Scala数据帧获取最近6个月的最新数据

import org.apache.spark.sql.functions._
import org.apache.spark.sql.types._
import org.apache.spark.sql.{SparkSession, DataFrame}

// 创建SparkSession
val spark = SparkSession.builder()
  .appName("Get Recent Data")
  .master("local")
  .getOrCreate()

// 创建数据框架
val schema = StructType(Seq(
  StructField("date", DateType, nullable = false),
  StructField("value", DoubleType, nullable = false)
))

val data = Seq(
  ("2022-01-01", 100.0),
  ("2022-02-01", 200.0),
  ("2022-03-01", 150.0),
  ("2022-04-01", 300.0),
  ("2022-05-01", 250.0),
  ("2022-06-01", 400.0),
  ("2022-07-01", 350.0)
)

val df = spark.createDataFrame(data).toDF("date", "value").withColumn("date", to_date(col("date")))

// 过滤最近6个月的数据
val currentDate = current_date()
val sixMonthsAgo = date_sub(currentDate, 180)

val filteredData = df.filter(col("date") >= sixMonthsAgo)

// 打印结果
filteredData.show()