Web前端一套全部清晰 ⑦ day4 CSS.2 复合选择器、CSS特性、背景属性、标签的显示模式-CFANZ编程社区

案例需求：

RFM模型的复习

商用航空行业LRFCM模型的推广：

-------------------------------------本次练习基于数据源提取上述五个指标分析航空客户商业价值。

数据源：数据源

数据指标说明：

Hive操作：

构建数据库表：

reate database air_data_base;
use air_data_base;
create table air_data_table(
            member_no string,
            ffp_date string,
            first_flight_date string,
            gender string,
            ffp_tier int,
            work_city string,
            work_province string,
            work_country string,
            age int,
            load_time string,
            flight_count int,
            bp_sum bigint,
            ep_sum_yr_1 int,
            ep_sum_yr_2 bigint,
            sum_yr_1 bigint,
            sum_yr_2 bigint,
            seg_km_sum bigint,
            weighted_seg_km double,
            last_flight_date string,
            avg_flight_count double,
            avg_bp_sum double,
            begin_to_first int,
            last_to_end int,
            avg_interval float,
            max_interval int,
            add_points_sum_yr_1 bigint,
            add_points_sum_yr_2 bigint,
            exchange_count int,
            avg_discount float,
            p1y_flight_count int,
            l1y_flight_count int,
            p1y_bp_sum bigint,
            1y_bp_sum bigint,
            ep_sum bigint,
            add_point_sum bigint,
            eli_add_point_sum bigint,
            l1y_eli_add_points bigint,
            points_sum bigint,
            l1y_points_sum float,
            ration_l1y_flight_count float,
            ration_p1y_flight_count float,
            ration_p1y_bps float,
            ration_l1y_bps float,
            point_notflight int
            )
            row format delimited fields terminated by ',';

将数据源上传到Linux本地文件夹中，再从本地上传到hive数据库中：

load data local inpath '/home/hadoop/air_data.csv' overwrite into table air_data_table;
select * from air_data_table limit 20;

create table sum_seg_avg_null as select * from
(select count(*) as sum_yr_1_null_count from air_data_table where sum_yr_1 is null) sum_yr_1,
(select count(*) as seg_km_sum_null from air_data_table where seg_km_sum is null) seg_km_sum,
(select count(*) as avg_discount_null from air_data_table where avg_discount is null) avg_discount;

create table sum_seg_avg_min as select
min(sum_yr_1) as sum_yr_1,
min(seg_km_sum) as seg_km_sum,
min(avg_discount) as avg_discount
from air_data_table;

数据清洗：

create table sas_not_0 as
select * from air_data_table
where sum_yr_1 is not null and
      avg_discount <> 0    and
      seg_km_sum > 0;

提取有用数据项：

create table flfasl as select ffp_date,load_time,flight_count,avg_discount,seg_km_sum,last_to_end from sas_not_0;
select * from flfasl limit 10;

create table lrfmc as
select
    round((unix_timestamp(load_time,'yyyy/MM/dd')-unix_timestamp(ffp_date,'yyyy/MM/dd'))/(30*24*60*60),2) as l,
    round(last_to_end/30,2) as r,
    flight_count as f,
    seg_km_sum as m,
    round(avg_discount,2) as c
from flfasl;

数据标准化：

create table standard_lrfmc as
     select (lrfmc.l-minlrfmc.l)/(maxlrfmc.l-minlrfmc.l) as l,
      (lrfmc.r-minlrfmc.r)/(maxlrfmc.r-minlrfmc.r) as r,
     (lrfmc.f-minlrfmc.f)/(maxlrfmc.f-minlrfmc.f) as f,
     (lrfmc.m-minlrfmc.m)/(maxlrfmc.m-minlrfmc.m) as m,
     (lrfmc.c-minlrfmc.c)/(maxlrfmc.c-minlrfmc.c) as c
     from lrfmc,
        (select max(l) as l,max(r) as r,max(f) as f,max(m) as m,max(c) as c from lrfmc) as maxlrfmc,
        (select min(l) as l,min(r) as r,min(f) as f,min(m) as m,min(c) as c from lrfmc) as minlrfmc;