hydraflow 0.2.4__py3-none-any.whl → 0.2.6__py3-none-any.whl

hydraflow/progress.py

@@ -0,0 +1,56 @@
+from __future__ import annotations
+
+from typing import TYPE_CHECKING
+
+import joblib
+from rich.progress import Progress, SpinnerColumn, TimeElapsedColumn
+
+if TYPE_CHECKING:
+    from collections.abc import Iterable
+
+
+def progress(
+    *iterables: Iterable[int | tuple[int, int]],
+    n_jobs: int = -1,
+    task_name: str = "#{:0>3}",
+    main_task_name: str = "main",
+) -> None:
+    with Progress(
+        SpinnerColumn(),
+        *Progress.get_default_columns(),
+        TimeElapsedColumn(),
+    ) as progress:
+        n = len(iterables)
+
+        task_main = progress.add_task(main_task_name, total=None) if n > 1 else None
+        tasks = [progress.add_task(task_name.format(i), start=False, total=None) for i in range(n)]
+
+        total = {}
+        completed = {}
+
+        def func(i: int) -> None:
+            completed[i] = 0
+            total[i] = None
+            progress.start_task(tasks[i])
+
+            for index in iterables[i]:
+                if isinstance(index, tuple):
+                    completed[i], total[i] = index[0] + 1, index[1]
+                else:
+                    completed[i] = index + 1
+
+                progress.update(tasks[i], total=total[i], completed=completed[i])
+                if task_main is not None:
+                    if all(t is not None for t in total.values()):
+                        t = sum(total.values())
+                    else:
+                        t = None
+                    c = sum(completed.values())
+                    progress.update(task_main, total=t, completed=c)
+
+        if n > 1:
+            it = (joblib.delayed(func)(i) for i in range(n))
+            joblib.Parallel(n_jobs, prefer="threads")(it)
+
+        else:
+            func(0)

hydraflow/runs.py

@@ -51,13 +51,6 @@ def search_runs(
             error if ``experiment_names`` is also not ``None`` or ``[]``.
             ``None`` will default to the active experiment if ``experiment_names``
             is ``None`` or ``[]``.
-        experiment_ids (list[str] | None): List of experiment IDs. Search can
-            work with experiment IDs or experiment names, but not both in the
-            same call. Values other than ``None`` or ``[]`` will result in
-            error if ``experiment_names`` is also not ``None`` or ``[]``.
-            ``experiment_names`` is also not ``None`` or ``[]``. ``None`` will
-            default to the active experiment if ``experiment_names`` is ``None``
-            or ``[]``.
         filter_string (str): Filter query string, defaults to searching all
             runs.
         run_view_type (int): one of enum values ``ACTIVE_ONLY``, ``DELETED_ONLY``,
@@ -501,6 +494,31 @@ class RunCollection:
         """
         return (func(download_artifacts(run_id=run.info.run_id)) for run in self._runs)
 
+    def group_by(self, *names: str | list[str]) -> dict[tuple[str | None, ...], RunCollection]:
+        """
+        Group runs by specified parameter names.
+
+        This method groups the runs in the collection based on the values of the
+        specified parameters. Each unique combination of parameter values will
+        form a key in the returned dictionary.
+
+        Args:
+            *names (str | list[str]): The names of the parameters to group by.
+                This can be a single parameter name or multiple names provided
+                as separate arguments or as a list.
+
+        Returns:
+            dict[tuple[str | None, ...], RunCollection]: A dictionary where the keys
+            are tuples of parameter values and the values are RunCollection objects
+            containing the runs that match those parameter values.
+        """
+        grouped_runs: dict[tuple[str | None, ...], list[Run]] = {}
+        for run in self._runs:
+            key = get_params(run, *names)
+            grouped_runs.setdefault(key, []).append(run)
+
+        return {key: RunCollection(runs) for key, runs in grouped_runs.items()}
+
 
 def _param_matches(run: Run, key: str, value: Any) -> bool:
     """
@@ -765,6 +783,34 @@ def try_get_run(runs: list[Run], config: object | None = None, **kwargs) -> Run
     raise ValueError(msg)
 
 
+def get_params(run: Run, *names: str | list[str]) -> tuple[str | None, ...]:
+    """
+    Retrieve the values of specified parameters from the given run.
+
+    This function extracts the values of the parameters identified by the
+    provided names from the specified run. It can accept both individual
+    parameter names and lists of parameter names.
+
+    Args:
+        run (Run): The run object from which to extract parameter values.
+        *names (str | list[str]): The names of the parameters to retrieve.
+            This can be a single parameter name or multiple names provided
+            as separate arguments or as a list.
+
+    Returns:
+        tuple[str | None, ...]: A tuple containing the values of the specified
+        parameters in the order they were provided.
+    """
+    names_ = []
+    for name in names:
+        if isinstance(name, list):
+            names_.extend(name)
+        else:
+            names_.append(name)
+
+    return tuple(run.data.params.get(name) for name in names_)
+
+
 def get_param_names(runs: list[Run]) -> list[str]:
     """
     Get the parameter names from the runs.

{hydraflow-0.2.4.dist-info → hydraflow-0.2.6.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: hydraflow
-Version: 0.2.4
+Version: 0.2.6
 Summary: Hydraflow integrates Hydra and MLflow to manage and track machine learning experiments.
 Project-URL: Documentation, https://github.com/daizutabi/hydraflow
 Project-URL: Source, https://github.com/daizutabi/hydraflow
@@ -17,7 +17,9 @@ Classifier: Topic :: Documentation
 Classifier: Topic :: Software Development :: Documentation
 Requires-Python: >=3.10
 Requires-Dist: hydra-core>1.3
+Requires-Dist: joblib
 Requires-Dist: mlflow>2.15
+Requires-Dist: rich
 Requires-Dist: setuptools
 Requires-Dist: watchdog
 Requires-Dist: watchfiles
@@ -48,7 +50,7 @@ Description-Content-Type: text/markdown
 
 ## Overview
 
-Hydraflow is a powerful library designed to seamlessly integrate
+Hydraflow is a library designed to seamlessly integrate
 [Hydra](https://hydra.cc/) and [MLflow](https://mlflow.org/), making it easier to
 manage and track machine learning experiments. By combining the flexibility of
 Hydra's configuration management with the robust experiment tracking capabilities

{hydraflow-0.2.4.dist-info → hydraflow-0.2.6.dist-info}/RECORD

@@ -3,8 +3,9 @@ hydraflow/asyncio.py,sha256=yh851L315QHzRBwq6r-uwO2oZKgz1JawHp-fswfxT1E,6175
 hydraflow/config.py,sha256=6TCKNQZ3sSrIEvl245T2udwFuknejyN1dMcIVmOHdrQ,2102
 hydraflow/context.py,sha256=8Qn99yCSkCarDDthQ6hjgW80CBBIg0H7fnLvtw4ZXo8,7248
 hydraflow/mlflow.py,sha256=gGr0fvFEllduA-ByHMeEamM39zVY_30tjtEbkSZ4lHA,3659
-hydraflow/runs.py,sha256=0t2xhjV9DMA1CNDzBYrsHiZrDZ6cNsaSTxi0ikf6k8c,29907
-hydraflow-0.2.4.dist-info/METADATA,sha256=Rw8m1Ir6Lio6jja44oPHnSMdlLbK2KtZ46UQRD38Lq8,4148
-hydraflow-0.2.4.dist-info/WHEEL,sha256=1yFddiXMmvYK7QYTqtRNtX66WJ0Mz8PYEiEUoOUUxRY,87
-hydraflow-0.2.4.dist-info/licenses/LICENSE,sha256=IGdDrBPqz1O0v_UwCW-NJlbX9Hy9b3uJ11t28y2srmY,1062
-hydraflow-0.2.4.dist-info/RECORD,,
+hydraflow/progress.py,sha256=dReFp-AfBuYpjGQnqRmkwPcoyFfe2WCgkklXuo9ZjNg,1709
+hydraflow/runs.py,sha256=TETX54OVJPJLi6rjpNcsXAhXH2Q9unhjXhGkOtFtHng,31559
+hydraflow-0.2.6.dist-info/METADATA,sha256=yOEx7M9jM5M7MNkLOZShO-DexNqXzIHjSkqbxcNMHQ0,4181
+hydraflow-0.2.6.dist-info/WHEEL,sha256=1yFddiXMmvYK7QYTqtRNtX66WJ0Mz8PYEiEUoOUUxRY,87
+hydraflow-0.2.6.dist-info/licenses/LICENSE,sha256=IGdDrBPqz1O0v_UwCW-NJlbX9Hy9b3uJ11t28y2srmY,1062
+hydraflow-0.2.6.dist-info/RECORD,,