feat!: transform into cookiecutter template

.gitattributes

@@ -1,5 +1,3 @@
-data/** filter=lfs diff=lfs merge=lfs -text
-
 # let git decide if a file is a text file or a binary files
 # for text files, convert all CRLF to LF on check-in (not in working tree)
 * text=auto

.gitlab-ci-test.yaml

@@ -2,7 +2,7 @@
     before_script:
         - eval "$(micromamba shell hook --shell=bash)"
         - micromamba activate
-        - micromamba install -n base --yes --file environment.yml
+        - micromamba install -n base --yes --file environment.yaml
         - micromamba install -n base -c conda-forge --yes git git-lfs
         - git config --global --add safe.directory $(pwd)
         - pre-commit install

.gitlab-ci.yml

@@ -0,0 +1,6 @@
+# the ci configuration is split into multiple files
+# this allows the semantic versioning (versioning the template itself) to be easily removed
+include:
+    - .gitlab-ci-stages.yaml
+    - .gitlab-ci-release.yaml
+    - .gitlab-ci-test.yaml

.pre-commit-config.yaml

@@ -38,24 +38,11 @@ repos:
             entry: black
             language: system
             types: [python]
-          - id: nbqa-black
-            name: nbqa-black
-            entry: nbqa black
-            language: system
-            files: \.ipynb
           - id: pylint
             name: pylint
             entry: pylint
             language: system
             types: [python]
-          - id: nbqa-pylint
-            name: nbqa-pylint
-            entry: nbqa pylint
-            language: system
-            files: \.ipynb
-            args:
-                - --disable=pointless-statement,duplicate-code,expression-not-assigned
-                - --const-rgx=(([A-Z_][A-Z0-9_]*)|(__.*__)|([a-z_][a-z0-9_]{0,50}))$
     - repo: https://github.com/prettier/pre-commit
       rev: v2.1.2
       hooks:

README.md

@@ -1,89 +1,46 @@
-# Data Science Template Repository
+# HSG Data Science Template
 
-Basic setup for a data science project.
+## Prerequisites
 
-## Requirements
+The template depends on the following software:
 
-`Mamba`
+-   `mamba` (e.g., `miniforge` with `mamba` a.k.a. `mambaforge` [link](https://github.com/conda-forge/miniforge))
+-   `python` (>= 3.7)
+-   `cookiecutter` ([link](https://pypi.org/project/cookiecutter/))
+-   `git`
 
----
+## Usage Instructions
 
-## Setup Instructions (Unix)
-
-<ol>
-<li>Create and enter directory for your new repository</li>
-<li>Clone template repository</li>
+To setup a new project with the HSG data science template create the project repository in gitlab, run
 
 ```
-git clone git@ac1-git1.umlaut.com:hsg/hsg/data-science/data-science-project-template.git .
+cookiecutter https://ac1-git1.umlaut.com/hsg/hsg/data-science/data-science-templates/data-science-project-template.git
 ```
 
-<li>Read template version and remove its git history</li>
+and fill out the needed information.
 
-```
-version_tag=`git describe --tags --abbrev=0`
-rm -rf .git
-rm .releaserc.json README.md
-sed -i -e '/release/d' .gitlab-ci-stages.yml
-```
+## Development Instructions
 
-<li>Initialize a new repository and push it</li>
+Checkout the repository, run
 
 ```
-git init
-git add .
-git commit -m "Initialize from data science template version ${version_tag}"
-git remote add origin git@ac1-git1.umlaut.com:hsg/YOUR/NEW/PROJECT.git
-```
-
-<li>Configure tools</li>
-
-```
-env_name=YOUR_NEW_MAMBA_ENV_NAME
-mamba env create --name=${env_name} -f environment.yml
-mamba activate $env_name
+mamba env create -f environment.yaml
+mamba activate data-science-project-template
 pre-commit install
 ```
 
-</ol>
-
----
-
-## Setup Instructions (Windows)
-
-<ol>
-<li>Create and enter directory for your new repository</li>
-<li>Clone template repository</li>
-
-```
-git clone git@ac1-git1.umlaut.com:hsg/hsg/data-science/data-science-project-template.git .
-```
-
-<li>Read template version and remove its git history</li>
+and start developing.
 
-```
-@for /f "delims=" %i in ('git describe --tags --abbrev^=0') do @set version_tag=%i
-rmdir /S /Q .git
-del .gitlab-ci.yml .releaserc.json README.md
-Set-Content -Path ".gitlab-ci-stages.yml" -Value (get-content -Path ".gitlab-ci-stages.yml" | Select-String -Pattern 'release' -NotMatch)
-```
+## Setup CI/CD pipelines in gitlab
 
-<li>Initialize a new repository and push it</li>
+The project is set up to run:
 
-```
-git init
-git add .
-git commit -m "Initialize from data science template version %version_tag%"
-git remote add origin git@ac1-git1.umlaut.com:hsg/YOUR/NEW/PROJECT.git
-```
-
-<li>Configure tools</li>
+-   `pre-commit` checks on every new commit pushed to gitlab
+-   `semantic-release` on every MR to main
 
-```
-set env_name=YOUR_NEW_MAMBA_ENV_NAME
-mamba env create --name=%env_name% -f environment.yml
-mamba activate %env_name%
-pre-commit install
-```
+To enable the CI/CD setup in gitlab please use the following steps:
 
-</ol>
+-   enable `CI/CD` pipelines in `Settings -> General -> Visibility, project features, permissions`.
+-   create a project access token named `GITLAB_TOKEN` in `Settings -> Access Tokens` with `Maintainer` role and `api` + `write_repository` scopes.
+-   copy the token value appearing at the top of the page after the token creation
+-   create a `masked` and `protected` variable called `GITLAB_TOKEN` in `CI/CD -> Variables` using the previously created token value

cookiecutter.json

@@ -0,0 +1,7 @@
+{
+    "project_name": "Data Science Project",
+    "project_description": "A short description of the project.",
+    "repo_name": "{{ cookiecutter.project_name.lower().replace(' ', '-') }}",
+    "repo_url": "URL to repository",
+    "env_name": "{{ cookiecutter.project_name.lower().replace(' ', '-') + '-env' }}"
+}

environment.yaml

@@ -1,9 +1,8 @@
+name: data-science-project-template
 channels:
     - conda-forge
 dependencies:
     - black=22.3.0
-    - nbqa=1.2.3
-    - ipykernel=6.9.1
     - python=3.9.7
     - pre-commit=2.18.1
     - pylint=2.12.2

hooks/post_gen_project.py

@@ -0,0 +1,17 @@
+import subprocess
+
+# initialize new project repository
+subprocess.run(["git", "init"], check=True)
+subprocess.run(["git", "branch", "-m", "main"], check=True)
+subprocess.run(["git", "add", "."], check=True)
+subprocess.run(
+    ["git", "commit", "-m", "chore: initialize repo from data science template"], check=True
+)
+subprocess.run(["git", "remote", "add", "origin", "{{cookiecutter.repo_url}}"], check=True)
+
+# setup environment
+subprocess.run(["mamba", "env", "create", "-f", "environment.yaml", "--quiet"], check=True)
+subprocess.run(
+    ["mamba", "run", "--no-banner", "-n", "{{cookiecutter.env_name}}", "pre-commit", "install"],
+    check=True,
+)

{{cookiecutter.repo_name}}/.commitlintrc.yaml

@@ -0,0 +1,27 @@
+extends:
+    - '@commitlint/config-conventional'
+rules:
+    # Scope enum should be customized to match project needs
+    scope-enum:
+        - 2
+        - always
+        - - scope-1
+          - scope-2
+    # Type enum should be consistent across data science projects
+    type-enum:
+        - 2
+        - always
+        - - build
+          - chore
+          - ci
+          - docs
+          - feat
+          - fix
+          - perf
+          - refactor
+          - revert
+          - style
+          - test
+          - data
+          - explore
+          - result

{{cookiecutter.repo_name}}/.gitattributes

@@ -0,0 +1,5 @@
+data/** filter=lfs diff=lfs merge=lfs -text
+
+# let git decide if a file is a text file or a binary files
+# for text files, convert all CRLF to LF on check-in (not in working tree)
+* text=auto

{{cookiecutter.repo_name}}/.gitignore

@@ -0,0 +1,85 @@
+# based on: https://github.com/github/gitignore/blob/master/Python.gitignore
+
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$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/
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# IDEs
+.idea
+.vscode
+
+# Data
+data/*
+!data/raw/

{{cookiecutter.repo_name}}/.gitlab-ci-stages.yaml

@@ -0,0 +1,2 @@
+stages:
+    - test

{{cookiecutter.repo_name}}/.gitlab-ci-test.yaml

@@ -0,0 +1,24 @@
+.setup_python_env: &setup_python_env
+    before_script:
+        - apt-get update && apt-get install -y --no-install-recommends git-core ca-certificates git-lfs
+        - conda env create -f environment.yaml --name=conda_env
+        - conda init bash
+        - source ~/.bashrc
+        - conda activate conda_env
+        - pre-commit install
+
+format_and_lint:
+    stage: test
+    image: continuumio/miniconda3
+    <<: *setup_python_env
+    script:
+        - pre-commit run --hook-stage manual --all-files
+        - git fetch
+        - chmod a+x check_commit_msgs.sh
+        - ./check_commit_msgs.sh -c "remotes/origin/${CI_COMMIT_BRANCH}" -m "remotes/origin/${CI_DEFAULT_BRANCH}"
+    rules:
+        - if: $CI_COMMIT_TAG
+          when: never
+        - if: '$CI_PIPELINE_SOURCE == "merge_request_event"'
+          when: never
+        - when: always

.gitlab-ci.yaml → {{cookiecutter.repo_name}}/.gitlab-ci.yml

@@ -1,6 +1,5 @@
 # the ci configuration is split into multiple files
 # this allows the semantic versioning (versioning the template itself) to be easily removed
 include:
-    - .gitlab-ci-stages.yml
-    - .gitlab-ci-release.yml
-    - .gitlab-ci-test.yml
+    - .gitlab-ci-stages.yaml
+    - .gitlab-ci-test.yaml