hydraflow 0.7.4__tar.gz → 0.7.5__tar.gz

{hydraflow-0.7.4 → hydraflow-0.7.5}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: hydraflow
-Version: 0.7.4
+Version: 0.7.5
 Summary: Hydraflow integrates Hydra and MLflow to manage and track machine learning experiments.
 Project-URL: Documentation, https://daizutabi.github.io/hydraflow/
 Project-URL: Source, https://github.com/daizutabi/hydraflow
@@ -55,7 +55,7 @@ Description-Content-Type: text/markdown
 [pypi-v-link]: https://pypi.org/project/hydraflow/
 [python-v-image]: https://img.shields.io/pypi/pyversions/hydraflow.svg
 [python-v-link]: https://pypi.org/project/hydraflow
-[GHAction-image]: https://github.com/daizutabi/hydraflow/actions/workflows/ci.yml/badge.svg?branch=main&event=push
+[GHAction-image]: https://github.com/daizutabi/hydraflow/actions/workflows/ci.yaml/badge.svg?branch=main&event=push
 [GHAction-link]: https://github.com/daizutabi/hydraflow/actions?query=event%3Apush+branch%3Amain
 [codecov-image]: https://codecov.io/github/daizutabi/hydraflow/coverage.svg?branch=main
 [codecov-link]: https://codecov.io/github/daizutabi/hydraflow?branch=main

{hydraflow-0.7.4 → hydraflow-0.7.5}/README.md

@@ -10,7 +10,7 @@
 [pypi-v-link]: https://pypi.org/project/hydraflow/
 [python-v-image]: https://img.shields.io/pypi/pyversions/hydraflow.svg
 [python-v-link]: https://pypi.org/project/hydraflow
-[GHAction-image]: https://github.com/daizutabi/hydraflow/actions/workflows/ci.yml/badge.svg?branch=main&event=push
+[GHAction-image]: https://github.com/daizutabi/hydraflow/actions/workflows/ci.yaml/badge.svg?branch=main&event=push
 [GHAction-link]: https://github.com/daizutabi/hydraflow/actions?query=event%3Apush+branch%3Amain
 [codecov-image]: https://codecov.io/github/daizutabi/hydraflow/coverage.svg?branch=main
 [codecov-link]: https://codecov.io/github/daizutabi/hydraflow?branch=main

{hydraflow-0.7.4 → hydraflow-0.7.5}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "hydraflow"
-version = "0.7.4"
+version = "0.7.5"
 description = "Hydraflow integrates Hydra and MLflow to manage and track machine learning experiments."
 readme = "README.md"
 license = { file = "LICENSE" }

{hydraflow-0.7.4 → hydraflow-0.7.5}/src/hydraflow/__init__.py

@@ -3,7 +3,13 @@
 from hydraflow.config import select_config, select_overrides
 from hydraflow.context import chdir_artifact, log_run, start_run
 from hydraflow.main import main
-from hydraflow.mlflow import list_runs, search_runs, set_experiment
+from hydraflow.mlflow import (
+    list_run_ids,
+    list_run_paths,
+    list_runs,
+    search_runs,
+    set_experiment,
+)
 from hydraflow.run_collection import RunCollection
 from hydraflow.utils import (
     get_artifact_dir,
@@ -22,6 +28,8 @@ __all__ = [
     "get_artifact_path",
     "get_hydra_output_dir",
     "get_overrides",
+    "list_run_ids",
+    "list_run_paths",
     "list_runs",
     "load_config",
     "load_overrides",

{hydraflow-0.7.4 → hydraflow-0.7.5}/src/hydraflow/mlflow.py

@@ -153,18 +153,17 @@ def search_runs(  # noqa: PLR0913
     return RunCollection(runs)  # type: ignore
 
 
-def list_runs(
+def list_run_paths(
     experiment_names: str | list[str] | None = None,
-    n_jobs: int = 0,
-    status: str | list[str] | int | list[int] | None = None,
-) -> RunCollection:
-    """List all runs for the specified experiments.
+    *other: str,
+) -> list[Path]:
+    """List all run paths for the specified experiments.
 
-    This function retrieves all runs for the given list of experiment names.
+    This function retrieves all run paths for the given list of experiment names.
     If no experiment names are provided (None), it defaults to searching all runs
     for the currently active experiment. If an empty list is provided, the function
     will search all runs for all experiments except the "Default" experiment.
-    The function returns the results as a `RunCollection` object.
+    The function returns the results as a list of `Path` objects.
 
     Note:
         The returned runs are sorted by their start time in ascending order.
@@ -174,27 +173,12 @@ def list_runs(
             for runs. If None or an empty list is provided, the function will
             search the currently active experiment or all experiments except
             the "Default" experiment.
-        n_jobs (int): The number of jobs to run in parallel. If 0, the function
-            will search runs sequentially.
-        status (str | list[str] | int | list[int] | None): The status of the runs
-            to filter.
+        other (str): The parts of the run directory to join.
 
     Returns:
-        RunCollection: A `RunCollection` instance containing the runs for the
-        specified experiments.
+        list[Path]: A list of run paths for the specified experiments.
 
     """
-    rc = _list_runs(experiment_names, n_jobs)
-    if status is None:
-        return rc
-
-    return rc.filter(status=status)
-
-
-def _list_runs(
-    experiment_names: str | list[str] | None = None,
-    n_jobs: int = 0,
-) -> RunCollection:
     if isinstance(experiment_names, str):
         experiment_names = [experiment_names]
 
@@ -202,14 +186,11 @@ def _list_runs(
         experiments = mlflow.search_experiments()
         experiment_names = [e.name for e in experiments if e.name != "Default"]
 
-    if n_jobs == 0:
-        return search_runs(experiment_names=experiment_names)
-
     if experiment_names is None:
         experiment_id = _get_experiment_id()
         experiment_names = [mlflow.get_experiment(experiment_id).name]
 
-    run_ids = []
+    run_paths: list[Path] = []
 
     for name in experiment_names:
         if experiment := mlflow.get_experiment_by_name(name):
@@ -217,9 +198,83 @@ def _list_runs(
 
             if isinstance(uri, str):
                 path = get_artifact_dir(uri=uri)
-                run_ids.extend(file.stem for file in path.iterdir() if file.is_dir())
+                run_paths.extend(p for p in path.iterdir() if p.is_dir())
+
+    if other:
+        return [p.joinpath(*other) for p in run_paths]
+
+    return run_paths
+
+
+def list_run_ids(experiment_names: str | list[str] | None = None) -> list[str]:
+    """List all run IDs for the specified experiments.
+
+    This function retrieves all runs for the given list of experiment names.
+    If no experiment names are provided (None), it defaults to searching all runs
+    for the currently active experiment. If an empty list is provided, the function
+    will search all runs for all experiments except the "Default" experiment.
+    The function returns the results as a list of string.
+
+    Note:
+        The returned runs are sorted by their start time in ascending order.
+
+    Args:
+        experiment_names (list[str] | None): List of experiment names to search
+            for runs. If None or an empty list is provided, the function will
+            search the currently active experiment or all experiments except
+            the "Default" experiment.
+
+    Returns:
+        list[str]: A list of run IDs for the specified experiments.
+
+    """
+    return [run_dir.stem for run_dir in list_run_paths(experiment_names)]
+
+
+def list_runs(
+    experiment_names: str | list[str] | None = None,
+    n_jobs: int = 0,
+    status: str | list[str] | int | list[int] | None = None,
+) -> RunCollection:
+    """List all runs for the specified experiments.
+
+    This function retrieves all runs for the given list of experiment names.
+    If no experiment names are provided (None), it defaults to searching all runs
+    for the currently active experiment. If an empty list is provided, the function
+    will search all runs for all experiments except the "Default" experiment.
+    The function returns the results as a `RunCollection` object.
+
+    Note:
+        The returned runs are sorted by their start time in ascending order.
+
+    Args:
+        experiment_names (list[str] | None): List of experiment names to search
+            for runs. If None or an empty list is provided, the function will
+            search the currently active experiment or all experiments except
+            the "Default" experiment.
+        n_jobs (int): The number of jobs to run in parallel. If 0, the function
+            will search runs sequentially.
+        status (str | list[str] | int | list[int] | None): The status of the runs
+            to filter.
+
+    Returns:
+        RunCollection: A `RunCollection` instance containing the runs for the
+        specified experiments.
+
+    """
+    run_ids = list_run_ids(experiment_names)
+
+    if n_jobs == 0:
+        runs = [mlflow.get_run(run_id) for run_id in run_ids]
+
+    else:
+        it = (joblib.delayed(mlflow.get_run)(run_id) for run_id in run_ids)
+        runs = joblib.Parallel(n_jobs, prefer="threads")(it)
 
-    it = (joblib.delayed(mlflow.get_run)(run_id) for run_id in run_ids)
-    runs = joblib.Parallel(n_jobs, prefer="threads")(it)
     runs = sorted(runs, key=lambda run: run.info.start_time)  # type: ignore
-    return RunCollection(runs)  # type: ignore
+    rc = RunCollection(runs)  # type: ignore
+
+    if status is None:
+        return rc
+
+    return rc.filter(status=status)

{hydraflow-0.7.4 → hydraflow-0.7.5}/tests/test_mlflow.py

@@ -92,3 +92,10 @@ def test_list_runs(experiment: Experiment, status, n, n_jobs, func):
     experiment_names = func(experiment.name)
     rc = list_runs(experiment_names=experiment_names, status=status, n_jobs=n_jobs)
     assert len(rc) == n
+
+
+def test_list_run_dirs(experiment: Experiment):
+    from hydraflow.mlflow import list_run_paths
+
+    dirs = list_run_paths(experiment.name, "artifacts")
+    assert all(d.is_dir() for d in dirs)