根据特征数据区分属于哪一类 比如微博 发表文章判断属于哪一类，正向还是负向
类别：支持向量机 决策树(本章具体描述决策树) **决策树：**将特征进行划分，进行一些列处理
例子：中午吃饭，兜里钱是否大于20，此时继续判断钱是否大于25，如果大于吃黄焖鸡+可乐，不大于黄焖鸡。如果兜里钱一开始就不大于20吃泡面
object Happiness { /** * 判断人是否幸福 * */ def main(args: Array[String]): Unit = { //读取数据 val spark = SparkSession.builder() .appName("happiness") .master("local") .getOrCreate() spark.sparkContext.setLogLevel("ERROR")//减少日志信息 val data = spark.read .option("header","true")//首行不读 .csv("data/happiness_train_complete.csv") //筛选需要的数据 //province:地点 gender:性别 religion：宗教信仰 edu:教育程度 floor_area:房屋占地面积 health:身体健康状况 //happiness：是否幸福 social_friend：和朋友娱乐程度 income:去年收入 .select("province","gender","religion","edu","floor_area" ,"health","social_friend","income","happiness") .rdd val labelPoint = data.map{ line => { var happiness = line.getString(8).toDouble if(happiness>3){ happiness = 1.0 }else{ happiness = 0.0 } var social_friend = line.getString(6) if(social_friend ==null || social_friend.equals("")){ social_friend = "0.0" } val feature = Array[Double](line.getString(0).toDouble, line.getString(1).toDouble,line.getString(2).toDouble, line.getString(3).toDouble,line.getString(4).toDouble, line.getString(5).toDouble,social_friend.toDouble, line.getString(7).toDouble ) LabeledPoint(happiness,Vectors.dense(feature)) } } //划分训练集和测试集 val Array(tranData,testData) = labelPoint.randomSplit(Array(0.8,0.2)) //训练 val model = DecisionTree.trainClassifier(tranData, 7,//特征数量 Map[Int,Int](),//保存类别特征类型 "gini",//数据完整度 表示不纯行度量方式 5,//树的深度 32//最大参数 ) //决策树 val result = testData.map{ line => { (line.label,model.predict(line.features)) } } result.take(10).foreach(println(_)) println(model.toDebugString) //获得相关值 val metrics = new MulticlassMetrics(result)//检测结果model println(s"结果准确度：${metrics.accuracy}") spark.close()//关闭资源 } }