Add train_01_xgb_ad_20250104: support negative sampling

recommend-model-produce/src/main/scala/com/tzld/piaoquan/recommend/model/train_01_xgb_ad_20250104.scala

@@ -0,0 +1,166 @@
+package com.tzld.piaoquan.recommend.model
+
+import ml.dmlc.xgboost4j.scala.spark.{XGBoostClassificationModel, XGBoostClassifier}
+import org.apache.commons.lang.math.NumberUtils
+import org.apache.commons.lang3.StringUtils
+import org.apache.hadoop.io.compress.GzipCodec
+import org.apache.spark.ml.evaluation.BinaryClassificationEvaluator
+import org.apache.spark.ml.feature.VectorAssembler
+import org.apache.spark.rdd.RDD
+import org.apache.spark.sql.types.DataTypes
+import org.apache.spark.sql.{Dataset, Row, SparkSession}
+
+import java.util
+import scala.io.Source
+import scala.util.Random
+
+object train_01_xgb_ad_20250104 {
+  def main(args: Array[String]): Unit = {
+    val spark = SparkSession
+      .builder()
+      .appName(this.getClass.getName)
+      .getOrCreate()
+    val sc = spark.sparkContext
+
+    val param = ParamUtils.parseArgs(args)
+    val featureFile = param.getOrElse("featureFile", "20240703_ad_feature_name.txt")
+    val trainPath = param.getOrElse("trainPath", "/dw/recommend/model/33_ad_train_data_v4/20240724")
+    val testPath = param.getOrElse("testPath", "/dw/recommend/model/33_ad_train_data_v4/20240725")
+    val savePath = param.getOrElse("savePath", "/dw/recommend/model/34_ad_predict_data/")
+    val featureFilter = param.getOrElse("featureFilter", "XXXXXX").split(",")
+    val eta = param.getOrElse("eta", "0.01").toDouble
+    val gamma = param.getOrElse("gamma", "0.0").toDouble
+    val max_depth = param.getOrElse("max_depth", "5").toInt
+    val num_round = param.getOrElse("num_round", "100").toInt
+    val num_worker = param.getOrElse("num_worker", "20").toInt
+    val func_object = param.getOrElse("func_object", "binary:logistic")
+    val func_metric = param.getOrElse("func_metric", "auc")
+    val repartition = param.getOrElse("repartition", "20").toInt
+    val negSampleRate = param.getOrElse("negSampleRate", "1").toDouble
+
+    val loader = getClass.getClassLoader
+    val resourceUrl = loader.getResource(featureFile)
+    val content =
+      if (resourceUrl != null) {
+        val content = Source.fromURL(resourceUrl).getLines().mkString("\n")
+        Source.fromURL(resourceUrl).close()
+        content
+      } else {
+        ""
+      }
+    println(content)
+
+    val features = content.split("\n")
+      .map(r => r.replace(" ", "").replaceAll("\n", ""))
+      .filter(r => r.nonEmpty || !featureFilter.contains(r))
+    println("features.size=" + features.length)
+
+    var fields = Array(
+      DataTypes.createStructField("label", DataTypes.IntegerType, true)
+    ) ++ features.map(f => DataTypes.createStructField(f, DataTypes.DoubleType, true))
+    fields = fields ++ Array(
+      DataTypes.createStructField("logKey", DataTypes.StringType, true)
+    )
+    val schema = DataTypes.createStructType(fields)
+
+    val trainData = createData4Ad(
+      sc.textFile(trainPath),
+      features,
+      negSampleRate
+    )
+    println("path %s, train data size：%d".format(trainPath, trainData.count()))
+    val trainDataSet: Dataset[Row] = spark.createDataFrame(trainData, schema)
+    val vectorAssembler = new VectorAssembler().setInputCols(features).setOutputCol("features")
+    val xgbInput = vectorAssembler.transform(trainDataSet).select("features", "label")
+
+    val xgbClassifier = new XGBoostClassifier()
+      .setEta(eta)
+      .setGamma(gamma)
+      .setMissing(0.0f)
+      .setMaxDepth(max_depth)
+      .setNumRound(num_round)
+      .setSubsample(0.8)
+      .setColsampleBytree(0.8)
+      .setScalePosWeight(1)
+      .setObjective(func_object)
+      .setEvalMetric(func_metric)
+      .setFeaturesCol("features")
+      .setLabelCol("label")
+      .setNthread(1)
+      .setNumWorkers(num_worker)
+      .setSeed(2024)
+      .setMinChildWeight(1)
+    val model = xgbClassifier.fit(xgbInput)
+
+    val testData = createData4Ad(
+      sc.textFile(testPath),
+      features
+    )
+    val testDataSet = spark.createDataFrame(testData, schema)
+    val testDataSetTrans = vectorAssembler.transform(testDataSet).select("features","label", "logKey")
+    val predictions = model.transform(testDataSetTrans)
+    println("columns:" + predictions.columns.mkString(","))
+    val saveData = predictions.select("label", "rawPrediction", "probability", "logKey").rdd
+      .map(r =>{
+        (r.get(0), r.get(1), r.get(2), r.get(3)).productIterator.mkString("\t")
+    })
+    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)
+      saveData.repartition(repartition).saveAsTextFile(hdfsPath, classOf[GzipCodec])
+    } else {
+      println("路径不合法，无法写入:" + hdfsPath)
+    }
+
+    val evaluator = new BinaryClassificationEvaluator()
+      .setLabelCol("label")
+      .setRawPredictionCol("probability")
+      .setMetricName("areaUnderROC")
+    val auc = evaluator.evaluate(predictions.select("label", "probability"))
+    println("auc:" + auc)
+
+    // 统计分cid的分数
+    sc.textFile(hdfsPath).map(r=>{
+      val rList = r.split("\t")
+      val cid = rList(3)
+      val score = rList(2).replace("[", "").replace("]", "")
+        .split(",")(1).toDouble
+      val label = rList(0).toDouble
+      (cid, (1, label, score))
+    }).reduceByKey{
+      case (a, b) => (a._1 + b._1, a._2 + b._2, a._3 + b._3)
+    }.map{
+      case (cid, (all, zheng, scores)) =>
+        (cid, all, zheng, scores, zheng / all, scores / all)
+    }.collect().sortBy(_._1).map(_.productIterator.mkString("\t")).foreach(println)
+
+  }
+
+  def createData4Ad(data: RDD[String], features: Array[String], negativeSampleRate: Double = 1): RDD[Row] = {
+    data.map(r => (r, r.split("\t", 2)(0).toInt, Random.nextDouble()))
+      .filter(r => r._3 < negativeSampleRate || r._2 > 0)
+      .map(r => r._1)
+      .map(r => {
+      val line: Array[String] = StringUtils.split(r, '\t')
+      val label: Int = NumberUtils.toInt(line(0))
+      val map: util.Map[String, Double] = new util.HashMap[String, Double]
+      var cid = "-1"
+      for (i <- 1 until line.length) {
+        val fv: Array[String] = StringUtils.split(line(i), ':')
+        map.put(fv(0), NumberUtils.toDouble(fv(1), 0.0))
+        if (fv(0).startsWith("cid_")) {
+          cid = fv(0).split("_")(1)
+        }
+      }
+
+      val v: Array[Any] = new Array[Any](features.length + 2)
+      v(0) = label
+      for (i <- features.indices) {
+        v(i + 1) = map.getOrDefault(features(i), 0.0d)
+      }
+      v(features.length + 1) = cid
+      Row(v: _*)
+    })
+  }
+}