import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;

public class HdfsFileOperation {

    public static void main(String[] args) throws Exception {
        // 配置Hadoop环境
        Configuration conf = new Configuration();
        conf.set("fs.defaultFS", "hdfs://localhost:9000");
        
        // 创建文件系统实例
        FileSystem fs = FileSystem.get(conf);
        
        // 创建一个新文件
        Path newFile = new Path("/user/hadoop/library/data/newFile.txt");
        if (fs.createNewFile(newFile)) {
            System.out.println("文件创建成功！");
        } else {
            System.out.println("文件已存在！");
        }
        
        // 关闭文件系统
        fs.close();
    }
}
import org.apache.spark.sql.SparkSession

object LibraryDataProcessing {
  def main(args: Array[String]): Unit = {
    // 创建Spark会话
    val spark = SparkSession.builder()
      .appName("Library Data Processing")
      .master("local[*]")
      .getOrCreate()

    // 读取数据
    val data = spark.read.json("hdfs://localhost:9000/user/hadoop/library/data/books.json")

    // 展示数据
    data.show()

    // 数据处理，例如：筛选特定类型的书籍
    val filteredData = data.filter($"genre" === "Science Fiction")

    // 保存处理后的数据
    filteredData.write.format("json").save("hdfs://localhost:9000/user/hadoop/library/processed_data/sci_fi_books")

    // 停止Spark会话
    spark.stop()
  }
}
import org.apache.spark.ml.clustering.KMeans
import org.apache.spark.sql.SparkSession

object UserBehaviorAnalysis {
  def main(args: Array[String]): Unit = {
    val spark = SparkSession.builder.appName("User Behavior Analysis").getOrCreate()

    // 读取用户行为数据
    val data = spark.read.format("libsvm").load("hdfs://localhost:9000/user/hadoop/library/data/user_behavior.libsvm")

    // 使用KMeans进行聚类分析
    val kmeans = new KMeans().setK(5).setSeed(1L)
    val model = kmeans.fit(data)

    // 输出聚类中心
    println("Cluster Centers: ")
    model.clusterCenters.foreach(println)

    spark.stop()
  }
}