广告分桶

src/main/resources/20240622_ad_feature_name.txt

@@ -0,0 +1,249 @@
+cpa
+b2_3h_ctr
+b2_3h_ctcvr
+b2_3h_cvr
+b2_3h_conver
+b2_3h_ecpm
+b2_6h_ctr
+b2_6h_ctcvr
+b2_6h_cvr
+b2_6h_conver
+b2_6h_ecpm
+b2_12h_ctr
+b2_12h_ctcvr
+b2_12h_cvr
+b2_12h_conver
+b2_12h_ecpm
+b2_1d_ctr
+b2_1d_ctcvr
+b2_1d_cvr
+b2_1d_conver
+b2_1d_ecpm
+b2_3d_ctr
+b2_3d_ctcvr
+b2_3d_cvr
+b2_3d_conver
+b2_3d_ecpm
+b2_7d_ctr
+b2_7d_ctcvr
+b2_7d_cvr
+b2_7d_conver
+b2_7d_ecpm
+b3_3h_ctr
+b3_3h_ctcvr
+b3_3h_cvr
+b3_3h_conver
+b3_3h_ecpm
+b3_6h_ctr
+b3_6h_ctcvr
+b3_6h_cvr
+b3_6h_conver
+b3_6h_ecpm
+b3_12h_ctr
+b3_12h_ctcvr
+b3_12h_cvr
+b3_12h_conver
+b3_12h_ecpm
+b3_1d_ctr
+b3_1d_ctcvr
+b3_1d_cvr
+b3_1d_conver
+b3_1d_ecpm
+b3_3d_ctr
+b3_3d_ctcvr
+b3_3d_cvr
+b3_3d_conver
+b3_3d_ecpm
+b3_7d_ctr
+b3_7d_ctcvr
+b3_7d_cvr
+b3_7d_conver
+b3_7d_ecpm
+b4_3h_ctr
+b4_3h_ctcvr
+b4_3h_cvr
+b4_3h_conver
+b4_3h_ecpm
+b4_6h_ctr
+b4_6h_ctcvr
+b4_6h_cvr
+b4_6h_conver
+b4_6h_ecpm
+b4_12h_ctr
+b4_12h_ctcvr
+b4_12h_cvr
+b4_12h_conver
+b4_12h_ecpm
+b4_1d_ctr
+b4_1d_ctcvr
+b4_1d_cvr
+b4_1d_conver
+b4_1d_ecpm
+b4_3d_ctr
+b4_3d_ctcvr
+b4_3d_cvr
+b4_3d_conver
+b4_3d_ecpm
+b4_7d_ctr
+b4_7d_ctcvr
+b4_7d_cvr
+b4_7d_conver
+b4_7d_ecpm
+b5_3h_ctr
+b5_3h_ctcvr
+b5_3h_cvr
+b5_3h_conver
+b5_3h_ecpm
+b5_6h_ctr
+b5_6h_ctcvr
+b5_6h_cvr
+b5_6h_conver
+b5_6h_ecpm
+b5_12h_ctr
+b5_12h_ctcvr
+b5_12h_cvr
+b5_12h_conver
+b5_12h_ecpm
+b5_1d_ctr
+b5_1d_ctcvr
+b5_1d_cvr
+b5_1d_conver
+b5_1d_ecpm
+b5_3d_ctr
+b5_3d_ctcvr
+b5_3d_cvr
+b5_3d_conver
+b5_3d_ecpm
+b5_7d_ctr
+b5_7d_ctcvr
+b5_7d_cvr
+b5_7d_conver
+b5_7d_ecpm
+b8_3h_ctr
+b8_3h_ctcvr
+b8_3h_cvr
+b8_3h_conver
+b8_3h_ecpm
+b8_6h_ctr
+b8_6h_ctcvr
+b8_6h_cvr
+b8_6h_conver
+b8_6h_ecpm
+b8_12h_ctr
+b8_12h_ctcvr
+b8_12h_cvr
+b8_12h_conver
+b8_12h_ecpm
+b8_1d_ctr
+b8_1d_ctcvr
+b8_1d_cvr
+b8_1d_conver
+b8_1d_ecpm
+b8_3d_ctr
+b8_3d_ctcvr
+b8_3d_cvr
+b8_3d_conver
+b8_3d_ecpm
+b8_7d_ctr
+b8_7d_ctcvr
+b8_7d_cvr
+b8_7d_conver
+b8_7d_ecpm
+b6_7d_ctr
+b6_7d_ctcvr
+b6_7d_cvr
+b6_7d_conver
+b6_7d_ecpm
+b6_14d_ctr
+b6_14d_ctcvr
+b6_14d_cvr
+b6_14d_conver
+b6_14d_ecpm
+b7_7d_ctr
+b7_7d_ctcvr
+b7_7d_cvr
+b7_7d_conver
+b7_7d_ecpm
+b7_14d_ctr
+b7_14d_ctcvr
+b7_14d_cvr
+b7_14d_conver
+b7_14d_ecpm
+viewAll
+clickAll
+converAll
+incomeAll
+ctr_all
+ctcvr_all
+cvr_all
+ecpm_all
+timediff_view
+timediff_click
+timediff_conver
+actionstatic_view
+actionstatic_click
+actionstatic_conver
+actionstatic_income
+actionstatic_ctr
+actionstatic_ctcvr
+actionstatic_cvr
+e1_tags_3d_matchnum
+e1_tags_3d_maxscore
+e1_tags_3d_avgscore
+e1_tags_7d_matchnum
+e1_tags_7d_maxscore
+e1_tags_7d_avgscore
+e1_tags_14d_matchnum
+e1_tags_14d_maxscore
+e1_tags_14d_avgscore
+e2_tags_3d_matchnum
+e2_tags_3d_maxscore
+e2_tags_3d_avgscore
+e2_tags_7d_matchnum
+e2_tags_7d_maxscore
+e2_tags_7d_avgscore
+e2_tags_14d_matchnum
+e2_tags_14d_maxscore
+e2_tags_14d_avgscore
+d1_feature_3h_ctr
+d1_feature_3h_ctcvr
+d1_feature_3h_cvr
+d1_feature_3h_conver
+d1_feature_3h_ecpm
+d1_feature_6h_ctr
+d1_feature_6h_ctcvr
+d1_feature_6h_cvr
+d1_feature_6h_conver
+d1_feature_6h_ecpm
+d1_feature_12h_ctr
+d1_feature_12h_ctcvr
+d1_feature_12h_cvr
+d1_feature_12h_conver
+d1_feature_12h_ecpm
+d1_feature_1d_ctr
+d1_feature_1d_ctcvr
+d1_feature_1d_cvr
+d1_feature_1d_conver
+d1_feature_1d_ecpm
+d1_feature_3d_ctr
+d1_feature_3d_ctcvr
+d1_feature_3d_cvr
+d1_feature_3d_conver
+d1_feature_3d_ecpm
+d1_feature_7d_ctr
+d1_feature_7d_ctcvr
+d1_feature_7d_cvr
+d1_feature_7d_conver
+d1_feature_7d_ecpm
+vid_rank_ctr_1d
+vid_rank_ctr_3d
+vid_rank_ctr_7d
+vid_rank_ctr_14d
+vid_rank_ctcvr_1d
+vid_rank_ctcvr_3d
+vid_rank_ctcvr_7d
+vid_rank_ctcvr_14d
+vid_rank_ecpm_1d
+vid_rank_ecpm_3d
+vid_rank_ecpm_7d
+vid_rank_ecpm_14d

src/main/scala/com/aliyun/odps/spark/examples/makedata_ad/makedata_32_bucket_20240622.scala

@@ -0,0 +1,94 @@
+package com.aliyun.odps.spark.examples.makedata_ad
+
+import com.alibaba.fastjson.JSON
+import com.aliyun.odps.spark.examples.myUtils.{MyHdfsUtils, ParamUtils}
+import org.apache.hadoop.io.compress.GzipCodec
+import org.apache.spark.sql.SparkSession
+
+import scala.collection.JavaConversions._
+import scala.collection.mutable.ArrayBuffer
+import scala.io.Source
+/*
+
+ */
+
+object makedata_32_bucket_20240622 {
+  def main(args: Array[String]): Unit = {
+
+    val spark = SparkSession
+      .builder()
+      .appName(this.getClass.getName)
+      .getOrCreate()
+    val sc = spark.sparkContext
+
+    val loader = getClass.getClassLoader
+    val resourceUrl = loader.getResource("20240622_ad_feature_name.txt")
+    val content =
+      if (resourceUrl != null) {
+        val content = Source.fromURL(resourceUrl).getLines().mkString("\n")
+        Source.fromURL(resourceUrl).close()
+        content
+      } else {
+        ""
+      }
+    println(content)
+    val contentList = content.split("\n")
+      .map(r=> r.replace(" ", "").replaceAll("\n", ""))
+      .filter(r=> r.nonEmpty).toList
+
+
+
+    // 1 读取参数
+    val param = ParamUtils.parseArgs(args)
+    val readPath = param.getOrElse("readPath", "/dw/recommend/model/31_ad_sample_data/20240620*")
+    val savePath = param.getOrElse("savePath", "/dw/recommend/model/32_bucket_data/")
+    val fileName = param.getOrElse("fileName", "20240620_100")
+    val sampleRate = param.getOrElse("sampleRate", "1.0").toDouble
+    val bucketNum = param.getOrElse("bucketNum", "100").toInt
+
+    val data = sc.textFile(readPath)
+    val data1 = data.map(r => {
+      val rList = r.split("\t")
+      val doubles = JSON.parseObject(rList(2)).mapValues(_.toString.toDouble)
+      doubles
+    }).sample(false, sampleRate ).repartition(20)
+
+    val result = new ArrayBuffer[String]()
+
+    for (i <- contentList.indices){
+      println("特征:" + contentList(i))
+      val data2 = data1.map(r => r.getOrDefault(contentList(i), 0D)).filter(_ > 1E-8).collect().sorted
+      val len = data2.length
+      val oneBucketNum = (len - 1) / (bucketNum - 1) + 1 // 确保每个桶至少有一个元素
+      val buffers = new ArrayBuffer[Double]()
+
+      var lastBucketValue = data2(0) // 记录上一个桶的切分点
+      for (j <- 0 until len by oneBucketNum) {
+        val d = data2(j)
+        if (j > 0 && d != lastBucketValue) {
+          // 如果当前切分点不同于上一个切分点，则保存当前切分点
+          buffers += d
+        }
+        lastBucketValue = d // 更新上一个桶的切分点
+      }
+
+      // 最后一个桶的结束点应该是数组的最后一个元素
+      if (!buffers.contains(data2.last)) {
+        buffers += data2.last
+      }
+      result.add(contentList(i) + "\t" + bucketNum.toString + "\t" + buffers.mkString(","))
+    }
+    val data3 = sc.parallelize(result)
+
+
+    // 4 保存数据到hdfs
+    val hdfsPath = savePath + "/" + fileName
+    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)
+      data3.repartition(1).saveAsTextFile(hdfsPath, classOf[GzipCodec])
+    } else {
+      println("路径不合法，无法写入:" + hdfsPath)
+    }
+  }
+}

src/main/scala/com/aliyun/odps/spark/examples/临时记录的脚本-广告

@@ -2,34 +2,24 @@
 
 
 nohup /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.makedata_ad_31_originData_20240620 \
+--class com.aliyun.odps.spark.examples.makedata_ad.makedata_ad_31_originData_20240620 \
 --master yarn --driver-memory 1G --executor-memory 2G --executor-cores 1 --num-executors 16 \
 ./target/spark-examples-1.0.0-SNAPSHOT-shaded.jar \
 tablePart:64 repartition:32 \
-beginStr:2024062008 endStr:2024062008 \
+beginStr:2024062009 endStr:2024062023 \
 savePath:/dw/recommend/model/31_ad_sample_data/ \
 table:alg_recsys_ad_sample_all \
 > p31_2024062008.log 2>&1 &
 
 
-nohup /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.makedata_14_valueData_20240608 \
---master yarn --driver-memory 1G --executor-memory 3G --executor-cores 1 --num-executors 32 \
-./target/spark-examples-1.0.0-SNAPSHOT-shaded.jar \
-readPath:/dw/recommend/model/13_sample_data/ \
-savePath:/dw/recommend/model/14_feature_data/ \
-beginStr:20240615 endStr:20240615 repartition:1000 \
-> p14_data_check.log 2>&1 &
 
 
 nohup /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.makedata_15_bucket_20240608 \
+--class com.aliyun.odps.spark.examples.makedata.makedata_32_bucket_20240622 \
 --master yarn --driver-memory 16G --executor-memory 1G --executor-cores 1 --num-executors 16 \
 --conf spark.driver.maxResultSize=16G \
 ./target/spark-examples-1.0.0-SNAPSHOT-shaded.jar \
-readPath:/dw/recommend/model/14_feature_data/20240606/ fileName:20240606_200_v3 \
-bucketNum:200 sampleRate:0.1 \
-> p15_data2.log 2>&1 &
+> p32_data.log 2>&1 &
 
 
 nohup /opt/apps/SPARK2/spark-2.4.8-hadoop3.2-1.0.8/bin/spark-class2 org.apache.spark.deploy.SparkSubmit \