Spark ML逻辑回归

import org.apache.log4j.{Level, Logger}
import org.apache.spark.ml.classification.LogisticRegression
import org.apache.spark.ml.linalg.Vectors
import org.apache.spark.sql.SparkSession

/**
  * 逻辑回归
  * Created by zhen on 2018/11/20.
  */
object LogisticRegression {
  Logger.getLogger("org").setLevel(Level.WARN) // 设置日志级别
  def main(args: Array[String]) {
    val spark = SparkSession.builder()
      .appName("LogisticRegression")
      .master("local[2]")
      .getOrCreate()
    val sqlContext = spark.sqlContext
    // 加载训练数据和测试数据
    val data = sqlContext.createDataFrame(Seq(
      (1.0, Vectors.dense(0.0, 1.1, 0.1)),
      (0.0, Vectors.dense(2.0, 1.0, -1.1)),
      (1.0, Vectors.dense(1.0, 2.1, 0.1)),
      (0.0, Vectors.dense(2.0, -1.3, 1.1)),
      (0.0, Vectors.dense(2.0, 1.0, -1.1)),
      (1.0, Vectors.dense(1.0, 2.1, 0.1)),
      (1.0, Vectors.dense(2.0, 1.3, 1.1)),
      (0.0, Vectors.dense(-2.0, 1.0, -1.1)),
      (1.0, Vectors.dense(1.0, 2.1, 0.1)),
      (0.0, Vectors.dense(2.0, -1.3, 1.1)),
      (1.0, Vectors.dense(2.0, 1.0, -1.1)),
      (1.0, Vectors.dense(1.0, 2.1, 0.1)),
      (0.0, Vectors.dense(-2.0, 1.3, 1.1)),
      (1.0, Vectors.dense(0.0, 1.2, -0.4))
    ))
    .toDF("label", "features")
    val weights = Array(0.8,0.2) //设置训练集和测试集的比例
    val split_data = data.randomSplit(weights) // 拆分训练集和测试集
    // 创建逻辑回归对象
    val lr = new LogisticRegression()
    // 设置参数
    lr.setMaxIter(10).setRegParam(0.01)
    // 训练模型
    val model = lr.fit(split_data(0))
    model.transform(split_data(1))
    .select("label", "features", "probability", "prediction")
    .collect()
    .foreach(println(_))
    //关闭spark
    spark.stop()
  }
}

结果：