File: bonds.py

package info (click to toggle)
python-mp-api 0.45.3-4
  • links: PTS, VCS
  • area: main
  • in suites: forky, sid, trixie
  • size: 6,988 kB
  • sloc: python: 6,712; makefile: 14
file content (134 lines) | stat: -rw-r--r-- 5,319 bytes parent folder | download
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
from __future__ import annotations

from emmet.core.molecules.bonds import MoleculeBondingDoc
from emmet.core.mpid import MPculeID

from mp_api.client.core import BaseRester


class MoleculesBondRester(BaseRester[MoleculeBondingDoc]):
    suffix = "molecules/bonding"
    document_model = MoleculeBondingDoc
    primary_key = "property_id"

    def search(
        self,
        molecule_ids: MPculeID | list[MPculeID] | None = None,
        property_ids: str | list[str] | None = None,
        method: str | None = None,
        bond_type: str | None = None,
        max_bond_length: float | None = None,
        min_bond_length: float | None = None,
        charge: int | None = None,
        spin_multiplicity: int | None = None,
        level_of_theory: str | None = None,
        solvent: str | None = None,
        lot_solvent: str | None = None,
        formula: str | list[str] | None = None,
        elements: list[str] | None = None,
        exclude_elements: list[str] | None = None,
        chemsys: str | list[str] | None = None,
        num_chunks: int | None = None,
        chunk_size: int = 1000,
        all_fields: bool = True,
        fields: list[str] | None = None,
    ):
        """Query molecules bonding docs using a variety of search criteria.

        Arguments:
            molecule_ids (MPculeID, List[MPculeID]): List of Materials Project Molecule IDs (MPculeIDs) to return data
                for.
            property_ids (str, List[str]): List of property IDs to return data for.
            method (str): Method used to generate bonding data
                (e.g. "nbo", "critic2", or "OpenBabelNN + metal_edge_extender")
            bond_type (str): Bond type of interest (e.g. "C-O" for carbon-oxygen bonds)
            max_bond_length (float): Maximum bond length in the molecule of the specified type
            min_bond_length (float): Minimum bond length in the molecule of the specified type
            charge (Tuple[int, int]): Minimum and maximum charge for the molecule.
            spin_multiplicity (Tuple[int, int]): Minimum and maximum spin for the molecule.
            level_of_theory (str): Desired level of theory (e.g. "wB97X-V/def2-TZVPPD/SMD")
            solvent (str): Desired solvent (e.g. "SOLVENT=WATER")
            lot_solvent (str): Desired combination of level of theory and solvent
                (e.g. "wB97X-V/def2-TZVPPD/SMD(SOLVENT=THF)")
            formula (str, List[str]): An alphabetical formula or list of formulas
                (e.g. "C2 Li2 O4", ["C2 H4", "C2 H6"]).
            elements (List[str]): A list of elements.
            exclude_elements (List(str)): List of elements to exclude.
            chemsys (str, List[str]): A chemical system, list of chemical systems
                (e.g., Li-C-O, [C-O-H-N, Li-N]).
            num_chunks (int): Maximum number of chunks of data to yield. None will yield all possible.
            chunk_size (int): Number of data entries per chunk.
            all_fields (bool): Whether to return all fields in the document. Defaults to True.
            fields (List[str]): List of fields in MoleculeDoc to return data for.
                Default is "molecule_id", "property_id", "solvent", "method", "last_updated"
                if all_fields is False.

        Returns:
            ([MoleculeBondingDoc]) List of bonding documents
        """
        query_params = {}  # type: dict

        if molecule_ids:
            if isinstance(molecule_ids, str):
                molecule_ids = [molecule_ids]

            query_params.update({"molecule_ids": ",".join(molecule_ids)})

        if property_ids:
            if isinstance(property_ids, str):
                property_ids = [property_ids]

            query_params.update({"property_ids": ",".join(property_ids)})

        if method:
            query_params.update({"method": method})

        if bond_type:
            query_params.update({"bond_type": bond_type})

        if max_bond_length:
            query_params.update({"max_bond_length": max_bond_length})

        if min_bond_length:
            query_params.update({"min_bond_length": max_bond_length})

        if charge:
            query_params.update({"charge": charge})

        if spin_multiplicity:
            query_params.update({"spin_multiplicity": spin_multiplicity})

        if level_of_theory:
            query_params.update({"level_of_theory": level_of_theory})

        if solvent:
            query_params.update({"solvent": solvent})

        if lot_solvent:
            query_params.update({"lot_solvent": lot_solvent})

        if formula:
            if isinstance(formula, str):
                formula = [formula]

            query_params.update({"formula": ",".join(formula)})

        if chemsys:
            if isinstance(chemsys, str):
                chemsys = [chemsys]

            query_params.update({"chemsys": ",".join(chemsys)})

        if elements:
            query_params.update({"elements": ",".join(elements)})

        if exclude_elements:
            query_params.update({"exclude_elements": ",".join(exclude_elements)})

        return super()._search(
            num_chunks=num_chunks,
            chunk_size=chunk_size,
            all_fields=all_fields,
            fields=fields,
            **query_params,
        )