[pre-commit.ci] pre-commit autoupdate (#188)

* [pre-commit.ci] pre-commit autoupdate

updates:
- [github.com/astral-sh/ruff-pre-commit: v0.1.3 → v0.2.1](astral-sh/ruff-pre-commit@v0.1.3...v0.2.1)
- [github.com/pre-commit/mirrors-mypy: v1.6.1 → v1.8.0](pre-commit/mirrors-mypy@v1.6.1...v1.8.0)

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* Fix type

* format

* fi

---------

Co-authored-by: Bas Nijholt <[email protected]>

Author: pre-commit-ci[bot]

.pre-commit-config.yaml

@@ -9,14 +9,14 @@ repos:
       - id: debug-statements
       - id: check-ast
   - repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: "v0.1.3"
+    rev: "v0.2.1"
     hooks:
       - id: ruff
         exclude: docs/source/conf.py|ipynb_filter.py
         args: ["--fix"]
       - id: ruff-format
   - repo: https://github.com/pre-commit/mirrors-mypy
-    rev: "v1.6.1"
+    rev: "v1.8.0"
     hooks:
       - id: mypy
         exclude: ipynb_filter.py|docs/source/conf.py

adaptive_scheduler/_mock_scheduler.py

@@ -53,6 +53,7 @@ class MockScheduler:
         ``bash`` executable.
     url
         The URL of the socket. Defaults to {DEFAULT_URL}.
+
     """
 
     def __init__(

adaptive_scheduler/_scheduler/base_scheduler.py

@@ -59,6 +59,7 @@ class BaseScheduler(abc.ABC):
     Returns
     -------
     `BaseScheduler` object.
+
     """
 
     _ext: ClassVar[str]
@@ -113,6 +114,7 @@ def queue(self, *, me_only: bool = True) -> dict[str, dict]:
         -----
         This function might return extra information about the job, however
         this is not used elsewhere in this package.
+
         """
 
     def queue_df(self) -> pd.DataFrame:
@@ -141,6 +143,7 @@ def job_script(self, options: dict[str, Any], *, index: int | None = None) -> st
         index
             The index of the job that is being run. This is used when
             specifying different resources for different jobs.
+
         """
 
     @property
@@ -188,6 +191,7 @@ def cancel(
             Display a progress bar using `tqdm`.
         max_tries
             Maximum number of attempts to cancel a job.
+
         """
 
         def cancel_jobs(job_ids: list[str]) -> None:

adaptive_scheduler/_scheduler/local.py

@@ -88,6 +88,7 @@ def job_script(self, options: dict[str, Any], *, index: int | None = None) -> st
         Currently, there is a problem that this will not properly cleanup.
         for example `ipengine ... &` will be detached and go on,
         normally a scheduler will take care of this.
+
         """
         job_script = textwrap.dedent(
             """\

adaptive_scheduler/_scheduler/pbs.py

@@ -135,6 +135,7 @@ def job_script(self, options: dict[str, Any], *, index: int | None = None) -> st
             The index of the job that is being run. This is used when
             specifying different resources for different jobs.
             Currently not implemented for PBS!
+
         """
         job_script = textwrap.dedent(
             f"""\

adaptive_scheduler/_scheduler/slurm.py

@@ -101,6 +101,7 @@ class SLURM(BaseScheduler):
     extra_script
         Extra script that will be executed after any environment variables are set,
         but before the main scheduler is run.
+
     """
 
     # Attributes that all schedulers need to have
@@ -297,6 +298,7 @@ def job_script(self, options: dict[str, Any], *, index: int | None = None) -> st
         index
             The index of the job that is being run. This is used when
             specifying different resources for different jobs.
+
         """
         cores = self._get_cores(index=index)
         job_script = textwrap.dedent(

adaptive_scheduler/_server_support/common.py

@@ -47,6 +47,7 @@ def get_allowed_url() -> str:
     url
         An url that can be used for the database manager, with the format
         ``tcp://ip_of_this_machine:allowed_port.``.
+
     """
     ip = socket.gethostbyname(socket.gethostname())
     port = zmq.ssh.tunnel.select_random_ports(1)[0]
@@ -98,6 +99,7 @@ def cleanup_scheduler_files(
         If None the file is removed.
     log_file_folder
         The folder in which to delete the log-files.
+
     """
     to_rm = _get_all_files(job_names, scheduler)
 
@@ -162,6 +164,7 @@ def periodically_clean_ipython_profiles(
     Returns
     -------
     asyncio.Task
+
     """
 
     async def clean(interval: float) -> None:

adaptive_scheduler/_server_support/database_manager.py

@@ -84,7 +84,7 @@ def __init__(self, db_fname: str | Path, *, clear_existing: bool = False) -> Non
                     raw_data = json.load(f)
                     self._data = [_DBEntry(**entry) for entry in raw_data["data"]]
 
-    def all(self) -> list[_DBEntry]:  # noqa: A003
+    def all(self) -> list[_DBEntry]:
         return self._data
 
     def insert_multiple(self, entries: list[_DBEntry]) -> None:
@@ -152,6 +152,7 @@ class DatabaseManager(BaseManager):
     ----------
     failed : list
         A list of entries that have failed and have been removed from the database.
+
     """
 
     def __init__(
@@ -363,6 +364,7 @@ async def _manage(self) -> None:
         Returns
         -------
         coroutine
+
         """
         log.debug("started database")
         socket = ctx.socket(zmq.REP)

adaptive_scheduler/_server_support/job_manager.py

@@ -65,6 +65,7 @@ def command_line_options(
     -------
     dict
         The command line options for the job_script.
+
     """
     if runner_kwargs is None:
         runner_kwargs = {}
@@ -142,6 +143,7 @@ class JobManager(BaseManager):
     ----------
     n_started : int
         Total number of jobs started by the `JobManager`.
+
     """
 
     def __init__(

adaptive_scheduler/_server_support/kill_manager.py

@@ -40,6 +40,7 @@ def logs_with_string_or_condition(
     -------
     has_string
         A list ``(job_name, fnames)``, which have the string inside their log-file.
+
     """
     if isinstance(error, str):
         has_error = lambda lines: error in "".join(lines)  # noqa: E731
@@ -90,6 +91,7 @@ class KillManager(BaseManager):
     move_to
         If a job is cancelled the log is either removed (if ``move_to=None``)
         or moved to a folder (e.g. if ``move_to='old_logs'``).
+
     """
 
     def __init__(

adaptive_scheduler/_server_support/parse_logs.py

@@ -52,6 +52,7 @@ def parse_log_files(
     Returns
     -------
     `~pandas.core.frame.DataFrame`
+
     """
     _queue = scheduler.queue()
     database_manager.update(_queue)

adaptive_scheduler/client_support.py

@@ -77,6 +77,7 @@ def get_learner(
         The filename of the learner that was chosen.
     initializer
         A function that runs before the process is forked.
+
     """
     _add_log_file_handler(log_fname)
     log.info(
@@ -120,6 +121,7 @@ def tell_done(url: str, fname: str | list[str]) -> None:
         (`adaptive_scheduler.server_support.manage_database`).
     fname
         The filename of the learner that is done.
+
     """
     log.info("goal reached! 🎉🎊🥳")
     with ctx.socket(zmq.REQ) as socket:
@@ -173,6 +175,7 @@ def log_info(runner: AsyncRunner, interval: float = 300) -> asyncio.Task:
         Adaptive Runner instance.
     interval
         Time in seconds between log entries.
+
     """
 
     async def coro(runner: AsyncRunner, interval: float) -> None:

adaptive_scheduler/utils.py

@@ -20,6 +20,7 @@
 from contextlib import contextmanager, suppress
 from datetime import datetime, timedelta, timezone
 from inspect import signature
+from itertools import chain
 from multiprocessing import Manager
 from pathlib import Path
 from typing import (
@@ -103,6 +104,7 @@ def split(seq: Iterable, n_parts: int) -> Iterable[tuple]:
         A list or other iterable that has to be split up.
     n_parts
         The sequence will be split up in this many parts.
+
     """
     lst = list(seq)
     n = math.ceil(len(lst) / n_parts)
@@ -131,14 +133,15 @@ def split_in_balancing_learners(
     Returns
     -------
     new_learners, new_fnames
+
     """
     new_learners = []
     new_fnames = []
     for x in split(zip(learners, fnames), n_parts):
         learners_part, fnames_part = zip(*x)
         learner = adaptive.BalancingLearner(learners_part, strategy=strategy)
         new_learners.append(learner)
-        new_fnames.append(fnames_part)
+        new_fnames.append(list(fnames_part))
     return new_learners, new_fnames
 
 
@@ -169,6 +172,7 @@ def split_sequence_learner(
         List of `~adaptive.SequenceLearner`\s.
     new_fnames
         List of str based on a hash of the sequence.
+
     """
     new_learners, new_fnames = split_sequence_in_sequence_learners(
         function=big_learner._original_function,
@@ -214,6 +218,7 @@ def split_sequence_in_sequence_learners(
         List of `~adaptive.SequenceLearner`\s.
     new_fnames
         List of str based on a hash of the sequence.
+
     """
     folder = Path(folder)
     new_learners = []
@@ -248,11 +253,11 @@ def combine_sequence_learners(
     -------
     adaptive.SequenceLearner
         Big `~adaptive.SequenceLearner` with data from ``learners``.
+
     """
     if big_learner is None:
-        big_sequence: list[Any] = sum(
-            (list(learner.sequence) for learner in learners),
-            [],
+        big_sequence: list[Any] = list(
+            chain.from_iterable(learner.sequence for learner in learners),
         )
         big_learner = adaptive.SequenceLearner(
             learners[0]._original_function,
@@ -282,6 +287,7 @@ def copy_from_sequence_learner(
         Learner to take the data from.
     learner_to
         Learner to tell the data to.
+
     """
     mapping = {
         hash_anything(learner_from.sequence[i]): v for i, v in learner_from.data.items()
@@ -420,6 +426,7 @@ def _remove_or_move_files(
         If None the file is removed.
     desc
         Description of the progressbar.
+
     """
     n_failed = 0
     for fname in _progress(fnames, with_progress_bar, desc or "Removing files"):
@@ -463,6 +470,7 @@ def load_parallel(
     max_workers
         The maximum number of parallel threads when loading the data.
         If ``None``, use the maximum number of threads that is possible.
+
     """
 
     def load(learner: adaptive.BaseLearner, fname: str) -> None:
@@ -492,6 +500,7 @@ def save_parallel(
         A list of filenames corresponding to `learners`.
     with_progress_bar
         Display a progress bar using `tqdm`.
+
     """
 
     def save(learner: adaptive.BaseLearner, fname: str) -> None:
@@ -562,6 +571,7 @@ def connect_to_ipyparallel(
     -------
     client
         An IPyparallel client.
+
     """
     from ipyparallel import Client
 
@@ -623,6 +633,7 @@ class LRUCachedCallable:
         Cache size of the LRU cache, by default 128.
     with_cloudpickle
         Use cloudpickle for storing the data in memory.
+
     """
 
     def __init__(
@@ -1015,6 +1026,7 @@ def smart_goal(
     Returns
     -------
     Callable[[adaptive.BaseLearner], bool]
+
     """
     if callable(goal):
         return goal
@@ -1083,6 +1095,7 @@ class WrappedFunction:
     >>> wrapped_function = WrappedFunction(square)
     >>> wrapped_function(4)
     16
+
     """
 
     def __init__(
@@ -1132,6 +1145,7 @@ def __call__(self, *args: Any, **kwargs: Any) -> Any:
         Any
             The result of calling the deserialized function with the provided
             arguments and keyword arguments.
+
         """
         global _GLOBAL_CACHE  # noqa: PLW0602
 
@@ -1258,6 +1272,7 @@ async def _track_file_creation_progress(
         The time interval (in seconds) at which to update the progress. The interval is dynamically
         adjusted to be at least 50 times the time it takes to update the progress. This ensures that
         updating the progress does not take up a significant amount of time.
+
     """
     # create total_files and add_total_progress before updating paths_dict
     total_files = sum(len(paths) for paths in paths_dict.values())
@@ -1348,6 +1363,7 @@ def track_file_creation_progress(
         "example2": {Path("/path/to/file3"), Path("/path/to/file4")},
     }
     >>> task = track_file_creation_progress(paths_dict)
+
     """
     get_console().clear_live()  # avoid LiveError, only 1 live render allowed at a time
     columns = (*Progress.get_default_columns(), TimeElapsedColumn())

pyproject.toml

@@ -112,6 +112,8 @@ exclude_lines = [
 [tool.ruff]
 line-length = 88
 target-version = "py38"
+
+[tool.ruff.lint]
 select = ["ALL"]
 ignore = [
     "T20",     # flake8-print
@@ -132,12 +134,12 @@ ignore = [
     "E501",    # Line too long
 ]
 
-[tool.ruff.per-file-ignores]
+[tool.ruff.lint.per-file-ignores]
 "tests/*" = ["SLF001", "PLR2004"]
 "tests/test_examples.py" = ["E501"]
 ".github/*" = ["INP001"]
 
-[tool.ruff.mccabe]
+[tool.ruff.lint.mccabe]
 max-complexity = 18
 
 [tool.mypy]

tests/test_utils.py

@@ -60,7 +60,7 @@ def test_split_in_balancing_learners(
     )
     assert len(new_learners) == n_parts
     assert all(isinstance(lrn, adaptive.BalancingLearner) for lrn in new_learners)
-    assert new_fnames == [(fnames[0],), (fnames[1],)]
+    assert new_fnames == [[fnames[0]], [fnames[1]]]
 
 
 def test_split_sequence_learner() -> None: