feat:修改hotscenetype特征获取

recommend/00_train_data_make.sh

@@ -42,15 +42,7 @@ for dt in "${dts[@]}"; do
     /root/zhaohp/recommend-emr-dataprocess/target/spark-examples-1.0.0-SNAPSHOT-shaded.jar \
     readPath:/dw/recommend/model/41_recsys_origin_date/${dt}*/* \
     savePath:/dw/recommend/model/41_recsys_sample_data/${dt} \
-    fuSampleRate:0.05 whatLabel:is_share repartition:64
+    fuSampleRate:1 whatLabel:is_share repartition:64
 
     echo "${dt} 负样本采样完成"
-
-    /opt/apps/SPARK2/spark-2.4.8-hadoop3.2-1.0.8/bin/spark-class2 org.apache.spark.deploy.SparkSubmit \
-    --class com.aliyun.odps.spark.examples.makedata_recsys.v20250218.makedata_recsys_43_bucketData_20250218 \
-    --master yarn --driver-memory 4G --executor-memory 8G --executor-cores 1 --num-executors 16 \
-    /root/zhaohp/recommend-emr-dataprocess/target/spark-examples-1.0.0-SNAPSHOT-shaded.jar \
-    readPath:/dw/recommend/model/41_recsys_sample_data/ \
-    savePath:/dw/recommend/model/43_recsys_train_data_20250218/ \
-    beginStr:${dt} endStr:${dt} whatLabel:is_share fileName:20250218_bucket_322.txt &
 done

src/main/scala/com/aliyun/odps/spark/examples/makedata_recsys/v20250218/makedata_recsys_41_ros_train_filter_20250304.scala

@@ -0,0 +1,84 @@
+package com.aliyun.odps.spark.examples.makedata_recsys.v20250218
+
+import com.alibaba.fastjson.JSON
+import com.aliyun.odps.TableSchema
+import com.aliyun.odps.data.Record
+import com.aliyun.odps.spark.examples.myUtils.{MyHdfsUtils, ParamUtils}
+import examples.utils.StatisticsUtil
+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
+
+/*
+   20250218 ROS训练数据过滤
+ */
+
+object makedata_recsys_41_ros_train_filter_20250304 {
+  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 repartition = param.getOrElse("repartition", "32").toInt
+    val readPath = param.getOrElse("readPath", "/dw/recommend/model/41_recsys_origin_date/20250221*/*")
+    val savePath = param.getOrElse("savePath", "/dw/recommend/model/41_recsys_ros_train_data/20250221")
+    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
+
+    val data = sc.textFile(readPath)
+      .filter(line => {
+        val rLine = line.split("\t")
+        val logJson = JSON.parseObject(rLine(0))
+        val page = logJson.getString("page")
+        val recommendPageType = logJson.getString("recommendpagetype")
+
+        val labelJson = JSON.parseObject(rLine(1))
+        val label = labelJson.getString(whatLabel)
+
+        whatApps.contains(logJson.getString("apptype")) && StatisticsUtil.isRecommendScene(page, recommendPageType) && "1".equals(label)
+      })
+      .map { line => line }
+
+    // 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)
+      data.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)
+  }
+}