Merge pull request #845 from RasmusOrsoe/fix_code_quality_workflow

RasmusOrsoe · web-flow · commit de50e86dafb4 · 2025-11-11T08:29:50.000+01:00
Code Quality Fix
diff --git a/.github/actions/install/action.yml b/.github/actions/install/action.yml
@@ -68,5 +68,5 @@ runs:
         echo "Installing graphnet with flags: ${{ steps.flags.outputs.user_flag }} ${{ steps.flags.outputs.editable_flag }}"
         echo "pip install ${{ steps.flags.outputs.user_flag }} ${{ steps.flags.outputs.editable_flag }} .[torch-${{ steps.flags.outputs.torch_flag }},${{ inputs.extras }}] -f https://data.pyg.org/whl/torch-${{ inputs.torch_version }}+${{ inputs.hardware }}.html"
         pip install ${{ steps.flags.outputs.user_flag }} ${{ steps.flags.outputs.editable_flag }} .[torch-${{ steps.flags.outputs.torch_flag }},${{ inputs.extras }}] -f https://data.pyg.org/whl/torch-${{ inputs.torch_version }}+${{ inputs.hardware }}.html
- 
+
         pip install git+https://github.com/thoglu/jammy_flows.git
diff --git a/.github/workflows/build.yml b/.github/workflows/build.yml
@@ -32,7 +32,7 @@ jobs:
           fi
 
   build-icetray:
-    name: Unit tests - IceTray (v1.13.0 - 3.10)  
+    name: Unit tests - IceTray (v1.13.0 - 3.10)
     needs: [ check-Qlty-credentials ]
     runs-on: ubuntu-22.04
     strategy:
@@ -43,7 +43,7 @@ jobs:
       # GitHub Actions overwrite the docker container entrypoint
       # inspect <image> --format '{{.Config.Entrypoint}}'
       image: icecube/icetray:icetray-devel-v1.13.0-ubuntu22.04-2025-02-12
-    
+
     steps:
       - name: Mimmick Docker Entrypoint
         # The entrypoint of the container sets python paths
@@ -62,7 +62,7 @@ jobs:
       - name: Verify IceCube is importable
         run: python3 -c "import icecube; print('Import Successful')"
       - name: Show python version
-        run: | 
+        run: |
           python3 --version
           pip --version
           pip3 list
@@ -122,9 +122,9 @@ jobs:
         shell: bash
         run: |
           source ~/venv/bin/activate
-          coverage run --source=graphnet -m pytest tests/ --ignore=tests/examples/04_training --ignore=tests/utilities 
+          coverage run --source=graphnet -m pytest tests/ --ignore=tests/examples/04_training --ignore=tests/utilities
           coverage run -a --source=graphnet -m pytest tests/examples/04_training
-          coverage run -a --source=graphnet -m pytest tests/utilities 
+          coverage run -a --source=graphnet -m pytest tests/utilities
           coverage xml -o coverage.xml
           coverage report -m
       - name: Work around permission issue
@@ -136,7 +136,7 @@ jobs:
         with:
           token: ${{secrets.QLTY_TOKEN}}
           files: coverage.xml
-          
+
 
   build-matrix-examples:
     name: Examples - Ubuntu 22.04
diff --git a/.github/workflows/code-quality.yml b/.github/workflows/code-quality.yml
@@ -23,14 +23,13 @@ jobs:
         hook: ["black", "flake8", "docformatter", "pydocstyle", "mypy"]
     steps:
       - uses: actions/checkout@v4
-      - name: Set up Python 3.10
-        uses: actions/setup-python@v3
+      - name: Set up Python 3.11
+        uses: actions/setup-python@v5
         with:
-          python-version: "3.10"
+          python-version: "3.11"
       - name: Install package
         uses: ./.github/actions/install
-        with:
-          
+
       - name: Run ${{ matrix.hook }}
         run: |
           pip show ${{ matrix.hook }}
diff --git a/.github/workflows/docker_action.yml b/.github/workflows/docker_action.yml
@@ -4,14 +4,14 @@ on:
   workflow_call:
     inputs:
       DOCKERHUB_NAME:        { type: string, required: true }
-      DOCKERFILE_PATH:       { type: string, required: true} 
+      DOCKERFILE_PATH:       { type: string, required: true}
       GRAPHNET_VERSION:      { type: string, default: "main" }
       BASE_IMAGE:            { type: string, default: "ubuntu:22.04" }
       TORCH_CHOICE:          { type: string, default: "torch-2.6.0" }  # torch-2.7.0|2.6.0|2.5.1|no_torch
       HARDWARE:              { type: string, default: "cpu" }          # cpu|cu118|cu121|cu124|cu126|cu128
       PYTHON_VERSION:        { type: string, default: "3.11" }
       PLATFORMS:             { type: string, default: "linux/amd64" }
-      CONTEXT_PATH:          { type: string, default: "." }           
+      CONTEXT_PATH:          { type: string, default: "." }
     secrets:
       DOCKERHUB_USERNAME:
         required: true
@@ -102,7 +102,7 @@ jobs:
         uses: docker/build-push-action@v6
         with:
           context:   ${{ inputs.CONTEXT_PATH }}
-          file:      ${{ inputs.DOCKERFILE_PATH }}         
+          file:      ${{ inputs.DOCKERFILE_PATH }}
           platforms: ${{ env.PLATFORMS }}
           push: true
           tags: ${{ steps.tag.outputs.full }}
diff --git a/.github/workflows/paper.yml b/.github/workflows/paper.yml
@@ -28,4 +28,4 @@ jobs:
           # This is the output path where Pandoc will write the compiled
           # PDF. Note, this should be the same directory as the input
           # paper.md
-          path: paper/paper.pdf
+          path: paper/paper.pdf
diff --git a/.gitignore b/.gitignore
@@ -150,9 +150,9 @@ data/examples/output/
 **.pth
 **.db
 **.parquet
-# Exception to pre-trained folders; here we want all .pth files 
+# Exception to pre-trained folders; here we want all .pth files
 !/graphnet/src/graphnet/models/pretrained/**/**/**/**/**.pth
-# Exception to geometry tables 
+# Exception to geometry tables
 !/data/geometry_tables/**/**.parquet
 !/data/tests/sqlite/upgrade_genie_step4_140028_000998_first_5_frames/upgrade_genie_step4_140028_000998_first_5_frames.db
 !/data/tests/parquet/oscNext_genie_level7_v02/merged/**
diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml
@@ -9,8 +9,8 @@ repos:
   - repo: https://github.com/pycqa/flake8
     rev: 7.1.1
     hooks:
-    - id: flake8
-      language_version: python3
+      - id: flake8
+        args: ["--config=.flake8", "--show-source", "--statistics"]
   - repo: https://github.com/pycqa/docformatter
     rev: v1.7.7
     hooks:
@@ -26,4 +26,9 @@ repos:
     hooks:
     - id: mypy
       args: [--follow-imports=silent, --disallow-untyped-defs, --disallow-incomplete-defs, --disallow-untyped-calls]
-      language_version: python3
+      language_version: python3
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v4.6.0
+    hooks:
+      - id: trailing-whitespace
+      - id: end-of-file-fixer
diff --git a/CITATION.cff b/CITATION.cff
@@ -54,4 +54,4 @@ version: 1.0.0
 date-released: 2023-05-12
 url: "https://github.com/graphnet-team/graphnet"
 license: Apache-2.0
-type: software
+type: software
diff --git a/black.toml b/black.toml
@@ -7,4 +7,4 @@ extend-exclude = '''
       versioneer.py
     | src/graphnet/_version.py
 )
-'''
+'''
diff --git a/configs/datasets/training_classification_example_data_sqlite.yml b/configs/datasets/training_classification_example_data_sqlite.yml
@@ -67,4 +67,4 @@ selection:
   train_nu_e: 60 random events ~ event_no % 5 > 1 & (dummy_pid == 12 | dummy_pid == -12)
   train_nu_mu: 60 random events ~ event_no % 5 > 1 & (dummy_pid == 14 | dummy_pid == -14)
   train_nu_tau: 60 random events ~ event_no % 5 > 1 & (dummy_pid == 16 | dummy_pid == -16)
-  train_mu: 60 random events ~ event_no % 5 > 1 & (dummy_pid == 13 | dummy_pid == -13)
+  train_mu: 60 random events ~ event_no % 5 > 1 & (dummy_pid == 13 | dummy_pid == -13)
diff --git a/configs/datasets/training_example_data_parquet.yml b/configs/datasets/training_example_data_parquet.yml
@@ -53,4 +53,4 @@ seed: 21
 selection:
   test: event_no % 5 == 0
   validation: event_no % 5 == 1
-  train: event_no % 5 > 1
+  train: event_no % 5 > 1
diff --git a/configs/datasets/training_example_data_sqlite.yml b/configs/datasets/training_example_data_sqlite.yml
@@ -53,4 +53,4 @@ seed: 21
 selection:
   test: event_no % 5 == 0
   validation: event_no % 5 == 1
-  train: event_no % 5 > 1
+  train: event_no % 5 > 1
diff --git a/docker/gnn-benchmarking/dockerfile b/docker/gnn-benchmarking/dockerfile
@@ -18,4 +18,4 @@ WORKDIR /root
 ADD module.py ./module.py
 ADD apply.py ./apply.py
 
-CMD [ "/bin/bash" ]
+CMD [ "/bin/bash" ]
diff --git a/dockerfile b/dockerfile
@@ -40,4 +40,4 @@ RUN echo 'PS1="🐳 \[\033[38;2;86;138;242m\]graphnet@\h \[\033[0m\]❯ \[\033[0
 RUN echo 'PS2="\[\033[38;5;236m\]❯\[\033[38;5;239m\]❯\[\033[0m\]❯ "' >> ~/.bashrc
 
 # Default command for executing container.
-CMD [ "/bin/bash" ]
+CMD [ "/bin/bash" ]
diff --git a/examples/04_training/README.md b/examples/04_training/README.md
@@ -30,7 +30,7 @@ This subfolder contains two main training scripts:
 # Same as above, as this is the default model config.
 (graphnet) $ python examples/04_training/03_train_dynedge_from_config.py \
     --model-config configs/models/example_energy_reconstruction_model.yml
-    
+
 # Train a vertex position reconstruction model
 (graphnet) $ python examples/04_training/03_train_dynedge_from_config.py \
     --model-config configs/models/example_vertex_position_reconstruction_model.yml
diff --git a/examples/05_liquido/README.md b/examples/05_liquido/README.md
@@ -1,3 +1,3 @@
 # LiquidO data conversion example
 
-This directory contain examples of converting data from LiqidO to intermediate data formats suitable for deep learning in GraphNeT 
+This directory contain examples of converting data from LiqidO to intermediate data formats suitable for deep learning in GraphNeT
diff --git a/examples/06_prometheus/README.md b/examples/06_prometheus/README.md
@@ -1,5 +1,5 @@
 # Prometheus data conversion example
 
-This directory contain examples of converting data from the open-source neutrino telescope Prometheus simulation to intermediate data formats suitable for deep learning in GraphNeT. 
+This directory contain examples of converting data from the open-source neutrino telescope Prometheus simulation to intermediate data formats suitable for deep learning in GraphNeT.
 
 More details on the Prometheus simulation project can be found [here](https://arxiv.org/pdf/2304.14526.pdf)
diff --git a/examples/README.md b/examples/README.md
@@ -7,7 +7,7 @@ Examples are grouped into five numbered subfolders, roughly in order of how you
 2. **Data.** Reading in data in intermediate formats, plotting feature distributions, and converting data between intermediate file formats. These examples are entirely self-contained and can be run by anyone.
 3. **Weights.** Fitting per-event weights.
 4. **Training.** Training GNN models on various physics tasks.
-5**LiquidO.** Converting h5 files from the LiquidO experiment into intermediate formats suitable for deep learning. 
+5**LiquidO.** Converting h5 files from the LiquidO experiment into intermediate formats suitable for deep learning.
 
 Each subfolder contains similarly numbered example scripts.
 Each example script comes with a simple command-line interface and help functionality, e.g.
diff --git a/setup.cfg b/setup.cfg
@@ -28,4 +28,5 @@ wrap-summaries = 79
 wrap-descriptions = 79
 
 [mypy]
-ignore_missing_imports = True
+ignore_missing_imports = True
+python_version = 3.11
diff --git a/src/graphnet/data/extractors/icecube/i3highesteparticleextractor.py b/src/graphnet/data/extractors/icecube/i3highesteparticleextractor.py
@@ -401,7 +401,7 @@ def highest_energy_track(
 
         return particle, EonEntrance, distance, visible_length, containment
 
-    def highest_energy_starting(
+    def highest_energy_starting(  # noqa: C901
         self,
         frame: "icetray.I3Frame",
         min_e: float = 0,
diff --git a/src/graphnet/models/data_representation/data_representation.py b/src/graphnet/models/data_representation/data_representation.py
@@ -289,14 +289,14 @@ def _validate_input(
         # `DataRepresentation` was instantiated with.
         assert len(input_feature_names) == len(
             self._input_feature_names
-        ), f"""Input features ({input_feature_names}) is not what 
+        ), f"""Input features ({input_feature_names}) is not what
                {self.__class__.__name__} was instatiated
                with ({self._input_feature_names})"""  # noqa
         for idx in range(len(input_feature_names)):
             assert (
                 input_feature_names[idx] == self._input_feature_names[idx]
             ), f""" Order of representation features in data
-                    are not the same as expected. Got {input_feature_names} 
+                    are not the same as expected. Got {input_feature_names}
                     vs. {self._input_feature_names}"""  # noqa
 
     def _perturb_input(self, input_features: np.ndarray) -> np.ndarray:
diff --git a/src/graphnet/models/pretrained/icecube/kaggle/icemix/neutrino_direction/README.md b/src/graphnet/models/pretrained/icecube/kaggle/icemix/neutrino_direction/README.md
@@ -11,7 +11,7 @@ Original repository can be found [here](https://github.com/DrHB/icecube-2nd-plac
 
 The state dict of the models is an exact copy of the one used in the competition, so further state_dict keys might be needed to load the models. Here is some pseudo-code which might help you load the weights into GraphNet:
 
-```python     
+```python
 checkpoint = torch.load(path_to_checkpoint, torch.device("cpu"))
 if "state_dict" in checkpoint:
        checkpoint = checkpoint["state_dict"]
@@ -65,7 +65,7 @@ class Direction_flipped(Label):
         ).reshape(-1, 1)
         z = torch.cos(graph[self._zenith_key]).reshape(-1, 1)
         return torch.cat((y, x, z), dim=1) # Flipped x and y
-```    
+```
 
 ## Hard Local Coincidence feature
 
@@ -89,7 +89,7 @@ def _hlc(self, x: torch.tensor) -> torch.tensor:
 
 The original models were stacked using a simple linear combination of the predictions. Here is some pseudo-code which can be used to stack the models:
 
-```python	
+```python
 MODEL_NAMES = [
     "B_d32",
     "B_d64",
@@ -183,4 +183,4 @@ def inference(
 
     return results
 
-```
+```
diff --git a/src/graphnet/training/loss_functions.py b/src/graphnet/training/loss_functions.py
@@ -271,39 +271,39 @@ def backward(
         ctx: Any, grad_output: Tensor
     ) -> Tensor:  # pylint: disable=invalid-name,arguments-differ
         """Backward pass for LogCMK computation.
-        
+
         Mathematical Background:
         -----------------------
-        For the von Mises-Fisher distribution, the gradient of log C_m(κ) with 
+        For the von Mises-Fisher distribution, the gradient of log C_m(κ) with
         respect to κ is given by the ratio of modified Bessel functions:
-        
+
         ∂/∂κ log C_m(κ) = (m/2-1)/κ - I_{m/2}(κ)/I_{m/2-1}(κ)
-        
+
         For m=3, this simplifies to the exact formula:
         ∂/∂κ log C_3(κ) = 1/κ - 1/tanh(κ)
-        
+
         For small κ values, we use the Taylor series approximation:
         f(κ) = -κ/3 + κ³/45 - 2κ⁵/945 + O(κ⁷)
-        
-        The first-order approximation -κ/3 provides sufficient accuracy for 
+
+        The first-order approximation -κ/3 provides sufficient accuracy for
         |κ| < 1e-6, with truncation error bounded by |κ|³/45 ≲ O(10⁻²¹).
-        
+
         Implementation Details:
         ----------------------
         Uses boolean masking to avoid double evaluation and RuntimeWarnings:
         - Small κ: |κ| < 1e-6 → gradient = -κ/3 (Taylor approximation)
         - Large κ: |κ| ≥ 1e-6 → gradient = 1/κ - 1/tanh(κ) (exact formula)
-        
+
         References:
         ----------
         [1] von Mises-Fisher distribution: Wikipedia
         [2] arXiv:1812.04616, Section 8.2
         [3] MIT License (c) 2019 Max Ryabinin - Modified for GraphNeT
-        
+
         Args:
             ctx: Autograd context containing saved tensors and metadata.
             grad_output: Gradient with respect to the output tensor.
-            
+
         Returns:
             Tuple of gradients: (None for m, gradient w.r.t. κ).
         """
@@ -314,16 +314,16 @@ def backward(
         if np.isclose(m, 3, atol=1e-6):
             # Initialize gradient array
             grads = np.zeros_like(kappa)
-            
+
             # Handle small kappa values (including zero) to avoid division by zero
             small_mask = np.abs(kappa) < 1e-6
             grads[small_mask] = -kappa[small_mask] / 3
-            
+
             # Handle large kappa values
             large_mask = ~small_mask
             if np.any(large_mask):
                 kappa_large = kappa[large_mask]
-                grads[large_mask] = 1/kappa_large - 1/np.tanh(kappa_large)
+                grads[large_mask] = 1 / kappa_large - 1 / np.tanh(kappa_large)
         else:
             grads = -(
                 (scipy.special.iv(m / 2.0, kappa))
diff --git a/tests/training/test_loss_functions.py b/tests/training/test_loss_functions.py

Original file line number	Diff line number	Diff line change
`@@ -7,4 +7,4 @@ extend-exclude = '''`
`7`	`7`	`versioneer.py`
`8`	`8`	`\| src/graphnet/_version.py`
`9`	`9`	`)`
`10`		`-'''`
	`10`	`+'''`