基于Hadoop和Hive实现聊天数据统计分析，构建聊天数据分析报表。_hadoop根据select结果建表

需求

• 统计今日总消息量
• 统计今日每小时消息量、发送和接收用户数
• 统计今日各地区发送消息数据量
• 统计今日发送消息和接收消息的用户数
• 统计今日发送消息最多的Top10用户
• 统计今日接收消息最多的Top10用户
• 统计发送人的手机型号分布情况
• 统计发送人的设备操作系统分布情况

drop database if exists db_msg cascade ;
--创建数据库
create database db_msg ;
--切换数据库
use db_msg ;
--列举数据库
show databases ;

--如果表已存在就删除
drop table if exists db_msg.tb_msg_source ;
--建表
create table db_msg.tb_msg_source(
msg_time string comment "消息发送时间"
, sender_name string comment "发送人昵称"
, sender_account bigint comment "发送人账号"
, sender_sex string comment "发送人性别"
, sender_ip string comment "发送人ip地址"
, sender_os string comment "发送人操作系统"
, sender_phonetype string comment "发送人手机型号"
, sender_network string comment "发送人网络类型"
, sender_gps string comment "发送人的GPS定位"
, receiver_name string comment "接收人昵称"
, receiver_ip string comment "接收人IP"
, receiver_account bigint comment "接收人账号"
, receiver_os string comment "接收人操作系统"
, receiver_phonetype string comment "接收人手机型号"
, receiver_network string comment "接收人网络类型"
, receiver_gps string comment "接收人的GPS定位"
, receiver_sex string comment "接收人性别"
, msg_type string comment "消息类型"
, distance string comment "双方距离"
, message string comment "消息内容" );
--指定分隔符为制表符
row format delimited fields terminated by '\t' ;
load data local inpath '/root/chat_data-10W.csv' into table db_msg.tb_msg_source;
//验证结果
select
msg_time,sender_name,sender_ip,sender_phonetype,receiver_name,receiver_network
from tb_msg_source limit 10;

--如果表已存在就删除
drop table if exists db_msg.tb_msg_etl;
--将Select语句的结果保存到新表中
create table db_msg.tb_msg_etl as
select
*,
substr(msg_time,0,10) as dayinfo, substr(msg_time,12,2) as hourinfo, --获取天和小时
split(sender_gps,",")[0] as sender_lng, split(sender_gps,",")[1] as sender_lat --提取经度纬度
from db_msg.tb_msg_source
--过滤字段为空的数据
where length(sender_gps) > 0 ;

select
msg_time,dayinfo,hourinfo,sender_gps,sender_lng,sender_lat
from db_msg.tb_msg_etl
limit 10;

--保存结果表
create table if not exists tb_rs_total_msg_cnt
comment "今日消息总量"
as
select
dayinfo,
count(*) as total_msg_cnt
from db_msg.tb_msg_etl
group by dayinfo;

--保存结果表
create table if not exists tb_rs_hour_msg_cnt
comment "每小时消息量趋势"
as
select
dayinfo,
hourinfo,
count(*) as total_msg_cnt,
count(distinct sender_account) as se

基于FineBI实现可视化报表