大数据综合实例—陌陌聊天数据分析

大数据综合实例—陌陌聊天数据分析

1. 需求分析

• 数据大小：14万条
• 列分隔符：制表符 \t
  

2. 建库建表与加载数据

• 建库

--------------1、建库-------------------

--如果数据库已存在就删除
drop database if exists db_msg cascade;
--创建数据库
create database db_msg;
--切换数据库
use db_msg;

• 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     string  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   string  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';

• 加载数据并做初步检测

--------------3、加载数据-------------------
--上传数据文件到node1服务器本地文件系统（HS2服务所在机器）
--shell:  mkdir -p /root/hivedata

--加载数据到表D
load data local inpath '/hiveData/data1.tsv' into table db_msg.tb_msg_source;
load data local inpath '/hiveData/data2.tsv' into table db_msg.tb_msg_source;

--查询表 验证数据文件是否映射成功
select * from tb_msg_source limit 10;

--统计行数
select count(*) as cnt from tb_msg_source;

3. ETL数据清洗

抽取（extract）、转换（transform）、加载（load) 处理不合法的数据

按照具体要求处理ETL数据

-- 问题1：当前数据中，有一些数据的字段为空，不是合法数据
select
   msg_time,
   sender_name,
   sender_gps
from db_msg.tb_msg_source
where length(sender_gps) = 0
limit 10;
-- 解决：用where&length 如果长度为0则排除



-- 问题2：需求中，需要统计每天、每个小时的消息量，但是数据中没有天和小时字段，只有整体时间字段，不好处理
select
   msg_time
from db_msg.tb_msg_source
limit 10;
-- 解决：利用substring函数做截取，将需要的时间截取出来作为单独的字段
select  msg_time,substr(msg_time,1,10) as dayinfo,substr(msg_time,12,2) as hourinfo
from  tb_msg_source limit 2;


-- 问题3：需求中，需要对经度和维度构建地区的可视化地图，但是数据中GPS经纬度为一个字段，不好处理
select
   sender_gps
from db_msg.tb_msg_source
limit 10;
-- 解决：使用切割函数split进行切割，将经度和纬度分为两个不同的字段

• CTAS语法

creat table as select : 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, --获取天
  substr(msg_time,12,2) as hourinfo, --获取小时
  split(sender_gps,",")[0] as sender_lng, --提取经度
  split(sender_gps,",")[1] as sender_lat --提取纬度
from db_msg.tb_msg_source
--过滤字段为空的数据
where length(sender_gps) > 0 ;

4. SQL编写思路与指标计算

• 编写思路

• 统计今日总消费量

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;

select * from tb_rs_total_msg_cnt;--结果验证

• 统计今日每小时消息量、发送和接收用户数

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 sender_usr_cnt,
  count(distinct receiver_account) as receiver_usr_cnt
from db_msg.tb_msg_etl
group by dayinfo,hourinfo;

• 统计今日各地区发送消息数据量

create table if not exists tb_rs_loc_cnt
comment "今日各地区发送消息总量"
as
select
  dayinfo,
  sender_gps,
  cast(sender_lng as double) as longitude,   -- cast将string类型转化为double类型
  cast(sender_lat as double) as latitude,
  count(*) as total_msg_cnt
from db_msg.tb_msg_etl
group by dayinfo,sender_gps,sender_lng,sender_lat;

select * from tb_rs_loc_cnt; --结果验证

• 统计今日发送消息和接收消息的用户数

create table if not exists tb_rs_usr_cnt
comment "今日发送消息人数、接受消息人数"
as
select
  dayinfo,
  count(distinct sender_account) as sender_usr_cnt,
  count(distinct receiver_account) as receiver_usr_cnt
from db_msg.tb_msg_etl
group by dayinfo;

select * from tb_rs_usr_cnt; --结果验证

• 统计今日发送消息最多的Top10用户

最：涉及排序问题 order by

create table if not exists tb_rs_susr_top10
comment "发送消息条数最多的Top10用户"
as
select
  dayinfo,
  sender_name as username,
  count(*) as sender_msg_cnt
from db_msg.tb_msg_etl
group by dayinfo,sender_name
order by sender_msg_cnt desc
limit 10;

select * from tb_rs_susr_top10; --结果验证

• 统计今日接收消息最多的Top10用户

create table if not exists tb_rs_rusr_top10
comment "接受消息条数最多的Top10用户"
as
select
  dayinfo,
  receiver_name as username,
  count(*) as receiver_msg_cnt
from db_msg.tb_msg_etl
group by dayinfo,receiver_name
order by receiver_msg_cnt desc
limit 10;

select * from tb_rs_rusr_top10;  --结果验证

• 统计发送人的手机型号分布情况

create table if not exists tb_rs_sender_phone
comment "发送人的手机型号分布"
as
select
  dayinfo,
  sender_phonetype,
  count(distinct sender_account) as cnt
from tb_msg_etl
group by dayinfo,sender_phonetype;

select * from tb_rs_sender_phone; --结果验证

• 统计发送人的设备操作系统分布情况

create table if not exists tb_rs_sender_os
comment "发送人的OS分布"
as
select
  dayinfo,
  sender_os,
  count(distinct sender_account) as cnt
from tb_msg_etl
group by dayinfo,sender_os;

select * from tb_rs_sender_os;  --结果验证

5. 数据可视化—FineBI

• 下载安装
• 加载本地插件
• 连接Hive数据库

• 数据准备

• 将Hive中查询完成的表添加到FinBI

业务包可进行自动或定时更新

• 新建仪表盘Momocase

• 编辑组件得到最终效果

大数据核心基础终于完结撒花了