[人工智能]基于新浪微博的?志数据分析

[{"beCommentWeiboId":"","beForwardWeiboId":"","catchTime":"1387159495","co mmentCount":"1419","content":"分享图
片","createTime":"1386981067","info1":"","info2":"","info3":"","mlevel":"" ,"musicurl":[],"pic_list": ["http://ww3.sinaimg.cn/thumbnail/40d61044jw1ebixhnsiknj20qo0qognx.jpg"]," praiseCount":"5265","reportCount":"1285","source":"iPad客户
端","userId":"1087770692","videourl": [],"weiboId":"3655325888057474","weiboUrl":"http://weibo.com/1087770692/An dhixO7g"}] 2 [{"beCommentWeiboId":"","beForwardWeiboId":"","catchTime":"1387159495","co mmentCount":"91","content":"行走：#去远方发现自己#@费勇主编，跨界明星联合执笔，
分享他们观行思趣的心发现、他们的成长与心路历程，当当网限量赠送出品人@陈坤抄诵印刷版
《心经》，赠完不再加印哦！详情请戳：
http://t.cn/8k622Sj","createTime":"1386925242","info1":"","info2":"","info 3":"","mlevel":"","musicurl":[],"pic_list": ["http://ww4.sinaimg.cn/thumbnail/b2336177jw1ebi6j4twk7j20m80tkgra.jpg"]," praiseCount":"1","reportCount":"721","source":"","userId":"2989711735","vi deourl": [],"weiboId":"3655091741442099","weiboUrl":"http://weibo.com/2989711735/An 7bE639F"}]

beCommentWeiboId 是否评论
beForwardWeiboId 是否是转发微博
catchTime 抓取时间
commentCount 评论次数
content 内容
createTime 创建时间
info1 信息字段1
info2信息字段2
info3信息字段3
mlevel no sure musicurl ?乐链接
pic_list 照?列表（可以有多个）
praiseCount 点赞?数
reportCount 转发?数
source 数据来源
userId ?户id
videourl 视频链接
weiboId 微博id
weiboUrl 微博?址

在hadoop创建目录

hadoop dfs -mkdir weibo
hadoop fs -put ./weibo/*  
hadoop fs -ls /weibo

hive创建库

create database if not exists weibo;
use weibo; 
create external table weibo(json string) location '/weibo';
select * from weibo limit 3;

处理json格式数据使用到get_json_object()和json_tuple(),其中两者都只认最外层是花括号 { } 才能正常解析.最外层是时 [ ] 不能解析,
当最外层时 [] 时可使用substring方法去掉最外层 [ ]

select get_json_object(substring(json,2,length(json)-1),'$.userId') from weibo limit 1;

统计需求

微博总量和独立用户数

#总量
select count(*) from weibo;
#独立用户数
select count(distinct(get_json_object(a.j,'$.userId'))) 
from 
(select substring(json,2,length(json)-1) as j from weibo) a;

用户所有微博被转发的总数，输出前3个用户
使用json_tuple提取多个字段

select b.id,sum(b.cnt) as bsum 
from 
(select 
json_tuple(a.j,'userId','reportCount') as (id,cnt) 
from 
(select substring(json,2,length(json)-1) as j from weibo) a) 
b 
group by b.id
order by bsum desc
limit 3;

被转发次数最多的前3条微博，输出用户id

select 
get_json_object(a.j,'$.userId') as id,
cast(get_json_object(a.j,'$.reportCount') as INT) as cnt 
from 
(select substring(json,2,length(json)-1) as j from weibo) a 
order by cnt desc 
limit 3;

每个用户发布的微博总数，存储到临时表

create table weibo_uid_wbcnt( 
userid string, wbcnt int ) 
row format delimited 
fields terminated by '\t'; 
insert overwrite table weibo_uid_wbcnt select get_json_object(a.j,'$.userId'),count(1) 
from 
(select substring(json,2,length(json)-2) as j from weibo) a 
group by get_json_object(a.j,'$.userId'); 

select * from weibo_uid_wbcnt limit 10;

统计带图片的微博数

select count(1) 
from 
(select substring(json,2,length(json)-2) as j from weibo) a 
where get_json_object(a.j,'$.pic_list') like '%http%'; 

统计使用iphone发微博的独立用户数

select count(distinct get_json_object(a.j,'$.userId')) 
from 
(select substring(json,2,length(json)-2) as j from weibo) a 
where lower(get_json_object(a.j,'$.source')) like '%iphone%';

微博中评论次数小于1000的用户id和数据来源，放入视图

 create view weibo_view as 
 select get_json_object(a.j,'$.userId') as id,get_json_object(a.j,'$.source') as source 
 from 
 (select substring(json,2,length(json)-2) as j from weibo) a 
 where get_json_object(a.j,'$.commentCount')<1000; 
 select * from weibo_view limit 10;

统计上条视图中数据来源“ipad客户端”的用户数目

select count(distinct id) as cnt from weibo_view where source='iPad客户端';

将微博的点赞数和转发数求和，降序，取前10条。

public class DemoTest1 extends UDF { 
public Integer evaluate(Integer num1,Integer num2){ 
try{ 
	return num1+num2; 
	}catch (Exception e){ 
	return null; } 
	} 
} 
create temporary function wb as 'DemoTest1';

select wb(cast(get_json_object(a.j,'$.praiseCount') as int),cast(get_json_object(a.j,'$.reportCount') as int)) as cnt 
from 
(select substring(json,2,length(json)-2) as j from weibo) a 
order by cnt desc limit 10;

?户微博内容中出现iphone关键词的最?次数

public class DemoTest2 extends UDF { 
	public int evaluate(String content,String word){ 
		int count = 0; 
		if(content != null&&content.length()>0){ 
		String[] array = content.split(word); 
		count = array.length-1; 
		} 
	return count; 
	} 
}
create temporary function wcount as 'DemoTest2';


select b.id,max(b.cnt) as cn 
from 
(select get_json_object(a.j,'$.userId') as id,wcount(get_json_object(a.j,'$.content'),'iphone') as cnt 
from 
(select substring(json,2,length(json)-2) as j from weibo) a) b 
group by b.id 
order by cn desc limit 10;