Full Code of cnstlungu/portable-data-stack-dagster for AI

Repository: cnstlungu/portable-data-stack-dagster
Branch: main
Commit: 9183b35e9c67
Files: 13
Total size: 10.3 KB

Directory structure:
gitextract_5c6bhaqa/

├── .gitignore
├── LICENSE
├── README.md
├── dagster/
│   ├── Dockerfile
│   ├── definitions.py
│   └── entrypoint.sh
├── dbt/
│   └── Dockerfile
├── docker-compose.yml
├── generator/
│   └── Dockerfile
├── shared/
│   ├── db/
│   │   ├── .keep
│   │   └── datamart.duckdb.example
│   └── parquet/
│       └── .keep
└── superset/
    └── Dockerfile

================================================
FILE CONTENTS
================================================

================================================
FILE: .gitignore
================================================
.venv
*.egg-info/
*.parquet
*.db
tmp*
__pycache__
target/
dbt_packages/
logs/
*.duckdb
*.env
**/.logs_queue
**/.nux
**/.telemetry
**/history
**/schedules
**/storage
dbt/postcard_company/*

# Keeps
!geography.csv
!dashboard.json

================================================
FILE: LICENSE
================================================
MIT License

Copyright (c) 2023 Constantin Lungu

Permission is hereby granted, free of charge, to any person obtaining a copy
of this software and associated documentation files (the "Software"), to deal
in the Software without restriction, including without limitation the rights
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
copies of the Software, and to permit persons to whom the Software is
furnished to do so, subject to the following conditions:

The above copyright notice and this permission notice shall be included in all
copies or substantial portions of the Software.

THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
SOFTWARE.


================================================
FILE: README.md
================================================
# Portable Data Stack

This application is an Analytics suite for an imaginary company selling postcards. The company sells both directly but also through resellers in the majority of European countries.

## Stack

- Dagster
- Docker (Docker Compose)
- DuckDB
- dbt core
- Superset

## Interested in the data model?

Generation of example data and the underlying dbt-core model is available in the [postcard-company-datamart](https://github.com/cnstlungu/postcard-company-datamart) project

## For other stacks using the same dbt-core model, check the below:

- [portable-data-stack-mage](https://github.com/cnstlungu/portable-data-stack-mage)
- [portable-data-stack-airflow](https://github.com/cnstlungu/portable-data-stack-airflow)
- [portable-data-stack-sqlmesh](https://github.com/cnstlungu/portable-data-stack-sqlmesh)

Implementations with other tools with a different model:
- [portable-data-stack-bruin](https://github.com/cnstlungu/portable-data-stack-bruin)
- [postcard-company-dataform](https://github.com/cnstlungu/postcard-company-dataform)


For the legacy version involving OLTP, CSV and JSON sources, check out the `legacy-oltp` branch.

### System requirements
* [Docker](https://docs.docker.com/engine/install/)

## Setup

1. Rename `.env.example` file to `.env` and set your desired password. Remember to never commit files containing passwords or any other sensitive information.

2. Rename `shared/db/datamart.duckdb.example` to `shared/db/datamart.duckdb` or init an empty database file there with that name.

3. With **Docker Engine** installed, change directory to the root folder of the project (also the one that contains docker-compose.yml) and run

    `docker compose up --build`

    Note that this may take several minutes to completed. Check out the console to see when the Dagster interface is ready.

4. Once the Docker suite has finished loading, open up [Dagster (dagit)](http://localhost:3000) , go to `Assets`, select all and click `Materialize selected`

![Dagit](resources/dagit.png "Dagit")

5. When the assets have been materialized, you can open the [Superset interface](http://localhost:8088)


### Demo Credentials

Demo credentials are set in the .env file mentioned above. 

### Ports exposed locally
* Dagster (dagit): 3000
* Superset: 8088

Generated parquet files are saved in the **shared** folder.

The data is fictional and automatically generated. Any similarities with existing persons, entities, products or businesses are purely coincidental.

### General flow

1. Generate test data as parquet files using Python
2. Import data to the staging area in the Data Warehouse (DuckDB), orchestrated by Dagster
3. Model data, build fact and dimension tables, load the Data Warehouse using dbt
    - installs dbt dependencies
    - seeds the database with static data (e.g. geography)
    - runs the model
    - tests the model
4. Analyze and visually explore the data using Superset or directly query the Data Warehouse database instance

For superset, the default credentials are: user = admin, password = admin


## Overview of architecture

The Docker process will begin building the application suite. The suite is made up of the following components, each within its own docker container:
* **generator**: this is a collection of Python scripts that will generate, insert and export the example data
* **dbt**: the data model, sourced from [postcard-company-datamart](https://github.com/cnstlungu/postcard-company-datamart) project
* **dagster**: this is the orchestrator tool that will trigger the ETL tasks; its GUI is locally available on port 3000; 
* **superset**: this contains the web-based Business Intelligence application we will use to explore the data; exposed on port 8088.

Once the Docker building process has completed, we may open the Dagster GUI (locally: localhost:3000) to view and materialize our assets.



![Dagster](resources/orchestration.png "Orchestration with Dagster")


After the assets have been materialized you can either analyze the data using the querying and visualization tools provided by Superset (available locally on port 8088), or query the Data Warehouse (available as a DuckDB Database)

![Apache Superset](resources/superset.png "Superset")


## Credits

Inspired by:
- [Build a poor man’s data lake from scratch with DuckDB](https://dagster.io/blog/duckdb-data-lake)
- [Using dbt with Dagster software-defined assets](https://docs.dagster.io/integrations/dbt/using-dbt-with-dagster)


================================================
FILE: dagster/Dockerfile
================================================
FROM python:3.11-slim

RUN apt-get update && apt-get install -y --no-install-recommends curl && rm -rf /var/lib/apt/lists/*

RUN pip install uv 

RUN uv pip install --system dagster==1.11.13 \
    dagster-dbt==0.27.13 \
    duckdb==1.4.0 \
    dbt-core==1.10.13 \
    dbt-duckdb==1.9.6 \
    dagster-duckdb==0.27.13 \
    dagster-webserver==1.11.13 \
    "pydantic<2.9.0" \
    "watchdog<5"

WORKDIR /

COPY dagster/definitions.py /definitions.py
COPY dagster/entrypoint.sh /entrypoint.sh

RUN chmod +x /entrypoint.sh

ENTRYPOINT ["/entrypoint.sh"]
CMD ["-h", "0.0.0.0", "-f", "/definitions.py"]

================================================
FILE: dagster/definitions.py
================================================
from pathlib import Path

from dagster import Definitions, AssetExecutionContext
from dagster_dbt import DbtCliResource, dbt_assets

# Paths inside the container
DBT_PROJECT_DIR = Path("/postcard_company")
DBT_PROFILES_DIR = Path("/postcard_company")  # you have profiles.yml there

# dbt CLI resource Dagster will use to run dbt
dbt_resource = DbtCliResource(
    project_dir=str(DBT_PROJECT_DIR),
    profiles_dir=str(DBT_PROFILES_DIR),
)

# dbt manifest produced by `dbt compile` or `dbt build`
MANIFEST_PATH = DBT_PROJECT_DIR / "target" / "manifest.json"


@dbt_assets(manifest=MANIFEST_PATH)
def postcard_company_dbt_assets(
    context: AssetExecutionContext,
    dbt: DbtCliResource,
):
    # You can change to ["run"], ["test"], etc.
    yield from dbt.cli(["build"], context=context).stream()


defs = Definitions(
    assets=[postcard_company_dbt_assets],
    resources={"dbt": dbt_resource},
)

================================================
FILE: dagster/entrypoint.sh
================================================
#!/bin/bash
set -e

echo "Running dbt setup..."

cd /postcard_company
dbt deps
dbt seed
dbt compile

echo "Starting Dagster..."

# Forward CMD arguments to Dagster
exec dagster dev "$@"

================================================
FILE: dbt/Dockerfile
================================================
FROM python:3.11-slim

RUN apt-get update && apt-get install -y git make automake gcc g++ subversion && rm -rf /var/lib/apt/lists/*

RUN git clone -n --depth=1 --filter=tree:0 https://github.com/cnstlungu/postcard-company-datamart.git /datamart

WORKDIR /datamart

RUN git sparse-checkout set --no-cone postcard_company

CMD ["git", "checkout"]

================================================
FILE: docker-compose.yml
================================================
services:
  generator:
    build:
      context: .
      dockerfile: ./generator/Dockerfile
    volumes:
      - ./shared:/shared
    environment:
      INPUT_FILES_PATH: /shared/parquet
  dbt:
    build:
      context: .
      dockerfile: ./dbt/Dockerfile
    volumes:
      - ./shared:/shared
      - ./dbt/postcard_company:/datamart/postcard_company
    environment:
      INPUT_FILES_PATH: /shared/parquet  
  dagster:
    build:
      context: .
      dockerfile: ./dagster/Dockerfile
    restart: always
    environment:
        DUCKDB_FILE_PATH: /shared/db/datamart.duckdb
        INPUT_FILES_PATH: /shared/parquet
    volumes:
        - ./shared:/shared
        - ./dbt/postcard_company:/postcard_company
    ports:
        - "3000:3000"
    depends_on:
      generator:
        condition: service_completed_successfully
      dbt:
        condition: service_completed_successfully
  superset:
    build:
      context: .
      dockerfile: ./superset/Dockerfile
      args:
        SUPERSET_ADMIN: $SUPERSET_ADMIN
        SUPERSET_PASSWORD: $SUPERSET_PASSWORD
        SUPERSET_SECRET_KEY: ${SUPERSET_SECRET_KEY}
    environment:
      SUPERSET_SECRET_KEY: ${SUPERSET_SECRET_KEY}
    ports:
        - "8088:8088"
    command:     gunicorn --bind  "0.0.0.0:8088" --access-logfile '-' --error-logfile '-' --workers 1 --worker-class gthread --threads 20 --timeout 60 --limit-request-line 0 --limit-request-field_size 0 "superset.app:create_app()"
    post_start:
      - command: "superset import-dashboards -p ./dashboard.zip -u ${SUPERSET_ADMIN}"
    volumes:
      - ./shared/db:/app/superset_home/db
    depends_on:
      - dagster


================================================
FILE: generator/Dockerfile
================================================
FROM python:3.11-slim

RUN apt-get update && apt-get install -y git make automake gcc g++ subversion

RUN git clone -n --depth=1 --filter=tree:0 https://github.com/cnstlungu/postcard-company-datamart.git /generator

WORKDIR /generator

RUN git sparse-checkout set --no-cone generator && git checkout

WORKDIR /generator/generator

RUN pip install uv

RUN uv pip install --system -r requirements.txt

CMD ["python3", "generate.py"]

================================================
FILE: shared/db/.keep
================================================


================================================
FILE: shared/parquet/.keep
================================================


================================================
FILE: superset/Dockerfile
================================================
FROM apache/superset:4.1.1

ARG SUPERSET_ADMIN
ARG SUPERSET_PASSWORD
ARG SUPERSET_SECRET_KEY
# Switching to root to install the required packages
USER root

RUN pip install uv

COPY --chown=superset:superset ./superset/assets .
RUN uv pip install --system duckdb-engine==0.17.0 duckdb==1.4.4
USER superset
RUN superset fab create-admin \
              --username ${SUPERSET_ADMIN} \
              --firstname Superset \
              --lastname Admin \
              --email admin@example.com \
              --password ${SUPERSET_PASSWORD}
RUN superset db upgrade
RUN superset init
RUN superset set_database_uri -d DW  -u duckdb:///superset_home/db/datamart.duckdb