/**
* Created by lkl on 2018/1/16.
*/
import org.apache.spark.mllib.evaluation.BinaryClassificationMetrics
import org.apache.spark.mllib.linalg.Vectors
import org.apache.spark.mllib.regression.LabeledPoint
import org.apache.spark.mllib.tree.GradientBoostedTrees
import org.apache.spark.mllib.tree.configuration.BoostingStrategy
import org.apache.spark.mllib.tree.model.GradientBoostedTreesModel
import org.apache.spark.sql.{Row, SaveMode}
import org.apache.spark.sql.hive.HiveContext
import org.apache.spark.sql.types.{DoubleType, StringType, StructField, StructType}
import org.apache.spark.{SparkConf, SparkContext}
import scala.collection.mutable.ArrayBuffer
object abregression3Model20180116 {
def main(args: Array[String]): Unit = { val sparkConf = new SparkConf().setAppName("abregression3Model20180116")
val sc = new SparkContext(sparkConf)
val hc = new HiveContext(sc)
val data = hc.sql(s"select * from lkl_card_score.fqz_score_dataset_03train").map {
row =>
val arr = new ArrayBuffer[Double]()
//剔除label、phone字段
for (i <- 3 until row.size) {
if (row.isNullAt(i)) {
arr += 0.0
}
else if (row.get(i).isInstanceOf[Int])
arr += row.getInt(i).toDouble
else if (row.get(i).isInstanceOf[Double])
arr += row.getDouble(i)
else if (row.get(i).isInstanceOf[Long])
arr += row.getLong(i).toDouble
else if (row.get(i).isInstanceOf[String])
arr += 0.0
}
LabeledPoint(row.getInt(2).toDouble, Vectors.dense(arr.toArray))
} // Split data into training (60%) and test (40%)
val Array(trainingData, testData) = data.randomSplit(Array(0.7,0.3), seed = 11L)
// 逻辑回归是迭代算法,所以缓存训练数据的RDD
trainingData.cache()
//使用SGD算法运行逻辑回归 val boostingStrategy = BoostingStrategy.defaultParams("Regression")
boostingStrategy.setNumIterations(40) // Note: Use more iterations in practice.
boostingStrategy.treeStrategy.setMaxDepth(6)
boostingStrategy.treeStrategy.setMinInstancesPerNode(50)
val model = GradientBoostedTrees.train(data, boostingStrategy)
model.save(sc, s"hdfs://ns1/user/songchunlin/model/abregression3Model20180116") sc.makeRDD(Seq(model.toDebugString)).repartition(1).saveAsTextFile(s"hdfs://ns1/user/songchunlin/model/toDebugString/abregression3Model20180116")
// 全量data数据打分,原本用testData打分
val omodel=GradientBoostedTreesModel.load(sc,s"hdfs://ns1/user/songchunlin/model/abregression3Model20180116")
val predictionAndLabels = data.map { case LabeledPoint(label, features) =>
val prediction = omodel.predict(features)
(prediction, label)
} println("testData count = " + testData.count())
println("predictionAndLabels count = " + predictionAndLabels.count())
predictionAndLabels.map(x => {"predicts: "+x._1+"--> labels:"+x._2}).saveAsTextFile(s"hdfs://ns1/user/szdsjkf/model_training/jrsc/20171218/predictionAndLabels") val metrics = new BinaryClassificationMetrics(predictionAndLabels) val precision = metrics.precisionByThreshold precision.map({case (t, p) =>
"Threshold: "+t+"Precision:"+p
}).saveAsTextFile(s"hdfs://ns1/user/szdsjkf/model_training/jrsc/20171218/precision") val recall = metrics.recallByThreshold recall.map({case (t, r) =>
"Threshold: "+t+"Recall:"+r
}).saveAsTextFile(s"hdfs://ns1/user/szdsjkf/model_training/jrsc/20171218/recall") val beta = 2
val f2Score = metrics.fMeasureByThreshold(beta) f2Score.map(x => {"Threshold: "+x._1+"--> F-score:"+x._2+"--> Beta = 2"})
.saveAsTextFile(s"hdfs://ns1/user/szdsjkf/model_training/jrsc/20171218/f1Score") val prc = metrics.pr
prc.map(x => {"Recall: " + x._1 + "--> Precision: "+x._2 }).saveAsTextFile(s"hdfs://ns1/user/szdsjkf/model_training/jrsc/20171218/prc") // AUPRC,精度,召回曲线下的面积
val auPRC = metrics.areaUnderPR
println("Area under precision-recall curve = " +auPRC)
sc.makeRDD(Seq("Area under precision-recall curve = " +auPRC)).saveAsTextFile(s"hdfs://ns1/user/szdsjkf/model_training/jrsc/20171218/auPRC") //roc
val roc = metrics.roc
roc.map(x => {"FalsePositiveRate:" + x._1 + "--> Recall: " +x._2}).saveAsTextFile(s"hdfs://ns1/user/szdsjkf/model_training/jrsc/20171218/roc") // AUC
val auROC = metrics.areaUnderROC
sc.makeRDD(Seq("Area under ROC = " + +auROC)).saveAsTextFile(s"hdfs://ns1/user/szdsjkf/model_training/jrsc/20171218/auROC")
println("Area under ROC = " + auROC)
//val accuracy = 1.0 * predictionAndLabels.filter(x => x._1 == x._2).count() / testData.count() val dataInstance = hc.sql(s"select * from lkl_card_score.fqz_score_dataset_03train").map {
row =>
val arr = new ArrayBuffer[Double]()
//剔除label、phone字段
for (i <- 3 until row.size) {
if (row.isNullAt(i)) {
arr += 0.0
}
else if (row.get(i).isInstanceOf[Int])
arr += row.getInt(i).toDouble
else if (row.get(i).isInstanceOf[Double])
arr += row.getDouble(i)
else if (row.get(i).isInstanceOf[Long])
arr += row.getLong(i).toDouble
else if (row.get(i).isInstanceOf[String])
arr += 0.0
}
(row(0),row(1),row(2),Vectors.dense(arr.toArray))
} val preditDataGBDT = dataInstance.map { point =>
val prediction = model.predict(point._4)
//order_id,apply_time,score
(point._1,point._2,point._3,prediction)
} //rdd转dataFrame
val rowRDD = preditDataGBDT.map(row => Row(row._1.toString,row._2.toString,row._3.toString,row._4))
val schema = StructType(
List(
StructField("order_id", StringType, true),
StructField("apply_time", StringType, true),
StructField("label", StringType, true),
StructField("score", DoubleType, true)
)
)
//将RDD映射到rowRDD,schema信息应用到rowRDD上
val scoreDataFrame = hc.createDataFrame(rowRDD,schema)
scoreDataFrame.count()
scoreDataFrame.write.mode(SaveMode.Overwrite).saveAsTable("lkl_card_score.fqz_score_dataset_03train_predict") // 自己测试建模 val balance = hc.sql(s"select * from lkl_card_score.overdue_result_all_new_woe_instant_v3_02train where label='1' limit 85152 union all select * from lkl_card_score.overdue_result_all_new_woe_instant_v3_02train where label='0'").map {
row =>
val arr = new ArrayBuffer[Double]()
//剔除label、phone字段
for (i <- 3 until row.size) {
if (row.isNullAt(i)) {
arr += 0.0
}
else if (row.get(i).isInstanceOf[Int])
arr += row.getInt(i).toDouble
else if (row.get(i).isInstanceOf[Double])
arr += row.getDouble(i)
else if (row.get(i).isInstanceOf[Long])
arr += row.getLong(i).toDouble
else if (row.get(i).isInstanceOf[String])
arr += 0.0
}
LabeledPoint(row.getInt(2).toDouble, Vectors.dense(arr.toArray))
} // 逻辑回归是迭代算法,所以缓存训练数据的RDD
balance.cache()
val boostingStrategy1 = BoostingStrategy.defaultParams("Regression")
boostingStrategy1.setNumIterations(40) // Note: Use more iterations in practice.
boostingStrategy1.treeStrategy.setMaxDepth(6)
boostingStrategy1.treeStrategy.setMinInstancesPerNode(50) val model2 = GradientBoostedTrees.train(balance, boostingStrategy1) val predictionAndLabels2 = data.map { case LabeledPoint(label, features) =>
val prediction = model2.predict(features)
(prediction, label)
}
val metrics2 = new BinaryClassificationMetrics(predictionAndLabels2)
// AUPRC,精度,召回曲线下的面积
val auPRC1 = metrics2.areaUnderPR val preditDataGBDT1 = dataInstance.map { point =>
val prediction2 = model2.predict(point._4)
//order_id,apply_time,score
(point._1,point._2,point._3,prediction2)
}
//rdd转dataFrame
val rowRDD2 = preditDataGBDT1.map(row => Row(row._1.toString,row._2.toString,row._3.toString,row._4))
val schema2 = StructType(
List(
StructField("order_id", StringType, true),
StructField("apply_time", StringType, true),
StructField("label", StringType, true),
StructField("score", DoubleType, true)
)
) val scoreDataFrame2 = hc.createDataFrame(rowRDD2,schema2)
scoreDataFrame2.count()
scoreDataFrame2.write.mode(SaveMode.Overwrite).saveAsTable("lkl_card_score.fqz_score_dataset_02val_170506_predict") }
}

lakala反欺诈建模实际应用代码GBDT监督学习的更多相关文章

  1. AI反欺诈:千亿的蓝海,烫手的山芋|甲子光年

    不久前,一家业界领先的机器学习公司告诉「甲子光年」:常有客户带着迫切的反欺诈需求主动找来,但是,我们不敢接. 难点何在? 作者|晕倒羊 编辑|甲小姐 设计|孙佳栋 生死欺诈 企业越急速发展,越容易产生 ...

  2. 反欺诈(Fraud Detection)中所用到的机器学习模型

    反欺诈应用的机器模型算法,多为二分类算法. 1.gbdt梯度提升决策树(Gradient Boosting Decision Tree,GBDT)算法,该算法的性能高,且在各类数据挖掘中应用广泛,表现 ...

  3. 基于Vue2和Node.js的反欺诈系统设计与实现

    最近包工头喊农民工小郑搬砖,小郑搬完砖后沉思片刻,决定写篇小作文分享下,作为一个初学者的全栈项目,去学习它的搭建,到落地,再到部署维护,是非常好的. ​ ------题记 写在前面 通过本文的学习,你 ...

  4. 反编译工具 使用.NET JustDecompile来反编译你的程序代码

    原文地址:http://www.it165.net/pro/html/201310/7383.html 前言 在项目的进行中有时会碰到需要去了解由第三方所开发的程序代码或者因为年久已经遗失原始码的程序 ...

  5. python金融反欺诈-项目实战

    python信用评分卡(附代码,博主录制) https://study.163.com/course/introduction.htm?courseId=1005214003&utm_camp ...

  6. Android Studio 动态调试 apk 反编译出的 smali 代码

    在信安大赛的准备过程中,主要通过 Android Studio 动态调试 apk 反编译出来的 smali 代码的方式来对我们分析的执行流程进行验证.该技巧的主要流程在此记录.以下过程使用 Andro ...

  7. 使用.NET JustDecompile来反编译你的程序代码

    前言 在项目的进行中有时会碰到需要去了解由第三方所开发的程序代码或者因为年久已经遗失原始码的程序,由于因为是别人写的所以我们并没有原始码可以直接阅读,碰到这种情况我们就需要去反编译这些程序及 DLL ...

  8. OAF_开发系列28_实现OAF中反编译获取class包代码JD Compiler(案例)

    20150730 Created By BaoXinjian

  9. 使用VBA进行JS加密的反混淆,还原JS代码。

    本文地址:http://www.cnblogs.com/Charltsing/p/JSEval.html 联系QQ:564955427 类似下面的代码是登陆 全国企业信用信息公示系统(安徽)(网址:h ...

随机推荐

  1. nexus 手动更改 私服包

    替换 linux 私服下的 nexus 目录

  2. 解决hibernate向mysql插入中文乱码问题(转)

    转载自:http://blog.csdn.net/peditable/article/details/7047573 1.首先需要修改MySQL数据库的配置文件my.ini,此文件放在mysql根目录 ...

  3. win10老提示系统错误,要注销

    win10老提示系统错误,要注销? 开启user manager 服务(对我没用) 用administrator账户(成功,不提示了) 或者创建一个新账户(未测)

  4. 处理异常json串的jar包JsonSerde

    参考下面文章: https://blog.csdn.net/SunnyYoona/article/details/70170173

  5. android开发(41) Fragment中使用POP_BACK_STACK_INCLUSIVE达到一次跳转到栈底。类似Activity的 采用FLAG_ACTIVITY_CLEAR_TOP

    需求场景: 在开发中遇到下面这样场景: 1.创建 Fragment A 显示.  这时栈的结构是: .Fragment A 2.创建 Fragment B 并 显示.  从下到上看,这时栈的结构是: ...

  6. linq操作符:分组操作符

    分组是根据一个特定的值将序列中的元素进行分组.LINQ只包含一个分组操作符:GroupBy.GroupBy操作符类似于T-SQL语言中的Group By语句.来看看GroupBy的方法定义: publ ...

  7. Entity Framework应用:根据实体的EntityState状态实现增删改查

    在上一篇文章中,我们讲解了使用EF实现简单的增删改成,在这篇文章中我们使用实体的EntityState状态来优化数据的增删改查. 一.修改数据 上篇文章中的修改数据的方法是EF官方推荐的方式,即先查询 ...

  8. eclipse配置google代码风格

    1.下载google code style的xml文件 地址:https://github.com/google/styleguide 导入xml文件 可能会遇到警告: 版本的问题,忽略即可. < ...

  9. librtmp编译for android and ios 不要openssl

    git clone git://git.ffmpeg.org/rtmpdump 不想要openssl 在rtmp.h里面 #undef CRYPTO 编译动态库与静态库只需要修改下面的 #includ ...

  10. 引用dataframe的值为什么会不同

    在R语言中,通常有一些操作符可以来提取对象的子集,如以下三种: 1.“[” 单层方括号,返回的对象与原对象类型相同,它也可以返回一个对象中的多个元素: 2.“[[” 双层方括号,用来从列表(list) ...