2025/1/11

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

val spark = SparkSession.builder.appName("MLlib Example").master("local").getOrCreate()

// 加载数据集
val data = spark.read.format("libsvm").load("data/mllib/sample_libsvm_data.txt")

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

// 创建逻辑回归模型
val lr = new LogisticRegression()
val model = lr.fit(trainingData)

// 评估模型
val predictions = model.transform(testData)
predictions.show()

spark.stop()