update

.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

.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

.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 }}

.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 }}

.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

.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/**

.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

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

black.toml

@@ -7,4 +7,4 @@ extend-exclude = '''
       versioneer.py
     | src/graphnet/_version.py
 )
-'''
+'''

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)

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

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

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" ]

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" ]

docs/source/installation/install.rst

@@ -55,6 +55,52 @@ To achieve this, we recommend installing |graphnet|\ GraphNeT into a CVMFS with
 
 Once installed, |graphnet|\ GraphNeT is available whenever you open the CVMFS locally.
 
+Installation with km3io (KM3NeT)
+-----------------------------------------------
+
+This installation is only necessary if you want to process KM3NeT/ARCA or KM3NeT/ORCA files. Processing means converting them from a `.root` offline format into a suitable format for training using |graphnet|. If you already have your KM3NeT data in `SQLite` or `parquet` format and only want to train a model or perform inference on this database, this specific installation is not needed.
+
+Note that this installation will add `km3io` ensuring it is built with a compatible versions. The steps below are provided for a conda environment, with an enviroment created in the same way it is done above in this page, but feel free to choose a different enviroment setup.
+
+As mentioned, it is highly reommended to create a conda enviroment where your installation is done to do not mess up any dependecy. It can be done with the following commands:
+
+.. code-block:: bash
+
+   # Create an environment with Python 3.10
+   conda create -p <full-path-to-env> --no-default-packages python=3.10 -y
+   # Activate the environment and move to the graphnet repository you just cloned. If using conda:
+   conda activate <full-path-to-env>
+
+The isntallation of GraphNeT is then done by:
+
+.. code-block:: bash
+
+   git clone https://github.com/graphnet-team/graphnet.git
+   cd graphnet
+
+Choose the appropriate requirements file based on your system. Here there is just an example of installation with PyTorch-2.5.1 but check the matrix above for a full idea of all the versions can be installed.
+
+For CPU-only enviroments:
+
+.. code-block:: bash
+
+   pip3 install torch==2.5.1 torchvision==0.20.1 torchaudio==2.5.1 --index-url https://download.pytorch.org/whl/cpu
+   pip3 install -e .[torch-25] -f https://data.pyg.org/whl/torch-2.5.1+cpu.html
+
+For GPU enviroments with, for instance, CUDA 11.8 drivers:
+
+.. code-block:: bash
+
+   pip3 install torch==2.5.1 torchvision==0.20.1 torchaudio==2.5.1 --index-url https://download.pytorch.org/whl/cu118
+   pip3 install -e .[torch-25] -f https://data.pyg.org/whl/torch-2.5.1+cu118.html
+
+Downgrade setuptools for compatibility between km3io and GraphNeT.
+
+.. code-block:: bash
+
+   pip3 install --force-reinstall setuptools==70.3.0
+   pip3 install km3io==1.2.0
+
+
 .. note::
    We recommend installing |graphnet|\ GraphNeT without GPU in clean metaprojects.
-

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

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

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)

examples/07_km3net/01_convert_km3net.py

@@ -0,0 +1,104 @@
+"""Code to run the extraction of km3net data."""
+
+import os
+import warnings
+
+from graphnet.constants import EXAMPLE_OUTPUT_DIR, TEST_DATA_DIR
+from graphnet.data.readers import KM3NeTReader
+from graphnet.data.writers import ParquetWriter, SQLiteWriter
+from graphnet.data import DataConverter
+from graphnet.data.extractors.km3net import (
+    KM3NeTTruthExtractor,
+    KM3NeTFullPulseExtractor,
+    KM3NeTTriggPulseExtractor,
+    KM3NeTHNLTruthExtractor,
+    KM3NeTRegularRecoExtractor,
+    KM3NeTHNLRecoExtractor,
+)
+
+from graphnet.utilities.argparse import ArgumentParser
+
+
+def main(backend: str, triggered: str, HNL: str, OUTPUT_DIR: str) -> None:
+    """Convert ROOT files from KM3NeT to `backend` format."""
+    warnings.simplefilter(action="ignore", category=FutureWarning)
+
+    input_dir = [f"{TEST_DATA_DIR}/km3net"]
+    if OUTPUT_DIR != "None":
+        outdir = f"{OUTPUT_DIR}/{backend}"
+    else:
+        outdir = f"{EXAMPLE_OUTPUT_DIR}/{backend}"
+    os.makedirs(outdir, exist_ok=True)
+    print(60 * "*")
+    print(f"Saving to {outdir}")
+    print(60 * "*")
+    if backend == "parquet":
+        save_method = ParquetWriter(truth_table="truth")
+    elif backend == "sqlite":
+        save_method = SQLiteWriter()  # type: ignore
+    else:
+        raise ValueError("Invalid backend choice")
+
+    if HNL == "km3net-vars":
+        truth_extractor = KM3NeTTruthExtractor(name="truth")
+        reco_extractor = KM3NeTRegularRecoExtractor(name="reco")
+    elif HNL == "hnl-vars":
+        truth_extractor = KM3NeTHNLTruthExtractor(name="truth")  # type: ignore
+        reco_extractor = KM3NeTHNLRecoExtractor(name="reco")  # type: ignore
+    else:
+        raise ValueError("Invalid HNL choice")
+
+    if triggered == "Triggered":
+        pulse_extractor = KM3NeTTriggPulseExtractor(name="pulse_map")
+    elif triggered == "Snapshot":
+        pulse_extractor = KM3NeTFullPulseExtractor(
+            name="pulse_map"
+        )  # type: ignore
+    else:
+        raise ValueError("Invalid triggered choice")
+
+    converter = DataConverter(
+        file_reader=KM3NeTReader(),
+        save_method=save_method,
+        extractors=[truth_extractor, pulse_extractor, reco_extractor],
+        outdir=outdir,
+        num_workers=1,
+    )
+
+    converter(input_dir=input_dir)
+
+
+if __name__ == "__main__":
+
+    # Parse command-line arguments
+    parser = ArgumentParser(
+        description="""
+            Convert root files from KM3NeT to an sqlite or parquet.
+            """
+    )
+
+    parser.add_argument(
+        "backend",
+        choices=["sqlite", "parquet"],
+        help="Choose the backend format",
+    )
+    parser.add_argument(
+        "triggered",
+        choices=["Triggered", "Snapshot"],
+        help="Choose between triggered or snapshot pulse maps",
+    )
+    parser.add_argument(
+        "HNL",
+        choices=["km3net-vars", "hnl-vars"],
+        help="Km3net truth or adding Heavy Neutral Lepton info",
+    )
+    parser.add_argument(
+        "OUTPUT_DIR",
+        default="None",
+        help="Output directory (optional)",
+    )
+
+    args, unknown = parser.parse_known_args()
+
+    # Run example script
+    main(args.backend, args.triggered, args.HNL, args.OUTPUT_DIR)