add template

Author: antheas

README.md

@@ -5,7 +5,7 @@
         <img alt="Pasteur Logo with text. Tagline reads: 'Sanitize Your Data'" src="./res/logo/logo_text_light.svg" width="90%">
     </picture>
 </h1>
-Pasteur is a library for performing end-to-end data synthesis.
+Pasteur is a library for performing privacy-aware end-to-end data synthesis.
 Gather your raw data and preprocess, synthesize, and evaluate it within a single
 project.
 Use the tools you're familiar with: numpy, pandas, scikit-learn, scipy or any other.

pyproject.toml

@@ -70,6 +70,9 @@ pasteur_mlflow = "pasteur.kedro.hooks:mlflow"
 [project.entry-points."kedro.project_commands"]
 pasteur = "pasteur.cli:cli"
 
+[project.entry-points."kedro.starters"]
+pasteur = "pasteur.kedro.starters:starters"
+
 [build-system]
 requires = ["setuptools>=61.0", "wheel", "numpy>=1.15"]
 build-backend = "setuptools.build_meta"
@@ -81,7 +84,7 @@ include = ["pasteur*"]  # package names should match these glob patterns (["*"]
 [tool.kedro]
 package_name = "project"
 project_name = "Pasteur Testing Project"
-project_version = "0.18.3"
+kedro_init_version = "0.18.5"
 
 [tool.isort]
 multi_line_output = 3

src/pasteur/cli.py

@@ -5,4 +5,13 @@
 else:
     cli = None
 
-__all__ = ["cli"]
+    import logging
+
+    logger = logging.getLogger(__name__)
+    logger.warn(
+        "Pasteur project not found in the current directory "
+        + "(settings.py file doesn't contain `PASTEUR_MODULES = ...`). "
+        + "Disabling Pasteur commands."
+    )
+
+__all__ = ["cli"]

src/pasteur/kedro/starters.py

@@ -0,0 +1,16 @@
+from pathlib import Path
+
+from kedro.framework.cli.starters import KedroStarterSpec
+
+import pasteur
+
+PASTEUR_PATH = Path(pasteur.__file__).parent
+TEMPLATE_PATH = PASTEUR_PATH / "templates" / "project"
+
+# plugin.py
+starters = [
+    KedroStarterSpec(
+        alias="pasteur",
+        template_path=str(TEMPLATE_PATH),
+    )
+]

src/pasteur/templates/project/cookiecutter.json

@@ -0,0 +1,6 @@
+{
+    "project_name": "New Pasteur Project",
+    "repo_name": "{{ cookiecutter.project_name.strip().replace(' ', '-').replace('_', '-').lower() }}",
+    "python_package": "{{ cookiecutter.project_name.strip().replace(' ', '_').replace('-', '_').lower() }}",
+    "kedro_version": "{{ cookiecutter.kedro_version }}"
+}

src/pasteur/templates/project/hooks/post_gen_project.py

@@ -0,0 +1,10 @@
+import pasteur
+
+# Inject pasteur version
+with open('src/requirements.txt', "r") as f:
+    reqs = f.read()
+
+reqs = reqs.replace("pasteur[opt,test,docs]", f"pasteur[opt,test,docs]~={pasteur.version}")
+
+with open('src/requirements.txt', "w") as f:
+    f.write(reqs)

src/pasteur/templates/project/prompts.yml

@@ -0,0 +1,9 @@
+project_name:
+  title: "Project Name"
+  text: |
+    Please enter a human readable name for your new project.
+    Spaces, hyphens, and underscores are allowed.
+  regex_validator: "^[\\w -]{2,}$"
+  error_message: |
+    It must contain only alphanumeric symbols, spaces, underscores and hyphens and
+    be at least 2 characters long.

src/pasteur/templates/project/{{ cookiecutter.repo_name }}/.gitignore

@@ -0,0 +1,174 @@
+##########################
+# KEDRO PROJECT
+
+# ignore all local configuration
+conf/local/**
+!conf/local/.gitkeep
+.telemetry
+
+# ignore potentially sensitive credentials files
+conf/**/*credentials*
+
+# ignore everything in the following folders
+data
+external
+data/**
+raw/**
+logs/**
+
+# except their sub-folders
+!data/**/
+!raw/**/
+!logs/**/
+!data/**/readme.md
+!raw/**/readme.md
+
+# also keep all .gitkeep files
+!.gitkeep
+
+# also keep the example dataset
+!data/01_raw/iris.csv
+
+
+##########################
+# Common files
+
+# IntelliJ
+.idea/
+*.iml
+out/
+.idea_modules/
+
+### macOS
+*.DS_Store
+.AppleDouble
+.LSOverride
+.Trashes
+
+# Vim
+*~
+.*.swo
+.*.swp
+
+# emacs
+*~
+\#*\#
+/.emacs.desktop
+/.emacs.desktop.lock
+*.elc
+
+# JIRA plugin
+atlassian-ide-plugin.xml
+
+# C extensions
+*.so
+
+### Python template
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+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/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+.hypothesis/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+.static_storage/
+.media/
+local_settings.py
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+.ipython/profile_default/history.sqlite
+.ipython/profile_default/startup/README
+
+# pyenv
+.python-version
+
+# celery beat schedule file
+celerybeat-schedule
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.envrc
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+
+# vscode
+.vscode
+
+# ShelveStore sessions
+sessions/
+
+# MLflwo dir
+mlruns/

src/pasteur/templates/project/{{ cookiecutter.repo_name }}/README.md

@@ -0,0 +1,122 @@
+# {{ cookiecutter.project_name }}
+
+## Overview
+
+This is your new Kedro project, which was generated using `Kedro {{ cookiecutter.kedro_version }}`.
+
+Take a look at the [Kedro documentation](https://kedro.readthedocs.io) to get started.
+
+## Rules and guidelines
+
+In order to get the best out of the template:
+
+* Don't remove any lines from the `.gitignore` file we provide
+* Make sure your results can be reproduced by following a [data engineering convention](https://kedro.readthedocs.io/en/stable/faq/faq.html#what-is-data-engineering-convention)
+* Don't commit data to your repository
+* Don't commit any credentials or your local configuration to your repository. Keep all your credentials and local configuration in `conf/local/`
+
+## How to install dependencies
+
+Declare any dependencies in `src/requirements.txt` for `pip` installation and `src/environment.yml` for `conda` installation.
+
+To install them, run:
+
+```
+pip install -r src/requirements.txt
+```
+
+## How to run your Kedro pipeline
+
+You can run your Kedro project with:
+
+```
+kedro run
+```
+
+## How to test your Kedro project
+
+Have a look at the file `src/tests/test_run.py` for instructions on how to write your tests. You can run your tests as follows:
+
+```
+kedro test
+```
+
+To configure the coverage threshold, go to the `.coveragerc` file.
+
+## Project dependencies
+
+To generate or update the dependency requirements for your project:
+
+```
+kedro build-reqs
+```
+
+This will `pip-compile` the contents of `src/requirements.txt` into a new file `src/requirements.lock`. You can see the output of the resolution by opening `src/requirements.lock`.
+
+After this, if you'd like to update your project requirements, please update `src/requirements.txt` and re-run `kedro build-reqs`.
+
+[Further information about project dependencies](https://kedro.readthedocs.io/en/stable/kedro_project_setup/dependencies.html#project-specific-dependencies)
+
+## How to work with Kedro and notebooks
+
+> Note: Using `kedro jupyter` or `kedro ipython` to run your notebook provides these variables in scope: `context`, `catalog`, and `startup_error`.
+>
+> Jupyter, JupyterLab, and IPython are already included in the project requirements by default, so once you have run `pip install -r src/requirements.txt` you will not need to take any extra steps before you use them.
+
+### Jupyter
+To use Jupyter notebooks in your Kedro project, you need to install Jupyter:
+
+```
+pip install jupyter
+```
+
+After installing Jupyter, you can start a local notebook server:
+
+```
+kedro jupyter notebook
+```
+
+### JupyterLab
+To use JupyterLab, you need to install it:
+
+```
+pip install jupyterlab
+```
+
+You can also start JupyterLab:
+
+```
+kedro jupyter lab
+```
+
+### IPython
+And if you want to run an IPython session:
+
+```
+kedro ipython
+```
+
+### How to convert notebook cells to nodes in a Kedro project
+You can move notebook code over into a Kedro project structure using a mixture of [cell tagging](https://jupyter-notebook.readthedocs.io/en/stable/changelog.html#release-5-0-0) and Kedro CLI commands.
+
+By adding the `node` tag to a cell and running the command below, the cell's source code will be copied over to a Python file within `src/<package_name>/nodes/`:
+
+```
+kedro jupyter convert <filepath_to_my_notebook>
+```
+> *Note:* The name of the Python file matches the name of the original notebook.
+
+Alternatively, you may want to transform all your notebooks in one go. Run the following command to convert all notebook files found in the project root directory and under any of its sub-folders:
+
+```
+kedro jupyter convert --all
+```
+
+### How to ignore notebook output cells in `git`
+To automatically strip out all output cell contents before committing to `git`, you can run `kedro activate-nbstripout`. This will add a hook in `.git/config` which will run `nbstripout` before anything is committed to `git`.
+
+> *Note:* Your output cells will be retained locally.
+
+## Package your Kedro project
+
+[Further information about building project documentation and packaging your project](https://kedro.readthedocs.io/en/stable/tutorial/package_a_project.html)