Spark SQL 编程初级实践详解

import org.apache.spark.sql.{DataFrame, SparkSession}
object t1 {
   def main(args: Array[String]): Unit = {
       val spark: SparkSession = SparkSession.builder()
         .appName("t1")
         .master("local[2]")
         .getOrCreate()
       import spark.implicits._
       val df: DataFrame = spark.read.json("dataset/ch05/employee.json")
//        df.show()
//        df.distinct().show()
//        df.drop("id").show()
//        df.filter(df("age") > 20).show()
//        df.groupBy("name").count().show()
//        df.sort(df("name").asc).show()
//        val rows = df.take(3)
//        rows.foreach(println)
//        df.select(df("name").as("username")).show()
//        df.agg("age" -> "avg").show()
       df.agg("age" -> "min").show()
   }
}

import org.apache.spark.sql.{DataFrame, SparkSession}
object t2 {
    def main(args: Array[String]): Unit = {
        val spark: SparkSession = SparkSession.builder()
          .appName("t1")
          .master("local[2]")
          .getOrCreate()
        val employeeInfo = spark.sparkContext.textFile("/input/dataset/employee.txt")
        import spark.implicits._
        val employeeDF: DataFrame = employeeInfo.map(_.split(","))
          .map(attributes =>
              Employee(attributes(0).trim.toInt, attributes(1), attributes(2).trim.toInt)
          ).toDF()
        employeeDF.createTempView("employee")
        val employeeRDD: DataFrame = spark.sql("select id, name, age from employee")
        employeeRDD.map(e => {
            "id:" + e(0) + ",name:" + e(1) + ",age:" + e(2)
        }).show(10, false)
    }
}
case class Employee(id: Long, name: String, age: Long) {
}

import java.util.Properties
import org.apache.spark.rdd.RDD
import org.apache.spark.sql.types.{IntegerType, StringType, StructField, StructType}
import org.apache.spark.sql.{DataFrame, Row, SparkSession}
object t3 {
    def main(args: Array[String]): Unit = {
        val spark: SparkSession = SparkSession.builder()
          .appName("t3")
          .master("local[2]")
          .getOrCreate()
        val employeeRDD: RDD[Array[String]] = spark.sparkContext.parallelize(
            Array("3 Mary F 26", "4 Tom M 23")).map(_.split(" ")
        )
        val schema: StructType = StructType(List(
            StructField("id", IntegerType, true),
            StructField("name", StringType, true),
            StructField("gender", StringType, true),
            StructField("age", IntegerType, true)
        ))
        val rowRDD: RDD[Row] = employeeRDD.map(p => Row(p(0).toInt, p(1).trim, p(2).trim, p(3).toInt))
        val df: DataFrame = spark.createDataFrame(rowRDD, schema)
        val properties = new Properties()
        properties.put("user", "root");
        properties.put("password", "123456");
        properties.put("driver", "com.mysql.jdbc.Driver");
        // serverTimezone=UTC语句需要跟在数据库连接语句的第一个位置，否则会报错
        df.write.mode("append").jdbc("jdbc:mysql://localhost:3306/bd01_spark?serverTimezone=UTC&characterEncoding=utf8&useUnicode=true&useSSL=false",
            "bd01_spark.employee", properties)
        val jdbcDF: DataFrame = spark.read.format("jdbc")
          .option("url", "jdbc:mysql://localhost:3306/bd01_spark")
          .option("driver", "com.mysql.jdbc.Driver")
          .option("dbtable", "employee")
          .option("user", "root")
          .option("password", "123456")
          .load()
        jdbcDF.agg("age" -> "max", "age" -> "sum").show(10, false)
    }
}