|
|
@@ -0,0 +1,554 @@
|
|
|
+package com.aliyun.odps.spark.examples.makedata_ad.xgb
|
|
|
+
|
|
|
+import com.alibaba.fastjson.{JSON, JSONObject}
|
|
|
+import com.aliyun.odps.TableSchema
|
|
|
+import com.aliyun.odps.data.Record
|
|
|
+import com.aliyun.odps.spark.examples.myUtils.{MyDateUtils, MyHdfsUtils, ParamUtils, env}
|
|
|
+import examples.extractor.{ExtractorUtils, RankExtractorFeature_20240530}
|
|
|
+import examples.utils.DateTimeUtil
|
|
|
+import org.apache.hadoop.io.compress.GzipCodec
|
|
|
+import org.apache.spark.sql.SparkSession
|
|
|
+import org.xm.Similarity
|
|
|
+
|
|
|
+import scala.collection.JavaConversions._
|
|
|
+import scala.collection.mutable.ArrayBuffer
|
|
|
+import scala.io.Source
|
|
|
+
|
|
|
+object makedata_31_bucketDataPrint_20240821 {
|
|
|
+ def main(args: Array[String]): Unit = {
|
|
|
+ // 1 读取参数
|
|
|
+ val param = ParamUtils.parseArgs(args)
|
|
|
+ val tablePart = param.getOrElse("tablePart", "64").toInt
|
|
|
+ val beginStr = param.getOrElse("beginStr", "2024061500")
|
|
|
+ val endStr = param.getOrElse("endStr", "2024061523")
|
|
|
+ val savePath = param.getOrElse("savePath", "/dw/recommend/model/33_for_check")
|
|
|
+ val project = param.getOrElse("project", "loghubods")
|
|
|
+ val table = param.getOrElse("table", "alg_recsys_ad_sample_all")
|
|
|
+ val repartition = param.getOrElse("repartition", "32").toInt
|
|
|
+ val readDate = param.getOrElse("readDate", "20240615")
|
|
|
+ val featureNameFile = param.getOrElse("featureName", "20240718_ad_feature_name_517.txt")
|
|
|
+ val featureBucketFile = param.getOrElse("featureBucketFile", "20240718_ad_bucket_517.txt");
|
|
|
+ val filterHours = param.getOrElse("filterHours", "00,01,02,03,04,05,06,07").split(",").toSet
|
|
|
+ val idDefaultValue = param.getOrElse("idDefaultValue", "1.0").toDouble
|
|
|
+
|
|
|
+ val spark = SparkSession
|
|
|
+ .builder()
|
|
|
+ .appName(this.getClass.getName)
|
|
|
+ .getOrCreate()
|
|
|
+ val sc = spark.sparkContext
|
|
|
+
|
|
|
+ val loader = getClass.getClassLoader
|
|
|
+ val featureNameUrl = loader.getResource(featureNameFile)
|
|
|
+ val content =
|
|
|
+ if (featureNameUrl != null) {
|
|
|
+ val content = Source.fromURL(featureNameUrl).getLines().mkString("\n")
|
|
|
+ Source.fromURL(featureNameUrl).close()
|
|
|
+ content
|
|
|
+ } else {
|
|
|
+ ""
|
|
|
+ }
|
|
|
+ println(content)
|
|
|
+ val featureNameList = content.split("\n")
|
|
|
+ .map(r => r.replace(" ", "").replaceAll("\n", ""))
|
|
|
+ .filter(r => r.nonEmpty).toList
|
|
|
+ val contentList_br = sc.broadcast(featureNameList)
|
|
|
+
|
|
|
+ val resourceUrlBucket = loader.getResource(featureBucketFile)
|
|
|
+ val buckets =
|
|
|
+ if (resourceUrlBucket != null) {
|
|
|
+ val buckets = Source.fromURL(resourceUrlBucket).getLines().mkString("\n")
|
|
|
+ Source.fromURL(resourceUrlBucket).close()
|
|
|
+ buckets
|
|
|
+ } else {
|
|
|
+ ""
|
|
|
+ }
|
|
|
+ println(buckets)
|
|
|
+ val bucketsMap = buckets.split("\n")
|
|
|
+ .map(r => r.replace(" ", "").replaceAll("\n", ""))
|
|
|
+ .filter(r => r.nonEmpty)
|
|
|
+ .map(r => {
|
|
|
+ val rList = r.split("\t")
|
|
|
+ (rList(0), (rList(1).toDouble, rList(2).split(",").map(_.toDouble)))
|
|
|
+ }).toMap
|
|
|
+ val bucketsMap_br = sc.broadcast(bucketsMap)
|
|
|
+ // 2 读取odps+表信息
|
|
|
+ val odpsOps = env.getODPS(sc)
|
|
|
+
|
|
|
+ // 3 循环执行数据生产
|
|
|
+ val timeRange = MyDateUtils.getDateHourRange(beginStr, endStr)
|
|
|
+ for (dt_hh <- timeRange) {
|
|
|
+ val dt = dt_hh.substring(0, 8)
|
|
|
+ val hh = dt_hh.substring(8, 10)
|
|
|
+ val partition = s"dt=$dt,hh=$hh"
|
|
|
+ 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 apptype = record.getString("apptype")
|
|
|
+ val extend: JSONObject = if (record.isNull("extend")) new JSONObject() else
|
|
|
+ JSON.parseObject(record.getString("extend"))
|
|
|
+
|
|
|
+
|
|
|
+ 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)
|
|
|
+ }
|
|
|
+
|
|
|
+ val hour = DateTimeUtil.getHourByTimestamp(ts)
|
|
|
+ featureMap.put("hour_" + hour, idDefaultValue)
|
|
|
+
|
|
|
+ val dayOfWeek = DateTimeUtil.getDayOrWeekByTimestamp(ts)
|
|
|
+ featureMap.put("dayofweek_" + dayOfWeek, idDefaultValue);
|
|
|
+
|
|
|
+ featureMap.put("apptype_" + apptype, idDefaultValue);
|
|
|
+
|
|
|
+ if (extend.containsKey("abcode") && extend.getString("abcode").nonEmpty) {
|
|
|
+ featureMap.put("abcode_" + extend.getString("abcode"), idDefaultValue)
|
|
|
+ }
|
|
|
+
|
|
|
+
|
|
|
+ if (b1.containsKey("cpa")) {
|
|
|
+ featureMap.put("cpa", b1.getString("cpa").toDouble)
|
|
|
+ }
|
|
|
+ if (b1.containsKey("weight") && b1.getString("weight").nonEmpty) {
|
|
|
+ featureMap.put("weight", b1.getString("weight").toDouble)
|
|
|
+ }
|
|
|
+
|
|
|
+ for ((bn, prefix1) <- List(
|
|
|
+ (b2, "b2"), (b3, "b3"), (b4, "b4"), (b5, "b5"), (b8, "b8"), (b9, "b9")
|
|
|
+ )) {
|
|
|
+ for (prefix2 <- List(
|
|
|
+ "1h", "2h", "3h", "4h", "5h", "6h", "12h", "1d", "3d", "7d", "today", "yesterday"
|
|
|
+ )) {
|
|
|
+ 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)
|
|
|
+ }
|
|
|
+ }
|
|
|
+
|
|
|
+ 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 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_conver_" + cid, 0.0),
|
|
|
+ midActionStatic.getOrDefault("actionstatic_click_" + 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"))
|
|
|
+ val d3: JSONObject = if (record.isNull("d3_feature")) new JSONObject() else
|
|
|
+ JSON.parseObject(record.getString("d3_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)
|
|
|
+ }
|
|
|
+ }
|
|
|
+ }
|
|
|
+ }
|
|
|
+
|
|
|
+ if (d3.nonEmpty) {
|
|
|
+ val vTitle = d3.getString("title")
|
|
|
+ val score = Similarity.conceptSimilarity(title, vTitle)
|
|
|
+ featureMap.put("ctitle_vtitle_similarity", score);
|
|
|
+ }
|
|
|
+
|
|
|
+ /*
|
|
|
+ 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 mid = record.getString("mid")
|
|
|
+ val flag = record.isNull("allfeaturemap")
|
|
|
+ val allfeature = if (record.isNull("allfeaturemap")) new JSONObject() else
|
|
|
+ JSON.parseObject(record.getString("allfeaturemap"))
|
|
|
+
|
|
|
+ val headvideoid = record.getString("headvideoid")
|
|
|
+ // val logKey = (apptype, mid, cid, ts, headvideoid).productIterator.mkString(",")
|
|
|
+ val labelKey = labels.toString()
|
|
|
+ //6 拼接数据，保存。
|
|
|
+ (apptype, mid, cid, ts, headvideoid, labelKey, allfeature, featureMap, flag)
|
|
|
+ }).filter {
|
|
|
+ case (apptype, mid, cid, ts, headvideoid, labelKey, allfeature, featureMap, flag) =>
|
|
|
+ flag
|
|
|
+ }.mapPartitions(row => {
|
|
|
+ val result = new ArrayBuffer[String]()
|
|
|
+ val bucketsMap = bucketsMap_br.value
|
|
|
+ row.foreach {
|
|
|
+ case (apptype, mid, cid, ts, headvideoid, labelKey, allfeature, featureMap, flag) =>
|
|
|
+ val offlineFeatureMap = featureMap.filter(r => bucketsMap.contains(r._1)).map(r => {
|
|
|
+ val score = r._2.toString.toDouble
|
|
|
+ val name = r._1
|
|
|
+ if (score > 1E-8) {
|
|
|
+ if (bucketsMap.contains(name)) {
|
|
|
+ val (bucketsNum, buckets) = bucketsMap(name)
|
|
|
+ val scoreNew = 1.0 / bucketsNum * (ExtractorUtils.findInsertPosition(buckets, score).toDouble + 1.0)
|
|
|
+ name + ":" + scoreNew.toString
|
|
|
+ } else {
|
|
|
+ name + ":" + score.toString
|
|
|
+ }
|
|
|
+ } else {
|
|
|
+ ""
|
|
|
+ }
|
|
|
+ }).filter(_.nonEmpty)
|
|
|
+ result.add(
|
|
|
+ (apptype, mid, cid, ts, headvideoid, labelKey, allfeature.toString(), offlineFeatureMap.iterator.mkString(",")).productIterator.mkString("\t")
|
|
|
+ )
|
|
|
+ }
|
|
|
+ result.iterator
|
|
|
+ })
|
|
|
+
|
|
|
+ // 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)
|
|
|
+ }
|
|
|
+ }
|
|
|
+
|
|
|
+ val data2 = sc.textFile(savePath + "/" + readDate + "*").mapPartitions(row => {
|
|
|
+ val result = new ArrayBuffer[(String, List[String], List[String], List[String])]()
|
|
|
+ val contentList = contentList_br.value
|
|
|
+ // 680实验，517个特征
|
|
|
+ row.foreach(r => {
|
|
|
+ val rList = r.split("\t")
|
|
|
+ val label = rList(5).toString
|
|
|
+ val allFeatureMap = JSON.parseObject(rList(6)).toMap.map(r => (r._1, r._2.toString))
|
|
|
+ val offlineFeature = rList(7).split(",").map(r => (r.split(":")(0), r.split(":")(1))).toMap
|
|
|
+ val offlineFeatureList = contentList.map(name => {
|
|
|
+ name + ":" + offlineFeature(name)
|
|
|
+ }).filter(_.nonEmpty)
|
|
|
+
|
|
|
+ val allFeatureV1 = allFeatureMap.map {
|
|
|
+ case (key, value) =>
|
|
|
+ key + ":" + value
|
|
|
+ }.toList
|
|
|
+
|
|
|
+ val allFeatureV2 = allFeatureMap.map {
|
|
|
+ case (key, value) =>
|
|
|
+ val b9FeatureSet = Set("b9_1h_ctr", "b9_1h_ctcvr", "b9_1h_cvr", "b9_1h_conver", "b9_1h_click", "b9_1h_conver*log(view)", "b9_1h_conver*ctcvr", "b9_2h_ctr", "b9_2h_ctcvr", "b9_2h_cvr", "b9_2h_conver", "b9_2h_click", "b9_2h_conver*log(view)", "b9_2h_conver*ctcvr", "b9_3h_ctr", "b9_3h_ctcvr", "b9_3h_cvr", "b9_3h_conver", "b9_3h_click", "b9_3h_conver*log(view)", "b9_3h_conver*ctcvr", "b9_6h_ctr", "b9_6h_ctcvr", "b9_6h_cvr", "b9_6h_conver", "b9_6h_click", "b9_6h_conver*log(view)", "b9_6h_conver*ctcvr", "b9_12h_ctr", "b9_12h_ctcvr", "b9_12h_cvr", "b9_12h_conver", "b9_12h_click", "b9_12h_conver*log(view)", "b9_12h_conver*ctcvr", "b9_1d_ctr", "b9_1d_ctcvr", "b9_1d_cvr", "b9_1d_conver", "b9_1d_click", "b9_1d_conver*log(view)", "b9_1d_conver*ctcvr", "b9_3d_ctr", "b9_3d_ctcvr", "b9_3d_cvr", "b9_3d_conver", "b9_3d_click", "b9_3d_conver*log(view)", "b9_3d_conver*ctcvr", "b9_7d_ctr", "b9_7d_ctcvr", "b9_7d_cvr", "b9_7d_conver", "b9_7d_click", "b9_7d_conver*log(view)", "b9_7d_conver*ctcvr", "b9_yesterday_ctr", "b9_yesterday_ctcvr", "b9_yesterday_cvr", "b9_yesterday_conver", "b9_yesterday_click", "b9_yesterday_conver*log(view)", "b9_yesterday_conver*ctcvr", "b9_today_ctr", "b9_today_ctcvr", "b9_today_cvr", "b9_today_conver", "b9_today_click", "b9_today_conver*log(view)", "b9_today_conver*ctcvr")
|
|
|
+ if (b9FeatureSet.contains(key) && offlineFeature.contains(key)) {
|
|
|
+ key + ":" + offlineFeature(key)
|
|
|
+ } else {
|
|
|
+ key + ":" + value
|
|
|
+ }
|
|
|
+ }.filter(_.nonEmpty).toList
|
|
|
+
|
|
|
+ result.add((label, offlineFeatureList, allFeatureV1, allFeatureV2))
|
|
|
+ })
|
|
|
+
|
|
|
+ result.iterator
|
|
|
+ })
|
|
|
+
|
|
|
+ val offlineSave = "/dw/recommend/model/33_for_check_offline/" + readDate
|
|
|
+ if (offlineSave.nonEmpty && offlineSave.startsWith("/dw/recommend/model/")) {
|
|
|
+ println("删除路径并开始数据写入:" + offlineSave)
|
|
|
+ MyHdfsUtils.delete_hdfs_path(offlineSave)
|
|
|
+ data2.map(r => r._1 + "\t" + r._2.mkString("\t")).saveAsTextFile(offlineSave, classOf[GzipCodec])
|
|
|
+ } else {
|
|
|
+ println("路径不合法，无法写入:" + offlineSave)
|
|
|
+ }
|
|
|
+
|
|
|
+ val allFeatureV1 = "/dw/recommend/model/33_for_check_all_v1/" + readDate
|
|
|
+ if (allFeatureV1.nonEmpty && allFeatureV1.startsWith("/dw/recommend/model/")) {
|
|
|
+ println("删除路径并开始数据写入:" + allFeatureV1)
|
|
|
+ MyHdfsUtils.delete_hdfs_path(allFeatureV1)
|
|
|
+ data2.map(r => r._1 + "\t" + r._3.mkString("\t")).saveAsTextFile(allFeatureV1, classOf[GzipCodec])
|
|
|
+ } else {
|
|
|
+ println("路径不合法，无法写入:" + allFeatureV1)
|
|
|
+ }
|
|
|
+
|
|
|
+ val allFeatureV2 = "/dw/recommend/model/33_for_check_all_v2/" + readDate
|
|
|
+ if (allFeatureV2.nonEmpty && allFeatureV2.startsWith("/dw/recommend/model/")) {
|
|
|
+ println("删除路径并开始数据写入:" + allFeatureV2)
|
|
|
+ MyHdfsUtils.delete_hdfs_path(allFeatureV2)
|
|
|
+ data2.map(r => r._1 + "\t" + r._4.mkString("\t")).saveAsTextFile(allFeatureV2, classOf[GzipCodec])
|
|
|
+ } else {
|
|
|
+ println("路径不合法，无法写入:" + allFeatureV2)
|
|
|
+ }
|
|
|
+
|
|
|
+ }
|
|
|
+ }
|
|
|
+
|
|
|
+ def func(record: Record, schema: TableSchema): Record = {
|
|
|
+ record
|
|
|
+ }
|
|
|
+
|
|
|
+ def funcC34567ForTags(tags: String, title: String): Tuple4[Double, String, Double, Double] = {
|
|
|
+ // 匹配数量 匹配词 语义最高相似度分 语义平均相似度分
|
|
|
+ val tagsList = tags.split(",")
|
|
|
+ var d1 = 0.0
|
|
|
+ val d2 = new ArrayBuffer[String]()
|
|
|
+ var d3 = 0.0
|
|
|
+ var d4 = 0.0
|
|
|
+ for (tag <- tagsList) {
|
|
|
+ if (title.contains(tag)) {
|
|
|
+ d1 = d1 + 1.0
|
|
|
+ d2.add(tag)
|
|
|
+ }
|
|
|
+ val score = Similarity.conceptSimilarity(tag, title)
|
|
|
+ d3 = if (score > d3) score else d3
|
|
|
+ d4 = d4 + score
|
|
|
+ }
|
|
|
+ d4 = if (tagsList.nonEmpty) d4 / tagsList.size else d4
|
|
|
+ (d1, d2.mkString(","), d3, d4)
|
|
|
+ }
|
|
|
+}
|
