java遍历dataframe,hivecontent实际操作（Dateframe获取稍有不同）

spark.json

{"id":1, "name":"leo", "age":18}

{"id":2, "name":"jack", "age":19}

{"id":3, "name":"marry", "age":17}

package com.pgliuyang.sparkproject;

import org.apache.spark.SparkConf;

import org.apache.spark.api.java.JavaSparkContext;

import org.apache.spark.sql.Dataset;

import org.apache.spark.sql.Row;

import org.apache.spark.sql.SQLContext;

public class DataFrameCreate {

public static void main(String[] args) {

SparkConf conf = new SparkConf().setAppName("DataFrameCreate").setMaster("local");

JavaSparkContext sc = new JavaSparkContext(conf);

SQLContext sqlContext = new SQLContext(sc);

Dataset df = sqlContext.read().json("C:\\Users\\Administrator\\Desktop\\spark.json");

// 打印DataFrame中所有的数据(select * from ...)

df.show();

// 打印DataFrame的元数据(schema)

df.printSchema();

// 查询某列所有数据

df.select("name").show();

// 查询某几个列所有数据并对列进行计算

df.select(df.col("name"), df.col("age").plus(1)).show();

// 过滤

df.filter(df.col("age").gt(18)).show();

// 按照组进行统计

df.groupBy(df.col("age")).count().show();

}

}