orto 1.8.2__py3-none-any.whl → 1.9.0__py3-none-any.whl

orto/__version__.py

@@ -1 +1 @@
-__version__ = '1.8.2'
+__version__ = '1.9.0'

orto/cli.py

@@ -11,6 +11,7 @@ import numpy as np
 import re
 from mmap import mmap, ACCESS_READ
 from shutil import move as shutilmove
+from subto.job import SlurmJob
 
 from . import job
 from . import utils as ut
@@ -329,6 +330,86 @@ def extract_gmatrix_func(uargs, save=True):
     return
 
 
+def gen_spden_func(uargs):
+    '''
+    Wrapper for CLI gen spin density call
+
+    Parameters
+    ----------
+    uargs : argparser object
+        User arguments
+
+    Returns
+    -------
+    None
+    '''
+
+    # Check orca module
+    if len(uargs.orca_load):
+        orca_load_val = copy.copy(uargs.orca_load)
+    elif os.getenv('orto_orca_load'):
+        try:
+            if len(os.getenv('orto_orca_load')):
+                orca_load_val = os.getenv('orto_orca_load')
+        except ValueError:
+            ut.red_exit(
+                (
+                    'Error in orto_orca_load environment variable'
+                )
+            )
+    else:
+        ut.red_exit(
+            (
+                'Missing orto_orca_load environment variable or '
+                '--orca_load argument'
+            )
+        )
+
+    # Create string of command numbers for orca plot to follow
+    command_nums = '1\\n3\\ny\\n4'
+    command_nums += f'\\n{uargs.n_pts:d}'
+    command_nums += '\\n5\\n7\\n11\\n12\\n'
+
+    # Generate job file for orca_plot
+    spin_job = SlurmJob(
+        pathlib.Path(f'{uargs.gbw_file.stem}_spin_density_job.sh')
+    )
+
+    # Create content of job
+    spin_job.content_block = ''
+
+    spin_job.content_block += '# Load orca module\n'
+    spin_job.content_block += f'module load {orca_load_val}\n'
+    spin_job.content_block += '# Run orca_plot to generate spin density cube file\n' # noqa
+    spin_job.content_block += f'time mpirun -np {uargs.n_procs:d} $(which orca_plot_mpi) {uargs.gbw_file.name} -i aa <<< $\'{command_nums}\'\n\n' # noqa
+
+    # Set job name
+    spin_job.job_name = f'{uargs.gbw_file.stem}_spin_density'
+
+    spin_job.ntasks_per_node = str(uargs.n_procs)
+    spin_job.mem_per_cpu = str(uargs.memory)
+
+    spin_job.error = f'{uargs.gbw_file.stem}_spin_density.%j.e'
+    spin_job.output = f'{uargs.gbw_file.stem}_spin_density.%j.o'
+
+    # Write job script
+    # with submitter configuration options specified
+    spin_job.write_script(True)
+
+    # Submit to queue
+    if not uargs.no_sub:
+        subprocess.call(
+            'cd {}; {} "{}"; cd ../'.format(
+                uargs.gbw_file.parents[0],
+                spin_job.SUBMIT_COMMAND,
+                spin_job.file_path
+                ),
+            shell=True
+        )
+
+    return
+
+
 def gen_trunc_molden_func(uargs):
     '''
     Wrapper for CLI gen truncmolden call
@@ -527,6 +608,14 @@ def gen_job_func(uargs):
         else:
             nbo_module = None
 
+        # Check structure in input file or xyz file
+        # unless skip_structure flag is set
+        if not uargs.skip_structure:
+            try:
+                inp.check_structure(oj.input_file)
+            except (DataNotFoundError, DataFormattingError) as e:
+                ut.red_exit(str(e))
+
         # Set SLURM error and output file names
         config['error'] = 'slurm.%j.e'
         config['output'] = 'slurm.%j.o'
@@ -1641,6 +1730,7 @@ def read_args(arg_list=None):
 
     extract_coords = extract_parser.add_parser(
         'coords',
+        aliases=['coord'],
         description='Extracts coordinates from Orca output file',
         formatter_class=argparse.RawTextHelpFormatter,
         usage=ut.cstring('orto extract coords <output_file> [options]', 'cyan')
@@ -1810,6 +1900,71 @@ def read_args(arg_list=None):
         )
     )
 
+    gen_spden = gen_parser.add_parser(
+        'spdens',
+        aliases=['spin_density', 'spden'],
+        description='Generate spin density cube file from gbw file', # noqa
+        usage=ut.cstring(
+            'orto gen spdens <gbw_file> <n_procs> [options]',
+            'cyan'
+        ),
+        formatter_class=argparse.RawTextHelpFormatter
+    )
+    gen_spden._positionals.title = 'Mandatory Arguments'
+    gen_spden.set_defaults(func=gen_spden_func)
+
+    gen_spden.add_argument(
+        'gbw_file',
+        type=pathlib.Path,
+        help='Orca gbw file name'
+    )
+
+    gen_spden.add_argument(
+        'n_procs',
+        type=int,
+        help='Number of processors/cores used in calculation',
+        default=1
+    )
+
+    gen_spden.add_argument(
+        '--n_pts',
+        '-n',
+        type=int,
+        default=100,
+        help=(
+            'Number of points in each dimension of cube file\n'
+            'Default: %(default)s'
+        )
+    )
+
+    gen_spden.add_argument(
+        '--memory',
+        '-mem',
+        type=int,
+        default=500,
+        help=(
+            'Per-core Memory to use in MB\n'
+            'Default: %(default)s'
+        )
+    )
+
+    gen_spden.add_argument(
+        '-om',
+        '--orca_load',
+        type=str,
+        default='',
+        help='Orca environment module (overrides ORTO_ORCA_LOAD envvar)'
+    )
+
+    gen_spden.add_argument(
+        '--no_sub',
+        '-ns',
+        action='store_true',
+        help=(
+            'Disables submission of job to queue'
+        )
+    )
+
     gen_job = gen_parser.add_parser(
         'job',
         description=(
@@ -1880,6 +2035,15 @@ def read_args(arg_list=None):
         )
     )
 
+    gen_job.add_argument(
+        '--skip_structure',
+        '-ss',
+        action='store_true',
+        help=(
+            'Disables checking of structure in input file or xyz file'
+        )
+    )
+
     gen_job.add_argument(
         '-om',
         '--orca_load',
@@ -2347,6 +2511,7 @@ def read_args(arg_list=None):
 
     plot_ailft = plot_parser.add_parser(
         'ailft_orbs',
+        aliases=['ailft_orb'],
         description='Plots AI-LFT orbital energies from output file',
         usage=ut.cstring(
             'orto plot ailft_orbs <output_file> [options]',

orto/extractor.py

@@ -2204,6 +2204,85 @@ class XYZInputExtractor(extto.LineExtractor):
         return _ext.data
 
 
+class StructureInputExtractor(extto.BetweenExtractor):
+    '''
+    Extracts structure from xyz file
+    '''
+
+    # Regex Start Pattern
+    START_PATTERN = rb'(?<=\*xyz )'
+
+    # Regex End Pattern
+    END_PATTERN = rb'(?=\*)'
+
+    @property
+    def data(self) -> tuple[list[str], NDArray]:
+        '''
+        list of atom labels and ndarray of coordinates (N, 3)
+        '''
+        return self._data
+
+    @staticmethod
+    def _process_block(block: str) -> tuple[list[str], NDArray]:
+        '''
+        Converts single block into data entries described in self.data
+
+        Parameters
+        ----------
+        block: str
+            String block extracted from file
+
+        Returns
+        -------
+        tuple[list[str], NDArray]
+        '''
+
+        # Get labels and coordinates
+        all_info = re.findall(
+            r'([A-Za-z]+\s*-?\d\.\d*\s+-?\d\.\d*\s+-?\d\.\d*)',
+            block
+        )
+
+        labels = re.findall(
+            r'([A-Za-z]+)',
+            block
+        )
+
+        coords = np.asarray([
+            [float(v) for v in val.split()[1:]]
+            for val in all_info
+        ])
+
+        if len(labels) != coords.shape[0]:
+            raise DataFormattingError(
+                'Number of atom labels does not match number of coordinates'
+            )
+
+        data = (labels, coords)
+
+        return data
+
+    @classmethod
+    def extract(cls, file_name: str | pathlib.Path) -> tuple[list[str], NDArray]: # noqa
+        '''
+        Convenience method which instantiates class, extracts blocks, and
+        returns processed datasets
+
+        Parameters
+        ----------
+        file_name: str | pathlib.Path
+            File to parse
+
+        Returns
+        -------
+        tuple[list[str], NDArray]
+            Each entry contains processed data, as defined in cls.data
+        '''
+        _ext = cls()
+        _ext(file_name, process=True)
+        return _ext.data
+
+
 class IntInputExtractor(XYZInputExtractor):
     '''
     Extracts *int line of an input file

orto/input.py

@@ -1,6 +1,7 @@
 from pathlib import Path
 import re
 import numpy as np
+import numpy.linalg as la
 import copy
 import xyz_py as xyzp
 
@@ -304,6 +305,77 @@ def check_xyz(file_name: str | Path, skip_check) -> None:
     return
 
 
+def check_structure(file_name: str | Path, threshold: float = 0.1) -> None:
+    '''
+    Checks that no atoms of the structure are overlapping.\n
+
+    Parameters
+    ----------
+    file_name: str | Path
+        Orca input file as either name or Path object
+    threshold: float
+        Minimum allowed distance between atoms in Angstroms
+
+    Returns
+    -------
+    None
+
+    Raises
+    ------
+    DataFormattingError
+        If any atoms are overlapping
+    '''
+
+    # Get xyz file name and check it exists and is formatted correctly
+    try:
+        xyz_file = oe.XYZFileInputExtractor.extract(file_name)
+    except DataNotFoundError:
+        xyz_file = []
+
+    try:
+        xyzline = oe.XYZInputExtractor.extract(file_name)
+    except DataNotFoundError:
+        xyzline = []
+
+    if not len(xyz_file) and not len(xyzline):
+        ut.red_exit(
+            'Error: missing or incorrect *xyzfile or *xyz line in input'
+        )
+
+    if len(xyz_file):
+        # Load structure from xyz file
+        xyz_file = Path(xyz_file[0])
+        labels, coords = xyzp.load_xyz(xyz_file)
+    else:
+        # Extract structure from input file
+        labels, coords = oe.StructureInputExtractor.extract(file_name)[0]
+
+    # Compute pairwise differences using broadcasting
+    # Broadcast to shape (N, N, 3)
+    # from (N, 1, 3) and (1, N, 3)
+    diffs = coords[:, np.newaxis, :] - coords[np.newaxis, :, :]
+
+    # Compute Euclidean distances
+    distances = la.norm(diffs, axis=-1)  # shape (N, N)
+
+    # Add large value to diagonal to avoid zero self-distances
+    distances += np.diag([100]*len(labels))
+    # Find index of zero distances
+    zero_dist = np.where(
+        distances < threshold
+    )
+    # and report
+    if len(zero_dist[0]):
+        raise DataFormattingError(
+            'Error: Overlapping atoms detected in structure'
+            ' at atom numbers:\n' + ', '.join(
+                str(i+1) for i in zero_dist[0]
+            )
+        )
+
+    return
+
+
 def check_moinp_moread(file_name: str | Path) -> None:
     '''
     Checks if MORead and/or MOInp are present in the input file.\n

orto/job.py

@@ -29,7 +29,7 @@ class OrcaJob():
         Orca output file name. Default is same as input with extension \n
         replaced by .out
     job_file: pathlib.Path
-        Submission script name. Default is same as input with extension \n
+        Submission script file path. Default is same as input with extension \n
         replaced by scheduler job file extension e.g. '.slm'
     job_name: str
         Job name. Default is same as input without extension
@@ -99,6 +99,9 @@ class OrcaJob():
 
     @property
     def job_file(self) -> pathlib.Path:
+        '''
+        The submission script file path
+        '''
         return self._job_file
 
     @job_file.setter
@@ -164,7 +167,7 @@ class OrcaJob():
         verbose: bool, default True
             If True, jobscript location is written to screen
         **kwargs
-            The keyword arguments are passed to `subto.job.Job` constructor
+            Keyword arguments passed to `subto.job.Job` constructor
         '''
 
         if len(self.load):

{orto-1.8.2.dist-info → orto-1.9.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: orto
-Version: 1.8.2
+Version: 1.9.0
 Summary: A package to make life easier when performing Orca calculations.
 Home-page: https://orto.kragskow.group
 Author: Jon Kragskow

orto-1.9.0.dist-info/RECORD

@@ -0,0 +1,17 @@
+orto/__init__.py,sha256=IedlltYr3qYZxChNUdz62qogXA9Pos_MUvXdGXqAa0E,41
+orto/__version__.py,sha256=w-88NSa4AsKUbL8rYWL8WNyh9CtUgEFkmfF69cJJ9ic,22
+orto/cli.py,sha256=i59s8-WthfZPYsHJDPWdMQfZ8ABCJJ8n5loieLeJVCA,86106
+orto/constants.py,sha256=anxaiTykO8Q_CXliR7zuOAdnXZrQ2-C4ndaviyl7kGc,419
+orto/data.py,sha256=960LHFeG7l626X_WA-8YxvG2toNAsgNvLo86OoYAmBY,14910
+orto/exceptions.py,sha256=D7oNeAEGeJNt5thzt6PaCn5FY6JcbJOWUE1N1LVhhuE,159
+orto/extractor.py,sha256=S27297-gasqLaLbMOqW9sj1X0U0mr3OjikxHcz9Es3o,77867
+orto/input.py,sha256=uUQV6A-8D0GZpRoY1rKK_aUPmk9kVVTnMzTHuisP5t4,11888
+orto/job.py,sha256=tDiz9omFwinoYJamgz66MZez0Ee9HMhuCIAeHMhXRF8,5916
+orto/plotter.py,sha256=_t9bow6sUMoRAvD6gVFGJTc-_ifW7RmeR0JAPWK_lm4,17799
+orto/utils.py,sha256=GcMZ9uebOSnkPQT_U5O0X49LUtTu8YpXZxEsNKgXNTY,9838
+orto-1.9.0.dist-info/licenses/LICENSE,sha256=46mU2C5kSwOnkqkw9XQAJlhBL2JAf1_uCD8lVcXyMRg,7652
+orto-1.9.0.dist-info/METADATA,sha256=v6KwljenLuZNETfGZexfXCkb7ECRGHFK2N7tJoat6bs,1184
+orto-1.9.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+orto-1.9.0.dist-info/entry_points.txt,sha256=HXenCglMp_03JkN34pK2phkjXK9CFcXTGHKv5QaVY8I,39
+orto-1.9.0.dist-info/top_level.txt,sha256=hQ-z28gTN_FZ2B5Kiwxr_9cUTcCoib9W5HjbkceDXw4,5
+orto-1.9.0.dist-info/RECORD,,

orto-1.8.2.dist-info/RECORD

@@ -1,17 +0,0 @@
-orto/__init__.py,sha256=IedlltYr3qYZxChNUdz62qogXA9Pos_MUvXdGXqAa0E,41
-orto/__version__.py,sha256=IHNGvfH_VZgoJtblUBUhux38WliEIBQJQgJavTtuxE8,22
-orto/cli.py,sha256=L2i5FHwXSH8AdE2hZHA0VcqJv1oxxGZ3MUgPSE9Dn_E,81704
-orto/constants.py,sha256=anxaiTykO8Q_CXliR7zuOAdnXZrQ2-C4ndaviyl7kGc,419
-orto/data.py,sha256=960LHFeG7l626X_WA-8YxvG2toNAsgNvLo86OoYAmBY,14910
-orto/exceptions.py,sha256=D7oNeAEGeJNt5thzt6PaCn5FY6JcbJOWUE1N1LVhhuE,159
-orto/extractor.py,sha256=d2_pGQeIjK_JbsMINTawUgcO2vcPq0b9uQj9VKuI720,75953
-orto/input.py,sha256=N8JbySSVEC_qmXZ7ppJsZ7Z1qel6PfalGYRtnX1hJ6U,9900
-orto/job.py,sha256=SM0nlc_bqhhPvfuuykhMvaUnkwC3Gp-6RvYw_a0TyGc,5855
-orto/plotter.py,sha256=_t9bow6sUMoRAvD6gVFGJTc-_ifW7RmeR0JAPWK_lm4,17799
-orto/utils.py,sha256=GcMZ9uebOSnkPQT_U5O0X49LUtTu8YpXZxEsNKgXNTY,9838
-orto-1.8.2.dist-info/licenses/LICENSE,sha256=46mU2C5kSwOnkqkw9XQAJlhBL2JAf1_uCD8lVcXyMRg,7652
-orto-1.8.2.dist-info/METADATA,sha256=mYOygGP_9fNfyFUXwTjT7woJLMHZdnTfX98diY-PvIE,1184
-orto-1.8.2.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-orto-1.8.2.dist-info/entry_points.txt,sha256=HXenCglMp_03JkN34pK2phkjXK9CFcXTGHKv5QaVY8I,39
-orto-1.8.2.dist-info/top_level.txt,sha256=hQ-z28gTN_FZ2B5Kiwxr_9cUTcCoib9W5HjbkceDXw4,5
-orto-1.8.2.dist-info/RECORD,,