feat(dagster): add Dagster

This commit is contained in:
Masaki Yatsu
2025-09-15 19:25:31 +09:00
parent c725124a7a
commit dbcbaedf6f
21 changed files with 4018 additions and 0 deletions

View File

@@ -0,0 +1,205 @@
# Byte-compiled / optimized / DLL files
__pycache__/
*.py[codz]
*$py.class
# C extensions
*.so
# Distribution / packaging
.Python
build/
develop-eggs/
dist/
downloads/
eggs/
.eggs/
lib/
lib64/
parts/
sdist/
var/
wheels/
share/python-wheels/
*.egg-info/
.installed.cfg
*.egg
MANIFEST
# PyInstaller
# Usually these files are written by a python script from a template
# before PyInstaller builds the exe, so as to inject date/other infos into it.
*.manifest
*.spec
# Installer logs
pip-log.txt
pip-delete-this-directory.txt
# Unit test / coverage reports
htmlcov/
.tox/
.nox/
.coverage
.coverage.*
.cache
nosetests.xml
coverage.xml
*.cover
*.py.cover
.hypothesis/
.pytest_cache/
cover/
# Translations
*.mo
*.pot
# Django stuff:
*.log
local_settings.py
db.sqlite3
db.sqlite3-journal
# Flask stuff:
instance/
.webassets-cache
# Scrapy stuff:
.scrapy
# Sphinx documentation
docs/_build/
# PyBuilder
.pybuilder/
target/
# Jupyter Notebook
.ipynb_checkpoints
# IPython
profile_default/
ipython_config.py
# pyenv
# For a library or package, you might want to ignore these files since the code is
# intended to run in multiple environments; otherwise, check them in:
# .python-version
# pipenv
# According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
# However, in case of collaboration, if having platform-specific dependencies or dependencies
# having no cross-platform support, pipenv may install dependencies that don't work, or not
# install all needed dependencies.
#Pipfile.lock
# UV
# Similar to Pipfile.lock, it is generally recommended to include uv.lock in version control.
# This is especially recommended for binary packages to ensure reproducibility, and is more
# commonly ignored for libraries.
#uv.lock
# poetry
# Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
# This is especially recommended for binary packages to ensure reproducibility, and is more
# commonly ignored for libraries.
# https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
#poetry.lock
#poetry.toml
# pdm
# Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
# pdm recommends including project-wide configuration in pdm.toml, but excluding .pdm-python.
# https://pdm-project.org/en/latest/usage/project/#working-with-version-control
#pdm.lock
#pdm.toml
.pdm-python
.pdm-build/
# pixi
# Similar to Pipfile.lock, it is generally recommended to include pixi.lock in version control.
#pixi.lock
# Pixi creates a virtual environment in the .pixi directory, just like venv module creates one
# in the .venv directory. It is recommended not to include this directory in version control.
.pixi
# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
__pypackages__/
# Celery stuff
celerybeat-schedule
celerybeat.pid
# SageMath parsed files
*.sage.py
# Environments
.env
.envrc
.venv
env/
venv/
ENV/
env.bak/
venv.bak/
# Spyder project settings
.spyderproject
.spyproject
# Rope project settings
.ropeproject
# mkdocs documentation
/site
# mypy
.mypy_cache/
.dmypy.json
dmypy.json
# Pyre type checker
.pyre/
# pytype static type analyzer
.pytype/
# Cython debug symbols
cython_debug/
# PyCharm
# JetBrains specific template is maintained in a separate JetBrains.gitignore that can
# be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
# and can be added to the global gitignore or merged into this file. For a more nuclear
# option (not recommended) you can uncomment the following to ignore the entire idea folder.
#.idea/
# Abstra
# Abstra is an AI-powered process automation framework.
# Ignore directories containing user credentials, local state, and settings.
# Learn more at https://abstra.io/docs
.abstra/
# Visual Studio Code
# Visual Studio Code specific template is maintained in a separate VisualStudioCode.gitignore
# that can be found at https://github.com/github/gitignore/blob/main/Global/VisualStudioCode.gitignore
# and can be added to the global gitignore or merged into this file. However, if you prefer,
# you could uncomment the following to ignore the entire vscode folder
# .vscode/
# Ruff stuff:
.ruff_cache/
# PyPI configuration file
.pypirc
# Marimo
marimo/_static/
marimo/_lsp/
__marimo__/
# Streamlit
.streamlit/secrets.toml
.tmp*

View File

@@ -0,0 +1,61 @@
# dagster_tutorial
## Getting started
### Installing dependencies
**Option 1: uv**
Ensure [`uv`](https://docs.astral.sh/uv/) is installed following their [official documentation](https://docs.astral.sh/uv/getting-started/installation/).
Create a virtual environment, and install the required dependencies using _sync_:
```bash
uv sync
```
Then, activate the virtual environment:
| OS | Command |
| --- | --- |
| MacOS | ```source .venv/bin/activate``` |
| Windows | ```.venv\Scripts\activate``` |
**Option 2: pip**
Install the python dependencies with [pip](https://pypi.org/project/pip/):
```bash
python3 -m venv .venv
```
Then active the virtual environment:
| OS | Command |
| --- | --- |
| MacOS | ```source .venv/bin/activate``` |
| Windows | ```.venv\Scripts\activate``` |
Install the required dependencies:
```bash
pip install -e ".[dev]"
```
### Running Dagster
Start the Dagster UI web server:
```bash
dg dev
```
Open http://localhost:3000 in your browser to see the project.
## Learn more
To learn more about this template and Dagster in general:
- [Dagster Documentation](https://docs.dagster.io/)
- [Dagster University](https://courses.dagster.io/)
- [Dagster Slack Community](https://dagster.io/slack)

View File

@@ -0,0 +1,32 @@
[project]
name = "dagster_tutorial"
requires-python = ">=3.9,<3.14"
version = "0.1.0"
dependencies = [
"dagster==1.11.10",
"dagster-duckdb>=0.27.10",
]
[dependency-groups]
dev = [
"dagster-webserver",
"dagster-dg-cli",
]
[build-system]
requires = ["hatchling"]
build-backend = "hatchling.build"
[tool.hatch.build.targets.wheel]
force-include = { "pyproject.toml" = "pyproject.toml" }
[tool.dg]
directory_type = "project"
[tool.dg.project]
root_module = "dagster_tutorial"
registry_modules = [
"dagster_tutorial.components.*",
]

View File

@@ -0,0 +1,8 @@
from pathlib import Path
from dagster import definitions, load_from_defs_folder
@definitions
def defs():
return load_from_defs_folder(path_within_project=Path(__file__).parent)

View File

@@ -0,0 +1,96 @@
import dagster as dg
from dagster_duckdb import DuckDBResource
@dg.asset
def customers(duckdb: DuckDBResource):
url = "https://raw.githubusercontent.com/dbt-labs/jaffle-shop-classic/refs/heads/main/seeds/raw_customers.csv"
table_name = "customers"
with duckdb.get_connection() as conn:
conn.execute(
f"""
create or replace table {table_name} as (
select * from read_csv_auto('{url}')
)
"""
)
@dg.asset
def orders(duckdb: DuckDBResource):
url = "https://raw.githubusercontent.com/dbt-labs/jaffle-shop-classic/refs/heads/main/seeds/raw_orders.csv"
table_name = "orders"
with duckdb.get_connection() as conn:
conn.execute(
f"""
create or replace table {table_name} as (
select * from read_csv_auto('{url}')
)
"""
)
@dg.asset
def payments(duckdb: DuckDBResource):
url = "https://raw.githubusercontent.com/dbt-labs/jaffle-shop-classic/refs/heads/main/seeds/raw_payments.csv"
table_name = "payments"
with duckdb.get_connection() as conn:
conn.execute(
f"""
create or replace table {table_name} as (
select * from read_csv_auto('{url}')
)
"""
)
@dg.asset(
deps=["customers", "orders", "payments"],
)
def orders_aggregation(duckdb: DuckDBResource):
table_name = "orders_aggregation"
with duckdb.get_connection() as conn:
conn.execute(
f"""
create or replace table {table_name} as (
select
c.id as customer_id,
c.first_name,
c.last_name,
count(distinct o.id) as total_orders,
count(distinct p.id) as total_payments,
coalesce(sum(p.amount), 0) as total_amount_spent
from customers c
left join orders o
on c.id = o.user_id
left join payments p
on o.id = p.order_id
group by 1, 2, 3
);
"""
)
@dg.asset_check(asset="orders_aggregation")
def orders_aggregation_check(duckdb: DuckDBResource) -> dg.AssetCheckResult:
table_name = "orders_aggregation"
with duckdb.get_connection() as conn:
res = conn.execute(f"select count(*) from {table_name}").fetchone()
if res is None:
return dg.AssetCheckResult(
passed=False, metadata={"message": "Order aggregation check failed"}
)
row_count = res[0]
if row_count == 0:
return dg.AssetCheckResult(
passed=False, metadata={"message": "Order aggregation check failed"}
)
return dg.AssetCheckResult(
passed=True, metadata={"message": "Order aggregation check passed"}
)

View File

@@ -0,0 +1,13 @@
import dagster as dg
from dagster_duckdb import DuckDBResource
database_resource = DuckDBResource(database="/tmp/jaffle_platform.duckdb")
@dg.definitions
def resources():
return dg.Definitions(
resources={
"duckdb": database_resource,
}
)

View File

@@ -0,0 +1,17 @@
from typing import Union
import dagster as dg
# @dg.schedule(cron_schedule="@daily", target="*")
# def schedules(context: dg.ScheduleEvaluationContext) -> Union[dg.RunRequest, dg.SkipReason]:
# return dg.SkipReason("Skipping. Change this to return a RunRequest to launch a run.")
@dg.schedule(cron_schedule="* * * * *", target="*")
def tutorial_schedule(
context: dg.ScheduleEvaluationContext,
) -> Union[dg.RunRequest, dg.SkipReason]:
return dg.SkipReason(
"Skipping. Change this to return a RunRequest to launch a run."
)

View File

@@ -0,0 +1 @@

2699
dagster/examples/dagster_tutorial/uv.lock generated Normal file

File diff suppressed because it is too large Load Diff