Add dbt for data modeling

Dockerfile

@@ -37,6 +37,8 @@ COPY quotaclimat ./quotaclimat
 COPY postgres ./postgres
 COPY alembic/ ./alembic
 COPY transform_program.py ./transform_program.py
+COPY _dbt/ ./_dbt
+COPY profiles.yml ./profiles.yml
 
 # Docker compose overwrite this config to have only one Dockerfile
 CMD ["ls"]

_dbt/.gitignore

@@ -0,0 +1,4 @@
+
+target/
+dbt_packages/
+logs/

_dbt/README.md

@@ -0,0 +1,15 @@
+Welcome to your new dbt project!
+
+### Using the starter project
+
+Try running the following commands:
+- dbt run
+- dbt test
+
+
+### Resources:
+- Learn more about dbt [in the docs](https://docs.getdbt.com/docs/introduction)
+- Check out [Discourse](https://discourse.getdbt.com/) for commonly asked questions and answers
+- Join the [chat](https://community.getdbt.com/) on Slack for live discussions and support
+- Find [dbt events](https://events.getdbt.com) near you
+- Check out [the blog](https://blog.getdbt.com/) for the latest news on dbt's development and best practices

_dbt/dbt_project.yml

@@ -0,0 +1,36 @@
+
+# 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: '_dbt'
+version: '1.0.0'
+
+# This setting configures which "profile" dbt uses for this project.
+profile: '_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:
+  _dbt:
+    # Config indicated by + and applies to all files under models/example/
+    example:
+      +materialized: view

_dbt/models/example/my_first_dbt_model.sql

@@ -0,0 +1,27 @@
+
+/*
+    Welcome to your first dbt model!
+    Did you know that you can also configure models directly within SQL files?
+    This will override configurations stated in dbt_project.yml
+
+    Try changing "table" to "view" below
+*/
+
+{{ config(materialized='table') }}
+
+with source_data as (
+
+    select 1 as id
+    union all
+    select null as id
+
+)
+
+select *
+from source_data
+
+/*
+    Uncomment the line below to remove records with null `id` values
+*/
+
+-- where id is not null

_dbt/models/example/my_second_dbt_model.sql

@@ -0,0 +1,6 @@
+
+-- Use the `ref` function to select from other models
+
+select *
+from {{ ref('my_first_dbt_model') }}
+where id = 1

_dbt/models/example/schema.yml

@@ -0,0 +1,21 @@
+
+version: 2
+
+models:
+  - name: my_first_dbt_model
+    description: "A starter dbt model"
+    columns:
+      - name: id
+        description: "The primary key for this table"
+        data_tests:
+          - unique
+          - not_null
+
+  - name: my_second_dbt_model
+    description: "A starter dbt model"
+    columns:
+      - name: id
+        description: "The primary key for this table"
+        data_tests:
+          - unique
+          - not_null

docker-compose.yml

@@ -26,6 +26,8 @@ services:
       - ./pyproject.toml:/app/pyproject.toml
       - ./alembic:/app/alembic
       - ./alembic.ini:/app/alembic.ini
+      - ./_dbt:/app/_dbt
+      - ./profiles.yml:/app/profiles.yml
     depends_on:
       nginxtest:
         condition: service_healthy
@@ -107,6 +109,29 @@ services:
       postgres_db:
         condition: service_healthy
 
+  dbt_runner:
+    build:
+      context: ./
+      dockerfile: Dockerfile
+    entrypoint: [ "poetry", "run", "dbt", "run", "--project-dir", "/app/_dbt" ]
+    environment:
+      ENV: docker
+      PYTHONPATH: /app
+      POSTGRES_USER: user
+      POSTGRES_DB: barometre
+      POSTGRES_PASSWORD: password
+      POSTGRES_HOST: postgres_db
+      POSTGRES_PORT: 5432
+    tty: true
+    volumes:
+      - ./quotaclimat/:/app/quotaclimat/
+      - ./postgres/:/app/postgres/
+      - ./_dbt:/app/_dbt
+      - ./profiles.yml:/app/profiles.yml
+    depends_on:
+      postgres_db:
+        condition: service_healthy
+
   postgres_db:
     image: postgres:15
     ports:

profiles.yml

@@ -0,0 +1,12 @@
+_dbt:
+  target: dev
+  outputs:
+    dev:
+      type: postgres
+      host: postgres_db
+      user: user
+      password: password
+      port: 5432
+      dbname: barometre
+      schema: public
+      threads: 1

pyproject.toml

@@ -31,6 +31,8 @@ sentry-sdk = "^2.13.0"
 modin = {extras = ["ray"], version = "^0.32.0"}
 numpy = "1.26.4"
 openpyxl = "^3.1.5"
+dbt-core = "^1.8.7"
+dbt-postgres = "^1.8.2"
 [build-system]
 requires = ["poetry-core>=1.1"]
 build-backend = "poetry.core.masonry.api"