fix: relax strict min-backbone-shift-types from 5 to 4

.gitignore

@@ -1,16 +1,23 @@
-build
-dist
-test*
-tmp*
-*.log
-*.zip
-*.txt
+# Build artifacts
+build/
+dist/
+*.egg-info/
+
+# Python cache
+__pycache__/
 *.pyc
-*.pkl
-*.txt
-__pycache__
-data
-*.csv
-notebooks
-*.egg-info
-2024-05-09
+
+# Runtime and temporary files
+tmp*/
+*.log
+
+# BMRB data and pipeline output (large, local-only)
+data/
+
+# Local working directories
+docs/
+notebooks/
+
+# Test scripts (local integration tests, not part of package)
+test/
+

pyproject.toml

@@ -0,0 +1,92 @@
+[build-system]
+requires = ["hatchling"]
+build-backend = "hatchling.build"
+
+[project]
+name = "trizod"
+version = "0.0.1"
+description = "Modern disorder scores for BMRB data"
+readme = "README.md"
+requires-python = ">=3.9"
+license = {text = "AGPL-3.0"}
+authors = [
+    {name = "Markus Haak", email = "markus.haak@tum.de"},
+    {name = "Tobias Senoner", email = "tobias.senoner@tum.de"}
+]
+classifiers = [
+    "Programming Language :: Python :: 3",
+    "License :: OSI Approved :: GNU Affero General Public License v3",
+    "Operating System :: OS Independent",
+    "Topic :: Scientific/Engineering :: Bio-Informatics",
+    "Intended Audience :: Science/Research",
+]
+dependencies = [
+    "pandas",
+    "numpy",
+    "matplotlib",
+    "tqdm",
+    "pandarallel",
+    "pynmrstar",
+    "scipy",
+]
+
+[project.urls]
+Repository = "https://github.com/MarkusHaak/trizod"
+
+[project.scripts]
+trizod = "trizod.trizod:main"
+
+[tool.hatch.build.targets.wheel]
+packages = ["trizod"]
+
+[tool.hatch.build.targets.wheel.force-include]
+"trizod/potenci/data" = "trizod/potenci/data"
+
+[dependency-groups]
+dev = [
+    "ruff",
+]
+
+[tool.ruff]
+line-length = 100
+indent-width = 4
+
+# Exclude legacy code and generated files
+exclude = [
+    "trizod/potenci/legacy",
+    "test",
+    "__pycache__",
+    "*.pyc",
+    ".git",
+    ".venv",
+    "build",
+    "dist",
+]
+
+[tool.ruff.lint]
+# Enable recommended rules for scientific Python code
+select = [
+    "E",   # pycodestyle errors
+    "W",   # pycodestyle warnings
+    "F",   # Pyflakes
+    "I",   # isort
+    "N",   # pep8-naming
+    "UP",  # pyupgrade
+    "B",   # flake8-bugbear
+    "C4",  # flake8-comprehensions
+    "SIM", # flake8-simplify
+]
+
+# Ignore specific rules that are too strict for scientific code
+ignore = [
+    "E501",   # Line too long (handled by formatter)
+    "N803",   # Argument name should be lowercase (scientific conventions)
+    "N806",   # Variable in function should be lowercase (scientific conventions)
+]
+
+[tool.ruff.format]
+quote-style = "double"
+indent-style = "space"
+skip-magic-trailing-comma = false
+line-ending = "auto"
+

test/test_cache_equality.py

@@ -1,49 +1,88 @@
-import os,sys
+import argparse
 import logging
+import os
+
 import numpy as np
 import pandas as pd
-import argparse
+
 from trizod.constants import BBATNS
 
+
 def parse_args():
-    parser = argparse.ArgumentParser(description='')
+    parser = argparse.ArgumentParser(description="")
 
-    parser.add_argument('cache_dir',
-        help='Cache directory that shall be tested.')
-    parser.add_argument('cache_comp',
-        help='Cache directory to compare against.')
+    parser.add_argument("cache_dir", help="Cache directory that shall be tested.")
+    parser.add_argument("cache_comp", help="Cache directory to compare against.")
 
     args = parser.parse_args()
     return args
 
+
 def main():
-    cache_files = {f for f in os.listdir(os.path.join(args.cache_dir, 'wSCS')) if os.path.isfile(os.path.join(args.cache_dir, 'wSCS', f)) and f.endswith('.npz')}
-    comp_files = {f for f in os.listdir(os.path.join(args.cache_comp, 'wSCS')) if os.path.isfile(os.path.join(args.cache_comp, 'wSCS', f)) and f.endswith('.npz')}
+    cache_files = {
+        f
+        for f in os.listdir(os.path.join(args.cache_dir, "wSCS"))
+        if os.path.isfile(os.path.join(args.cache_dir, "wSCS", f)) and f.endswith(".npz")
+    }
+    comp_files = {
+        f
+        for f in os.listdir(os.path.join(args.cache_comp, "wSCS"))
+        if os.path.isfile(os.path.join(args.cache_comp, "wSCS", f)) and f.endswith(".npz")
+    }
     common_files = list(cache_files & comp_files)
     common_files.sort()
     print(len(common_files))
     res = []
     for fn in common_files:
-        with open(os.path.join(args.cache_dir, 'wSCS', fn), 'rb') as f1, open(os.path.join(args.cache_comp, 'wSCS', fn), 'rb') as f2:
+        with open(os.path.join(args.cache_dir, "wSCS", fn), "rb") as f1, open(
+            os.path.join(args.cache_comp, "wSCS", fn), "rb"
+        ) as f2:
             z = np.load(f1)
-            shw, ashwi, cmp_mask, olf, offf, shw0, ashwi0, ol0, off0 = z['shw'], z['ashwi'], z['cmp_mask'], z['olf'], z['offf'], z['shw0'], z['ashwi0'], z['ol0'], z['off0']
-            offf, off0 = {at:off for at,off in zip(BBATNS, offf)}, {at:off for at,off in zip(BBATNS, off0)}
-
-            z =  np.load(f2)
-            shw_, ashwi_, cmp_mask_, olf_, offf_, shw0_, ashwi0_, ol0_, off0_ = z['shw'], z['ashwi'], z['cmp_mask'], z['olf'], z['offf'], z['shw0'], z['ashwi0'], z['ol0'], z['off0']
-            offf_, off0_ = {at:off for at,off in zip(BBATNS, offf_)}, {at:off for at,off in zip(BBATNS, off0_)}
+            shw, ashwi, cmp_mask, olf, offf, shw0, ashwi0, ol0, off0 = (
+                z["shw"],
+                z["ashwi"],
+                z["cmp_mask"],
+                z["olf"],
+                z["offf"],
+                z["shw0"],
+                z["ashwi0"],
+                z["ol0"],
+                z["off0"],
+            )
+            offf, off0 = (
+                {at: off for at, off in zip(BBATNS, offf)},
+                {at: off for at, off in zip(BBATNS, off0)},
+            )
+
+            z = np.load(f2)
+            shw_, ashwi_, cmp_mask_, olf_, offf_, shw0_, ashwi0_, ol0_, off0_ = (
+                z["shw"],
+                z["ashwi"],
+                z["cmp_mask"],
+                z["olf"],
+                z["offf"],
+                z["shw0"],
+                z["ashwi0"],
+                z["ol0"],
+                z["off0"],
+            )
+            offf_, off0_ = (
+                {at: off for at, off in zip(BBATNS, offf_)},
+                {at: off for at, off in zip(BBATNS, off0_)},
+            )
         if ashwi.shape != ashwi_.shape:
             res.append("shape mismatch")
             continue
         if not np.allclose(ashwi, ashwi_):
-            res.append('not close')
+            res.append("not close")
             continue
-        res.append('close')
-    df = pd.DataFrame(res, columns=['result'], index=common_files)
+        res.append("close")
+    df = pd.DataFrame(res, columns=["result"], index=common_files)
     breakpoint()
 
-if __name__ == '__main__':
+
+if __name__ == "__main__":
     level = logging.INFO
-    logging.basicConfig(level=level, format=f'%(levelname)s : %(message)s')
+    logging.basicConfig(level=level, format=f"%(levelname)s : %(message)s")
     args = parse_args()
-    main()
+    main()

trizod/bmrb/__init__.py

@@ -1 +1,3 @@
-from .bmrb import BmrbEntry, get_valid_bbshifts
+from .bmrb import BmrbEntry, get_valid_bbshifts
+
+__all__ = ["BmrbEntry", "get_valid_bbshifts"]