个人记录

src/main/scala/com/aliyun/odps/spark/examples/makedata/makedata_17_bucketDataPrint_20240617.scala

@@ -34,6 +34,7 @@ object makedata_17_bucketDataPrint_20240617 {
     val project = param.getOrElse("project", "loghubods")
     val table = param.getOrElse("table", "alg_recsys_sample_all_new")
     val repartition = param.getOrElse("repartition", "32").toInt
+    val readDate = param.getOrElse("readDate", "20240615")
 
 
     val loader = getClass.getClassLoader
@@ -74,202 +75,201 @@ object makedata_17_bucketDataPrint_20240617 {
     // 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"
-      println("开始执行partiton:" + partition)
-      val odpsData = odpsOps.readTable(project = project,
-        table = table,
-        partition = partition,
-        transfer = func,
-        numPartition = tablePart)
-        .map(record => {
-          val featureMap = new JSONObject()
-
-          // 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 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"))
-          val b17: JSONObject = if (record.isNull("b17_feature")) new JSONObject() else
-            JSON.parseObject(record.getString("b17_feature"))
-          val b18: JSONObject = if (record.isNull("b18_feature")) new JSONObject() else
-            JSON.parseObject(record.getString("b18_feature"))
-          val b19: JSONObject = if (record.isNull("b19_feature")) new JSONObject() else
-            JSON.parseObject(record.getString("b19_feature"))
-
-
-          val origin_data = List(
-            (b1, b2, b3, "b123"), (b1, b6, b7, "b167"),
-            (b8, b9, b10, "b8910"), (b11, b12, b13, "b111213"),
-            (b17, b18, b19, "b171819")
-          )
-          for ((b_1, b_2, b_3, prefix1) <- origin_data) {
-            for (prefix2 <- List(
-              "1h", "2h", "3h", "4h", "12h", "1d", "3d", "7d"
-            )) {
-              val exp = if (b_1.isEmpty) 0D else b_1.getIntValue("exp_pv_" + prefix2).toDouble
-              val share = if (b_2.isEmpty) 0D else b_2.getIntValue("share_pv_" + prefix2).toDouble
-              val returns = if (b_3.isEmpty) 0D else b_3.getIntValue("return_uv_" + prefix2).toDouble
-              val f1 = RankExtractorFeature_20240530.calDiv(share, exp)
-              val f2 = RankExtractorFeature_20240530.calLog(share)
-              val f3 = RankExtractorFeature_20240530.calDiv(returns, exp)
-              val f4 = RankExtractorFeature_20240530.calLog(returns)
-              val f5 = f3 * f4
-              featureMap.put(prefix1 + "_" + prefix2 + "_" + "STR", f1)
-              featureMap.put(prefix1 + "_" + prefix2 + "_" + "log(share)", f2)
-              featureMap.put(prefix1 + "_" + prefix2 + "_" + "ROV", f3)
-              featureMap.put(prefix1 + "_" + prefix2 + "_" + "log(return)", f4)
-              featureMap.put(prefix1 + "_" + prefix2 + "_" + "ROV*log(return)", f5)
-            }
-          }
-
-          val video_info: JSONObject = if (record.isNull("t_v_info_feature")) new JSONObject() else
-            JSON.parseObject(record.getString("t_v_info_feature"))
-          featureMap.put("total_time", if (video_info.containsKey("total_time")) video_info.getIntValue("total_time").toDouble else 0D)
-          featureMap.put("bit_rate", if (video_info.containsKey("bit_rate")) video_info.getIntValue("bit_rate").toDouble else 0D)
-
-          val c1: JSONObject = if (record.isNull("c1_feature")) new JSONObject() else
-            JSON.parseObject(record.getString("c1_feature"))
-          if (c1.nonEmpty) {
-            featureMap.put("playcnt_6h", if (c1.containsKey("playcnt_6h")) c1.getIntValue("playcnt_6h").toDouble else 0D)
-            featureMap.put("playcnt_1d", if (c1.containsKey("playcnt_1d")) c1.getIntValue("playcnt_1d").toDouble else 0D)
-            featureMap.put("playcnt_3d", if (c1.containsKey("playcnt_3d")) c1.getIntValue("playcnt_3d").toDouble else 0D)
-            featureMap.put("playcnt_7d", if (c1.containsKey("playcnt_7d")) c1.getIntValue("playcnt_7d").toDouble else 0D)
-          }
-          val c2: JSONObject = if (record.isNull("c2_feature")) new JSONObject() else
-            JSON.parseObject(record.getString("c2_feature"))
-          if (c2.nonEmpty) {
-            featureMap.put("share_pv_12h", if (c2.containsKey("share_pv_12h")) c2.getIntValue("share_pv_12h").toDouble else 0D)
-            featureMap.put("share_pv_1d", if (c2.containsKey("share_pv_1d")) c2.getIntValue("share_pv_1d").toDouble else 0D)
-            featureMap.put("share_pv_3d", if (c2.containsKey("share_pv_3d")) c2.getIntValue("share_pv_3d").toDouble else 0D)
-            featureMap.put("share_pv_7d", if (c2.containsKey("share_pv_7d")) c2.getIntValue("share_pv_7d").toDouble else 0D)
-            featureMap.put("return_uv_12h", if (c2.containsKey("return_uv_12h")) c2.getIntValue("return_uv_12h").toDouble else 0D)
-            featureMap.put("return_uv_1d", if (c2.containsKey("return_uv_1d")) c2.getIntValue("return_uv_1d").toDouble else 0D)
-            featureMap.put("return_uv_3d", if (c2.containsKey("return_uv_3d")) c2.getIntValue("return_uv_3d").toDouble else 0D)
-            featureMap.put("return_uv_7d", if (c2.containsKey("return_uv_7d")) c2.getIntValue("return_uv_7d").toDouble else 0D)
-          }
-
-          val title = if (video_info.containsKey("title")) video_info.getString("title") else ""
-          if (!title.equals("")) {
-            for (key_feature <- List("c3_feature", "c4_feature", "c5_feature", "c6_feature", "c7_feature")) {
-              val c34567: JSONObject = if (record.isNull(key_feature)) new JSONObject() else
-                JSON.parseObject(record.getString(key_feature))
-              for (key_time <- List("tags_1d", "tags_3d", "tags_7d")) {
-                val tags = if (c34567.containsKey(key_time)) c34567.getString(key_time) else ""
-                if (!tags.equals("")) {
-                  val (f1, f2, f3, f4) = funcC34567ForTags(tags, title)
-                  featureMap.put(key_feature + "_" + key_time + "_matchnum", f1)
-                  featureMap.put(key_feature + "_" + key_time + "_maxscore", f3)
-                  featureMap.put(key_feature + "_" + key_time + "_avgscore", f4)
-                }
-              }
-            }
-          }
-
-          val vid = if (record.isNull("vid")) "" else record.getString("vid")
-          if (!vid.equals("")) {
-            for (key_feature <- List("c8_feature", "c9_feature")) {
-              val c89: JSONObject = if (record.isNull(key_feature)) new JSONObject() else
-                JSON.parseObject(record.getString(key_feature))
-              for (key_action <- List("share", "return")) {
-                val cfListStr = if (c89.containsKey(key_action)) c89.getString(key_action) else ""
-                if (!cfListStr.equals("")) {
-                  val cfMap = cfListStr.split(",").map(r => {
-                    val rList = r.split(":")
-                    (rList(0), (rList(1), rList(2), rList(3)))
-                  }).toMap
-                  if (cfMap.contains(vid)) {
-                    val (score, num, rank) = cfMap(vid)
-                    featureMap.put(key_feature + "_" + key_action + "_score", score.toDouble)
-                    featureMap.put(key_feature + "_" + key_action + "_num", num.toDouble)
-                    featureMap.put(key_feature + "_" + key_action + "_rank", 1.0 / rank.toDouble)
-                  }
-                }
-              }
-            }
-          }
-
-          val d1: JSONObject = if (record.isNull("d1_feature")) new JSONObject() else
-            JSON.parseObject(record.getString("d1_feature"))
-          if (d1.nonEmpty) {
-            featureMap.put("d1_exp", if (d1.containsKey("exp")) d1.getString("exp").toDouble else 0D)
-            featureMap.put("d1_return_n", if (d1.containsKey("return_n")) d1.getString("return_n").toDouble else 0D)
-            featureMap.put("d1_rovn", if (d1.containsKey("rovn")) d1.getString("rovn").toDouble else 0D)
-          }
-
-
-
-          val allfeaturemap = if (record.isNull("allfeaturemap")) new JSONObject() else
-            JSON.parseObject(record.getString("allfeaturemap"))
-//          val featuresStr = allfeaturemap.toMap.map(r=> r._1 + ":" + r._2.toString).toSeq
-          val apptype = record.getString("apptype")
-          val pagesource = record.getString("pagesource")
-          val abcode = record.getString("abcode")
-          val level = if (record.isNull("level")) "0" else record.getString("level")
-          val label = record.getString("is_return")
-          (apptype, pagesource, level, label, abcode, allfeaturemap, featureMap)
-        }).filter{
-          case (apptype, pagesource, level, label, abcode, allfeaturemap, featureMap) =>
-            apptype.equals("3") && pagesource.endsWith("recommend") &&
-            Set("ab0", "ab1", "ab2", "ab3").contains(abcode) && level.equals("0")
-        }.mapPartitions(row => {
-          val result = new ArrayBuffer[String]()
-          val bucketsMap = bucketsMap_br.value
-          row.foreach {
-            case (apptype, pagesource, level, label, abcode, allfeaturemap, featureMap) =>
-              val offlineFeatrueMap = featureMap.filter(r => bucketsMap.containsKey(r._1)).map(r =>{
-                val score = r._2.toString.toDouble
-                if (score > 1E-8) {
-                  val (bucketNum, buckets) = bucketsMap(r._1)
-                  val scoreNew = 1.0 / bucketNum * (ExtractorUtils.findInsertPosition(buckets, score).toDouble + 1.0)
-                  r._1 + ":" + scoreNew.toString
-                } else {
-                  ""
-                }
-              }).filter(_.nonEmpty)
-              result.add((apptype, pagesource, level, label, abcode, allfeaturemap.toString, offlineFeatrueMap.iterator.mkString(","))
-              .productIterator.mkString("\t"))
-          }
-          result.iterator
-        })
-
-      // 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)
-      }
-    }
-    // 合并一天数据
-
-    val data2 = sc.textFile(savePath + "/20240615*").mapPartitions(row=>{
+//    // 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"
+//      println("开始执行partiton:" + partition)
+//      val odpsData = odpsOps.readTable(project = project,
+//        table = table,
+//        partition = partition,
+//        transfer = func,
+//        numPartition = tablePart)
+//        .map(record => {
+//          val featureMap = new JSONObject()
+//
+//          // 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 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"))
+//          val b17: JSONObject = if (record.isNull("b17_feature")) new JSONObject() else
+//            JSON.parseObject(record.getString("b17_feature"))
+//          val b18: JSONObject = if (record.isNull("b18_feature")) new JSONObject() else
+//            JSON.parseObject(record.getString("b18_feature"))
+//          val b19: JSONObject = if (record.isNull("b19_feature")) new JSONObject() else
+//            JSON.parseObject(record.getString("b19_feature"))
+//
+//
+//          val origin_data = List(
+//            (b1, b2, b3, "b123"), (b1, b6, b7, "b167"),
+//            (b8, b9, b10, "b8910"), (b11, b12, b13, "b111213"),
+//            (b17, b18, b19, "b171819")
+//          )
+//          for ((b_1, b_2, b_3, prefix1) <- origin_data) {
+//            for (prefix2 <- List(
+//              "1h", "2h", "3h", "4h", "12h", "1d", "3d", "7d"
+//            )) {
+//              val exp = if (b_1.isEmpty) 0D else b_1.getIntValue("exp_pv_" + prefix2).toDouble
+//              val share = if (b_2.isEmpty) 0D else b_2.getIntValue("share_pv_" + prefix2).toDouble
+//              val returns = if (b_3.isEmpty) 0D else b_3.getIntValue("return_uv_" + prefix2).toDouble
+//              val f1 = RankExtractorFeature_20240530.calDiv(share, exp)
+//              val f2 = RankExtractorFeature_20240530.calLog(share)
+//              val f3 = RankExtractorFeature_20240530.calDiv(returns, exp)
+//              val f4 = RankExtractorFeature_20240530.calLog(returns)
+//              val f5 = f3 * f4
+//              featureMap.put(prefix1 + "_" + prefix2 + "_" + "STR", f1)
+//              featureMap.put(prefix1 + "_" + prefix2 + "_" + "log(share)", f2)
+//              featureMap.put(prefix1 + "_" + prefix2 + "_" + "ROV", f3)
+//              featureMap.put(prefix1 + "_" + prefix2 + "_" + "log(return)", f4)
+//              featureMap.put(prefix1 + "_" + prefix2 + "_" + "ROV*log(return)", f5)
+//            }
+//          }
+//
+//          val video_info: JSONObject = if (record.isNull("t_v_info_feature")) new JSONObject() else
+//            JSON.parseObject(record.getString("t_v_info_feature"))
+//          featureMap.put("total_time", if (video_info.containsKey("total_time")) video_info.getIntValue("total_time").toDouble else 0D)
+//          featureMap.put("bit_rate", if (video_info.containsKey("bit_rate")) video_info.getIntValue("bit_rate").toDouble else 0D)
+//
+//          val c1: JSONObject = if (record.isNull("c1_feature")) new JSONObject() else
+//            JSON.parseObject(record.getString("c1_feature"))
+//          if (c1.nonEmpty) {
+//            featureMap.put("playcnt_6h", if (c1.containsKey("playcnt_6h")) c1.getIntValue("playcnt_6h").toDouble else 0D)
+//            featureMap.put("playcnt_1d", if (c1.containsKey("playcnt_1d")) c1.getIntValue("playcnt_1d").toDouble else 0D)
+//            featureMap.put("playcnt_3d", if (c1.containsKey("playcnt_3d")) c1.getIntValue("playcnt_3d").toDouble else 0D)
+//            featureMap.put("playcnt_7d", if (c1.containsKey("playcnt_7d")) c1.getIntValue("playcnt_7d").toDouble else 0D)
+//          }
+//          val c2: JSONObject = if (record.isNull("c2_feature")) new JSONObject() else
+//            JSON.parseObject(record.getString("c2_feature"))
+//          if (c2.nonEmpty) {
+//            featureMap.put("share_pv_12h", if (c2.containsKey("share_pv_12h")) c2.getIntValue("share_pv_12h").toDouble else 0D)
+//            featureMap.put("share_pv_1d", if (c2.containsKey("share_pv_1d")) c2.getIntValue("share_pv_1d").toDouble else 0D)
+//            featureMap.put("share_pv_3d", if (c2.containsKey("share_pv_3d")) c2.getIntValue("share_pv_3d").toDouble else 0D)
+//            featureMap.put("share_pv_7d", if (c2.containsKey("share_pv_7d")) c2.getIntValue("share_pv_7d").toDouble else 0D)
+//            featureMap.put("return_uv_12h", if (c2.containsKey("return_uv_12h")) c2.getIntValue("return_uv_12h").toDouble else 0D)
+//            featureMap.put("return_uv_1d", if (c2.containsKey("return_uv_1d")) c2.getIntValue("return_uv_1d").toDouble else 0D)
+//            featureMap.put("return_uv_3d", if (c2.containsKey("return_uv_3d")) c2.getIntValue("return_uv_3d").toDouble else 0D)
+//            featureMap.put("return_uv_7d", if (c2.containsKey("return_uv_7d")) c2.getIntValue("return_uv_7d").toDouble else 0D)
+//          }
+//
+//          val title = if (video_info.containsKey("title")) video_info.getString("title") else ""
+//          if (!title.equals("")) {
+//            for (key_feature <- List("c3_feature", "c4_feature", "c5_feature", "c6_feature", "c7_feature")) {
+//              val c34567: JSONObject = if (record.isNull(key_feature)) new JSONObject() else
+//                JSON.parseObject(record.getString(key_feature))
+//              for (key_time <- List("tags_1d", "tags_3d", "tags_7d")) {
+//                val tags = if (c34567.containsKey(key_time)) c34567.getString(key_time) else ""
+//                if (!tags.equals("")) {
+//                  val (f1, f2, f3, f4) = funcC34567ForTags(tags, title)
+//                  featureMap.put(key_feature + "_" + key_time + "_matchnum", f1)
+//                  featureMap.put(key_feature + "_" + key_time + "_maxscore", f3)
+//                  featureMap.put(key_feature + "_" + key_time + "_avgscore", f4)
+//                }
+//              }
+//            }
+//          }
+//
+//          val vid = if (record.isNull("vid")) "" else record.getString("vid")
+//          if (!vid.equals("")) {
+//            for (key_feature <- List("c8_feature", "c9_feature")) {
+//              val c89: JSONObject = if (record.isNull(key_feature)) new JSONObject() else
+//                JSON.parseObject(record.getString(key_feature))
+//              for (key_action <- List("share", "return")) {
+//                val cfListStr = if (c89.containsKey(key_action)) c89.getString(key_action) else ""
+//                if (!cfListStr.equals("")) {
+//                  val cfMap = cfListStr.split(",").map(r => {
+//                    val rList = r.split(":")
+//                    (rList(0), (rList(1), rList(2), rList(3)))
+//                  }).toMap
+//                  if (cfMap.contains(vid)) {
+//                    val (score, num, rank) = cfMap(vid)
+//                    featureMap.put(key_feature + "_" + key_action + "_score", score.toDouble)
+//                    featureMap.put(key_feature + "_" + key_action + "_num", num.toDouble)
+//                    featureMap.put(key_feature + "_" + key_action + "_rank", 1.0 / rank.toDouble)
+//                  }
+//                }
+//              }
+//            }
+//          }
+//
+//          val d1: JSONObject = if (record.isNull("d1_feature")) new JSONObject() else
+//            JSON.parseObject(record.getString("d1_feature"))
+//          if (d1.nonEmpty) {
+//            featureMap.put("d1_exp", if (d1.containsKey("exp")) d1.getString("exp").toDouble else 0D)
+//            featureMap.put("d1_return_n", if (d1.containsKey("return_n")) d1.getString("return_n").toDouble else 0D)
+//            featureMap.put("d1_rovn", if (d1.containsKey("rovn")) d1.getString("rovn").toDouble else 0D)
+//          }
+//
+//
+//
+//          val allfeaturemap = if (record.isNull("allfeaturemap")) new JSONObject() else
+//            JSON.parseObject(record.getString("allfeaturemap"))
+////          val featuresStr = allfeaturemap.toMap.map(r=> r._1 + ":" + r._2.toString).toSeq
+//          val apptype = record.getString("apptype")
+//          val pagesource = record.getString("pagesource")
+//          val abcode = record.getString("abcode")
+//          val level = if (record.isNull("level")) "0" else record.getString("level")
+//          val label = record.getString("is_return")
+//          (apptype, pagesource, level, label, abcode, allfeaturemap, featureMap)
+//        }).filter{
+//          case (apptype, pagesource, level, label, abcode, allfeaturemap, featureMap) =>
+//            apptype.equals("3") && pagesource.endsWith("recommend") &&
+//            Set("ab0", "ab1", "ab2", "ab3").contains(abcode) && level.equals("0")
+//        }.mapPartitions(row => {
+//          val result = new ArrayBuffer[String]()
+//          val bucketsMap = bucketsMap_br.value
+//          row.foreach {
+//            case (apptype, pagesource, level, label, abcode, allfeaturemap, featureMap) =>
+//              val offlineFeatrueMap = featureMap.filter(r => bucketsMap.containsKey(r._1)).map(r =>{
+//                val score = r._2.toString.toDouble
+//                if (score > 1E-8) {
+//                  val (bucketNum, buckets) = bucketsMap(r._1)
+//                  val scoreNew = 1.0 / bucketNum * (ExtractorUtils.findInsertPosition(buckets, score).toDouble + 1.0)
+//                  r._1 + ":" + scoreNew.toString
+//                } else {
+//                  ""
+//                }
+//              }).filter(_.nonEmpty)
+//              result.add((apptype, pagesource, level, label, abcode, allfeaturemap.toString, offlineFeatrueMap.iterator.mkString(","))
+//              .productIterator.mkString("\t"))
+//          }
+//          result.iterator
+//        })
+//
+//      // 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)
+//      }
+//    }
+
+    val data2 = sc.textFile(savePath + "/" + readDate + "*").mapPartitions(row=>{
       val result = new ArrayBuffer[(String, Map[String, String], Map[String, String], List[String], List[String])]()
       val contentList = contentList_br.value
       row.foreach(r=>{
@@ -319,7 +319,7 @@ object makedata_17_bucketDataPrint_20240617 {
       result.iterator
     })
 
-    val saveV1 = "/dw/recommend/model/17_for_check_v1/20240615/"
+    val saveV1 = "/dw/recommend/model/17_for_check_v1/" + readDate
     if (saveV1.nonEmpty && saveV1.startsWith("/dw/recommend/model/")) {
       println("删除路径并开始数据写入:" + saveV1)
       MyHdfsUtils.delete_hdfs_path(saveV1)
@@ -328,7 +328,7 @@ object makedata_17_bucketDataPrint_20240617 {
       println("路径不合法，无法写入:" + saveV1)
     }
 
-    val saveV2 = "/dw/recommend/model/17_for_check_v2/20240615/"
+    val saveV2 = "/dw/recommend/model/17_for_check_v2/" + readDate
     if (saveV2.nonEmpty && saveV2.startsWith("/dw/recommend/model/")) {
       println("删除路径并开始数据写入:" + saveV2)
       MyHdfsUtils.delete_hdfs_path(saveV2)
@@ -337,7 +337,7 @@ object makedata_17_bucketDataPrint_20240617 {
       println("路径不合法，无法写入:" + saveV2)
     }
 
-    val saveV3 = "/dw/recommend/model/17_for_check_v3/20240615/"
+    val saveV3 = "/dw/recommend/model/17_for_check_v3/" + readDate
     if (saveV3.nonEmpty && saveV3.startsWith("/dw/recommend/model/")) {
       println("删除路径并开始数据写入:" + saveV3)
       MyHdfsUtils.delete_hdfs_path(saveV3)
@@ -346,7 +346,7 @@ object makedata_17_bucketDataPrint_20240617 {
       println("路径不合法，无法写入:" + saveV3)
     }
 
-    val saveV4 = "/dw/recommend/model/17_for_check_v4/20240615/"
+    val saveV4 = "/dw/recommend/model/17_for_check_v4/" + readDate
     if (saveV4.nonEmpty && saveV4.startsWith("/dw/recommend/model/")) {
       println("删除路径并开始数据写入:" + saveV4)
       MyHdfsUtils.delete_hdfs_path(saveV4)

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

@@ -156,4 +156,5 @@ nohup /opt/apps/SPARK2/spark-2.4.8-hadoop3.2-1.0.8/bin/spark-class2 org.apache.s
 --class com.aliyun.odps.spark.examples.makedata.makedata_17_bucketDataPrint_20240617 \
 --master yarn --driver-memory 2G --executor-memory 4G --executor-cores 1 --num-executors 16 \
 ./target/spark-examples-1.0.0-SNAPSHOT-shaded.jar \
+beginStr:2024061800 endStr:2024061814 \
 > p17_data_check.log 2>&1 &