feat:修改str特征生产脚本

src/main/scala/com/aliyun/odps/spark/examples/makedata_recsys/v20250218/makedata_recsys_41_str_train_data_sample_20250319.scala

@@ -0,0 +1,217 @@
+package com.aliyun.odps.spark.examples.makedata_recsys.v20250218
+
+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
+import examples.extractor.v20250218.ExtractFeature20250218
+import examples.utils.{FestiveUtil, SimilarityUtils, StatisticsUtil}
+import org.apache.hadoop.io.compress.GzipCodec
+import org.apache.spark.sql.SparkSession
+import org.xm.Similarity
+
+import java.util
+import scala.collection.JavaConversions._
+import scala.collection.mutable.ArrayBuffer
+import scala.util.Random
+
+/*
+   20250218 提取特征
+ */
+
+object makedata_recsys_41_str_train_data_sample_20250319 {
+  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", "2025021812")
+    val endStr = param.getOrElse("endStr", "2025021812")
+    val project = param.getOrElse("project", "loghubods")
+    val table = param.getOrElse("table", "dwd_recsys_alg_sample_all_20250212")
+    val repartition = param.getOrElse("repartition", "32").toInt
+    val savePath = param.getOrElse("savePath", "/dw/recommend/model/41_sample_data/")
+    val fuSampleRate = param.getOrElse("fuSampleRate", "0.05").toDouble
+    val whatLabel = param.getOrElse("whatLabel", "is_share")
+    val whatApps = param.getOrElse("whatApps", "0,4,2,32,17,18,21,22,24,25,26,27,28,29,3,30,31,33,34,35,36").split(",").filter(r => r.nonEmpty).toList
+
+
+    // 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)
+
+    val partitions = timeRange.map { dt_hh =>
+      val dt = dt_hh.substring(0, 8)
+      val hh = dt_hh.substring(8, 10)
+      s"dt=$dt,hh=$hh"
+    }
+
+    val odpsData = partitions.map { partition => {
+      println(s"开始读取分区: $partition")
+      odpsOps.readTable(
+          project = project,
+          table = table,
+          partition = partition,
+          transfer = func,
+          numPartition = tablePart)
+        .filter(record => {
+          val page = record.getString("page")
+          val recommendPageType = record.getString("recommendpagetype")
+          val apptype = record.getString("apptype")
+          whatApps.contains(apptype) && StatisticsUtil.isRecommendScene(page, recommendPageType)
+        })
+        .filter(record => {
+          val label = record.getString(whatLabel)
+          "1".equals(label) || new Random().nextDouble() <= fuSampleRate
+        })
+        .mapPartitions(p => {
+          SimilarityUtils.init()
+          FestiveUtil.init()
+          p.map(record => {
+
+            val featureMap = new JSONObject()
+            val vid = if (record.isNull("vid")) "" else record.getString("vid")
+            val ts = if (record.isNull("ts")) 0 else record.getString("ts").toLong
+            // a 视频特征
+            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"))
+            val b10: JSONObject = if (record.isNull("b10_feature")) new JSONObject() else JSON.parseObject(record.getString("b10_feature"))
+            val b11: JSONObject = if (record.isNull("b11_feature")) new JSONObject() else JSON.parseObject(record.getString("b11_feature"))
+            val b12: JSONObject = if (record.isNull("b12_feature")) new JSONObject() else JSON.parseObject(record.getString("b12_feature"))
+            val b13: JSONObject = if (record.isNull("b13_feature")) new JSONObject() else JSON.parseObject(record.getString("b13_feature"))
+
+            // 用户特征
+            val c1: JSONObject = if (record.isNull("c1_feature")) new JSONObject() else JSON.parseObject(record.getString("c1_feature"))
+            val c2: JSONObject = if (record.isNull("c2_feature")) new JSONObject() else JSON.parseObject(record.getString("c2_feature"))
+            val c3: JSONObject = if (record.isNull("c3_feature")) new JSONObject() else JSON.parseObject(record.getString("c3_feature"))
+            val c4: JSONObject = if (record.isNull("c4_feature")) new JSONObject() else JSON.parseObject(record.getString("c4_feature"))
+            val c5: JSONObject = if (record.isNull("c5_feature")) new JSONObject() else JSON.parseObject(record.getString("c5_feature"))
+            val c6: JSONObject = if (record.isNull("c6_feature")) new JSONObject() else JSON.parseObject(record.getString("c6_feature"))
+            val c7: JSONObject = if (record.isNull("c7_feature")) new JSONObject() else JSON.parseObject(record.getString("c7_feature"))
+            val c8: JSONObject = if (record.isNull("c8_feature")) new JSONObject() else JSON.parseObject(record.getString("c8_feature"))
+
+            // 视频基础信息 v1-待推荐视频，v2-头部视频
+            val v1: JSONObject = if (record.isNull("v1_feature")) new JSONObject() else JSON.parseObject(record.getString("v1_feature"))
+            val v2: JSONObject = if (record.isNull("v2_feature")) new JSONObject() else JSON.parseObject(record.getString("v2_feature"))
+
+            // CF特征
+            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"))
+
+            val bFeatureMap = new util.HashMap[String, util.Map[String, Object]]();
+            bFeatureMap.put("b2", b2);
+            bFeatureMap.put("b3", b3);
+            bFeatureMap.put("b4", b4);
+            bFeatureMap.put("b5", b5);
+            bFeatureMap.put("b6", b6);
+            bFeatureMap.put("b7", b7);
+            bFeatureMap.put("b8", b8);
+            bFeatureMap.put("b9", b9);
+            bFeatureMap.put("b10", b10);
+            bFeatureMap.put("b11", b11);
+            bFeatureMap.put("b13", b13);
+
+            ExtractFeature20250218.handleB1(b1, featureMap)
+            ExtractFeature20250218.handleB2ToB11AndB13(bFeatureMap, featureMap);
+            ExtractFeature20250218.handleB12(b12, featureMap)
+            ExtractFeature20250218.handleC1(c1, featureMap)
+            ExtractFeature20250218.handleC2ToC3(c2, c3, featureMap)
+            ExtractFeature20250218.handleC4(c4, featureMap)
+            ExtractFeature20250218.handleC5ToC6(c5, c6, v1, featureMap)
+
+            val c78Map = ExtractFeature20250218.handleC7ToC8(c7, c8)
+            ExtractFeature20250218.useC7ToC8(c78Map, vid, featureMap)
+
+            ExtractFeature20250218.handleD1(d1, featureMap)
+            ExtractFeature20250218.handleD2(d2, featureMap)
+            ExtractFeature20250218.handleD3(d3, featureMap)
+            ExtractFeature20250218.handleVideoBasicFeature(v1, ts, featureMap)
+            ExtractFeature20250218.handleVideoSimilarity(v1, v2, featureMap)
+
+            //4 处理label信息。
+            val labels = new JSONObject
+            for (labelKey <- List(
+              "is_share", "share_cnt",
+              "is_return_1", "return_1_uv",
+              "is_return_n", "return_n_uv",
+              "is_return_noself", "return_1_uv_noself",
+              "is_return_n_noself", "return_n_uv_noself"
+            )) {
+              if (!record.isNull(labelKey)) {
+                labels.put(labelKey, record.getString(labelKey))
+              }
+            }
+
+            //5 处理log key表头。
+            val logs = new JSONObject()
+            for (key <- List("apptype", "abcode", "mid", "vid", "page", "recommendpagetype", "level", "ts", "headvideoid", "flowpool", "level", "hotsencetype")) {
+              if (!record.isNull(key)) {
+                logs.put(key, record.getString(key))
+              }
+            }
+            logs.put("hour", ExtractorUtils.getHourByTimestamp(ts))
+            logs.put("day_of_week", ExtractorUtils.getDayOfWeekByTimestamp(ts))
+
+            val logKey = logs.toString()
+            val labelKey = labels.toString()
+            val featureKey = featureMap.toString()
+            //6 拼接数据，保存。
+            logKey + "\t" + labelKey + "\t" + featureKey
+
+          })
+        })
+    }
+    }.reduce(_ union _)
+
+    // 4 保存数据到hdfs
+    val hdfsPath = savePath
+    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)
+  }
+}