("actionstatic_conver_" + cid, 0.0))
+                midActionStatic.put("actionstatic_income_" + cid, income + midActionStatic.getOrDefault("actionstatic_income_" + cid, 0.0))
+            }
+
+            if (midTimeDiff.contains("timediff_view_" + cid)) {
+              featureMap.put("timediff_view", midTimeDiff.getOrDefault("timediff_view_" + cid, 0.0))
+            }
+            if (midTimeDiff.contains("timediff_click_" + cid)) {
+              featureMap.put("timediff_click", midTimeDiff.getOrDefault("timediff_click_" + cid, 0.0))
+            }
+            if (midTimeDiff.contains("timediff_conver_" + cid)) {
+              featureMap.put("timediff_conver", midTimeDiff.getOrDefault("timediff_conver_" + cid, 0.0))
+            }
+            if (midActionStatic.contains("actionstatic_view_" + cid)) {
+              featureMap.put("actionstatic_view", midActionStatic.getOrDefault("actionstatic_view_" + cid, 0.0))
+            }
+            if (midActionStatic.contains("actionstatic_click_" + cid)) {
+              featureMap.put("actionstatic_click", midActionStatic.getOrDefault("actionstatic_click_" + cid, 0.0))
+            }
+            if (midActionStatic.contains("actionstatic_conver_" + cid)) {
+              featureMap.put("actionstatic_conver", midActionStatic.getOrDefault("actionstatic_conver_" + cid, 0.0))
+            }
+            if (midActionStatic.contains("actionstatic_income_" + cid)) {
+              featureMap.put("actionstatic_income", midActionStatic.getOrDefault("actionstatic_income_" + cid, 0.0))
+            }
+            if (midActionStatic.contains("actionstatic_view_" + cid) && midActionStatic.contains("actionstatic_click_" + cid)) {
+              featureMap.put("actionstatic_ctr", RankExtractorFeature_20240530.calDiv(
+                midActionStatic.getOrDefault("actionstatic_click_" + cid, 0.0),
+                midActionStatic.getOrDefault("actionstatic_view_" + cid, 0.0)
+              ))
+            }
+            if (midActionStatic.contains("actionstatic_view_" + cid) && midActionStatic.contains("actionstatic_conver_" + cid)) {
+              featureMap.put("actionstatic_ctcvr", RankExtractorFeature_20240530.calDiv(
+                midActionStatic.getOrDefault("actionstatic_conver_" + cid, 0.0),
+                midActionStatic.getOrDefault("actionstatic_view_" + cid, 0.0)
+              ))
+            }
+            if (midActionStatic.contains("actionstatic_conver_" + cid) && midActionStatic.contains("actionstatic_click_" + cid)) {
+              featureMap.put("actionstatic_cvr", RankExtractorFeature_20240530.calDiv(
+                midActionStatic.getOrDefault("actionstatic_click_" + cid, 0.0),
+                midActionStatic.getOrDefault("actionstatic_conver_" + cid, 0.0)
+              ))
+            }
+
+            val e1: JSONObject = if (record.isNull("e1_feature")) new JSONObject() else
+              JSON.parseObject(record.getString("e1_feature"))
+            val e2: JSONObject = if (record.isNull("e2_feature")) new JSONObject() else
+              JSON.parseObject(record.getString("e2_feature"))
+            val title = b1.getOrDefault("cidtitle", "").toString
+            if (title.nonEmpty) {
+              for ((en, prefix1) <- List((e1, "e1"), (e2, "e2"))) {
+                for (prefix2 <- List("tags_3d", "tags_7d", "tags_14d")) {
+                  if (en.nonEmpty && en.containsKey(prefix2) && en.getString(prefix2).nonEmpty) {
+                    val (f1, f2, f3, f4) = funcC34567ForTags(en.getString(prefix2), title)
+                    featureMap.put(prefix1 + "_" + prefix2 + "_matchnum", f1)
+                    featureMap.put(prefix1 + "_" + prefix2 + "_maxscore", f3)
+                    featureMap.put(prefix1 + "_" + prefix2 + "_avgscore", f4)
+
+                  }
                 }
               }
             }
-          }
-
-          val d1: JSONObject = if (record.isNull("d1_feature")) new JSONObject() else
-            JSON.parseObject(record.getString("d1_feature"))
-          val d2: JSONObject = if (record.isNull("d2_feature")) new JSONObject() else
-            JSON.parseObject(record.getString("d2_feature"))
-
-          if (d1.nonEmpty){
-            for (prefix <- List("3h", "6h", "12h", "1d", "3d", "7d")) {
-              val view = if (!d1.containsKey("ad_view_" + prefix)) 0D else d1.getIntValue("ad_view_" + prefix).toDouble
-              val click = if (!d1.containsKey("ad_click_" + prefix)) 0D else d1.getIntValue("ad_click_" + prefix).toDouble
-              val conver = if (!d1.containsKey("ad_conversion_" + prefix)) 0D else d1.getIntValue("ad_conversion_" + prefix).toDouble
-              val income = if (!d1.containsKey("ad_income_" + prefix)) 0D else d1.getIntValue("ad_income_" + prefix).toDouble
-              val f1 = RankExtractorFeature_20240530.calDiv(click, view)
-              val f2 = RankExtractorFeature_20240530.calDiv(conver, view)
-              val f3 = RankExtractorFeature_20240530.calDiv(conver, click)
-              val f4 = conver
-              val f5 = RankExtractorFeature_20240530.calDiv(income * 1000, view)
-              featureMap.put("d1_feature" + "_" + prefix + "_" + "ctr", f1)
-              featureMap.put("d1_feature" + "_" + prefix + "_" + "ctcvr", f2)
-              featureMap.put("d1_feature" + "_" + prefix + "_" + "cvr", f3)
-              featureMap.put("d1_feature" + "_" + prefix + "_" + "conver", f4)
-              featureMap.put("d1_feature" + "_" + prefix + "_" + "ecpm", f5)
+
+            val d1: JSONObject = if (record.isNull("d1_feature")) new JSONObject() else
+              JSON.parseObject(record.getString("d1_feature"))
+            val d2: JSONObject = if (record.isNull("d2_feature")) new JSONObject() else
+              JSON.parseObject(record.getString("d2_feature"))
+
+            if (d1.nonEmpty) {
+              for (prefix <- List("3h", "6h", "12h", "1d", "3d", "7d")) {
+                val view = if (!d1.containsKey("ad_view_" + prefix)) 0D else d1.getIntValue("ad_view_" + prefix).toDouble
+                val click = if (!d1.containsKey("ad_click_" + prefix)) 0D else d1.getIntValue("ad_click_" + prefix).toDouble
+                val conver = if (!d1.containsKey("ad_conversion_" + prefix)) 0D else d1.getIntValue("ad_conversion_" + prefix).toDouble
+                val income = if (!d1.containsKey("ad_income_" + prefix)) 0D else d1.getIntValue("ad_income_" + prefix).toDouble
+                val f1 = RankExtractorFeature_20240530.calDiv(click, view)
+                val f2 = RankExtractorFeature_20240530.calDiv(conver, view)
+                val f3 = RankExtractorFeature_20240530.calDiv(conver, click)
+                val f4 = conver
+                val f5 = RankExtractorFeature_20240530.calDiv(income * 1000, view)
+                featureMap.put("d1_feature" + "_" + prefix + "_" + "ctr", f1)
+                featureMap.put("d1_feature" + "_" + prefix + "_" + "ctcvr", f2)
+                featureMap.put("d1_feature" + "_" + prefix + "_" + "cvr", f3)
+                featureMap.put("d1_feature" + "_" + prefix + "_" + "conver", f4)
+                featureMap.put("d1_feature" + "_" + prefix + "_" + "ecpm", f5)
+              }
             }
-          }
 
-          val vidRankMaps = scala.collection.mutable.Map[String, scala.collection.immutable.Map[String, Double]]()
-          if (d2.nonEmpty){
-            d2.foreach(r => {
-              val key = r._1
-              val value = d2.getString(key).split(",").map(r=> {
-                val rList = r.split(":")
-                (rList(0), rList(2).toDouble)
-              }).toMap
-              vidRankMaps.put(key, value)
-            })
-          }
-          for (prefix1 <- List("ctr", "ctcvr", "ecpm")) {
-            for (prefix2 <- List("1d", "3d", "7d", "14d")) {
-              if (vidRankMaps.contains(prefix1 + "_" + prefix2)){
-                val rank = vidRankMaps(prefix1 + "_" + prefix2).getOrDefault(cid, 0.0)
-                if (rank >= 1.0){
-                  featureMap.put("vid_rank_" + prefix1 + "_" + prefix2, 1.0 / rank)
+            val vidRankMaps = scala.collection.mutable.Map[String, scala.collection.immutable.Map[String, Double]]()
+            if (d2.nonEmpty) {
+              d2.foreach(r => {
+                val key = r._1
+                val value = d2.getString(key).split(",").map(r => {
+                  val rList = r.split(":")
+                  (rList(0), rList(2).toDouble)
+                }).toMap
+                vidRankMaps.put(key, value)
+              })
+            }
+            for (prefix1 <- List("ctr", "ctcvr", "ecpm")) {
+              for (prefix2 <- List("1d", "3d", "7d", "14d")) {
+                if (vidRankMaps.contains(prefix1 + "_" + prefix2)) {
+                  val rank = vidRankMaps(prefix1 + "_" + prefix2).getOrDefault(cid, 0.0)
+                  if (rank >= 1.0) {
+                    featureMap.put("vid_rank_" + prefix1 + "_" + prefix2, 1.0 / rank)
+                  }
                 }
               }
             }
-          }
-
-
-          /*
-          广告
-            sparse：cid adid adverid targeting_conversion
-
-            cpa --> 1个
-            adverid下的 3h 6h 12h 1d 3d 7d 、 ctr ctcvr cvr conver ecpm  --> 30个
-            cid下的 3h 6h 12h 1d 3d 7d 、 ctr ctcvr cvr ecpm conver --> 30个
-            地理//cid下的 3h 6h 12h 1d 3d 7d 、 ctr ctcvr cvr ecpm conver --> 30个
-            app//cid下的 3h 6h 12h 1d 3d 7d 、 ctr ctcvr cvr ecpm conver --> 30个
-            手机品牌//cid下的 3h 6h 12h 1d 3d 7d 、 ctr ctcvr cvr ecpm conver --> 30个
-            系统 无数据
-            week//cid下的 7d 14d、 ctr ctcvr cvr ecpm conver --> 10个
-            hour//cid下的 7d 14d、 ctr ctcvr cvr ecpm conver --> 10个
-
-          用户
-            用户历史 点击/转化 的title tag；3d 7d 14d； cid的title； 数量/最高分/平均分 --> 18个
-            用户历史 14d 看过/点过/转化次数/income； ctr cvr ctcvr ecpm；  --> 8个
-
-            用户到cid的ui特征 --> 10个
-              1/用户最近看过这个cid的时间间隔
-              1/用户最近点过这个cid的时间间隔
-              1/用户最近转过这个cid的时间间隔
-              用户看过这个cid多少次
-              用户点过这个cid多少次
-              用户转过这个cid多少次
-              用户对这个cid花了多少钱
-              用户对这个cid的ctr ctcvr cvr
-
-          视频
-            title与cid的 sim-score-1/-2 无数据
-            vid//cid下的 3h 6h 12h 1d 3d 7d 、 ctr ctcvr cvr ecpm conver --> 30个
-            vid//cid下的 1d 3d 7d 14d、 ctr ctcvr ecpm 的rank值 倒数 --> 12个
-
-           */
-
-
-
-          //4 处理label信息。
-          val labels = new JSONObject
-          for (labelKey <- List("ad_is_click", "ad_is_conversion")){
-            if (!record.isNull(labelKey)){
-              labels.put(labelKey, record.getString(labelKey))
+
+
+            /*
+            广告
+              sparse：cid adid adverid targeting_conversion
+
+              cpa --> 1个
+              adverid下的 3h 6h 12h 1d 3d 7d 、 ctr ctcvr cvr conver ecpm  --> 30个
+              cid下的 3h 6h 12h 1d 3d 7d 、 ctr ctcvr cvr ecpm conver --> 30个
+              地理//cid下的 3h 6h 12h 1d 3d 7d 、 ctr ctcvr cvr ecpm conver --> 30个
+              app//cid下的 3h 6h 12h 1d 3d 7d 、 ctr ctcvr cvr ecpm conver --> 30个
+              手机品牌//cid下的 3h 6h 12h 1d 3d 7d 、 ctr ctcvr cvr ecpm conver --> 30个
+              系统 无数据
+              week//cid下的 7d 14d、 ctr ctcvr cvr ecpm conver --> 10个
+              hour//cid下的 7d 14d、 ctr ctcvr cvr ecpm conver --> 10个
+
+            用户
+              用户历史 点击/转化 的title tag；3d 7d 14d； cid的title； 数量/最高分/平均分 --> 18个
+              用户历史 14d 看过/点过/转化次数/income； ctr cvr ctcvr ecpm；  --> 8个
+
+              用户到cid的ui特征 --> 10个
+                1/用户最近看过这个cid的时间间隔
+                1/用户最近点过这个cid的时间间隔
+                1/用户最近转过这个cid的时间间隔
+                用户看过这个cid多少次
+                用户点过这个cid多少次
+                用户转过这个cid多少次
+                用户对这个cid花了多少钱
+                用户对这个cid的ctr ctcvr cvr
+
+            视频
+              title与cid的 sim-score-1/-2 无数据
+              vid//cid下的 3h 6h 12h 1d 3d 7d 、 ctr ctcvr cvr ecpm conver --> 30个
+              vid//cid下的 1d 3d 7d 14d、 ctr ctcvr ecpm 的rank值 倒数 --> 12个
+
+             */
+
+
+            //4 处理label信息。
+            val labels = new JSONObject
+            for (labelKey <- List("ad_is_click", "ad_is_conversion")) {
+              if (!record.isNull(labelKey)) {
+                labels.put(labelKey, record.getString(labelKey))
+              }
             }
-          }
-          //5 处理log key表头。
-          val apptype = record.getString("apptype")
-          val mid = record.getString("mid")
-          val headvideoid = record.getString("headvideoid")
-          val logKey = (apptype, mid, cid, ts, headvideoid).productIterator.mkString(",")
-          val labelKey = labels.toString()
-          val featureKey = featureMap.toString()
-          //6 拼接数据，保存。
-          logKey + "\t" + labelKey + "\t" + featureKey
-        })
-
-      // 4 保存数据到hdfs
-      val savePartition = dt + hh
-      val hdfsPath = savePath + "/" + savePartition
-      if (hdfsPath.nonEmpty && hdfsPath.startsWith("/dw/recommend/model/")){
-        println("删除路径并开始数据写入:" + hdfsPath)
-        MyHdfsUtils.delete_hdfs_path(hdfsPath)
-        odpsData.coalesce(repartition).saveAsTextFile(hdfsPath, classOf[GzipCodec])
-      }else{
-        println("路径不合法，无法写入:" + hdfsPath)
+            //5 处理log key表头。
+            val apptype = record.getString("apptype")
+            val mid = record.getString("mid")
+            val headvideoid = record.getString("headvideoid")
+            val logKey = (apptype, mid, cid, ts, headvideoid).productIterator.mkString(",")
+            val labelKey = labels.toString()
+            val featureKey = featureMap.toString()
+            //6 拼接数据，保存。
+            logKey + "\t" + labelKey + "\t" + featureKey
+          })
+
+        // 4 保存数据到hdfs
+        val savePartition = dt + hh
+        val hdfsPath = savePath + "/" + savePartition
+        if (hdfsPath.nonEmpty && hdfsPath.startsWith("/dw/recommend/model/")) {
+          println("删除路径并开始数据写入:" + hdfsPath)
+          MyHdfsUtils.delete_hdfs_path(hdfsPath)
+          odpsData.coalesce(repartition).saveAsTextFile(hdfsPath, classOf[GzipCodec])
+        } else {
+          println("路径不合法，无法写入:" + hdfsPath)
+        }
       }
+
     }
   }
 

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

@@ -5,10 +5,11 @@ nohup /opt/apps/SPARK2/spark-2.4.8-hadoop3.2-1.0.8/bin/spark-class2 org.apache.s
 --class com.aliyun.odps.spark.examples.makedata_ad.makedata_ad_31_originData_20240620 \
 --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 \
+tablePart:64 repartition:16 \
 beginStr:2024062008 endStr:2024062223 \
 savePath:/dw/recommend/model/31_ad_sample_data_fix/ \
-table:alg_recsys_ad_sample_all \
+table:alg_recsys_ad_sample_all filterHours:00,01,02,03,04,05,06,07 \
+idDefaultValue:0.01 \
 > p31_2024062008.log 2>&1 &
 
 
@@ -20,6 +21,7 @@ nohup /opt/apps/SPARK2/spark-2.4.8-hadoop3.2-1.0.8/bin/spark-class2 org.apache.s
 --conf spark.driver.maxResultSize=16G \
 ./target/spark-examples-1.0.0-SNAPSHOT-shaded.jar \
 fileName:20240620_100_fix \
+readPath:/dw/recommend/model/31_ad_sample_data_fix/20240620* \
 savePath:/dw/recommend/model/32_bucket_data/ \
 > p32_data.log 2>&1 &
 
@@ -49,8 +51,8 @@ nohup /opt/apps/SPARK2/spark-2.4.8-hadoop3.2-1.0.8/bin/spark-class2 org.apache.s
 --class com.aliyun.odps.spark.examples.makedata_ad.makedata_ad_33_bucketDataPrint_20240628 \
 --master yarn --driver-memory 2G --executor-memory 4G --executor-cores 1 --num-executors 16 \
 ./target/spark-examples-1.0.0-SNAPSHOT-shaded.jar \
-beginStr:2024062717 endStr:2024062723 \
-readDate:20240627 \
+beginStr:2024062908 endStr:2024062923 \
+readDate:20240629 \
 table:alg_recsys_ad_sample_all_new \
 savePath:/dw/recommend/model/33_for_check/ \
 > p33_data_check.log 2>&1 &

src/main/scala/com/aliyun/odps/spark/examples/临时记录的脚本-推荐

@@ -156,8 +156,8 @@ nohup /opt/apps/SPARK2/spark-2.4.8-hadoop3.2-1.0.8/bin/spark-class2 org.apache.s
 --class com.aliyun.odps.spark.examples.makedata.makedata_17_bucketDataPrint_20240617 \
 --master yarn --driver-memory 2G --executor-memory 4G --executor-cores 1 --num-executors 16 \
 ./target/spark-examples-1.0.0-SNAPSHOT-shaded.jar \
-beginStr:2024062700 endStr:2024062723 \
-readDate:20240627 \
-> p17_data_check.log 2>&1 &
+beginStr:2024062600 endStr:2024062623 \
+readDate:20240626 \
+> p17_20240626.log 2>&1 &
 
 /dw/recommend/model/17_for_check/

zhangbo/01_train.sh

@@ -16,8 +16,10 @@ $HADOOP fs -text ${train_path}/${day}/* | /root/sunmingze/alphaFM/bin/fm_train -
 # nohup sh 01_train.sh 20240606 /dw/recommend/model/16_train_data/ model_aka4 1,1,4 >p1_model_aka4.log 2>&1 &
 
 
-# nohup sh 01_train.sh 20240620 /dw/recommend/model/33_ad_train_data_nosparse/ model_bkb0_3 1,1,0 >p1_model_bkb0.log 2>&1 &
+# nohup sh 01_train.sh 20240623 /dw/recommend/model/33_ad_train_data_nosparse/ model_test 1,1,0 >p1_model_bkb0.log 2>&1 &
 # nohup sh 01_train.sh 20240620 /dw/recommend/model/33_ad_train_data/ model_bkb8_2 1,1,8 >p1_model_bkb8_2.log 2>&1 &
 # nohup sh 01_train.sh 20240620 /dw/recommend/model/33_ad_train_data/ model_bkb4 1,1,4 >p1_model_bkb4.log 2>&1 &
 # nohup sh 01_train.sh 20240620 /dw/recommend/model/33_ad_train_data/ model_bkb12 1,1,12 >p1_model_bkb12.log 2>&1 &
-# nohup sh 01_train.sh 20240620 /dw/recommend/model/33_ad_train_data/ model_bkb16 1,1,16 >p1_model_bkb16.log 2>&1 &
+# nohup sh 01_train.sh 20240620 /dw/recommend/model/33_ad_train_data/ model_bkb16 1,1,16 >p1_model_bkb16.log 2>&1 &
+
+

zhangbo/03_predict.sh

@@ -17,7 +17,7 @@ cat predict/${output_file}_$day.txt | /root/sunmingze/AUC/AUC
 # nohup sh 03_predict.sh 20240613 /dw/recommend/model/16_train_data/ model_aka8_20240612.txt model_aka8_20240612 8 >p3_model_aka8_12.log 2>&1 &
 
 
-# nohup sh 03_predict.sh 20240615 /dw/recommend/model/16_train_data_print_online_merge/ model_aka8_20240608.txt model_aka8_20240608 8 >p3_model_aka8_on.log 2>&1 &
+# nohup sh 03_predict.sh 20240624 /dw/recommend/model/33_ad_train_data_nosparse/ model_test_20240623.txt model_test_20240623 0 >p3_model_aka8_on.log 2>&1 &
 
 
 
@@ -25,18 +25,25 @@ cat predict/${output_file}_$day.txt | /root/sunmingze/AUC/AUC
 # cat tmpfile | /root/sunmingze/alphaFM/bin/fm_predict -m model/model_bkb0_20240622.txt -dim 0 -core 1 -out tmpfile_out.txt
 
 
-# nohup sh 03_predict.sh 20240618 /dw/recommend/model/17_for_check_v1/ model_aka8_20240608.txt v1 8 >v1.log 2>&1 &
-# nohup sh 03_predict.sh 20240618 /dw/recommend/model/17_for_check_v2/ model_aka8_20240608.txt v2 8 >v2.log 2>&1 &
-# nohup sh 03_predict.sh 20240618 /dw/recommend/model/17_for_check_v3/ model_aka8_20240608.txt v3 8 >v3.log 2>&1 &
-# nohup sh 03_predict.sh 20240618 /dw/recommend/model/17_for_check_v4/ model_aka8_20240608.txt v4 8 >v4.log 2>&1 &
-# nohup sh 03_predict.sh 20240618 /dw/recommend/model/17_for_check_v5/ model_aka8_20240608.txt v4 8 >v5.log 2>&1 &
-# nohup sh 03_predict.sh 20240618 /dw/recommend/model/17_for_check_v6/ model_aka8_20240608.txt v4 8 >v6.log 2>&1 &
+# nohup sh 03_predict.sh 20240629 /dw/recommend/model/33_for_check_v1/ model_bkb0_20240622.txt v1 0 >v1.log 2>&1 &
+# nohup sh 03_predict.sh 20240629 /dw/recommend/model/33_for_check_v2/ model_bkb0_20240622.txt v2 0 >v2.log 2>&1 &
+# nohup sh 03_predict.sh 20240629 /dw/recommend/model/33_for_check_v3/ model_bkb0_20240622.txt v3 0 >v3.log 2>&1 &
+# nohup sh 03_predict.sh 20240627 /dw/recommend/model/33_for_check_v4/ model_bkb0_20240622.txt v4 0 >v4.log 2>&1 &
+# nohup sh 03_predict.sh 20240627 /dw/recommend/model/33_for_check_v5/ model_bkb0_20240622.txt v4 0 >v5.log 2>&1 &
+# nohup sh 03_predict.sh 20240627 /dw/recommend/model/33_for_check_v6/ model_bkb0_20240622.txt v4 0 >v6.log 2>&1 &
 
+# nohup sh 03_predict.sh 20240626 /dw/recommend/model/17_for_check_v1/ model_aka8_20240608.txt v1 8 >v1.log 2>&1 &
+# nohup sh 03_predict.sh 20240626 /dw/recommend/model/17_for_check_v2/ model_aka8_20240608.txt v2 8 >v2.log 2>&1 &
+# nohup sh 03_predict.sh 20240626 /dw/recommend/model/17_for_check_v3/ model_aka8_20240608.txt v3 8 >v3.log 2>&1 &
+# nohup sh 03_predict.sh 20240626 /dw/recommend/model/17_for_check_v4/ model_aka8_20240608.txt v4 8 >v4.log 2>&1 &
+# nohup sh 03_predict.sh 20240626 /dw/recommend/model/17_for_check_v5/ model_aka8_20240608.txt v4 8 >v5.log 2>&1 &
+# nohup sh 03_predict.sh 20240626 /dw/recommend/model/17_for_check_v6/ model_aka8_20240608.txt v4 8 >v6.log 2>&1 &
 
 
 
-# nohup sh 03_predict.sh 20240623 /dw/recommend/model/33_ad_train_data/ model_bkb0_20240622.txt model_bkb0_20240622 0 >p3_model_bkb0.log 2>&1 &
-# nohup sh 03_predict.sh 20240621 /dw/recommend/model/33_ad_train_data/ model_bkb4_20240620.txt model_bkb4_20240620 4 >p3_model_bkb4.log 2>&1 &
+
+# nohup sh 03_predict.sh 20240630 /dw/recommend/model/33_ad_train_data/ model_bkb0_20240622.txt model_bkb0_20240622 0 >p3_model_bkb0.log 2>&1 &
+# nohup sh 03_predict.sh 20240630 /dw/recommend/model/33_ad_train_data/ model_bkb4_20240620.txt model_bkb4_20240620 4 >p3_model_bkb4.log 2>&1 &
 # nohup sh 03_predict.sh 20240624 /dw/recommend/model/33_ad_train_data/ model_bkb8_20240622.txt model_bkb8_20240622 8 >p3_model_bkb8.log 2>&1 &
 # nohup sh 03_predict.sh 20240621 /dw/recommend/model/33_ad_train_data/ model_bkb12_20240620.txt model_bkb12_20240620 12 >p3_model_bkb12.log 2>&1 &
 # nohup sh 03_predict.sh 20240621 /dw/recommend/model/33_ad_train_data/ model_bkb16_20240620.txt model_bkb16_20240620 16 >p3_model_bkb16.log 2>&1 &