在scala中使用嵌套模式时向DataFrame追加行

import org.apache.spark.sql.{DataFrame, Row, SparkSession}
import org.apache.spark.sql.types.{ArrayType, IntegerType, StringType, StructField, StructType}

val spark = SparkSession.builder()
  .appName("DataFrame Append Row")
  .master("local")
  .getOrCreate()

val schema = StructType(Seq(
  StructField("name", StringType, nullable = false),
  StructField("age", IntegerType, nullable = false),
  StructField("hobbies", ArrayType(StringType), nullable = false)
))

val data = Seq(
  Row("John", 25, Seq("reading", "swimming")),
  Row("Jane", 30, Seq("painting", "dancing"))
)

val df = spark.createDataFrame(spark.sparkContext.parallelize(data), schema)

val newRow = Row("Alice", 35, Seq("singing", "cooking"))

val appendedDF = spark.createDataFrame(df.rdd.union(spark.sparkContext.parallelize(Seq(newRow))), schema)

appendedDF.show()