update pre-commit config, add black-compatible flake8 linting

Author: erwulff

.pre-commit-config.yaml

@@ -20,7 +20,26 @@ repos:
   - repo: https://github.com/pre-commit/pre-commit-hooks
     rev: v6.0.0
     hooks:
+    - id: trailing-whitespace
+    - id: check-added-large-files
+    - id: check-ast
     - id: check-json
+    - id: check-merge-conflict
+    - id: check-xml
     - id: check-yaml
-    - id: trailing-whitespace
+    - id: debug-statements
     - id: end-of-file-fixer
+    - id: requirements-txt-fixer
+    - id: mixed-line-ending
+      args: ['--fix=no']
+
+  - repo: https://github.com/PyCQA/flake8
+    rev: 6.0.0
+    hooks:
+    - id: flake8
+      # black-compatible flake-8 config
+
+      # E203 is not PEP8 compliant
+      # E402 due to logging.basicConfig in pipeline.py
+      args: ['--max-line-length=150',
+            '--extend-ignore=E203,E402,W605']

requirements.txt

@@ -1,28 +1,28 @@
-numpy
-scipy
-matplotlib
-plotly
-pandas
-scikit-learn
+--extra-index-url https://download.pytorch.org/whl/cu121
+awkward
+fastjet
 h5py
-tqdm
+hydra-colorlog
+hydra-core
 ipykernel
-uproot
-awkward
-vector
+jupyterlab
 kaleido
+lightning
+matplotlib
+nbdev
 nbformat
-jupyterlab
-fastjet
-pyarrow
+numpy
+omegaconf
+pandas
+plotly
 pre-commit
---extra-index-url https://download.pytorch.org/whl/cu121
+pyarrow
+scikit-learn
+scipy
+tensorboardX
 torch==2.5.1
-torchvision==0.20.1
 torchaudio==2.5.1
-nbdev
-lightning
-tensorboardX
-hydra-core
-hydra-colorlog
-omegaconf
+torchvision==0.20.1
+tqdm
+uproot
+vector

src/datasets/utils.py

@@ -1,4 +1,3 @@
-import numpy as np
 import torch
 
 

src/utils/arrays.py

@@ -3,7 +3,10 @@
 import torch
 import vector
 
+from src.utils.pylogger import get_pylogger
+
 vector.register_awkward()
+logger = pylogger = get_pylogger(__name__)
 
 
 def p4s_from_ptetaphimass(
@@ -578,7 +581,7 @@ def calc_additional_kinematic_features(ak_particles):
             "part_pz": p4s.pz,
             "part_ptrel": ak_particles.part_pt / p4s_jet.pt,
             "part_energy": p4s.energy,
-            "part_energy_raw": p4s.energy,  # this is a workaround to be able to use the energy twice (once for lorentz vectors, once as particle feature)
+            "part_energy_raw": p4s.energy,  # this is a workaround to use the energy twice (once for lorentz vectors, once as particle feature)
             "part_erel": p4s.energy / p4s_jet.energy,
             "part_deltaR": p4s.deltaR(p4s_jet),
         }