Add makedata_ad_31_originData_20250110

src/main/java/examples/extractor/RankExtractorFeature_20240530.java

@@ -15,6 +15,19 @@ public class RankExtractorFeature_20240530 {
         return Math.log(a + 1.0);
     }
 
+    public static Double divSmooth1(double a, double b, double zscore) {
+        // division with wilson smoothing
+        // for confidence level 0.95, zscore should be 1.96
+        if (a == 0 || b == 0) {
+            return 0D;
+        }
+        double zscore2 = zscore * zscore;
+        double p = a / b;
+        double numerator = p + zscore2 / (2 * b) - zscore * Math.sqrt((p * (1 - p) + zscore2 / (4 * b)) / b);
+        double denominator = 1 + zscore2 / b;
+        return numerator / denominator;
+    }
+
     public static void main(String[] args) {
         System.out.println(Math.log(10));
         System.out.println(Math.log(100));

src/main/scala/com/aliyun/odps/spark/examples/makedata_ad/v20240718/makedata_ad_31_originData_20250110.scala

@@ -0,0 +1,438 @@
+package com.aliyun.odps.spark.examples.makedata_ad.v20240718
+
+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.RankExtractorFeature_20240530
+import examples.utils.{AdUtil, 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
+
+/*
+   原始特征处理20250110版本，基于20240718修改
+   * 广告/创意粒度增加CTR类统计特征平滑
+ */
+
+object makedata_ad_31_originData_20250110 {
+  val WILSON_ZSCORE = 1.96
+
+  def main(args: Array[String]): Unit = {
+    val spark = SparkSession
+      .builder()
+      .appName(this.getClass.getName)
+      .getOrCreate()
+    val sc = spark.sparkContext
+
+    // 1 读取参数
+    val param = ParamUtils.parseArgs(args)
+    val tablePart = param.getOrElse("tablePart", "64").toInt
+    val beginStr = param.getOrElse("beginStr", "2024062008")
+    val endStr = param.getOrElse("endStr", "2024062023")
+    val savePath = param.getOrElse("savePath", "/dw/recommend/model/31_ad_sample_data/")
+    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)
+
+    // 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)
+          .filter(record => {
+            AdUtil.isApi(record)
+          })
+          .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
+                // NOTE(zhoutian):
+                // 这里cpc只是为了计算cpm的平滑的工具量，没有实际业务意义，因为cpm并非比率，本身不适合直接计算平滑
+                // 不使用cpa的原因是未来可能出现广告采用cpc计费的情况或者无法获取转化量的情况，用点击更为稳定
+                // 其它几组特征亦采用相同逻辑
+                val cpc = if (click == 0) 0D else income / click
+                val f1 = RankExtractorFeature_20240530.divSmooth1(click, view, WILSON_ZSCORE)
+                val f2 = RankExtractorFeature_20240530.divSmooth1(conver, view, WILSON_ZSCORE)
+                val f3 = RankExtractorFeature_20240530.divSmooth1(conver, click, WILSON_ZSCORE)
+                val f4 = conver
+                val f5 = RankExtractorFeature_20240530.divSmooth1(click, view, WILSON_ZSCORE) * cpc * 1000
+                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 cpc = if (click == 0) 0D else income / click
+                val f1 = RankExtractorFeature_20240530.divSmooth1(click, view, WILSON_ZSCORE)
+                val f2 = RankExtractorFeature_20240530.divSmooth1(conver, view, WILSON_ZSCORE)
+                val f3 = RankExtractorFeature_20240530.divSmooth1(conver, click, WILSON_ZSCORE)
+                val f4 = conver
+                val f5 = RankExtractorFeature_20240530.divSmooth1(click, view, WILSON_ZSCORE) * cpc * 1000
+                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 cpc = if (click == 0) 0D else income / click
+                val f1 = RankExtractorFeature_20240530.divSmooth1(click, view, WILSON_ZSCORE)
+                val f2 = RankExtractorFeature_20240530.divSmooth1(conver, view, WILSON_ZSCORE)
+                val f3 = RankExtractorFeature_20240530.divSmooth1(conver, click, WILSON_ZSCORE)
+                val f4 = conver
+                val f5 = RankExtractorFeature_20240530.divSmooth1(click, view, WILSON_ZSCORE) * cpc * 1000
+                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 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)
+        }
+      }
+
+    }
+  }
+
+  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)
+  }
+}