4867e8f6d0
# Description Changes: * Creation of a deal-based model that contains when a "deal has appeared in new dash". This is tricky because a Deal can still have multiple users, thus it needs to be attributed to a date. I've chosen the first user appearance for the rest of the metrics. * Adaptation of dimension deals in KPIs to include a client type, that indicates if the deal is from APIs or not (Platform, i.e., Dashboard). * Xero metrics by Business Scope. This is the previous "dash source" that I need to change in the previously worked models. I decided to include APIs in the segmentation since in most cases we distinguish old dash from new dash by just "anything that is not in new dash". This is very wrong for invoicing metrics, in which we have APIs. So this actually properly computes a client segmentation by scope. Note that I'll need to handle the monthly/mtd metrics/agg for these 2 metric models (Resolutions + Invoiced revenue) separately. # Checklist - [X] The edited models and dependants run properly with production data. - [X] 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. - [X] 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: #27356
86 lines
3.1 KiB
YAML
86 lines
3.1 KiB
YAML
# Name your project! Project names should contain only lowercase characters
|
|
# and underscores. A good package name should reflect your organization's
|
|
# name or the intended use of these models
|
|
name: "dwh_dbt"
|
|
version: "1.0.0"
|
|
config-version: 2
|
|
|
|
# This setting configures which "profile" dbt uses for this project.
|
|
profile: "dwh_dbt"
|
|
|
|
# These configurations specify where dbt should look for different types of files.
|
|
# The `model-paths` config, for example, states that models in this project can be
|
|
# found in the "models/" directory. You probably won't need to change these!
|
|
model-paths: ["models"]
|
|
analysis-paths: ["analyses"]
|
|
test-paths: ["tests"]
|
|
seed-paths: ["seeds"]
|
|
macro-paths: ["macros"]
|
|
snapshot-paths: ["snapshots"]
|
|
|
|
clean-targets: # directories to be removed by `dbt clean`
|
|
- "target"
|
|
- "dbt_packages"
|
|
|
|
# Configuring models
|
|
# Full documentation: https://docs.getdbt.com/docs/configuring-models
|
|
|
|
# In this example config, we tell dbt to build all models in the example/
|
|
# directory as views. These settings can be overridden in the individual model
|
|
# files using the `{{ config(...) }}` macro.
|
|
models:
|
|
+unlogged: true
|
|
# ^ This makes all the tables created by dbt be unlogged. This is a Postgres
|
|
# specific setting that we activate for performance. It has deep implications
|
|
# on how Postgres handles tables and is typically considered crazy risky, but
|
|
# it's very fitting for our needs. You can read more here:
|
|
# https://www.crunchydata.com/blog/postgresl-unlogged-tables
|
|
dwh_dbt:
|
|
+post-hook:
|
|
sql: "VACUUM ANALYZE {{ this }}"
|
|
transaction: false
|
|
# ^ This makes dbt run a VACUUM ANALYZE on the models after building each.
|
|
# It's pointless for views, but it doesn't matter because Postgres fails
|
|
# silently withour raising an unhandled exception.
|
|
staging:
|
|
+materialized: table
|
|
+schema: staging
|
|
intermediate:
|
|
+materialized: view
|
|
+schema: intermediate
|
|
reporting:
|
|
+materialized: table
|
|
+schema: reporting
|
|
|
|
seeds:
|
|
dwh_dbt:
|
|
schema: staging
|
|
|
|
vars:
|
|
"dbt_date:time_zone": "Europe/London"
|
|
# A general cutoff date for relevancy. Many models assume this to be the point
|
|
# in time after which they should work.
|
|
"start_date": "'2020-01-01'"
|
|
|
|
# KPIs Start Date. This is the date from which we start calculating KPIs.
|
|
"kpis_start_date": "'2022-04-01'"
|
|
|
|
# New Dash First Invoicing Date. This is the first date considered for New Dash invoicing.
|
|
"new_dash_first_invoicing_date": "'2024-12-31'"
|
|
|
|
# A distant future date to use as a default when cutoff values are missing.
|
|
"end_of_time": "'2050-12-31'"
|
|
|
|
# Booking state variables
|
|
# States should be strings in capital letters. Models need to force an upper()
|
|
"cancelled_booking_state": "'CANCELLED'"
|
|
"approved_booking_state": "'APPROVED'"
|
|
"flagged_booking_state": "'FLAGGED'"
|
|
|
|
# Payment state variables
|
|
# States should be strings in capital letters. Models need to force an upper()
|
|
"paid_payment_state": "'PAID'"
|
|
|
|
# Protection service state variables
|
|
# States should be strings in capital letters. Models need to force an upper()
|
|
"default_service": "'BASIC SCREENING'"
|