2025/1/25

 

import org.apache.spark.ml.classification.LogisticRegression
import org.apache.spark.ml.evaluation.BinaryClassificationEvaluator
import org.apache.spark.sql.SparkSession

 

object LogisticRegressionExample {
def main(args: Array[String]): Unit = {
// 创建SparkSession
val spark = SparkSession.builder()
.appName("LogisticRegressionExample")
.master("local[*]")
.getOrCreate()

 

// 加载LibSVM格式的数据
val data = spark.read.format("libsvm").load("data/sample_libsvm_data.txt")

 

// 划分训练集和测试集
val Array(trainingData, testData) = data.randomSplit(Array(0.7, 0.3), seed = 1234L)

 

// 创建逻辑回归模型
val lr = new LogisticRegression()
.setMaxIter(10)
.setRegParam(0.3)
.setElasticNetParam(0.8)

 

// 训练模型
val model = lr.fit(trainingData)

 

// 预测
val predictions = model.transform(testData)
predictions.select("features", "label", "prediction").show(10)

 

// 评估模型
val evaluator = new BinaryClassificationEvaluator()
.setLabelCol("label")
.setRawPredictionCol("prediction")
.setMetricName("areaUnderROC")
val auc = evaluator.evaluate(predictions)
println(s"Area Under ROC: $auc")

 

// 停止SparkSession
spark.stop()
}
}