dataframe sparksession

import org.apache.spark.SparkConf
import org.apache.spark.sql.{DataFrame, SparkSession}

object DataFrameOperate {
  def main(args: Array[String]): Unit = {
    val sparkConf = new SparkConf().setMaster("local[*]").setAppName("dataframe")
    val sparkSession = SparkSession.builder().config(sparkConf).getOrCreate()
    val dataFrame: DataFrame = sparkSession.read.format("jdbc")
      .option("url", "jdbc:mysql://hadoop01:3306/test")
      .option("dbtable", "student")
      .option("user", "root")
      .option("password", "root")
      .load()
    dataFrame.show()

    sparkSession.close()
  }

}

import org.apache.spark.SparkConf
import org.apache.spark.rdd.RDD
import org.apache.spark.sql.types._
import org.apache.spark.sql.{DataFrame, Row, SparkSession}

object DataFrameOperate {
  def main(args: Array[String]): Unit = {
    val sparkConf = new SparkConf().setMaster("local[*]").setAppName("dataframe")
    val sparkSession = SparkSession.builder().config(sparkConf).getOrCreate()

    val rdd: RDD[(Int, String, Int)] = sparkSession.sparkContext.parallelize(
      List(
        (1, "chinese", 86),
        (1, "english", 77),
        (1, "math", 99),
        (2, "chinese", 76),
        (2, "english", 86),
        (2, "math", 99),
        (3, "chinese", 77),
        (3, "english", 77),
        (3, "math", 99)
      ))
    val rowRDD: RDD[Row] = rdd.map(a => Row.fromTuple(a))

    val id: StructField = StructField("id", IntegerType, true)
    val subject: StructField = StructField("subject", StringType, true)
    val score: StructField = StructField("score", IntegerType, true)
    val structType: StructType = StructType(Array(id, subject, score))

    val dataFrame: DataFrame = sparkSession.createDataFrame(rowRDD, structType)
    dataFrame.show()
    dataFrame.groupBy("id").pivot("subject").avg("score").show()

    sparkSession.close()
  }
}