Merge pull request #104 from MolarVerse/dev

Merge dev into main for release v1.2

.github/workflows/pylint.yml

@@ -47,20 +47,17 @@ jobs:
           python .github/scripts/parse_pylint.py pylint_output.txt | tee comment.txt
         fi
 
-
-    #check if the first line of comment.txt rates higher than 9.75 with following format
-    #Your code has been rated at 9.86/10 (previous run: 7.63/10, +2.22)
     - name: Check if pylint score is higher than 9.75
       id: check_pylint_score
       run: |
         head -n3 comment.txt | tail -n 1
         head -n3 comment.txt | tail -n 1 | awk '{print $7}'
         head -n3 comment.txt | tail -n 1 | awk '{print $7}' | cut -d '/' -f 1
         score=$(head -n3 comment.txt | tail -n 1 | awk '{print $7}' | cut -d '/' -f 1)
-        if (( $(echo "$score > 9.5" | bc -l) )); then
-          echo "Pylint score is higher than 9.5 and is $score"
+        if (( $(echo "$score > 9.75" | bc -l) )); then
+          echo "Pylint score is higher than 9.75 and is $score"
         else
-          echo "Pylint score is lower than 9.5 and is $score"
+          echo "Pylint score is lower than 9.75 and is $score"
           exit 1
         fi
       shell: bash

PQAnalysis/__init__.py

@@ -21,7 +21,6 @@
 # BEARTYPE SETUP #
 ##################
 
-# TODO: change the default level to "RELEASE" after all changes are implemented
 __beartype_default_level__ = "RELEASE"
 __beartype_level__ = os.getenv(
     "PQANALYSIS_BEARTYPE_LEVEL", __beartype_default_level__

PQAnalysis/atomic_system/_decorators.py

@@ -17,7 +17,6 @@
     of atoms is equal to the number of positions.
 """
 
-import sys
 import numpy as np
 
 from beartype.typing import Any

PQAnalysis/core/api.py

@@ -17,7 +17,7 @@ def distance(
     pos1: Np1DNumberArray | Np2DNumberArray,
     pos2: Np1DNumberArray | Np2DNumberArray,
     cell: _cell.Cell = _cell.Cell(),
-    **kwargs
+    **kwargs  # pylint: disable=unused-argument
 ) -> PositiveReal | Np1DNumberArray | Np2DNumberArray:
     """
     Returns the distances between all combinations of two position arrays.
@@ -66,7 +66,7 @@ def distance(
     cell : Cell, optional
         The unit cell of the system. Default is Cell().
     **kwargs
-        Arbitrary keyword arguments.
+        Additional keyword arguments.
 
     Returns
     -------

PQAnalysis/io/gen_file/gen_file_reader.py

@@ -93,6 +93,7 @@ def _read_header(self,
         """
         n_atoms, periodicity = header[0].split()
         n_atoms = int(n_atoms)
+        is_periodic = False  # Default value
 
         if periodicity.lower() == "c":
             is_periodic = False

PQAnalysis/io/input_file_reader/input_file_parser.py

@@ -79,6 +79,9 @@ def parse(self) -> "InputDictionary":
         InputDictionary: InputDictionary
             The parsed input file dictionary.
         """
+
+        grammar_file = None  # to avoid linter warning
+
         if self.input_format == InputFileFormat.PQANALYSIS:
             grammar_file = "inputGrammar.lark"
         elif self.input_format in [InputFileFormat.PQ, InputFileFormat.QMCFC]:

PQAnalysis/io/input_file_reader/pq/output_files.py

@@ -2,8 +2,6 @@
 A module containing a Mixin class for output files of a PQ input file.
 """
 
-from PQAnalysis.exceptions import PQKeyError
-
 
 
 class _OutputFileMixin:

PQAnalysis/io/nep/nep_writer.py

@@ -316,6 +316,8 @@ def write_from_files(
 
                 self.is_validation = False
 
+                file_to_write = None  # to avoid linting warning
+
                 if j in train_indices:
                     self.n_train_frames += 1
                     file_to_write = self.train_file
@@ -339,7 +341,11 @@ def write_from_files(
                     )
 
                 self.write_from_atomic_system(
-                    system, file_to_write, use_forces, use_stress, use_virial
+                    system,
+                    file_to_write,
+                    use_forces,
+                    use_stress,
+                    use_virial,
                 )
 
                 if self.is_validation:
@@ -437,12 +443,16 @@ def _setup_frame_splitting_for_training(
                 exception=NEPError
             )
 
+        n_train = 0.0
+        n_validation = 0.0
+        n_test = 0.0
+
         if total_ratios is not None:
             ratios = total_ratios.split(":")
             if len(ratios) == 2:
                 n_train = float(ratios[0])
                 n_test = float(ratios[1])
-                n_validation = 0
+                n_validation = 0.0
             elif len(ratios) == 3:
                 n_train = float(ratios[0])
                 n_test = float(ratios[1])
@@ -456,10 +466,6 @@ def _setup_frame_splitting_for_training(
                     ),
                     exception=NEPError
                 )
-        else:
-            n_train = 0.0
-            n_validation = 0.0
-            n_test = 0.0
 
         sum_frames = n_train + n_test + n_validation
 

PQAnalysis/io/topology_file/topology_file_reader.py

@@ -209,6 +209,11 @@ def _parse_bonds(self, block: List[str]) -> List[Bond]:
 
             line, comment = self._get_data_line_comment(line)
 
+            index = None  # to avoid linter warning
+            target_index = None  # to avoid linter warning
+            bond_type = None  # to avoid linter warning
+            is_linker = None  # to avoid linter warning
+
             if len(line.split()) == 4:
                 index, target_index, bond_type, _ = line.split()
                 is_linker = True
@@ -263,6 +268,12 @@ def _parse_angles(self, block: List[str]) -> List[Angle]:
 
             line, comment = self._get_data_line_comment(line)
 
+            index1 = None  # to avoid linter warning
+            index2 = None  # to avoid linter warning
+            index3 = None  # to avoid linter warning
+            angle_type = None  # to avoid linter warning
+            is_linker = None  # to avoid linter warning
+
             if len(line.split()) == 5:
                 index1, index2, index3, angle_type, _ = line.split()
                 is_linker = True
@@ -318,6 +329,13 @@ def _parse_dihedrals(self, block: List[str]) -> List[Dihedral]:
 
             line, comment = self._get_data_line_comment(line)
 
+            index1 = None  # to avoid linter warning
+            index2 = None  # to avoid linter warning
+            index3 = None  # to avoid linter warning
+            index4 = None  # to avoid linter warning
+            dihedral_type = None  # to avoid linter warning
+            is_linker = None  # to avoid linter warning
+
             if len(line.split()) == 6:
                 index1, index2, index3, index4, dihedral_type, _ = line.split()
                 is_linker = True
@@ -374,6 +392,13 @@ def _parse_impropers(self, block: List[str]) -> List[Dihedral]:
 
             line, comment = self._get_data_line_comment(line)
 
+            index1 = None  # to avoid linter warning
+            index2 = None  # to avoid linter warning
+            index3 = None  # to avoid linter warning
+            index4 = None  # to avoid linter warning
+            dihedral_type = None  # to avoid linter warning
+            is_linker = None  # to avoid linter warning
+
             if len(line.split()) == 6:
                 index1, index2, index3, index4, dihedral_type, _ = line.split()
                 is_linker = True
@@ -431,6 +456,11 @@ def _parse_shake(self, block: List[str]) -> List[Bond]:
 
             line, comment = self._get_data_line_comment(line)
 
+            index = None  # to avoid linter warning
+            target_index = None  # to avoid linter warning
+            distance = None  # to avoid linter warning
+            is_linker = None  # to avoid linter warning
+
             if len(line.split()) == 4:
                 index, target_index, distance, _ = line.split()
                 is_linker = True

PQAnalysis/io/traj_file/.gitignore

@@ -0,0 +1,2 @@
+*.so
+process_lines.c

PQAnalysis/io/traj_file/frame_reader.py

@@ -17,6 +17,7 @@
 from PQAnalysis import __package_name__
 
 from .exceptions import FrameReaderError
+from .process_lines import process_lines_with_atoms  # pylint: disable=import-error
 
 
 
@@ -98,7 +99,7 @@ def read(
 
         # This should never happen - only for safety
         self.logger.error(
-            f'Invalid TrajectoryFormat given.{traj_format=}',
+            f'Invalid TrajectoryFormat given. {traj_format=}',
             exception=FrameReaderError
         )
 
@@ -315,6 +316,9 @@ def _read_header_line(self, header_line: str) -> Tuple[int, Cell]:
             If the header line is not valid. Either it contains too many or too few values.
         """
 
+        n_atoms = 0  # default value
+        cell = None  # default value
+
         header_line = header_line.split()
 
         if len(header_line) == 4:
@@ -364,15 +368,7 @@ def _read_xyz(
             If the given string does not contain the correct number of lines.
         """
         try:
-            # Pre-allocate xyz and atoms
-            xyz = np.empty((n_atoms, 3), dtype=np.float32)
-            atoms = [None] * n_atoms
-
-            # Fill xyz and atoms in a single loop
-            for i, line in enumerate(splitted_frame_string[2:2 + n_atoms]):
-                split_line = line.split()
-                atoms[i] = split_line[0]
-                xyz[i] = split_line[1:4]
+            atoms, xyz = process_lines_with_atoms(splitted_frame_string[2:], n_atoms)
 
             return xyz, atoms
         except ValueError:

PQAnalysis/io/traj_file/process_lines.pyx

@@ -0,0 +1,94 @@
+"""
+This module contains the functions that are used to parse the body of 
+xyz formatted files. The functions are written in Cython and are compiled
+to C code.
+"""
+
+import numpy as np
+cimport numpy as np
+from libc.stdio cimport sscanf
+
+def process_lines_with_atoms(input, int n_atoms):
+    """
+    Function to parse the body of an xyz file. The function expects a list of
+    strings, where each string is a line in the file. The function will parse
+    the lines and return a tuple with two elements. The first element is a list
+    of strings, where each string is the atom type of the corresponding atom in
+    the xyz file. The second element is a numpy array with the xyz coordinates
+    of the atoms in the file.
+
+    Parameters
+    ----------
+    input : list
+        A list of strings, where each string is a line in the xyz file.
+    n_atoms : int
+        The number of atoms in the xyz file.
+
+    Returns
+    -------
+    tuple
+        A tuple with two elements. The first element is a list of strings, where
+        each string is the atom type of the corresponding atom in the xyz file.
+        The second element is a numpy array with the xyz coordinates of the atoms
+        in the file.
+    """
+
+    cdef np.ndarray[np.float32_t, ndim=2] xyz = np.zeros((n_atoms, 3), dtype=np.float32)
+    cdef list atoms = [None] * n_atoms
+    cdef char[5] atom
+    cdef float x, y, z
+    cdef int ret
+
+    for i in range(n_atoms):
+        line = input[i]
+        line_str = line.encode('utf-8')
+
+        ret = sscanf(line_str, "%s %f %f %f", atom, &x, &y, &z)
+        if ret != 4:
+            raise ValueError("Could not parse line")
+
+        xyz[i, 0] = x
+        xyz[i, 1] = y
+        xyz[i, 2] = z
+
+        atoms[i] = atom.decode('utf-8')
+
+    return atoms, xyz
+
+def process_lines(input, int n_atoms):
+    """
+    Function to parse the body of an xyz file. The function expects a list of
+    strings, where each string is a line in the file. The function will parse
+    the lines and return a numpy array with the xyz coordinates of the atoms
+    in the file.
+
+    Parameters
+    ----------
+    input : list
+        A list of strings, where each string is a line in the xyz file.
+    n_atoms : int
+        The number of atoms in the xyz file.
+
+    Returns
+    -------
+    numpy.ndarray
+        A numpy array with the xyz coordinates of the atoms in the file.
+    """
+
+    cdef np.ndarray[np.float32_t, ndim=2] xyz = np.zeros((n_atoms, 3), dtype=np.float32)
+    cdef float x, y, z
+    cdef int ret
+
+    for i in range(n_atoms):
+        line = input[i]
+        line_str = line.encode('utf-8')
+
+        ret = sscanf(line_str, "%*s %f %f %f", &x, &y, &z)
+        if ret != 3:
+            raise ValueError("Could not parse line")
+
+        xyz[i, 0] = x
+        xyz[i, 1] = y
+        xyz[i, 2] = z
+
+    return xyz

pyproject.toml

@@ -1,5 +1,5 @@
 [build-system]
-requires = ["setuptools>=42", "setuptools_scm>=8"]
+requires = ["setuptools>=42", "setuptools_scm>=8", "wheel", "numpy", "Cython"]
 build-backend = "setuptools.build_meta"
 
 [project]
@@ -32,16 +32,19 @@ dependencies = [
     "argcomplete",
     "yapf",
     "rich-argparse",
+    "Cython",
 ]
 
 [project.optional-dependencies]
 test = [
     "pytest",
-    "coverage",
     "pytest-cov",
+    "pytest-runner",
     "pylint",
     "pylint-django",
+    "coverage",
     "docstr-coverage",
+    "setuptools",
 ]
 docs = [
     "sphinx",

pytest.sh

@@ -1,8 +1,18 @@
 export PQANALYSIS_BEARTYPE_LEVEL=DEBUG
-python -m pytest $@
+#check if $@ is empty
+if [ -z "$@" ]; then
+    python setup.py pytest
+else
+    python setup.py pytest --addopts $@
+fi
 if [ $? -ne 0 ]; then
     exit 1
 fi
 
 export PQANALYSIS_BEARTYPE_LEVEL=RELEASE
-python -m pytest $@
+#check if $@ is empty
+if [ -z "$@" ]; then
+    python setup.py pytest
+else
+    python setup.py pytest --addopts $@
+fi