Merge pull request #160 from ReactionMechanismGenerator/rec_libs

Added auto-completion for RMG thermo and kinetics libraries based on the chemistry set

data/libraries.yml

@@ -0,0 +1,153 @@
+# Recommended RMG libraries per application
+
+primary:
+  thermo:
+    - primaryThermoLibrary
+    - BurkeH2O2
+    - Spiekermann_refining_elementary_reactions
+    - thermo_DFT_CCSDTF12_BAC
+    - DFT_QCI_thermo
+    - CBS_QB3_1dHR
+  kinetics:
+    - primaryH2O2
+
+nitrogen:
+  thermo:
+    - NH3
+    - NitrogenCurran
+    - CHON_G4
+    - CN
+    - NOx2018
+    - name: primaryNS
+      credence: low
+    - name: CHN
+      credence: low
+    - name: CHON
+      credence: low
+    - name: BurcatNS
+      credence: low
+  kinetics:
+    - primaryNitrogenLibrary
+    - HydrazinePDep
+    - Ethylamine
+
+sulfur:
+  thermo:
+    - name: primaryNS
+      credence: low
+    - name: SulfurGlarborgH2S
+      credence: low
+    - name: SulfurGlarborgBozzeli
+      credence: low
+    - name: BurcatNS
+      credence: low
+  kinetics:
+    - primarySulfurLibrary
+    - Sulfur/DMDS
+    - Sulfur/DMS
+
+combustion:
+  thermo:
+    - FFCM1(-)
+    - NOx2018
+    - name: CHO
+      credence: low
+  kinetics:
+    - FFCM1(-)
+    - 2006_Joshi_OH_CO
+    - 2005_Senosiain_OH_C2H2
+    - NOx2018
+
+CH_pyrolysis:
+  thermo:
+    - NOx2018
+    - Butadiene_Dimerization
+    - C10H11
+    - s3_5_7_ane
+    - Fulvene_H
+    - naphthalene_H
+    - vinylCPD_H
+    - Lai_Hexylbenzene
+    - Narayanaswamy
+    - SABIC_aromatics_1dHR_extended
+    - SABIC_aromatics_1dHR
+    - SABIC_aromatics
+    - heavy_oil_ccsdtf12_1dHR
+    - bio_oil
+    - Chernov
+    - CurranPentane
+    - Klippenstein_Glarborg2016
+    - name: CH
+      credence: low
+  kinetics:
+    - 2001_Tokmakov_H_Toluene_to_CH3_Benzene
+    - 2003_Miller_Propargyl_Recomb_High_P
+    - 2009_Sharma_C5H5_CH3_highP
+    - 2015_Buras_C2H3_C4H6_highP
+    - Butadiene_Dimerization
+    - C10H11
+    - C12H11_pdep
+    - C2H2_init
+    - C6H5_C4H4_Mebel
+    - Fulvene_H
+    - Mebel_Naphthyl
+    - Mebel_C6H5_C2H2
+    - biCPD_H_shift
+    - c-C5H5_CH3_Sharma
+    - fascella
+    - kislovB
+    - naphthalene_H
+    - vinylCPD_H
+    - First_to_Second_Aromatic_Ring/2005_Ismail_C6H5_C4H6_highP
+    - First_to_Second_Aromatic_Ring/2012_Matsugi_C3H3_C7H7_highP
+    - First_to_Second_Aromatic_Ring/2016_Mebel_C10H9_highP
+    - First_to_Second_Aromatic_Ring/2016_Mebel_C9H9_highP
+    - First_to_Second_Aromatic_Ring/2016_Mebel_Indene_CH3_highP
+    - First_to_Second_Aromatic_Ring/2017_Buras_C6H5_C3H6_highP
+    - First_to_Second_Aromatic_Ring/2017_Mebel_C6H4C2H_C2H2_highP
+    - First_to_Second_Aromatic_Ring/2017_Mebel_C6H5C2H2_C2H2_highP
+    - First_to_Second_Aromatic_Ring/2017_Mebel_C6H5_C2H2_highP
+    - First_to_Second_Aromatic_Ring/2017_Mebel_C6H5_C4H4_highP
+    - First_to_Second_Aromatic_Ring/phenyl_diacetylene_effective
+    - Aromatics_high_pressure/C10H10_1
+    - Aromatics_high_pressure/C10H10_2
+    - Aromatics_high_pressure/C10H10_H_abstraction
+    - Aromatics_high_pressure/C10H11_1
+    - Aromatics_high_pressure/C10H11_2
+    - Aromatics_high_pressure/C10H11_3
+    - Aromatics_high_pressure/C10H11_4
+    - Aromatics_high_pressure/C10H7
+    - Aromatics_high_pressure/C10H8_H_abstraction_H_recomb
+    - Aromatics_high_pressure/C10H9_1
+    - Aromatics_high_pressure/C10H9_2
+    - Aromatics_high_pressure/C10H9_3
+    - Aromatics_high_pressure/C10H9_4
+    - Aromatics_high_pressure/C12H10_1
+    - Aromatics_high_pressure/C12H10_2
+    - Aromatics_high_pressure/C12H10_H_abstraction
+    - Aromatics_high_pressure/C12H11
+    - Aromatics_high_pressure/C12H8_H_abstraction
+    - Aromatics_high_pressure/C12H9
+    - Aromatics_high_pressure/C14H10_H_abstraction_H_recomb
+    - Aromatics_high_pressure/C14H11_1
+    - Aromatics_high_pressure/C14H11_2
+    - Aromatics_high_pressure/C14H11_3
+    - Aromatics_high_pressure/C14H11_4
+    - Aromatics_high_pressure/C14H9
+    - Aromatics_high_pressure/C16H11
+    - Aromatics_high_pressure/C7H8
+    - Aromatics_high_pressure/C7H8_H_abstraction
+    - Aromatics_high_pressure/C7H9
+    - Aromatics_high_pressure/C8H6_H_abstraction
+    - Aromatics_high_pressure/C8H7
+    - Aromatics_high_pressure/C8H8_H_abstraction
+    - Aromatics_high_pressure/C8H9
+    - Aromatics_high_pressure/C9H10_H_abstraction
+    - Aromatics_high_pressure/C9H11
+    - Aromatics_high_pressure/C9H7
+    - Aromatics_high_pressure/C9H8_1
+    - Aromatics_high_pressure/C9H8_2
+    - Aromatics_high_pressure/C9H8_H_abstraction
+    - Aromatics_high_pressure/C9H9_1
+    - Aromatics_high_pressure/C9H9_2
+

examples/commented/input.yml

@@ -72,8 +72,10 @@ rmg:
 
   # database (a required block)
   database:
-    thermo_libraries: ['BurkeH2O2', 'DFT_QCI_thermo', 'primaryThermoLibrary', 'CBS_QB3_1dHR']  # *required*, can be an empty list
-    kinetics_libraries: ['BurkeH2O2inN2', 'NOx2018', 'Klippenstein_Glarborg2016']  # *required*, can be an empty list
+    thermo_libraries: ['BurkeH2O2', 'DFT_QCI_thermo', 'primaryThermoLibrary', 'CBS_QB3_1dHR']  # Can be None for auto-completion
+    kinetics_libraries: ['BurkeH2O2inN2', 'NOx2018', 'Klippenstein_Glarborg2016']  # Can be None for auto-completion
+    chemistry_sets: ['primary', 'nitrogen', 'combustion']  # The chemistry systems for which thermo and kinetics libraries will be loaded. Can be None to avoid auto-completion
+    use_low_credence_libraries: False # Whether to use low credence libraries during auto-completion, default: ``False``
     transport_libraries: ['PrimaryTransportLibrary', 'OneDMinN2', 'NOx2018', 'GRI-Mech']  # optional, default: ['PrimaryTransportLibrary', 'OneDMinN2', 'NOx2018', 'GRI-Mech']
     seed_mechanisms: []  # optional, default: []
     kinetics_depositories: default  # optional, default: 'default'

t3/common.py

@@ -14,8 +14,9 @@
 VERSION = '0.1.0'
 
 t3_path = os.path.abspath(os.path.dirname(os.path.dirname(__file__)))  # absolute path to the T3 folder
-DATA_BASE_PATH = os.path.join(t3_path, 'tests', 'data')
-SIMULATE_DATA_BASE_PATH = os.path.join(t3_path, 'tests', 'test_simulate_adapters', 'data')
+DATA_BASE_PATH = os.path.join(t3_path, 'data')
+TEST_DATA_BASE_PATH = os.path.join(t3_path, 'tests', 'data')
+SIMULATE_TEST_DATA_BASE_PATH = os.path.join(t3_path, 'tests', 'test_simulate_adapters', 'data')
 EXAMPLES_BASE_PATH = os.path.join(t3_path, 'examples')
 SCRATCH_BASE_PATH = os.path.join(t3_path, 'tests', 'scratch')
 IPYTHON_SIMULATOR_EXAMPLES_PATH = os.path.join(t3_path, 'ipython', 'simulator_adapter_examples')

t3/main.py

@@ -45,7 +45,12 @@
 from arc.species.species import ARCSpecies, check_label
 from arc.species.converter import check_xyz_dict
 
-from t3.common import PROJECTS_BASE_PATH, VALID_CHARS, delete_root_rmg_log, get_species_by_label, time_lapse
+from t3.common import (DATA_BASE_PATH,
+                       PROJECTS_BASE_PATH,
+                       VALID_CHARS,
+                       delete_root_rmg_log,
+                       get_species_by_label,
+                       time_lapse)
 from t3.logger import Logger
 from t3.runners.rmg_runner import rmg_runner
 from t3.schema import InputBase
@@ -177,6 +182,7 @@ def __init__(self,
         self.project_directory = self.schema['project_directory']
         self.t3 = self.schema['t3']
         self.rmg = self.schema['rmg']
+        self.rmg['database'] = auto_complete_rmg_libraries(database=self.rmg['database'])
         self.qm = self.schema['qm']
         self.verbose = self.schema['verbose']
 
@@ -1538,3 +1544,38 @@ def get_species_with_qm_label(species: Species,
                                 rmg_species=qm_species,
                                 )
     return qm_species
+
+
+def auto_complete_rmg_libraries(database: dict) -> dict:
+    """
+    Update the RMG libraries using auto-completion.
+
+    Args:
+        database (dict): The RMG libraries dictionary.
+
+    Returns:
+        dict: The updated RMG libraries dictionary.
+    """
+    database['thermo_libraries'] = database['thermo_libraries'] or list()
+    database['kinetics_libraries'] = database['kinetics_libraries'] or list()
+    if database['chemistry_sets'] is not None:
+        libraries_dict = read_yaml_file(path=os.path.join(DATA_BASE_PATH, 'libraries.yml'))
+        low_credence = database['use_low_credence_libraries']
+        for chemistry_set in database['chemistry_sets']:
+            if chemistry_set not in libraries_dict:
+                raise ValueError(f"Chemistry set '{chemistry_set}' not found in the libraries.yml file.")
+            for key, libraries in zip(['thermo', 'kinetics'], [database['thermo_libraries'], database['kinetics_libraries']]):
+                low_credence_libraries = list()
+                if key in libraries_dict[chemistry_set]:
+                    for entry in libraries_dict[chemistry_set][key]:
+                        if isinstance(entry, str) and entry not in libraries:
+                            libraries.append(entry)
+                        elif isinstance(entry, dict):
+                            if entry['credence'] != 'low' and entry['name'] not in libraries:
+                                libraries.append(entry['name'])
+                            if entry['credence'] == 'low' and low_credence and entry['name'] not in libraries:
+                                low_credence_libraries.append(entry['name'])
+                libraries.extend(low_credence_libraries)
+    del database['chemistry_sets']
+    del database['use_low_credence_libraries']
+    return database

t3/schema.py

@@ -1,16 +1,17 @@
 """
 t3 schema module
 used for input validation
-
-Todo: add "live" validators for actually implemented adapters, need to access the respective factory register dicts
 """
 
+import os
 from enum import Enum
 from typing import Dict, List, Optional, Tuple, Union
 
 from pydantic import BaseModel, conint, confloat, constr, root_validator, validator
 
-from t3.common import VALID_CHARS
+from arc.common import read_yaml_file
+
+from t3.common import DATA_BASE_PATH, VALID_CHARS
 from t3.simulate.factory import _registered_simulate_adapters
 
 
@@ -174,8 +175,10 @@ class RMGDatabase(BaseModel):
     """
     A class for validating input.RMG.database arguments
     """
-    thermo_libraries: List[str]
-    kinetics_libraries: List[str]
+    thermo_libraries: Optional[List[str]] = None
+    kinetics_libraries: Optional[List[str]] = None
+    chemistry_sets: Optional[List[str]] = None
+    use_low_credence_libraries: bool = False
     transport_libraries: List[str] = ['OneDMinN2', 'PrimaryTransportLibrary', 'NOx2018', 'GRI-Mech']
     seed_mechanisms: List[str] = list()
     kinetics_depositories: Union[List[str], str] = 'default'
@@ -185,6 +188,17 @@ class RMGDatabase(BaseModel):
     class Config:
         extra = "forbid"
 
+    @validator('chemistry_sets')
+    def check_chemistry_sets(cls, value, values):
+        """RMGDatabase.chemistry_sets validator"""
+        libraries_dict = read_yaml_file(path=os.path.join(DATA_BASE_PATH, 'libraries.yml'))
+        allowed_values = libraries_dict.keys()
+        if value and any(v not in allowed_values for v in value):
+            raise ValueError(f'The chemistry sets must be within of the following:\n{allowed_values}\nGot: {value}')
+        if value is None and (values['thermo_libraries'] is None or values['kinetics_libraries'] is None):
+            raise ValueError('The chemistry set must be specified if thermo or kinetics libraries are not specified.')
+        return value
+
 
 class RadicalTypeEnum(str, Enum):
     """

tests/common.py

@@ -19,7 +19,18 @@ def run_minimal(project: Optional[str] = None,
                 iteration: Optional[int] = None,
                 set_paths: bool = False,
                 ) -> T3:
-    """A helper function for running the minimal example"""
+    """
+    A helper function for running the minimal example.
+
+    Args:
+        project (str, optional): The project name.
+        project_directory (str, optional): The project directory.
+        iteration (int, optional): The iteration number.
+        set_paths (bool, optional): Whether to set the paths.
+
+    Returns:
+        T3: The T3 object.
+    """
     minimal_input = os.path.join(EXAMPLES_BASE_PATH, 'minimal', 'input.yml')
     input_dict = read_yaml_file(path=minimal_input)
     input_dict['verbose'] = 10

tests/test_common.py

@@ -11,7 +11,7 @@
 from rmgpy.species import Species
 
 import t3.common as common
-from t3.common import DATA_BASE_PATH
+from t3.common import TEST_DATA_BASE_PATH
 from t3.schema import RMGSpecies
 from tests.common import run_minimal
 
@@ -33,7 +33,7 @@ def test_dict_to_str():
 
 def test_get_species_by_label():
     """Test getting species by label"""
-    t3 = run_minimal(project_directory=os.path.join(DATA_BASE_PATH, 'minimal_data'),
+    t3 = run_minimal(project_directory=os.path.join(TEST_DATA_BASE_PATH, 'minimal_data'),
                      iteration=1,
                      set_paths=True,
                      )
@@ -131,7 +131,7 @@ def test_get_interval():
 
 def test_get_chem_to_rmg_rxn_index_map():
     """Test the get_chem_to_rmg_rxn_index_map() function"""
-    chemkin_path = os.path.join(DATA_BASE_PATH, 'chem_annotated_1.inp')
+    chemkin_path = os.path.join(TEST_DATA_BASE_PATH, 'chem_annotated_1.inp')
     rxn_map = common.get_chem_to_rmg_rxn_index_map(chem_annotated_path=chemkin_path)
     assert rxn_map == {1: 1, 2: 2, 3: 3, 4: 4, 5: 5, 6: 5, 7: 6, 8: 7, 9: 8, 10: 9, 11: 9, 12: 10, 13: 11, 14: 12,
                        15: 13, 16: 14, 17: 15, 18: 16, 19: 17, 20: 18, 21: 19, 22: 20, 23: 21, 24: 22, 25: 23, 26: 24,

tests/test_functional.py

@@ -12,7 +12,7 @@
 from arc.common import read_yaml_file
 
 from t3 import T3
-from t3.common import DATA_BASE_PATH
+from t3.common import TEST_DATA_BASE_PATH
 from t3.runners.rmg_runner import backup_rmg_files
 from t3.utils.dependencies import check_dependencies
 
@@ -58,7 +58,7 @@ def test_computing_thermo():
     Tests computing thermo for two species and running RMG with the updated data
     Need xtb installed
     """
-    functional_test_directory = os.path.join(DATA_BASE_PATH, 'functional_2_thermo')
+    functional_test_directory = os.path.join(TEST_DATA_BASE_PATH, 'functional_2_thermo')
     #delete_selective_content_from_test_dirs(test_dir=functional_test_directory)
     input_file = os.path.join(functional_test_directory, 'input.yml')
     input_dict = read_yaml_file(path=input_file)
@@ -113,7 +113,7 @@ def test_rmg_files_backup_before_restart():
     3.chem_edge_annotated
     4.RMG log files
     """
-    backup_test_directory = os.path.join(DATA_BASE_PATH, 'backup_rmg_files_before_restart','iteration_1', 'RMG')
+    backup_test_directory = os.path.join(TEST_DATA_BASE_PATH, 'backup_rmg_files_before_restart','iteration_1', 'RMG')
     backup_rmg_files(backup_test_directory)
     # Find the backup directory (there should only be one per restart)
     backup_directories = [d for d in os.listdir(backup_test_directory) if d.startswith('restart_backup')]
@@ -152,11 +152,11 @@ def delete_selective_content_from_test_dirs(test_dir: str):
 
 def teardown_module():
     """teardown any state that was previously setup with a setup_module method."""
-    test_dirs_to_selectively_delete = [os.path.join(DATA_BASE_PATH, 'functional_2_thermo'),
+    test_dirs_to_selectively_delete = [os.path.join(TEST_DATA_BASE_PATH, 'functional_2_thermo'),
                                        ]
     for test_dir in test_dirs_to_selectively_delete:
         delete_selective_content_from_test_dirs(test_dir)
-    test_dirs = [os.path.join(DATA_BASE_PATH, 'T3_functional_test_1'),
+    test_dirs = [os.path.join(TEST_DATA_BASE_PATH, 'T3_functional_test_1'),
                  ]
     for test_dir in test_dirs:
         shutil.rmtree(test_dir, ignore_errors=True)