使用Java和Scala在IDE中开发DataFrame

Java版本代码如下：

import org.apache.spark.SparkConf;
import org.apache.spark.SparkContext;
import org.apache.spark.sql.DataFrame;
import org.apache.spark.sql.SQLContext;

/**
 * 使用Java的方式实战对DataFrame的操作
 */
public class DataFrameOps {

    public static void main(String[] args) {
        //创建SparkConf用于读取系统配置信息并设置当前应用程序的名字
        SparkConf conf = new SparkConf()
                .setMaster("local")
                .setAppName("DataFrameOps");
        //创建JavaSparkContext对象实例作为整个Driver的核心基石
        SparkContext sc = new SparkContext(conf);
        //创建SQLContext上下文对象用于SQL的分析
        SQLContext sqlContext = new SQLContext(sc);

        //创建DataFrame，可以简单的认为DataFrame是一张表。
        DataFrame df = sqlContext.read().json("E://people.json");

        //select * from table
        df.show();

        //desc table
        df.printSchema();

        //select name from table
        df.select("name").show();

        //select name,age + 1 from tables;
        df.select(df.col("name"),df.col("age").plus(10)).show();

        //select * from table where age > 10
        df.filter(df.col("age").gt(10)).show();

        //select count(1) from table group by age
        df.groupBy(df.col("age")).count().show();
    }

}

Scala版本;

import org.apache.spark.SparkConf
import org.apache.spark.SparkContext
import org.apache.spark.sql.SQLContext

object DataFrameOps {
  def main(args:Array[String]):Unit={
    val conf = new SparkConf().setMaster("local").setAppName("DataFrameOps")
    val sc = new SparkContext(conf)

    val sqlContext = new SQLContext(sc)

    val df = sqlContext.read.json("E://people.json")

    df.show()
    df.printSchema()
    df.select("name").show()
    df.select(df.col("name"),df.col("age").plus(10)).show()
    df.filter(df.col("age").gt(10)).show()
    df.groupBy(df.col("age")).count().show()