Adds pre-commit hooks (#216)

* Adds a first version of the Ehrlich function proposed by Stanton et al

* Adds seeds for all functions in Ehrlich

* Adds tests for motif matching, seeding and optimal sequence creation

* Adds problem factory and associated tests

* Adds docstrings

* Adds pre-commit hooks

* Adds isort with black compatiblity

* Removes the examples folder from isort

* Adds pre-commit hooks

* Adds isort with black compatiblity

* Removes the examples folder from isort

.pre-commit-config.yaml

@@ -0,0 +1,16 @@
+repos:
+-   repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v3.2.0
+    hooks:
+    -   id: trailing-whitespace
+        exclude: '.*\.pdb$'
+    -   id: check-yaml
+    -   id: check-added-large-files
+-   repo: https://github.com/psf/black
+    rev: 24.1.1
+    hooks:
+    -   id: black
+-   repo: https://github.com/PyCQA/isort
+    rev: 5.13.2
+    hooks:
+    -   id: isort

examples/minimal_working_example.py

@@ -6,6 +6,7 @@
 """
 
 import numpy as np
+
 from poli import objective_factory
 
 problem = objective_factory.create(name="white_noise")

examples/observers/adding_a_wandb_observer/example_logging_rdkit_qed_using_wandb.py

@@ -9,12 +9,11 @@
 from pathlib import Path
 
 import numpy as np
+from wandb_observer import WandbObserver
 
 from poli.core.problem import Problem
 from poli.objective_repository import QEDProblemFactory
 
-from wandb_observer import WandbObserver
-
 THIS_DIR = Path(__file__).parent.resolve()
 
 if __name__ == "__main__":

examples/observers/adding_a_wandb_observer/wandb_observer.py

@@ -6,8 +6,8 @@
 """
 
 import numpy as np
-import wandb
 
+import wandb
 from poli.core.black_box_information import BlackBoxInformation
 from poli.core.util.abstract_observer import AbstractObserver
 

examples/observers/adding_an_mlflow_observer/example_logging_rdkit_logp_using_mlflow.py

@@ -15,11 +15,10 @@
 from pathlib import Path
 
 import numpy as np
+from mlflow_observer import MlFlowObserver
 
 from poli import objective_factory
 
-from mlflow_observer import MlFlowObserver
-
 THIS_DIR = Path(__file__).parent.resolve()
 
 if __name__ == "__main__":

examples/observers/adding_an_mlflow_observer/mlflow_observer.py

@@ -11,6 +11,7 @@
 """
 
 from pathlib import Path
+
 import mlflow
 import numpy as np
 

examples/observers/registering_an_observer/00_registering_an_observer.py

@@ -15,10 +15,10 @@
 of how to instantiate it after registration.
 """
 
-from poli.core.registry import register_observer
-
 from print_observer import SimplePrintObserver
 
+from poli.core.registry import register_observer
+
 if __name__ == "__main__":
     register_observer(
         observer=SimplePrintObserver(),

examples/observers/registering_an_observer/02_discouraged_use.py

@@ -6,11 +6,10 @@
 """
 
 import numpy as np
-
-from poli.core.registry import DEFAULT_OBSERVER_NAME
 from print_observer import SimplePrintObserver
-from poli import objective_factory
 
+from poli import objective_factory
+from poli.core.registry import DEFAULT_OBSERVER_NAME
 
 if __name__ == "__main__":
     # Instantiate the objective

examples/protein_stability_and_sasa/saturation_mutagenesis_for_two_proteins_using_rasp/saturation_mutagenesis_at_first_position.py

@@ -13,8 +13,8 @@
 import numpy as np
 import pandas as pd
 
-from poli.core.util.proteins.defaults import AMINO_ACIDS
 from poli import objective_factory
+from poli.core.util.proteins.defaults import AMINO_ACIDS
 
 THIS_DIR = Path(__file__).parent.resolve()
 

examples/small_molecules/querying_qed_and_logp_of_selfies/querying_qed_and_logp.py

@@ -13,7 +13,7 @@
 
 import numpy as np
 
-from poli.objective_repository import QEDBlackBox, LogPBlackBox
+from poli.objective_repository import LogPBlackBox, QEDBlackBox
 
 THIS_DIR = Path(__file__).parent.resolve()
 

examples/the_basics/a_simple_objective_function_registration/registering_aloha.py

@@ -5,8 +5,8 @@
 the initial point, and its first evaluation.
 """
 
-from typing import Tuple
 from string import ascii_uppercase
+from typing import Tuple
 
 import numpy as np
 

pyproject.toml

@@ -37,4 +37,7 @@ Homepage = "https://github.com/MachineLearningLifeScience/poli"
 [tool.pytest.ini_options]
 markers = [
     "slow: marks tests as slow (deselect with '-m \"not slow\"')",
-]
+]
+
+[tool.isort]
+profile = "black"

src/poli/__init__.py

@@ -1,7 +1,8 @@
 """poli, a library for discrete black-box objective functions."""
 
 __author__ = "Simon Bartels & Miguel González-Duque (MLLS)"
+from .core.util.isolation.instancing import instance_function_as_isolated_process
+
 # from .core import get_problems
 from .objective_factory import create
-from .core.util.isolation.instancing import instance_function_as_isolated_process
 from .objective_repository import get_problems

src/poli/benchmarks/__init__.py

@@ -1,7 +1,7 @@
+from .guacamol import GuacaMolGoalDirectedBenchmark
+from .pmo import PMOBenchmark
 from .toy_continuous_functions_benchmark import (
-    ToyContinuousFunctionsBenchmark,
     EmbeddedBranin2D,
     EmbeddedHartmann6D,
+    ToyContinuousFunctionsBenchmark,
 )
-from .guacamol import GuacaMolGoalDirectedBenchmark
-from .pmo import PMOBenchmark

src/poli/benchmarks/guacamol.py

@@ -20,14 +20,13 @@
 [2] Huang, Kexin, Tianfan Fu, Wenhao Gao, Yue Zhao, Yusuf Roohani, Jure Leskovec,
     Connor W Coley, Cao Xiao, Jimeng Sun, and Marinka Zitnik.
     “Therapeutics Data Commons: Machine Learning Datasets and Tasks for Drug Discovery and Development.”
-    Proceedings of Neural Information Processing Systems, NeurIPS Datasets and Benchmarks, 2021. 
+    Proceedings of Neural Information Processing Systems, NeurIPS Datasets and Benchmarks, 2021.
 """
 
 from typing import Literal, Union
 
-from poli.core.problem import Problem
 from poli.core.abstract_benchmark import AbstractBenchmark
-
+from poli.core.problem import Problem
 from poli.objective_repository import (
     AlbuterolSimilarityProblemFactory,
     AmlodipineMPOProblemFactory,
@@ -36,14 +35,14 @@
     FexofenadineMPOProblemFactory,
     IsomerC7H8N2O2ProblemFactory,
     IsomerC9H10N2O2PF2ClProblemFactory,
+    LogPProblemFactory,
     Median1ProblemFactory,
     Median2ProblemFactory,
     MestranolSimilarityProblemFactory,
     OsimetrinibMPOProblemFactory,
     PerindoprilMPOProblemFactory,
-    RanolazineMPOProblemFactory,
-    LogPProblemFactory,
     QEDProblemFactory,
+    RanolazineMPOProblemFactory,
     SAProblemFactory,
     ScaffoldHopProblemFactory,
     SitagliptinMPOProblemFactory,

src/poli/benchmarks/pmo.py

@@ -23,16 +23,16 @@
 [3] Huang, Kexin, Tianfan Fu, Wenhao Gao, Yue Zhao, Yusuf Roohani, Jure Leskovec,
     Connor W Coley, Cao Xiao, Jimeng Sun, and Marinka Zitnik.
     “Therapeutics Data Commons: Machine Learning Datasets and Tasks for Drug Discovery and Development.”
-    Proceedings of Neural Information Processing Systems, NeurIPS Datasets and Benchmarks, 2021. 
+    Proceedings of Neural Information Processing Systems, NeurIPS Datasets and Benchmarks, 2021.
 
 """
 
 from typing import Literal, Union
 
 from poli.objective_repository import (
     DRD2ProblemFactory,
-    JNK3ProblemFactory,
     GSK3BetaProblemFactory,
+    JNK3ProblemFactory,
 )
 
 from .guacamol import GuacaMolGoalDirectedBenchmark

src/poli/benchmarks/toy_continuous_functions_benchmark.py

@@ -15,15 +15,15 @@
     https://www.sfu.ca/~ssurjano/optimization.html.
 """
 
-from typing import Union, List
+from typing import List, Union
+
 from poli.core.abstract_benchmark import AbstractBenchmark
 from poli.core.problem import Problem
-
 from poli.objective_repository import ToyContinuousProblemFactory
 from poli.objective_repository.toy_continuous_problem.toy_continuous_problem import (
     POSSIBLE_FUNCTIONS,
-    TWO_DIMENSIONAL_PROBLEMS,
     SIX_DIMENSIONAL_PROBLEMS,
+    TWO_DIMENSIONAL_PROBLEMS,
 )
 
 

src/poli/core/abstract_black_box.py

@@ -2,18 +2,17 @@
 all objective functions should inherit.
 """
 
+from multiprocessing import Pool, cpu_count
 from warnings import warn
 
 import numpy as np
-from multiprocessing import Pool, cpu_count
 
 from poli.core.black_box_information import BlackBoxInformation
+from poli.core.exceptions import BudgetExhaustedException
 from poli.core.problem_setup_information import ProblemSetupInformation
-
 from poli.core.util.abstract_observer import AbstractObserver
-from poli.core.util.batch import batched
 from poli.core.util.alignment import is_aligned_input
-from poli.core.exceptions import BudgetExhaustedException
+from poli.core.util.batch import batched
 
 
 class AbstractBlackBox:

src/poli/core/benchmark_information.py

@@ -1,4 +1,4 @@
-from typing import Union, Literal
+from typing import Literal, Union
 
 
 class BenchmarkInformation:

src/poli/core/black_box_information.py

@@ -12,7 +12,7 @@
 - The alphabet of allowed characters.
 """
 
-from typing import Union, Literal
+from typing import Literal, Union
 
 
 class BlackBoxInformation:

src/poli/core/chemistry/tdc_black_box.py

@@ -21,7 +21,6 @@
 import numpy as np
 
 from poli.core.abstract_black_box import AbstractBlackBox
-
 from poli.core.util.isolation.instancing import get_inner_function
 
 

src/poli/core/chemistry/tdc_isolated_function.py

@@ -12,11 +12,9 @@
 """
 
 import numpy as np
-
 from tdc import Oracle
 
 from poli.core.abstract_isolated_function import AbstractIsolatedFunction
-
 from poli.core.util.chemistry.string_to_molecule import translate_selfies_to_smiles
 
 

src/poli/core/multi_objective_black_box.py

@@ -9,8 +9,8 @@
 import numpy as np
 
 from poli.core.abstract_black_box import AbstractBlackBox
-from poli.core.problem_setup_information import ProblemSetupInformation
 from poli.core.black_box_information import BlackBoxInformation
+from poli.core.problem_setup_information import ProblemSetupInformation
 
 
 class MultiObjectiveBlackBox(AbstractBlackBox):

src/poli/core/proteins/foldx_black_box.py

@@ -11,20 +11,19 @@
     33(suppl_2), W382-W388.
 """
 
-from typing import Union, List
+from multiprocessing import cpu_count
 from pathlib import Path
 from time import time
+from typing import List, Union
 from uuid import uuid4
-from multiprocessing import cpu_count
 
 from poli.core.abstract_black_box import AbstractBlackBox
 from poli.core.problem_setup_information import ProblemSetupInformation
-
+from poli.core.util.proteins.foldx import FoldxInterface
 from poli.core.util.proteins.pdb_parsing import (
     parse_pdb_as_residue_strings,
     parse_pdb_as_residues,
 )
-from poli.core.util.proteins.foldx import FoldxInterface
 
 # This is the folder where all the files
 # generated by FoldX will be stored.

src/poli/core/proteins/foldx_isolated_function.py

@@ -1,19 +1,18 @@
-from typing import Union, List
+from multiprocessing import cpu_count
 from pathlib import Path
 from time import time
+from typing import List, Union
 from uuid import uuid4
-from multiprocessing import cpu_count
 
 import numpy as np
 
 from poli.core.abstract_isolated_function import AbstractIsolatedFunction
 from poli.core.problem_setup_information import ProblemSetupInformation
-
+from poli.core.util.proteins.foldx import FoldxInterface
 from poli.core.util.proteins.pdb_parsing import (
     parse_pdb_as_residue_strings,
     parse_pdb_as_residues,
 )
-from poli.core.util.proteins.foldx import FoldxInterface
 
 # This is the folder where all the files
 # generated by FoldX will be stored.

src/poli/core/registry.py

@@ -1,21 +1,20 @@
 """This module contains utilities for registering problems and observers.
 """
 
-from typing import List, Union, Dict, Type
 import configparser
-from pathlib import Path
-import warnings
 import subprocess
+import warnings
+from pathlib import Path
+from typing import Dict, List, Type, Union
 
-from poli.core.abstract_isolated_function import AbstractIsolatedFunction
 from poli.core.abstract_black_box import AbstractBlackBox
+from poli.core.abstract_isolated_function import AbstractIsolatedFunction
 from poli.core.abstract_problem_factory import AbstractProblemFactory
-
 from poli.core.util.abstract_observer import AbstractObserver
 from poli.core.util.objective_management.make_run_script import (
-    make_run_script,
-    make_observer_script,
     make_isolated_function_script,
+    make_observer_script,
+    make_run_script,
 )
 
 # from poli.objective_repository import AVAILABLE_PROBLEM_FACTORIES, AVAILABLE_OBJECTIVES

src/poli/core/util/batch/batch_input.py

@@ -1,7 +1,7 @@
 """This module implements a batched input generator."""
 
-from typing import Iterable
 from itertools import islice
+from typing import Iterable
 
 
 def batched(iterable: Iterable, chunk_size: int):

src/poli/core/util/chemistry/string_to_molecule.py

@@ -4,9 +4,8 @@
 
 from typing import List
 
-from rdkit import Chem
-
 import selfies as sf
+from rdkit import Chem
 
 
 def translate_smiles_to_selfies(