package sql;
import org.apache.spark.SparkConf;
import org.apache.spark.api.java.JavaSparkContext;
import org.apache.spark.sql.DataFrame;
import org.apache.spark.sql.SQLContext;
/**
*
*/
public class DataFrameReadJsonOps2 {
/**
* @param args
*/
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().setAppName("DataFrameOps").setMaster("local");
//创建JavaSparkContext对象实例作为整个Driver的核心基石
JavaSparkContext sc = new JavaSparkContext(conf);
//设置日志级别为WARN
sc.setLogLevel("WARN");
//创建SQLContext上下文对象用于SQL的分析
SQLContext sqlContext = new SQLContext(sc);
//创建Data Frame，可以简单的认为DataFrame是一张表
DataFrame df = sqlContext.read().json("c:/resources/people.json");
//select * from table
df.show();
//desc table
df.printSchema();
//select name from table
df.select(df.col("name")).show();
//select name, age+10 from table
df.select(df.col("name"), df.col("age").plus(10)).show();
//select * from table where age > 21
df.filter(df.col("age").gt(21)).show();
//select age, count(1) from table group by age
df.groupBy("age").count().show(); //df.groupBy(df.col("age")).count().show();
}
}
//
//SLF4J: Class path contains multiple SLF4J bindings.
//SLF4J: Found binding in [jar:file:/E:/bigdata/spark-1.4.0-bin-hadoop2.6/lib/spark-assembly-1.4.0-hadoop2.6.0.jar!/org/slf4j/impl/StaticLoggerBinder.class]
//SLF4J: Found binding in [jar:file:/E:/bigdata/spark-1.4.0-bin-hadoop2.6/lib/spark-examples-1.4.0-hadoop2.6.0.jar!/org/slf4j/impl/StaticLoggerBinder.class]
//SLF4J: See http://www.slf4j.org/codes.html#multiple_bindings for an explanation.
//SLF4J: Actual binding is of type [org.slf4j.impl.Log4jLoggerFactory]
//Using Spark's default log4j profile: org/apache/spark/log4j-defaults.properties
//17/12/29 14:15:10 INFO SparkContext: Running Spark version 1.4.0
//17/12/29 14:15:24 WARN NativeCodeLoader: Unable to load native-hadoop library for your platform... using builtin-java classes where applicable
//17/12/29 14:15:28 INFO SecurityManager: Changing view acls to: alamps
//17/12/29 14:15:28 INFO SecurityManager: Changing modify acls to: alamps
//17/12/29 14:15:28 INFO SecurityManager: SecurityManager: authentication disabled; ui acls disabled; users with view permissions: Set(alamps); users with modify permissions: Set(alamps)
//17/12/29 14:15:37 INFO Slf4jLogger: Slf4jLogger started
//17/12/29 14:15:39 INFO Remoting: Starting remoting
//17/12/29 14:15:44 INFO Remoting: Remoting started; listening on addresses :[akka.tcp://sparkDriver@172.18.3.7:55458]
//17/12/29 14:15:44 INFO Utils: Successfully started service 'sparkDriver' on port 55458.
//17/12/29 14:15:45 INFO SparkEnv: Registering MapOutputTracker
//17/12/29 14:15:46 INFO SparkEnv: Registering BlockManagerMaster
//17/12/29 14:15:46 INFO DiskBlockManager: Created local directory at C:\Users\alamps\AppData\Local\Temp\spark-cd3ecbc3-41b5-4d8b-8e78-8c2c368ce80b\blockmgr-660894dd-39d3-4c8a-bf25-ae1d3850953d
//17/12/29 14:15:46 INFO MemoryStore: MemoryStore started with capacity 467.6 MB
//17/12/29 14:15:47 INFO HttpFileServer: HTTP File server directory is C:\Users\alamps\AppData\Local\Temp\spark-cd3ecbc3-41b5-4d8b-8e78-8c2c368ce80b\httpd-106ce90e-d496-4e96-a383-b471aeb5a224
//17/12/29 14:15:47 INFO HttpServer: Starting HTTP Server
//17/12/29 14:15:48 INFO Utils: Successfully started service 'HTTP file server' on port 55464.
//17/12/29 14:15:48 INFO SparkEnv: Registering OutputCommitCoordinator
//17/12/29 14:15:49 INFO Utils: Successfully started service 'SparkUI' on port 4040.
//17/12/29 14:15:49 INFO SparkUI: Started SparkUI at http://172.18.3.7:4040
//17/12/29 14:15:49 INFO Executor: Starting executor ID driver on host localhost
//17/12/29 14:15:50 INFO Utils: Successfully started service 'org.apache.spark.network.netty.NettyBlockTransferService' on port 55483.
//17/12/29 14:15:50 INFO NettyBlockTransferService: Server created on 55483
//17/12/29 14:15:50 INFO BlockManagerMaster: Trying to register BlockManager
//17/12/29 14:15:50 INFO BlockManagerMasterEndpoint: Registering block manager localhost:55483 with 467.6 MB RAM, BlockManagerId(driver, localhost, 55483)
//17/12/29 14:15:50 INFO BlockManagerMaster: Registered BlockManager
//+----+-------+
//| age| name|
//+----+-------+
//|null|Michael|
//| 30| Andy|
//| 19| Justin|
//+----+-------+
//
//root
// |-- age: long (nullable = true)
// |-- name: string (nullable = true)
//
//+-------+
//| name|
//+-------+
//|Michael|
//| Andy|
//| Justin|
//+-------+
//
//+-------+----------+
//| name|(age + 10)|
//+-------+----------+
//|Michael| null|
//| Andy| 40|
//| Justin| 29|
//+-------+----------+
//
//+---+----+
//|age|name|
//+---+----+
//| 30|Andy|
//+---+----+
//
//+----+-----+
//| age|count|
//+----+-----+
//|null| 1|
//| 19| 1|
//| 30| 1|
//+----+-----+
