counterweight/data-dwh-dbt-project
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Merged PR 3472: Remove unused models and schema entries for deals and accommodations

Browse source 
# Description

Eliminates models that have been switched with new kpis flow.
Also deletes temporary tests and schema entries.

# Checklist

- [X] The edited models and dependants run properly with production data.
- [NA] The edited models are sufficiently documented.
- [X] The edited models contain PK tests, and I've ran and passed them.
- [X] I have checked for DRY opportunities with other models and docs.
- [NA] I've picked the right materialization for the affected models.

# Other

- [ ] Check if a full-refresh is required after this PR is merged.

Related work items: #23762
This commit is contained in:
Oriol Roqué Paniagua 2024-11-08 12:05:40 +00:00
parent 5e1b418570
commit 2f80642f6c
10 changed files with 1 additions and 1358 deletions
Download patch file Download diff file Expand all files Collapse all files

52
models/intermediate/core/int_core__monthly_accommodation_history_by_deal.sql
View file

@ -1,52 +0,0 @@
/*
This model provides monthly accommodation metrics for those hosts that have a deal assigned.
*/
{{ config(materialized="table", unique_key=["date", "id_deal"]) }}
with
int_core__mtd_accommodation_lifecycle as (select * from {{ ref("int_core__mtd_accommodation_lifecycle") }}),
int_dates_by_deal as (select * from {{ ref("int_dates_by_deal") }}),
int_core__unique_accommodation_to_user as (select * from {{ ref("int_core__unique_accommodation_to_user") }}),
int_core__unified_user as (select * from {{ ref("int_core__unified_user") }}),
listings_metric_aggregation_per_date_and_deal as (
select
al.date,
u.id_deal,
COUNT(distinct case when al.accommodation_lifecycle_state = '01-New' then al.id_accommodation else null end) as new_listings,
COUNT(distinct case when al.accommodation_lifecycle_state = '02-Never Booked' then al.id_accommodation else null end) as never_booked_listings,
COUNT(distinct case when al.accommodation_lifecycle_state = '03-First Time Booked' then al.id_accommodation else null end) as first_time_booked_listings,
COUNT(distinct case when al.accommodation_lifecycle_state = '04-Active' then al.id_accommodation else null end) as active_listings,
COUNT(distinct case when al.accommodation_lifecycle_state = '05-Churning' then al.id_accommodation else null end) as churning_listings,
COUNT(distinct case when al.accommodation_lifecycle_state = '06-Inactive' then al.id_accommodation else null end) as inactive_listings,
COUNT(distinct case when al.accommodation_lifecycle_state = '07-Reactivated' then al.id_accommodation else null end) as reactivated_listings,
SUM(case when has_been_booked_within_current_month then 1 else 0 end) as listings_booked_in_month,
SUM(case when has_been_booked_within_last_6_months then 1 else 0 end) as listings_booked_in_6_months,
SUM(case when has_been_booked_within_last_12_months then 1 else 0 end) as listings_booked_in_12_months
from int_core__mtd_accommodation_lifecycle al
inner join int_core__unique_accommodation_to_user atu
on al.id_accommodation = atu.id_accommodation
inner join int_core__unified_user u
on atu.id_user_owner = u.id_user
where id_deal is not null
group by al.date, u.id_deal
)
select
d.year,
d.month,
d.day,
d.date,
d.id_deal,
l.new_listings as new_listings,
l.never_booked_listings as never_booked_listings,
l.first_time_booked_listings as first_time_booked_listings,
l.active_listings as active_listings,
l.churning_listings as churning_listings,
l.inactive_listings as inactive_listings,
l.reactivated_listings as reactivated_listings,
l.listings_booked_in_month as listings_booked_in_month,
l.listings_booked_in_6_months as listings_booked_in_6_months,
l.listings_booked_in_12_months as listings_booked_in_12_months
from int_dates_by_deal d
left join listings_metric_aggregation_per_date_and_deal l
on d.date = l.date and d.id_deal = l.id_deal

169
models/intermediate/core/int_core__mtd_accommodation_lifecycle.sql
View file

@ -1,169 +0,0 @@
/*
This model provides Month-To-Date (MTD) accommodation lifecycle based on booking metrics.
*/
{{ config(materialized="table", unique_key=["date","id_accommodation"]) }}
with
int_core__bookings as (select * from {{ ref("int_core__bookings") }}),
stg_core__accommodation as (select * from {{ ref("stg_core__accommodation") }}),
int_core__unique_accommodation_to_user as (select * from {{ ref("int_core__unique_accommodation_to_user")}}),
int_dates_mtd as (select * from {{ ref("int_dates_mtd") }}),
booked_days_per_accommodation as (
select
id_accommodation,
created_date_utc,
lag(created_date_utc, 1) over (
partition by id_accommodation order by created_date_utc asc
) as previous_booked_date
from int_core__bookings
group by id_accommodation, created_date_utc
),
accommodation_historic_booking_dates as (
select
d.date,
a.id_accommodation,
date(a.created_at_utc) as creation_date_utc,
min(b.created_date_utc) as first_time_booked_date_utc,
max(b.created_date_utc) as last_time_booked_date_utc,
max(b.previous_booked_date) as second_to_last_time_booked_date_utc
from int_dates_mtd d
inner join stg_core__accommodation a on d.date >= date(a.created_at_utc)
-- Inclusion of unique accommodation to user to force that the
-- accommodation needs to have a host assigned into it.
inner join int_core__unique_accommodation_to_user uatu on uatu.id_accommodation = a.id_accommodation
left join
booked_days_per_accommodation b
on uatu.id_accommodation = b.id_accommodation
and d.date >= b.created_date_utc
group by d.date, a.id_accommodation, date(a.created_at_utc)
),
accommodation_historic_booking_features as (
select
ahbd.date,
ahbd.id_accommodation,
ahbd.creation_date_utc,
ahbd.first_time_booked_date_utc,
ahbd.last_time_booked_date_utc,
ahbd.second_to_last_time_booked_date_utc,
case
when ahbd.first_time_booked_date_utc is not null then true else false
end as accommodation_has_at_least_one_booking,
case
when
date_trunc('month', ahbd.creation_date_utc)
= date_trunc('month', ahbd.date)
then true
else false
end as accommodation_was_created_this_month,
case
when
date_trunc('month', ahbd.first_time_booked_date_utc)
= date_trunc('month', ahbd.last_time_booked_date_utc)
then true
else false
end as accommodation_has_first_booking,
case
when
date_trunc('month', ahbd.last_time_booked_date_utc)
= date_trunc('month', ahbd.date)
then true
else false
end as has_been_booked_within_current_month,
case
when
date_trunc('month', ahbd.last_time_booked_date_utc)
+ interval '6 months'
> date_trunc('month', ahbd.date)
then true
else false
end as has_been_booked_within_last_6_months,
case
when
date_trunc('month', ahbd.last_time_booked_date_utc)
+ interval '12 months'
> date_trunc('month', ahbd.date)
then true
else false
end as has_been_booked_within_last_12_months,
case
when
date_trunc('month', ahbd.last_time_booked_date_utc)
+ interval '12 months'
= date_trunc('month', ahbd.date)
then true
else false
end as last_booking_was_12_months_ago,
case
when
date_trunc('month', ahbd.second_to_last_time_booked_date_utc)
+ interval '12 months'
< date_trunc('month', ahbd.last_time_booked_date_utc)
then true
else false
end as had_previous_booking_more_than_12_months_before_the_last
from accommodation_historic_booking_dates ahbd
)
select
date,
id_accommodation,
creation_date_utc,
first_time_booked_date_utc,
last_time_booked_date_utc,
second_to_last_time_booked_date_utc,
case
-- 01-New: The listing has been created this month and has not had any booking
when
not accommodation_has_at_least_one_booking
and accommodation_was_created_this_month
then '01-New'
-- 02-Never Booked: The listing has been created before this month and has not
-- had any booking
when
not accommodation_has_at_least_one_booking
and not accommodation_was_created_this_month
then '02-Never Booked'
-- 03-First Time Booked: The listing has been booked for the first time and it
-- has been created this month
when accommodation_has_first_booking and has_been_booked_within_current_month
then '03-First Time Booked'
-- 04-Active: The listing has had at least 1 booking in its history and it's
-- been less than 12 months since the last booking
-- and is not reactivated and is not FTB
when
accommodation_has_at_least_one_booking
and has_been_booked_within_last_12_months
-- not reactivated
and not (
had_previous_booking_more_than_12_months_before_the_last
and has_been_booked_within_current_month
)
-- not FTB
and not (
accommodation_has_first_booking and has_been_booked_within_current_month
)
then '04-Active'
-- 05-Churning: The listing has been booked at least once and it's been 12
-- months since the last booking
when accommodation_has_at_least_one_booking and last_booking_was_12_months_ago
then '05-Churning'
-- 06-Inactive: The listing has been booked at least once and it's been more
-- than 12 months since the last booking
when
accommodation_has_at_least_one_booking
and not has_been_booked_within_last_12_months
and not last_booking_was_12_months_ago
then '06-Inactive'
-- 07-Reactivated: The listing was churned/inactive but has had a new booking
-- this month
when
had_previous_booking_more_than_12_months_before_the_last
and has_been_booked_within_current_month
then '07-Reactivated'
else null
end as accommodation_lifecycle_state,
has_been_booked_within_current_month,
has_been_booked_within_last_6_months,
has_been_booked_within_last_12_months
from accommodation_historic_booking_features

136
models/intermediate/core/int_core__mtd_accommodation_metrics.sql
View file

@ -1,136 +0,0 @@
/*
This model provides Month-To-Date (MTD) based on Accommodation metrics.
*/
{% set dimensions = get_kpi_dimensions() %}
{{ config(materialized="table", unique_key=["date", "dimension", "dimension_value"]) }}
with
int_core__mtd_accommodation_lifecycle as (
select * from {{ ref("int_core__mtd_accommodation_lifecycle") }}
),
int_core__user_host as (select * from {{ ref("int_core__user_host") }}),
int_core__mtd_accommodation_segmentation as (
select * from {{ ref("int_core__mtd_accommodation_segmentation") }}
),
int_dates_mtd_by_dimension as (
select * from {{ ref("int_dates_mtd_by_dimension") }}
),
int_core__unique_accommodation_to_user as (
select * from {{ ref("int_core__unique_accommodation_to_user") }}
),
listings_metric_aggregation_per_date as (
{% for dimension in dimensions %}
select
al.date,
{{ dimension.dimension }} as dimension,
{{ dimension.dimension_value }} as dimension_value,
count(
distinct case
when al.accommodation_lifecycle_state = '01-New'
then al.id_accommodation
else null
end
) as new_listings,
count(
distinct case
when al.accommodation_lifecycle_state = '02-Never Booked'
then al.id_accommodation
else null
end
) as never_booked_listings,
count(
distinct case
when al.accommodation_lifecycle_state = '03-First Time Booked'
then al.id_accommodation
else null
end
) as first_time_booked_listings,
count(
distinct case
when al.accommodation_lifecycle_state = '04-Active'
then al.id_accommodation
else null
end
) as active_listings,
count(
distinct case
when al.accommodation_lifecycle_state = '05-Churning'
then al.id_accommodation
else null
end
) as churning_listings,
count(
distinct case
when al.accommodation_lifecycle_state = '06-Inactive'
then al.id_accommodation
else null
end
) as inactive_listings,
count(
distinct case
when al.accommodation_lifecycle_state = '07-Reactivated'
then al.id_accommodation
else null
end
) as reactivated_listings,
sum(
case when has_been_booked_within_current_month then 1 else 0 end
) as listings_booked_in_month,
sum(
case when has_been_booked_within_last_6_months then 1 else 0 end
) as listings_booked_in_6_months,
sum(
case when has_been_booked_within_last_12_months then 1 else 0 end
) as listings_booked_in_12_months
from int_core__mtd_accommodation_lifecycle al
{% if dimension.dimension == "'by_number_of_listings'" %}
inner join
int_core__unique_accommodation_to_user atu
on atu.id_accommodation = al.id_accommodation
inner join int_core__user_host u on atu.id_user_owner = u.id_user_host
inner join
int_core__mtd_accommodation_segmentation mas
on u.id_deal = mas.id_deal
and al.date = mas.date
{% elif dimension.dimension == "'by_billing_country'" %}
inner join int_core__unique_accommodation_to_user atu
on atu.id_accommodation = al.id_accommodation
inner join int_core__user_host u on atu.id_user_owner = u.id_user_host
and u.main_billing_country_iso_3_per_deal is not null
{% endif %}
group by 1, 2, 3
{% if not loop.last %}
union all
{% endif %}
{% endfor %}
)
-- Final aggregation of subqueries --
select
d.year,
d.month,
d.day,
d.date,
d.dimension,
d.dimension_value,
d.is_end_of_month,
d.is_current_month,
nullif(l.new_listings, 0) as new_listings,
nullif(l.never_booked_listings, 0) as never_booked_listings,
nullif(l.first_time_booked_listings, 0) as first_time_booked_listings,
nullif(l.active_listings, 0) as active_listings,
nullif(l.churning_listings, 0) as churning_listings,
nullif(l.inactive_listings, 0) as inactive_listings,
nullif(l.reactivated_listings, 0) as reactivated_listings,
nullif(l.listings_booked_in_month, 0) as listings_booked_in_month,
nullif(l.listings_booked_in_6_months, 0) as listings_booked_in_6_months,
nullif(l.listings_booked_in_12_months, 0) as listings_booked_in_12_months
from int_dates_mtd_by_dimension d
left join
listings_metric_aggregation_per_date l
on l.date = d.date
and l.dimension = d.dimension
and l.dimension_value = d.dimension_value

42
models/intermediate/core/int_core__mtd_accommodation_segmentation.sql
View file

@ -1,42 +0,0 @@
{{ config(materialized="table", unique_key=["date", "id_deal"]) }}
with
int_core__mtd_accommodation_lifecycle as (
select * from {{ ref("int_core__mtd_accommodation_lifecycle") }}
),
int_core__unique_accommodation_to_user as (
select * from {{ ref("int_core__unique_accommodation_to_user") }}
),
int_core__unified_user as (select * from {{ ref("int_core__unified_user") }}),
active_accommodations_per_deal as (
select
al.date,
uu.id_deal,
sum(
case when al.has_been_booked_within_last_12_months then 1 else 0 end
) as accommodations_booked_in_12_months
from int_core__mtd_accommodation_lifecycle al
inner join
int_core__unique_accommodation_to_user atu
on al.id_accommodation = atu.id_accommodation
inner join int_core__unified_user uu on uu.id_user = atu.id_user_owner
where uu.id_deal is not null
group by 1, 2
)
select
date,
id_deal,
case
when accommodations_booked_in_12_months = 0
then '0'
when accommodations_booked_in_12_months between 1 and 5
then '01-05'
when accommodations_booked_in_12_months between 6 and 20
then '06-20'
when accommodations_booked_in_12_months between 21 and 60
then '21-60'
when accommodations_booked_in_12_months >= 61
then '61+'
end as active_accommodations_per_deal_segmentation,
accommodations_booked_in_12_months
from active_accommodations_per_deal

219
models/intermediate/core/schema.yml
View file

@ -436,71 +436,6 @@ models:
"The amount for which the guest user is covered if he faces problems
during check-in in GBP."
- name: int_core__monthly_accommodation_history_by_deal
description: |
This model contains the historic information regarding the accommodations, also known
as listings, for each deal id. It's used for the business KPIs in the view by deal id.
Data is aggregated at the last day of the month, or up to yesterday if it's the
current month.
tests:
- dbt_utils.unique_combination_of_columns:
combination_of_columns:
- date
- id_deal
deprecation_date: 2024-11-30
columns:
- name: date
data_type: date
description: The last day of the month or yesterday for historic listing metrics.
tests:
- not_null
- name: id_deal
data_type: character varying
description: Id of the deal associated to the host.
tests:
- not_null
- name: int_core__mtd_accommodation_metrics
description: |
This model contains the historic information regarding the accommodations in an aggregated manner.
It's used for the business KPIs. Data is aggregated at the last day of the month and in the
days necessary for the Month-to-Date computation of the current month.
deprecation_date: 2024-11-30
tests:
- dbt_utils.unique_combination_of_columns:
combination_of_columns:
- date
- dimension
- dimension_value
columns:
- name: date
data_type: date
description: The date for the month-to-date accommodation-related metrics.
tests:
- not_null
- name: dimension
data_type: string
description: The dimension or granularity of the metrics.
tests:
- accepted_values:
values:
- global
- by_number_of_listings
- by_billing_country
- name: dimension_value
data_type: string
description: The value or segment available for the selected dimension.
tests:
- not_null
- name: int_core__verification_request_completeness
description: |
The `int_core__verification_request_completeness` model allows to determine if a verification request is
@ -961,8 +896,7 @@ models:
Boolean to indicate if the listing is active or not. If false, this is considered as a
hard deactivation - meaning no more bookings can be assigned to this listing. However,
even if a listing is active, that does not necessarily mean that it's receiving bookings.
Do not confuse this column with the lifecycle activity of a listing that is computed in
int_core__mtd_accommodation_lifecycle.
Do not confuse this column with the lifecycle activity of a listing.
- name: town
data_type: character varying
@ -1019,157 +953,6 @@ models:
data_type: timestamp
description: Timestamp of when the accommodation record was extracted from the backend into the DWH.
- name: int_core__mtd_accommodation_lifecycle
description: |
This model contains the historic information regarding the lifecycle of accommodations, also known as
listings. The information regarding the booking-related time allows for the current status of any listing
regarding its activity. This information is encapsulated in the following columns:
accommodation_lifecycle_state: contains one of the following states
- 01-New: Listings that have been created in the current month, without bookings
- 02-Never Booked: Listings that have been created before the current month, without bookings.
- 03-First Time Booked: Listings that have been booked for the first time in the current month.
- 04-Active: Listings that have booking activity in the past 12 months (that are not FTB nor reactivated)
- 05-Churning: Listings that are becoming inactive because of lack of bookings in the past 12 months
- 06-Inactive: Listings that have not had a booking for more than 12 months.
- 07-Reactivated: Listings that have had a booking in the current month that were inactive or churning before.
- Finally, if none of the logic applies, which should not happen, null will be set and a dbt alert will raise.
Since the states of Active, First Time Booked and Reactivated indicate certain booking activity and are
mutually exclusive, the model also provides information of the recency of the bookings by the following
booleans:
- has_been_booked_within_current_month: If a listing has had a booking created in the current month
- has_been_booked_within_last_6_months: If a listing has had a booking created in the past 6 months
- has_been_booked_within_last_12_months: If a listing has had a booking created in the past 12 months
Note that if a listing has had a booking created in a given month, all 3 columns will be true. Similarly,
if the last booking created to a listing was 5 months ago, only the column has_been_booked_in_1_month
will be false; while the other 2 will be true.
tests:
- dbt_utils.unique_combination_of_columns:
combination_of_columns:
- date
- id_accommodation
deprecation_date: 2024-11-30
columns:
- name: date
data_type: date
description: The date for the month-to-date. Information is inclusive to the date displayed.
tests:
- not_null
- name: id_accommodation
data_type: bigint
description: Id of the accommodation or listing.
tests:
- not_null
- name: creation_date_utc
data_type: date
description: Date of when the listing was created.
- name: first_time_booked_date_utc
data_type: date
description: |
Date of the first booking created for a given listing. Can be null if the listing
has never had a booking associated with it.
- name: last_time_booked_date_utc
data_type: date
description: |
Date of the last booking created for a given listing. Can be null if the listing
has never had a booking associated with it. Can be the same as first_time_booked_date_utc
if the listing only had 1 booking in its history.
- name: second_to_last_time_booked_date_utc
data_type: date
description: |
Date of the second-to-last booking created for a given listing, meaning the creation
date of the booking that precedes the last one. It's relevant for the reactivation computation
on the lifecycle. Can be null if the listing has never had a booking associated with it or if
the listing only had 1 booking in its history.
- name: accommodation_lifecycle_state
data_type: character varying
description: |
Contains the lifecycle state of a Listing. The accepted values are:
01-New, 02-Never Booked, 03-First Time Booked, 04-Active, 05-Churning, 06-Inactive,
07-Reactivated. Failing to implement the logic will result in alert.
tests:
- not_null
- name: has_been_booked_within_current_month
data_type: boolean
description: If the listing has had a booking created in the current month.
- name: has_been_booked_within_last_6_months
data_type: boolean
description: If the listing has had a booking created in the past 6 months.
- name: has_been_booked_within_last_12_months
data_type: boolean
description: If the listing has had a booking created in the past 12 months.
- name: int_core__mtd_accommodation_segmentation
description: |
This model contains the historic information regarding the customer segmentation based on active accommodations,
also known as listings. This model depends on the int_core__mtd_accommodation_lifecycle, thus the time granularity
is the same as for any mtd model.
The segmentation is applied at deal level, not at user host level. This has the drawback that hosts without a
deal assigned won't be considered in this segmentation. However, it correctly categorises customers based on the
number of listings across the different user hosts each deal can have.
The segmentation is available in the field active_accommodations_per_deal_segmentation. It considers listings that
have been booked within the last 12 months. Thus, it means it only considers the lifecycle states of
03-First Time Booked, 04-Active and 07-Reactivated. The segments are the following:
- '0'
- '01-05'
- '06-20'
- '21-60'
- '61+'
These segments are inspired from the ones RevOps team uses, but the associated deals and listings volume will differ
since the listing activity logic considered is different.
deprecation_date: 2024-11-30
tests:
- dbt_utils.unique_combination_of_columns:
combination_of_columns:
- date
- id_deal
columns:
- name: date
data_type: date
description: The date for the month-to-date. Information is inclusive to the date displayed.
tests:
- not_null
- name: id_deal
data_type: character varying
description: Id of the deal associated to the host.
tests:
- not_null
- name: active_accommodations_per_deal_segmentation
data_type: character varying
description: The segmentation based on the number of listings booked in the last 12 months.
tests:
- not_null
- accepted_values:
values:
- "0"
- "01-05"
- "06-20"
- "21-60"
- "61+"
- name: accommodations_booked_in_12_months
data_type: integer
description: Informative field of the actual number of listings booked in the last 12 months
- name: int_core__check_in_cover_users
description:
This model contains information about hosts that offer check in cover.