fixed typo in logging output

Reviewed-on: #5

src/mdevaluate/__init__.py

@@ -16,7 +16,7 @@ from . import reader
 from . import system
 from . import utils
 from . import extra
-from .logging import logger
+from .logging_util import logger
 
 
 def open(

src/mdevaluate/autosave.py

@@ -5,7 +5,7 @@ from typing import Optional, Callable, Iterable
 
 import numpy as np
 from .checksum import checksum
-from .logging import logger
+from .logging_util import logger
 
 autosave_directory: Optional[str] = None
 load_autosave_data = False

src/mdevaluate/checksum.py

@@ -1,9 +1,14 @@
 import functools
 import hashlib
-from .logging import logger
+from .logging_util import logger
 from types import ModuleType, FunctionType
 import inspect
 from typing import Iterable
+import ast
+import io
+import tokenize
+import re
+import textwrap
 
 import numpy as np
 
@@ -28,19 +33,46 @@ def version(version_nr: int, calls: Iterable = ()):
     return decorator
 
 
-def strip_comments(s: str):
-    """Strips comment lines and docstring from Python source string."""
-    o = ""
-    in_docstring = False
-    for l in s.split("\n"):
-        if l.strip().startswith(("#", '"', "'")) or in_docstring:
-            in_docstring = l.strip().startswith(('"""', "'''")) + in_docstring == 1
+def strip_comments(source: str) -> str:
+    """Removes docstrings, comments, and irrelevant whitespace from Python source code."""
+
+    # Step 1: Remove docstrings using AST
+    def remove_docstrings(node):
+        if isinstance(node, (ast.FunctionDef, ast.AsyncFunctionDef, ast.ClassDef, ast.Module)):
+            if (doc := ast.get_docstring(node, clean=False)):
+                first_stmt = node.body[0]
+                if isinstance(first_stmt, ast.Expr) and isinstance(first_stmt.value, ast.Constant):
+                    node.body.pop(0)  # Remove the docstring entirely
+        for child in ast.iter_child_nodes(node):
+            remove_docstrings(child)
+
+    tree = ast.parse(textwrap.dedent(source))
+    remove_docstrings(tree)
+    code_without_docstrings = ast.unparse(tree)
+
+    # Step 2: Remove comments using tokenize
+    tokens = tokenize.generate_tokens(io.StringIO(code_without_docstrings).readline)
+    result = []
+    last_lineno = -1
+    last_col = 0
+
+    for toknum, tokval, (srow, scol), (erow, ecol), line in tokens:
+        if toknum == tokenize.COMMENT:
             continue
-        o += l + "\n"
-    return o
+        if srow > last_lineno:
+            last_col = 0
+        if scol > last_col:
+            result.append(" " * (scol - last_col))
+        result.append(tokval)
+        last_lineno, last_col = erow, ecol
+
+    code_no_comments = ''.join(result)
+
+    # Step 3: Remove empty lines (whitespace-only or truly blank)
+    return "\n".join([line for line in code_no_comments.splitlines() if line.strip() != ""])
 
 
-def checksum(*args, csum=None):
+def checksum(*args, csum=None, _seen=None):
     """
     Calculate a checksum of any object, by sha1 hash.
 
@@ -60,7 +92,15 @@ def checksum(*args, csum=None):
         csum = hashlib.sha1()
         csum.update(str(SALT).encode())
 
+    if _seen is None:
+        _seen = set()
+
     for arg in args:
+        obj_id = id(arg)
+        if obj_id in _seen:
+            continue
+        _seen.add(obj_id)
+
         if hasattr(arg, "__checksum__"):
             logger.debug("Checksum via __checksum__: %s", str(arg))
             csum.update(str(arg.__checksum__()).encode())
@@ -73,17 +113,19 @@ def checksum(*args, csum=None):
         elif isinstance(arg, FunctionType):
             csum.update(strip_comments(inspect.getsource(arg)).encode())
             c = inspect.getclosurevars(arg)
-            for v in {**c.nonlocals, **c.globals}.values():
+            merged = {**c.nonlocals, **c.globals}
+            for key in sorted(merged):  # deterministic ordering
+                v = merged[key]
                 if v is not arg:
-                    checksum(v, csum=csum)
+                    checksum(v, csum=csum, _seen=_seen)
         elif isinstance(arg, functools.partial):
             logger.debug("Checksum via partial for %s", str(arg))
-            checksum(arg.func, csum=csum)
+            checksum(arg.func, csum=csum, _seen=_seen)
             for x in arg.args:
-                checksum(x, csum=csum)
+                checksum(x, csum=csum, _seen=_seen)
             for k in sorted(arg.keywords.keys()):
                 csum.update(k.encode())
-                checksum(arg.keywords[k], csum=csum)
+                checksum(arg.keywords[k], csum=csum, _seen=_seen)
         elif isinstance(arg, np.ndarray):
             csum.update(arg.tobytes())
         else:

src/mdevaluate/coordinates.py

@@ -1,6 +1,6 @@
 from functools import partial, wraps
 from copy import copy
-from .logging import logger
+from .logging_util import logger
 from typing import Optional, Callable, List, Tuple
 
 import numpy as np

src/mdevaluate/correlation.py

@@ -431,9 +431,9 @@ def non_gaussian_parameter(
     trajectory: Coordinates = None,
     axis: str = "all",
 ) -> float:
-    """
+    r"""
     Calculate the non-Gaussian parameter.
-    ..math:
+    .. math:
       \alpha_2 (t) =
         \frac{3}{5}\frac{\langle r_i^4(t)\rangle}{\langle r_i^2(t)\rangle^2} - 1
     """

src/mdevaluate/distribution.py

@@ -182,10 +182,10 @@ def tetrahedral_order(
     )
 
     # Connection vectors
-    neighbors_1 -= atoms
-    neighbors_2 -= atoms
-    neighbors_3 -= atoms
-    neighbors_4 -= atoms
+    neighbors_1 = pbc_diff(neighbors_1, atoms, box=atoms.box)
+    neighbors_2 = pbc_diff(neighbors_2, atoms, box=atoms.box)
+    neighbors_3 = pbc_diff(neighbors_3, atoms, box=atoms.box)
+    neighbors_4 = pbc_diff(neighbors_4, atoms, box=atoms.box)
 
     # Normed Connection vectors
     neighbors_1 /= np.linalg.norm(neighbors_1, axis=-1).reshape(-1, 1)

src/mdevaluate/extra/free_energy_landscape.py

@@ -4,7 +4,6 @@ from typing import Optional
 import numpy as np
 from numpy.typing import ArrayLike, NDArray
 from numpy.polynomial.polynomial import Polynomial as Poly
-import math
 from scipy.spatial import KDTree
 import pandas as pd
 import multiprocessing as mp
@@ -49,7 +48,7 @@ def _pbc_points_reduced(
 
 def _build_tree(points, box, r_max, pore_geometry):
     if np.all(np.diag(np.diag(box)) == box):
-        tree = KDTree(points, boxsize=box)
+        tree = KDTree(points % box, boxsize=box)
         points_pbc_index = None
     else:
         points_pbc, points_pbc_index = _pbc_points_reduced(
@@ -79,8 +78,7 @@ def occupation_matrix(
     z_bins = np.arange(0, box[2][2] + edge_length, edge_length)
     bins = [x_bins, y_bins, z_bins]
     # Trajectory is split for parallel computing
-    size = math.ceil(len(frame_indices) / nodes)
-    indices = [frame_indices[i : i + size] for i in range(0, len(frame_indices), size)]
+    indices = np.array_split(frame_indices, nodes)
     pool = mp.Pool(nodes)
     results = pool.map(
         partial(_calc_histogram, trajectory=trajectory, bins=bins), indices
@@ -274,7 +272,11 @@ def distance_resolved_energies(
 
 
 def find_energy_maxima(
-    energy_df: pd.DataFrame, r_min: float, r_max: float
+    energy_df: pd.DataFrame,
+    r_min: float,
+    r_max: float,
+    r_eval: float = None,
+    degree: int = 2,
 ) -> pd.DataFrame:
     distances = []
     energies = []
@@ -283,6 +285,9 @@ def find_energy_maxima(
         x = np.array(data_d["r"])
         y = np.array(data_d["energy"])
         mask = (x >= r_min) * (x <= r_max)
-        p3 = Poly.fit(x[mask], y[mask], deg=2)
-        energies.append(np.max(p3(np.linspace(r_min, r_max, 1000))))
+        p3 = Poly.fit(x[mask], y[mask], deg=degree)
+        if r_eval is None:
+            energies.append(np.max(p3(np.linspace(r_min, r_max, 1000))))
+        else:
+            energies.append(p3(r_eval))
     return pd.DataFrame({"d": distances, "energy": energies})

src/mdevaluate/pbc.py

@@ -7,7 +7,7 @@ from numpy.typing import ArrayLike, NDArray
 
 from itertools import product
 
-from .logging import logger
+from .logging_util import logger
 
 if TYPE_CHECKING:
     from mdevaluate.coordinates import CoordinateFrame

src/mdevaluate/reader.py

@@ -19,13 +19,13 @@ import MDAnalysis
 from scipy import sparse
 
 from .checksum import checksum
-from .logging import logger
+from .logging_util import logger
 from . import atoms
 from .coordinates import Coordinates
 
 CSR_ATTRS = ("data", "indices", "indptr")
 NOJUMP_MAGIC = 2016
-Group_RE = re.compile("\[ ([-+\w]+) \]")
+Group_RE = re.compile(r"\[ ([-+\w]+) \]")
 
 
 class NojumpError(Exception):
@@ -275,7 +275,7 @@ def load_nojump_matrices(reader: BaseReader):
                 "Loaded Nojump matrices: {}".format(nojump_load_filename(reader))
             )
         else:
-            logger.info("Invlaid Nojump Data: {}".format(nojump_load_filename(reader)))
+            logger.info("Invalid Nojump Data: {}".format(nojump_load_filename(reader)))
     except KeyError:
         logger.info("Removing zip-File: %s", zipname)
         os.remove(nojump_load_filename(reader))

src/mdevaluate/utils.py

@@ -14,7 +14,7 @@ from scipy.ndimage import uniform_filter1d
 from scipy.interpolate import interp1d
 from scipy.optimize import curve_fit
 
-from .logging import logger
+from .logging_util import logger
 from .functions import kww, kww_1e