integrated workflow friom david

.github/workflows/test-snake.yml

@@ -0,0 +1,47 @@
+name: Snakemake CI
+
+on:
+  push:
+    branches: [ main ]
+  pull_request:
+    branches: [ main ]
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    strategy:
+      fail-fast: true
+      matrix:
+        python-version: ["3.11.2"]
+        poetry-version: ["1.8.3"]
+
+    steps:
+      - uses: actions/checkout@v3
+      - name: Set up Python ${{ matrix.python-version }}
+        uses: actions/setup-python@v4
+        with:
+          python-version: ${{ matrix.python-version }}
+          cache: "pip"
+
+      - uses: mamba-org/setup-micromamba@v1
+        with:
+          micromamba-version: '1.5.6-0' 
+          environment-file: environment.yml
+          init-shell: >-
+            bash
+          cache-environment: true
+          post-cleanup: 'all'
+
+      - name: Install dependencies
+        run: |
+          pip install -e .
+
+      - name: Snakemake Linting
+        run: |
+          snakemake --lint -s workflow/Snakefile
+
+      - name: Snakemake Testing
+        run: |
+          snakemake --cores 1 --snakefile workflow/Snakefile --directory .test --verbose
+
+      

.github/workflows/test.yml

@@ -1,7 +1,7 @@
 # This pipeline checks whether the package
 # installs properly, passes unit tests and whether
 # the code formatting is right.
-name: build
+name: CI/CD
 
 on:
   push:

.gitignore

@@ -1,5 +1,16 @@
+# Local file system
 .DS_Store
-poetry.lock
+
+# IDE
 .vscode/
+
+# Poetry
+poetry.lock
+
+# Byte-compiled / optimized / DLL files
 __pycache__/
-*.pyc
+*.pyc
+
+# Snakemake
+workflow/.snakemake
+ .snakemake/

.pre-commit-config.yaml

@@ -27,4 +27,19 @@ repos:
         entry: poetry run pyright
         language: node
         pass_filenames: true
-        types: [python]
+        types: [python]
+  - repo: local
+    hooks:
+      - id: snakemake-lint
+        name: Snakemake Lint
+        entry: bash -c 'cd workflow && snakemake --lint'
+        language: system
+        files: (Snakefile|\.smk$)
+        pass_filenames: false
+
+      - id: snakemake-dryrun
+        name: Snakemake Dry Run
+        entry: bash -c 'cd workflow && snakemake --lint'
+        language: system
+        files: (Snakefile|\.smk$)
+        pass_filenames: false

README.md

@@ -1,5 +1,6 @@
 [![Project Status: WIP – This project is currently under active development.](https://www.repostatus.org/badges/latest/wip.svg)](https://www.repostatus.org/#wip)
-[![build](https://github.com/gordonkoehn/UsefulGnom/actions/workflows/test.yml/badge.svg)](https://github.com/gordonkoehn/UsefulGnom/actions/workflows/test.yml)
+[![CI/CD](https://github.com/gordonkoehn/UsefulGnom/actions/workflows/test.yml/badge.svg)](https://github.com/gordonkoehn/UsefulGnom/actions/workflows/test.yml)
+![Snakemake CI](https://github.com/gordonkoehn/UsefulGnom/actions/workflows/test-snake.yml/badge.svg?branch=coverage-smk-tests)
 [![Ruff](https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/charliermarsh/ruff/main/assets/badge/v2.json)](https://github.com/charliermarsh/ruff)
 [![Code style: black](https://img.shields.io/badge/code%20style-black-000000.svg)](https://github.com/psf/black)
 

config/README.md

@@ -0,0 +1 @@
+This directory contains the Snakemake config file as well as ruls specific config files of input and output files.

config/config.yaml

@@ -0,0 +1,2 @@
+# some placeholder values
+root: .

config/smk_testing_config.yaml

@@ -0,0 +1,3 @@
+orderbook: "data/AMZN_2012-06-21_34200000_57600000_message_1.csv"
+statistics: "results/statistics.csv"
+interval: 5  # interval in minutes

environment.yml

@@ -7,6 +7,11 @@ channels:
   - conda-forge
   - defaults
 dependencies:
-  - python=3.11.2
   - snakemake=8.18.2
-  - poetry=1.8.3
+  - poetry=1.8.3
+  - matplotlib=3.9.2
+  - pandas=2.2.2
+  - seaborn=0.13.2
+  - pip
+  - pip:
+    - -e .

pyproject.toml

@@ -13,11 +13,12 @@ matplotlib = "^3.9.2"
 seaborn = "^0.13.2"
 pandas-stubs = "^2.2.2.240807"
 click = "^8.1.7"
+snakemake = "^8.20.4"
 
 [tool.poetry.group.dev.dependencies]
 pytest = "^7.2.1"
 ruff = "^0.0.253"
-black = "^23.1.0"
+black = "^24.8.0"
 pytest-cov = "^4.0.0"
 pytest-xdist = "^3.2.0"
 pre-commit = "^3.1.0"

src/usefulgnom/analyze/basecnt_coverage.py

@@ -1,4 +1,5 @@
-"""Implements the read coverage analysis.
+"""
+    Implements the read coverage analysis.
 
     Credits:
         - core code: @AugusteRi ([email protected])

src/usefulgnom/serialize/basecnt_coverage.py

@@ -1,16 +1,17 @@
-"""Implements loading and converting the base nucleotide coverage data.
-
-e.g.: of base nucleotide coverage file -  bascnt.tsv:
-
-sample		B3_25_2024_08_11/20240823_2346503305	\ 
-B3_25_2024_08_11/20240823_2346503305	B3_25_2024_08_11/20240823_2346503305 \
-B3_25_2024_08_11/20240823_2346503305	B3_25_2024_08_11/20240823_2346503305
-nt		A	C	G	T	-
-ref	pos					
-NC_045512.2	1	0	0	0	0	0
-NC_045512.2	2	0	0	0	0	0
-NC_045512.2	3	0	0	0	0	0
-NC_045512.2	4	0	0	0	0	0
+"""
+    Implements loading and converting the base nucleotide coverage data.
+
+    e.g.: of base nucleotide coverage file -  bascnt.tsv:
+
+    sample		B3_25_2024_08_11/20240823_2346503305	
+    B3_25_2024_08_11/20240823_2346503305	B3_25_2024_08_11/20240823_2346503305 
+    B3_25_2024_08_11/20240823_2346503305	B3_25_2024_08_11/20240823_2346503305
+    nt		A	C	G	T	-
+    ref	pos					
+    NC_045512.2	1	0	0	0	0	0
+    NC_045512.2	2	0	0	0	0	0
+    NC_045512.2	3	0	0	0	0	0
+    NC_045512.2	4	0	0	0	0	0
 
 """