|
@@ -33,12 +33,12 @@ object makedata_ad_33_bucketData_20240726 {
|
|
|
val repartition = param.getOrElse("repartition", "100").toInt
|
|
|
val filterNames = param.getOrElse("filterNames", "").split(",").toSet
|
|
|
val whatLabel = param.getOrElse("whatLabel", "ad_is_conversion")
|
|
|
- val featureNameFile = param.getOrElse("featureNameFile", "20240718_ad_feature_name.txt");
|
|
|
+ val featureNameFile = param.getOrElse("featureNameFile", "20240718_ad_feature_name_517.txt");
|
|
|
|
|
|
|
|
|
val loader = getClass.getClassLoader
|
|
|
|
|
|
- val resourceUrlBucket = loader.getResource("20240718_ad_bucket_688.txt")
|
|
|
+ val resourceUrlBucket = loader.getResource("20240718_ad_bucket_517.txt")
|
|
|
val buckets =
|
|
|
if (resourceUrlBucket != null) {
|
|
|
val buckets = Source.fromURL(resourceUrlBucket).getLines().mkString("\n")
|
|
@@ -87,6 +87,13 @@ object makedata_ad_33_bucketData_20240726 {
|
|
|
jsons.foreach(r => {
|
|
|
features.put(r._1, jsons.getDoubleValue(r._1))
|
|
|
})
|
|
|
+
|
|
|
+ for (name <- contentList) {
|
|
|
+ if (!features.contains(name)) {
|
|
|
+ features.put(name, 0)
|
|
|
+ }
|
|
|
+ }
|
|
|
+
|
|
|
(logKey, labelKey, features)
|
|
|
})
|
|
|
.filter {
|
|
@@ -106,39 +113,32 @@ object makedata_ad_33_bucketData_20240726 {
|
|
|
val bucketsMap = bucketsMap_br.value
|
|
|
row.foreach {
|
|
|
case (label, features) =>
|
|
|
- val featuresBucket = new ArrayBuffer[String]()
|
|
|
- for (name <- contentList) {
|
|
|
- var ifFilter = false
|
|
|
- if (filterNames.nonEmpty) {
|
|
|
- filterNames.foreach(r => if (!ifFilter && name.contains(r)) {
|
|
|
- ifFilter = true
|
|
|
- })
|
|
|
- }
|
|
|
- if (!ifFilter) {
|
|
|
- if (features.contains(name)) {
|
|
|
- val score = features(name)
|
|
|
+ val featuresBucket = features.map {
|
|
|
+ case (name, score) =>
|
|
|
+ var ifFilter = false
|
|
|
+ if (filterNames.nonEmpty) {
|
|
|
+ filterNames.foreach(r => if (!ifFilter && name.contains(r)) {
|
|
|
+ ifFilter = true
|
|
|
+ })
|
|
|
+ }
|
|
|
+ if (ifFilter) {
|
|
|
+ ""
|
|
|
+ } else {
|
|
|
if (score > 1E-8) {
|
|
|
if (bucketsMap.contains(name)) {
|
|
|
val (bucketsNum, buckets) = bucketsMap(name)
|
|
|
- val scoreNew = 0.01 + 1.0 / bucketsNum * (ExtractorUtils.findInsertPosition(buckets, score).toDouble + 1.0)
|
|
|
- featuresBucket.add(name + ":" + scoreNew.toString)
|
|
|
+ val scoreNew = 0.01 + (1.0 / bucketsNum * (ExtractorUtils.findInsertPosition(buckets, score).toDouble + 1.0))
|
|
|
+ name + ":" + scoreNew.toString
|
|
|
} else {
|
|
|
- featuresBucket.add(name + ":" + score.toString)
|
|
|
+ name + ":" + score.toString
|
|
|
}
|
|
|
} else {
|
|
|
- featuresBucket.add(name + ":" + "0.01")
|
|
|
+ name + ":" + "0.01"
|
|
|
}
|
|
|
-
|
|
|
- } else {
|
|
|
- featuresBucket.add(name + ":" + "0.01")
|
|
|
}
|
|
|
- }
|
|
|
-
|
|
|
- }
|
|
|
-
|
|
|
+ }.filter(_.nonEmpty)
|
|
|
result.add(label + "\t" + featuresBucket.mkString("\t"))
|
|
|
}
|
|
|
-
|
|
|
result.iterator
|
|
|
})
|
|
|
|