sparkmllib分类算法之决策树学习

val orig_file=sc.textFile("train_nohead.tsv")
    //println(orig_file.first())
    val data_file=orig_file.map(_.split("\t")).map{
      r =>
        val trimmed =r.map(_.replace("\"",""))
        val lable=trimmed(r.length-1).toDouble
        val feature=trimmed.slice(4,r.length-1).map(d => if(d=="?")0.0
        else d.toDouble)
        LabeledPoint(lable,Vectors.dense(feature))
    }
   /*特征标准化优化，似乎对决策数没啥影响*/
    val vectors=data_file.map(x =>x.features)
    val rows=new RowMatrix(vectors)
    println(rows.computeColumnSummaryStatistics().variance)//每列的方差
    val scaler=new StandardScaler(withMean=true,withStd=true).fit(vectors)//标准化
    val scaled_data=data_file.map(point => LabeledPoint(point.label,scaler.transform(point.features)))
        .randomSplit(Array(0.7,0.3),11L)//固定seed为11L，确保每次每次实验能得到相同的结果
    val data_train=scaled_data(0)
    val data_test=scaled_data(1)

/*训练决策树模型*/
    val model_DT=DecisionTree.train(data_train,Algo.Classification,Entropy,maxTreeDepth)
 /*决策树的精确度*/
    val predectionAndLabeledDT=data_test.map { point =>
      val predectLabeled = if (model_DT.predict(point.features) > 0.5) 1.0 else 0.0
      (predectLabeled,point.label)
    }
    val metricsDT=new MulticlassMetrics(predectionAndLabeledDT)
    println(metricsDT.accuracy)//0.6273062730627307
/*决策树的PR曲线和AOC曲线*/
    val dtMetrics = Seq(model_DT).map{ model =>
      val scoreAndLabels = data_test.map { point =>
        val score = model.predict(point.features)
        (if (score > 0.5) 1.0 else 0.0, point.label)
      }
      val metrics = new BinaryClassificationMetrics(scoreAndLabels)
      (model.getClass.getSimpleName, metrics.areaUnderPR, metrics.areaUnderROC)
    }
    val allMetrics = dtMetrics
    allMetrics.foreach{ case (m, pr, roc) =>
      println(f"$m, Area under PR: ${pr * 100.0}%2.4f%%, Area under ROC: ${roc * 100.0}%2.4f%%")
    }
/*
DecisionTreeModel, Area under PR: 74.2335%, Area under ROC: 62.4326%
*/

/*调参函数*/
    def trainDTWithParams(input: RDD[LabeledPoint], maxDepth: Int,
                          impurity: Impurity) = {
      DecisionTree.train(input, Algo.Classification, impurity, maxDepth)
    }

 /*改变深度*/
    val dtResultsEntropy = Seq(1, 2, 3, 4, 5, 10, 20).map { param =>
      val model = trainDTWithParams(data_train, param, Entropy)
      val scoreAndLabels = data_test.map { point =>
        val score = model.predict(point.features)
        (if (score > 0.5) 1.0 else 0.0, point.label)
      }
      val metrics = new BinaryClassificationMetrics(scoreAndLabels)
      (s"$param tree depth", metrics.areaUnderROC)
    }
    dtResultsEntropy.foreach { case (param, auc) => println(f"$param, " +
      f"AUC = ${auc * 100}%2.2f%%") }
/*
1 tree depth, AUC = 58.57%
2 tree depth, AUC = 60.69%
3 tree depth, AUC = 61.40%
4 tree depth, AUC = 61.30%
5 tree depth, AUC = 62.43%
10 tree depth, AUC = 62.26%
20 tree depth, AUC = 60.59%
*/

 /*改变纯度*/
    val dtResultsEntropy = Seq(Gini,Entropy).map { param =>
      val model = trainDTWithParams(data_train, 5, param)
      val scoreAndLabels = data_test.map { point =>
        val score = model.predict(point.features)
        (if (score > 0.5) 1.0 else 0.0, point.label)
      }
      val metrics = new BinaryClassificationMetrics(scoreAndLabels)
      (s"$param tree depth", metrics.areaUnderROC)
    }
    dtResultsEntropy.foreach { case (param, auc) => println(f"$param, " +
      f"AUC = ${auc * 100}%2.2f%%") }
/*
org.apache.spark.mllib.tree.impurity.Gini$@32d8e58d tree depth, AUC = 62.37%
org.apache.spark.mllib.tree.impurity.Entropy$@1ddba7a0 tree depth, AUC = 62.43%
*/