SPARK 简单操作

1、从本地上传文件到hdfs

hdfs dfs -put  ~/Downloads/tac

删除文件夹

hdfs dfs -rm -r ./tac
 cd /usr/local/dbtaobao/dataset
//下面删除user_log.csv中的第1行
sed -i '1d' user_log.csv //1d表示删除第1行，同理，3d表示删除第3行，nd表示删除第n行
 //下面再用head命令去查看文件的前5行记录，就看不到字段名称这一行了
head -5 user_log.csv

2、创建trajectory表

在做


 CREATE EXTERNAL TABLE dbtac.trajectory(vme_id STRING,gps_time STRING,work_state INT,ultrasonic_station INT,limit_switch_state INT,work_deep INT,longtitude DOUBLE,latitude DOUBLE,elevation INT,speed INT, course_direction INT)
   ROW FORMAT DELIMITED FIELDS TERMINATED BY '\t' STORED AS TEXTFILE ;


 load data inpath '/dbtac/tac/S901100003_2015.csv' into table trajectory;
LOAD DATA LOCAL INPATH '/win/test/test10.csv' INTO TABLE trajectory;

 load data inpath '/dbtac/tac/*.csv' into table trajectory;

DROP TABLE IF EXISTS trajectory;