Merge branch 'main' of https://github.com/EliHei2/segger_dev into main

Conflicts:
	docs/notebooks/segger_tutorial.ipynb
	src/segger/cli/configs/predict/default.yaml
	src/segger/cli/configs/train/default.yaml

.github/ISSUE_TEMPLATE/➕-performance-improvement.md

@@ -0,0 +1,16 @@
+---
+name: "➕ Performance Improvement"
+about: Suggest an improvement in the performance
+title: ""
+labels: ""
+assignees: andrewmoorman, EliHei2
+---
+
+**Describe the issue with the current implementation**
+A clear and concise description of what is wrong or not efficient in the implementation.
+
+**Suggested improvement**
+If you know how to fix it, provide suggestions on what to change.
+
+**Additional context**
+Any other context or screenshots that might help clarify the issue.

.github/ISSUE_TEMPLATE/🐛-bug-report.md

@@ -0,0 +1,43 @@
+---
+name: "\U0001F41B Bug Report"
+about: Create a report to help us improve
+title: "[BUG]"
+labels: ""
+assignees: andrewmoorman, EliHei2
+---
+
+---
+
+name: Bug Report
+about: Report a bug or unexpected behavior
+title: "[BUG] "
+labels: bug
+assignees: ''
+
+---
+
+**Describe the bug**
+A clear and concise description of what the bug is.
+
+**To Reproduce**
+Steps to reproduce the behavior:
+
+1. Go to '...'
+2. Click on '....'
+3. Scroll down to '....'
+4. See error
+
+**Expected behavior**
+A clear and concise description of what you expected to happen.
+
+**Screenshots or logs**
+If applicable, add screenshots or logs to help explain your problem.
+
+**Environment (please complete the following information):**
+
+- OS: [e.g. macOS, Windows, Linux]
+- Python version: [e.g. 3.9]
+- Package version: [e.g. 1.2.3]
+
+**Additional context**
+Add any other context about the problem here.

.github/ISSUE_TEMPLATE/🚀-feature-request.md

@@ -0,0 +1,19 @@
+---
+name: "\U0001F680 Feature Request"
+about: Suggest an idea for this project
+title: ""
+labels: ""
+assignees: ""
+---
+
+**Is your feature request related to a problem? Please describe.**
+A clear and concise description of what the problem is. Ex. I'm always frustrated when [...]
+
+**Describe the solution you'd like**
+A clear and concise description of what you want to happen.
+
+**Describe alternatives you've considered**
+A clear and concise description of any alternative solutions or features you've considered.
+
+**Additional context**
+Add any other context or screenshots about the feature request here.

.github/workflows/python-publish.yml

@@ -17,23 +17,22 @@ permissions:
 
 jobs:
   deploy:
-
     runs-on: ubuntu-latest
 
     steps:
-    - uses: actions/checkout@v4
-    - name: Set up Python
-      uses: actions/setup-python@v3
-      with:
-        python-version: '3.x'
-    - name: Install dependencies
-      run: |
-        python -m pip install --upgrade pip
-        pip install build
-    - name: Build package
-      run: python -m build
-    - name: Publish package
-      uses: pypa/gh-action-pypi-publish@27b31702a0e7fc50959f5ad993c78deac1bdfc29
-      with:
-        user: __token__
-        password: ${{ secrets.PYPI_API_TOKEN }}
+      - uses: actions/checkout@v4
+      - name: Set up Python
+        uses: actions/setup-python@v3
+        with:
+          python-version: "3.x"
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install build
+      - name: Build package
+        run: python -m build
+      - name: Publish package
+        uses: pypa/gh-action-pypi-publish@27b31702a0e7fc50959f5ad993c78deac1bdfc29
+        with:
+          user: __token__
+          password: ${{ secrets.PYPI_API_TOKEN }}

.github/workflows/static.yml

@@ -2,13 +2,11 @@ name: Deploy MkDocs to GitHub Pages
 
 on:
   push:
-    branches: ["main"]  # Change "main" to your default branch if necessary
-
-  # Allows you to run this workflow manually from the Actions tab
+    branches: ["main"]
   workflow_dispatch:
 
 permissions:
-  contents: read
+  contents: write
   pages: write
   id-token: write
 
@@ -21,38 +19,34 @@ jobs:
     runs-on: ubuntu-latest
 
     steps:
-      # Step 1: Checkout the repository
       - name: Checkout repository
         uses: actions/checkout@v4
 
-      # Step 2: Set up Python environment
       - name: Set up Python
         uses: actions/setup-python@v4
         with:
-          python-version: '3.x'
+          python-version: "3.10"
 
-      # Step 3: Install your package from the repository
-      - name: Install package
+      - name: Install package and documentation dependencies
         run: |
-          export PYTHONPATH='./src'
-          export PYTHONPATH='./src/segger'
-      
-      # Step 4: Install MkDocs and dependencies
-      - name: Install dependencies
+          pip install -e .
+
+      - name: Install MkDocs and plugins
         run: |
           pip install mkdocs mkdocs-material mkdocs-autorefs mkdocstrings[python] mkdocs-jupyter pymdown-extensions termynal mkdocs-minify-plugin
 
-      # Step 5: Build the MkDocs site
+      - name: Debug environment
+        run: |
+          python -m pip freeze
+          python -m mkdocs --version
+
       - name: Build MkDocs site
         run: mkdocs build --verbose
 
-      # Step 6: Upload the generated site directory as an artifact for GitHub Pages
-      - name: Upload artifact
-        uses: actions/upload-pages-artifact@v3
-        with:
-          path: './site'  # Only upload the generated `site` folder
-
-      # Step 7: Deploy to GitHub Pages
       - name: Deploy to GitHub Pages
-        id: deployment
-        uses: actions/deploy-pages@v4
+        run: |
+          git config --global user.name "GitHub Actions"
+          git config --global user.email "actions@github.com"
+          mkdocs gh-deploy --force --remote-name origin
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}

.gitignore

@@ -163,9 +163,12 @@ cython_debug/
 
 
 data_*
+data/*
 model_*
 
 *.egg_info
 figure*
 
 dev*
+.DS_Store
+.idea/

.pre-commit-config.yaml

@@ -0,0 +1,22 @@
+fail_fast: false
+default_language_version:
+  python: python3
+default_stages:
+  - pre-commit
+  - pre-push
+minimum_pre_commit_version: 2.16.0
+ci:
+  skip: []
+repos:
+  - repo: https://github.com/psf/black
+    rev: 24.10.0
+    hooks:
+      - id: black
+  - repo: https://github.com/pre-commit/mirrors-prettier
+    rev: v4.0.0-alpha.8
+    hooks:
+      - id: prettier
+  - repo: https://github.com/asottile/blacken-docs
+    rev: 1.19.1
+    hooks:
+      - id: blacken-docs

.prettierignore

@@ -0,0 +1,3 @@
+# Ignore artifacts:
+docs/*
+mkdocs.yml

.scripts/create_dataset.py

@@ -2,7 +2,7 @@
 import os
 from pathlib import Path
 from urllib import request
-from segger.data.utils import XeniumSample
+from segger.data.io import XeniumSample
 
 
 def download_file(url, dest):
@@ -30,9 +30,7 @@ def main(args):
     download_file(transcripts_url, transcripts_path)
     download_file(nuclei_url, nuclei_path)
 
-    xs = XeniumSample().load_transcripts(
-        path=transcripts_path, min_qv=args.min_qv
-    )
+    xs = XeniumSample().load_transcripts(path=transcripts_path, min_qv=args.min_qv)
     xs.load_nuclei(path=nuclei_path)
 
     if args.parallel:
@@ -83,9 +81,7 @@ def main(args):
 
 
 if __name__ == "__main__":
-    parser = argparse.ArgumentParser(
-        description="Create dataset from Xenium Human Pancreatic data."
-    )
+    parser = argparse.ArgumentParser(description="Create dataset from Xenium Human Pancreatic data.")
     parser.add_argument(
         "--raw_data_dir",
         type=str,
@@ -104,9 +100,7 @@ def main(args):
         required=True,
         help="URL for transcripts data.",
     )
-    parser.add_argument(
-        "--nuclei_url", type=str, required=True, help="URL for nuclei data."
-    )
+    parser.add_argument("--nuclei_url", type=str, required=True, help="URL for nuclei data.")
     parser.add_argument(
         "--min_qv",
         type=int,
@@ -125,21 +119,11 @@ def main(args):
         default=180,
         help="Step size in y direction for tiles.",
     )
-    parser.add_argument(
-        "--x_size", type=int, default=200, help="Width of each tile."
-    )
-    parser.add_argument(
-        "--y_size", type=int, default=200, help="Height of each tile."
-    )
-    parser.add_argument(
-        "--margin_x", type=int, default=None, help="Margin in x direction."
-    )
-    parser.add_argument(
-        "--margin_y", type=int, default=None, help="Margin in y direction."
-    )
-    parser.add_argument(
-        "--r_tx", type=int, default=3, help="Radius for building the graph."
-    )
+    parser.add_argument("--x_size", type=int, default=200, help="Width of each tile.")
+    parser.add_argument("--y_size", type=int, default=200, help="Height of each tile.")
+    parser.add_argument("--margin_x", type=int, default=None, help="Margin in x direction.")
+    parser.add_argument("--margin_y", type=int, default=None, help="Margin in y direction.")
+    parser.add_argument("--r_tx", type=int, default=3, help="Radius for building the graph.")
     parser.add_argument(
         "--val_prob",
         type=float,
@@ -158,9 +142,7 @@ def main(args):
         default=3,
         help="Number of nearest neighbors for nuclei.",
     )
-    parser.add_argument(
-        "--dist_nc", type=int, default=10, help="Distance threshold for nuclei."
-    )
+    parser.add_argument("--dist_nc", type=int, default=10, help="Distance threshold for nuclei.")
     parser.add_argument(
         "--k_tx",
         type=int,
@@ -179,12 +161,8 @@ def main(args):
         default=True,
         help="Whether to compute edge labels.",
     )
-    parser.add_argument(
-        "--sampling_rate", type=float, default=1, help="Rate of sampling tiles."
-    )
-    parser.add_argument(
-        "--parallel", action="store_true", help="Use parallel processing."
-    )
+    parser.add_argument("--sampling_rate", type=float, default=1, help="Rate of sampling tiles.")
+    parser.add_argument("--parallel", action="store_true", help="Use parallel processing.")
     parser.add_argument(
         "--num_workers",
         type=int,

.scripts/predict.py

@@ -30,9 +30,7 @@ def main(args: argparse.Namespace) -> None:
 
 
 if __name__ == "__main__":
-    parser = argparse.ArgumentParser(
-        description="Predict using the Segger model"
-    )
+    parser = argparse.ArgumentParser(description="Predict using the Segger model")
     parser.add_argument(
         "--dataset_path",
         type=str,
@@ -51,24 +49,16 @@ def main(args: argparse.Namespace) -> None:
         required=True,
         help="Path to the model checkpoint",
     )
-    parser.add_argument(
-        "--init_emb", type=int, default=8, help="Initial embedding size"
-    )
+    parser.add_argument("--init_emb", type=int, default=8, help="Initial embedding size")
     parser.add_argument(
         "--hidden_channels",
         type=int,
         default=64,
         help="Number of hidden channels",
     )
-    parser.add_argument(
-        "--out_channels", type=int, default=16, help="Number of output channels"
-    )
-    parser.add_argument(
-        "--heads", type=int, default=4, help="Number of attention heads"
-    )
-    parser.add_argument(
-        "--aggr", type=str, default="sum", help="Aggregation method"
-    )
+    parser.add_argument("--out_channels", type=int, default=16, help="Number of output channels")
+    parser.add_argument("--heads", type=int, default=4, help="Number of attention heads")
+    parser.add_argument("--aggr", type=str, default="sum", help="Aggregation method")
     parser.add_argument(
         "--score_cut",
         type=float,
@@ -81,9 +71,7 @@ def main(args: argparse.Namespace) -> None:
         default=4,
         help="Number of nearest neighbors for nuclei",
     )
-    parser.add_argument(
-        "--dist_nc", type=int, default=20, help="Distance threshold for nuclei"
-    )
+    parser.add_argument("--dist_nc", type=int, default=20, help="Distance threshold for nuclei")
     parser.add_argument(
         "--k_tx",
         type=int,