如何快速把hdfs数据动态导入到hive表
1. hdfs 文件
{"retCode":1,"retMsg":"Success","data":[{"secID":"000001.XSHE","ticker":"000001","secShortName":"深发展A","exchangeCD":"XSHE","tradeDate":"1991-10-21","preClosePrice":24,"actPreClosePrice":24,"openPrice":24,"highestPrice":24.4,"lowestPrice":23.85,"closePrice":23.9,"turnoverVol":355700,"turnoverValue":8582250,"turnoverRate":0.0058,"accumAdjFactor":0.0117201563,"negMarketValue":1462295257.8,"marketValue":2145064267.7,"PB":2.2666,"isOpen":1},{"secID":"000002.XSHE","ticker":"000002","secShortName":"深万科A","exchangeCD":"XSHE","tradeDate":"1991-10-21","preClosePrice":8,"actPreClosePrice":8,"openPrice":8,"highestPrice":8,"lowestPrice":7.7,"closePrice":7.9,"turnoverVol":375000,"turnoverValue":2944200,"turnoverRate":0.0066,"accumAdjFactor":0.0117337592,"negMarketValue":451011000,"marketValue":615927450,"PB":1.0001,"isOpen":1},{"secID":"000004.XSHE","ticker":"000004","secShortName":"深安达A","exchangeCD":"XSHE","tradeDate":"1991-10-21","preClosePrice":7.25,"actPreClosePrice":7.25,"openPrice":7.25,"highestPrice":7.25,"lowestPrice":7.2,"closePrice":7.2,"turnoverVol":92000,"turnoverValue":665125,"turnoverRate":0.0078,"accumAdjFactor":0.2649084628,"negMarketValue":84977100,"marketValue":175500000,"PB":7.4199,"isOpen":1},{"secID":"000005.XSHE","ticker":"000005","secShortName":"深原野A","exchangeCD":"XSHE","tradeDate":"1991-10-21","preClosePrice":6.46,"actPreClosePrice":6.46,"openPrice":6.49,"highestPrice":6.49,"lowestPrice":6.49,"closePrice":6.49,"turnoverVol":94500,"turnoverValue":613305,"turnoverRate":0.0021,"accumAdjFactor":0.1016459912,"negMarketValue":287756865,"marketValue":584100000,"PB":9.1783,"isOpen":1},{"secID":"000009.XSHE","ticker":"000009","secShortName":"深宝安A","exchangeCD":"XSHE","tradeDate":"1991-10-21","preClosePrice":5.75,"actPreClosePrice":5.75,"openPrice":5.7,"highestPrice":5.8,"lowestPrice":5.65,"closePrice":5.75,"turnoverVol":767500,"turnoverValue":4382245,"turnoverRate":0.0084,"accumAdjFactor":0.1026538759,"negMarketValue":524745000,"marketValue":1293922500,"PB":2.4503,"isOpen":1},{"secID":"600601.XSHG","ticker":"600601","secShortName":"延中实业","exchangeCD":"XSHG","tradeDate":"1991-10-21","preClosePrice":65.7,"actPreClosePrice":65.7,"openPrice":66.4,"highestPrice":66.4,"lowestPrice":66.4,"closePrice":66.4,"turnoverVol":5333,"turnoverValue":354111,"dealAmount":81,"turnoverRate":0.0053,"accumAdjFactor":0.0010592167,"negMarketValue":66400000,"marketValue":66400000,"PB":40.7703,"isOpen":1},{"secID":"600602.XSHG","ticker":"600602","secShortName":"真空电子","exchangeCD":"XSHG","tradeDate":"1991-10-21","preClosePrice":640.6,"actPreClosePrice":640.6,"openPrice":647,"highestPrice":647,"lowestPrice":647,"closePrice":647,"turnoverVol":2589,"turnoverValue":1675083,"dealAmount":227,"turnoverRate":0.0051,"accumAdjFactor":0.0019640692,"negMarketValue":330552300,"marketValue":1294000000,"PB":287.6707,"isOpen":1},{"secID":"600651.XSHG","ticker":"600651","secShortName":"飞乐音响","exchangeCD":"XSHG","tradeDate":"1991-10-21","preClosePrice":119.6,"actPreClosePrice":119.6,"openPrice":120.8,"highestPrice":120.8,"lowestPrice":120.8,"closePrice":120.8,"turnoverVol":1102,"turnoverValue":133122,"dealAmount":14,"turnoverRate":0.0022,"accumAdjFactor":0.0008192464,"negMarketValue":60400000,"marketValue":60400000,"PB":39.6397,"isOpen":1},{"secID":"600652.XSHG","ticker":"600652","secShortName":"爱使电子","exchangeCD":"XSHG","tradeDate":"1991-10-21","preClosePrice":83.2,"actPreClosePrice":83.2,"openPrice":0,"highestPrice":0,"lowestPrice":0,"closePrice":83.2,"turnoverVol":0,"turnoverValue":0,"dealAmount":0,"turnoverRate":0,"accumAdjFactor":0.0006920481,"negMarketValue":22464000,"marketValue":22464000,"PB":33.8019,"isOpen":0},{"secID":"600653.XSHG","ticker":"600653","secShortName":"申华电工","exchangeCD":"XSHG","tradeDate":"1991-10-21","preClosePrice":103.4,"actPreClosePrice":103.4,"openPrice":104.4,"highestPrice":104.4,"lowestPrice":104.4,"closePrice":104.4,"turnoverVol":240,"turnoverValue":25056,"dealAmount":4,"turnoverRate":0.0005,"accumAdjFactor":0.0009289199,"negMarketValue":52200000,"marketValue":52200000,"PB":97.279,"isOpen":1},{"secID":"600654.XSHG","ticker":"600654","secShortName":"飞乐股份","exchangeCD":"XSHG","tradeDate":"1991-10-21","preClosePrice":633.2,"actPreClosePrice":633.2,"openPrice":639.5,"highestPrice":639.5,"lowestPrice":639.5,"closePrice":639.5,"turnoverVol":101,"turnoverValue":64590,"dealAmount":26,"turnoverRate":0.0048,"accumAdjFactor":0.000663586,"negMarketValue":13429500,"marketValue":134358950,"PB":282.9834,"isOpen":1},{"secID":"600656.XSHG","ticker":"600656","secShortName":"浙江凤凰","exchangeCD":"XSHG","tradeDate":"1991-10-21","preClosePrice":1242.9,"actPreClosePrice":1242.9,"openPrice":1255.3,"highestPrice":1255.3,"lowestPrice":1255.3,"closePrice":1255.3,"turnoverVol":140,"turnoverValue":175742,"dealAmount":7,"turnoverRate":0.0031,"accumAdjFactor":0.0007136096,"negMarketValue":56502308.3,"marketValue":321798665.6,"PB":-604.4303,"isOpen":1}]}
2. 创建 hive 临时表
CREATE EXTERNAL TABLE if not exists sensitop.equd_json_tmp (
retCode string,
retMsg string,
data array<struct<
secID: string,
tradeDate: date,
ticker: string,
secShortName: string,
exchangeCD: string,
preClosePrice: double,
actPreClosePrice: double,
openPrice: double,
highestPrice: double,
lowestPrice: double,
closePrice: double,
turnoverVol: double,
turnoverValue: double,
dealAmount: int,
turnoverRate: double,
accumAdjFactor: double,
negMarketValue: double,
marketValue: double,
PE: double,
PE1: double,
PB: double,
isOpen: int>>)
ROW FORMAT SERDE 'org.apache.hive.hcatalog.data.JsonSerDe'
LOCATION 'hdfs://hdfs1.wdp:8020/sensitop/finance/equd';
3. 创建 hive 表
需要把上面表里数组里的数据一条一条放入这个表：
CREATE TABLE if not exists sensitop.equd_h(
secID string,
ticker string,
secShortName string,
exchangeCD string,
tradeDate date,
preClosePrice double,
actPreClosePrice double,
openPrice double,
highestPrice double,
lowestPrice double,
closePrice double,
turnoverVol double,
turnoverValue double,
dealAmount int,
turnoverRate double,
accumAdjFactor double,
negMarketValue double,
marketValue double,
PE double,
PE1 double,
PB double,
isOpen int)
partitioned by (year string)
ROW FORMAT SERDE 'org.apache.hive.hcatalog.data.JsonSerDe'
然后新建一个最张表
CREATE TABLE if not exists sensitop.equd(
secID string,
ticker string,
secShortName string,
exchangeCD string,
tradeDate date,
preClosePrice double,
actPreClosePrice double,
openPrice double,
highestPrice double,
lowestPrice double,
closePrice double,
turnoverVol double,
turnoverValue double,
dealAmount int,
turnoverRate double,
accumAdjFactor double,
negMarketValue double,
marketValue double,
PE double,
PE1 double,
PB double,
isOpen int)
partitioned by (year string)
注意：这里的字段顺序和上面临时表的顺序要一致。
4. 用 Partition 更新数据
insert overwrite table sensitop.equd_tmp
partition (year='2016')
select b.dt.secID,
b.dt.ticker,
b.dt.secShortName,
b.dt.exchangeCD,
b.dt.tradeDate,
b.dt.preClosePrice,
b.dt.actPreClosePrice,
b.dt.openPrice,
b.dt.highestPrice,
b.dt.lowestPrice,
b.dt.closePrice,
b.dt.turnoverVol,
b.dt.turnoverValue,
b.dt.dealAmount,
b.dt.turnoverRate,
b.dt.accumAdjFactor,
b.dt.negMarketValue,
b.dt.marketValue,
b.dt.PE,
b.dt.PE1,
b.dt.PB,
b.dt.isOpen
from sensitop.equd_json_tmp LATERAL VIEW explode(equd_json_tmp.data) b AS dt
where dt.tradedate >= '2016-01-01' and dt.tradedate <= '2016-12-31';
insert overwrite table sensitop.equd
partition (year='2016')
select secID,
ticker,
secShortName,
exchangeCD,
tradeDate,
preClosePrice,
actPreClosePrice,
openPrice,
highestPrice,
lowestPrice,
closePrice,
turnoverVol,
turnoverValue,
dealAmount,
turnoverRate,
accumAdjFactor,
negMarketValue,
marketValue,
PE,
PE1,
PB,
isOpen
from sensitop.equd_tmp dt
where year = '2016';
5. 用nifi实现动态插入数据
这里有二个分支，左边一个是每天20：00更新当年的partion； 右边一个是更新1990 到 2015 年的数据，而且只需要更新一次。
insert overwrite table sensitop.equd_h
partition (year='${year}')
select b.dt.secID,
b.dt.ticker,
b.dt.secShortName,
b.dt.exchangeCD,
b.dt.tradeDate,
b.dt.preClosePrice,
b.dt.actPreClosePrice,
b.dt.openPrice,
b.dt.highestPrice,
b.dt.lowestPrice,
b.dt.closePrice,
b.dt.turnoverVol,
b.dt.turnoverValue,
b.dt.dealAmount,
b.dt.turnoverRate,
b.dt.accumAdjFactor,
b.dt.negMarketValue,
b.dt.marketValue,
b.dt.PE,
b.dt.PE1,
b.dt.PB,
b.dt.isOpen
from sensitop.equd_json_tmp LATERAL VIEW explode(equd_json_tmp.data) b AS dt
where dt.tradedate >= '${year}-01-01' and dt.tradedate <= '${year}-12-31'
insert overwrite table sensitop.equd
partition (year='${year}')
select secID,
ticker,
secShortName,
exchangeCD,
tradeDate,
preClosePrice,
actPreClosePrice,
openPrice,
highestPrice,
lowestPrice,
closePrice,
turnoverVol,
turnoverValue,
dealAmount,
turnoverRate,
accumAdjFactor,
negMarketValue,
marketValue,
PE,
PE1,
PB,
isOpen
from sensitop.equd_tmp dt
where year = '${year}'
NIFI 中国社区 QQ群：595034369
如何快速把hdfs数据动态导入到hive表的更多相关文章
- 11.把文本文件的数据导入到Hive表中
先在hive里面创建一个表 create table mydb2.t3(id int,name string,age int) row format delimited fields terminat ...
- 使用 sqoop 将mysql数据导入到hive表（import）
Sqoop将mysql数据导入到hive表中 先在mysql创建表 CREATE TABLE `sqoop_test` ( `id` ) DEFAULT NULL, `name` varchar() ...
- mysql中把一个表的数据批量导入另一个表中
mysql中把一个表的数据批量导入另一个表中 不管是在网站开发还是在应用程序开发中,我们经常会碰到需要将MySQL或MS SQLServer某个表的数据批量导入到另一个表的情况,甚至有时还需要指定 ...
- 大数据开发实战：Hive表DDL和DML
1.Hive 表 DDL 1.1.创建表 Hive中创建表的完整语法如下: CREATE [EXTERNAL] TABLE [IF NOT EXISTS] table_name [ (col_nam ...
- 将DataFrame数据如何写入到Hive表中
1.将DataFrame数据如何写入到Hive表中?2.通过那个API实现创建spark临时表?3.如何将DataFrame数据写入hive指定数据表的分区中? 从spark1.2 到spark1.3 ...
- 用sqoop将mysql的数据导入到hive表中
1:先将mysql一张表的数据用sqoop导入到hdfs中 准备一张表 需求 将 bbs_product 表中的前100条数据导 导出来 只要id brand_id和 name 这3个字段 数据存 ...
- 用puthivestreaming把hdfs里的数据流到hive表
全景图: 1. 创建hive表 CREATE TABLE IF NOT EXISTS newsinfo.test( name STRING ) CLUSTERED BY (name)INTO 3 ...
- 用sqoop将mysql的数据导入到hive表
一.先将mysql一张表的数据用sqoop导入到hdfs 1.1.先在mysql中准备一张测试用的表 mysql> desc user_info; +-----------+---------- ...
- 从Oracle导出数据并导入到Hive
1.配置源和目标的数据连接 源(oracle): 目标(Hive 2.1.1),需要事先将hive的驱动程序导入HHDI的lib目录中. Hive2.1.1需要的jar包如下:可根据自身情况更换had ...
随机推荐
- mysql通过data文件恢复数据库的方式
1.首先定位mysql的my.ini配置文件,查找datadir的位置 #Path to the database rootdatadir="C:/ProgramData/MySQL/MyS ...
- 深入浅出Symfony2 - 结合MongoDB开发LBS应用
简介 随着近几年各类移动终端的迅速普及,基于地理位置的服务(LBS)和相关应用也越来越多,而支撑这些应用的最基础技术之一,就是基于地理位置信息的处理.我所在的项目也正从事相关系统的开发,我们使用的是S ...
- LINUX 命令定期执行可执行文件
linux命令将nodejs文件变成可执行文件 在linux中一般我们在运行node文件时用的命令为: node example.js 首先.删除文件后缀,在linux命令下添加可执行权限 mv ex ...
- js和php对bool值的判断区别
一.将一种数据类型转换为bool值时,PHP和JS的转换规则不同 PHP中 当转换为 boolean 时,以下值被认为是 FALSE : 布尔值 FALSE 本身 整型值 0(零) 浮点型值 0.0( ...
- ReportViewer 不预览，直接导出 PDF文件
作为笔记记着,以免以后再到处找资料 1. 在不预览的情况下导出文件 先看一个方法说明,想知道ReportViewer支持导出哪些文件类型,在Render方法说明中就有描述 // // Summary: ...
- MCMC and Bayesian Data Analysis(PPT在文件模块)
How to generate a sample from $p(x)$? Let's first see how Matlab samples from a $p(x)$. In Matlab, t ...
- url中，中文乱码的问题
1// 在jsp中 String add = java.net.URLEncoder.encode("添加", "utf-8"); add = java.net ...
- prism4 StockTrader RI 项目分析一些体会
StockTrader RI 代码分析也有一段时间了 刚从codeplex获取到源代码的时候,看得一头雾水,不知所云(因为之前没做过wpf的项目,看文档也静不下那心来看) 后来就想了个笨办法,模拟项目 ...
- iOS emoji表情转码 或者判断
如果项目中有评论或者信息恢复的地方,往往会用到emoji,有时候如后台不支持emoji,就会显示乱码错误,我们可以把emoji转成unicode编码或者utf8编码格式传给服务器.当然如果后台服务器接 ...
- Linux的phpstudy mysql登录
使用绝对路径登录 /phpStudy/mysql/bin/mysql -uroot -p; 设置远程登录密码 GRANT ALL PRIVILEGES ON *.* TO 'itoffice'@'%' ...