hydraflow 0.2.18__py3-none-any.whl → 0.3.0__py3-none-any.whl

hydraflow/__init__.py

@@ -1,5 +1,6 @@
+"""Provide a collection of MLflow runs."""
+
 from .context import chdir_artifact, log_run, start_run, watch
-from .info import get_artifact_dir, get_hydra_output_dir, load_config
 from .mlflow import (
     list_runs,
     search_runs,
@@ -7,6 +8,8 @@ from .mlflow import (
 )
 from .progress import multi_tasks_progress, parallel_progress
 from .run_collection import RunCollection
+from .run_data import load_config
+from .run_info import get_artifact_dir, get_hydra_output_dir
 
 __all__ = [
     "RunCollection",

hydraflow/config.py

@@ -11,6 +11,20 @@ if TYPE_CHECKING:
     from typing import Any
 
 
+def collect_params(config: object) -> dict[str, Any]:
+    """Iterate over parameters and collect them into a dictionary.
+
+    Args:
+        config (object): The configuration object to iterate over.
+        prefix (str): The prefix to prepend to the parameter keys.
+
+    Returns:
+        dict[str, Any]: A dictionary of collected parameters.
+
+    """
+    return dict(iter_params(config))
+
+
 def iter_params(config: object, prefix: str = "") -> Iterator[tuple[str, Any]]:
     """Recursively iterate over the parameters in the given configuration object.
 

hydraflow/context.py

@@ -14,8 +14,8 @@ from hydra.core.hydra_config import HydraConfig
 from watchdog.events import FileModifiedEvent, PatternMatchingEventHandler
 from watchdog.observers import Observer
 
-from hydraflow.info import get_artifact_dir
 from hydraflow.mlflow import log_params
+from hydraflow.run_info import get_artifact_dir
 
 if TYPE_CHECKING:
     from collections.abc import Callable, Iterator

hydraflow/run_collection.py

@@ -24,10 +24,12 @@ from itertools import chain
 from typing import TYPE_CHECKING, Any, Concatenate, ParamSpec, TypeVar, overload
 
 from mlflow.entities import RunStatus
+from polars.dataframe import DataFrame
 
 import hydraflow.param
-from hydraflow.config import iter_params
-from hydraflow.info import RunCollectionInfo
+from hydraflow.config import collect_params, iter_params
+from hydraflow.run_data import RunCollectionData
+from hydraflow.run_info import RunCollectionInfo
 
 if TYPE_CHECKING:
     from collections.abc import Callable, Iterator
@@ -61,8 +63,12 @@ class RunCollection:
     _info: RunCollectionInfo = field(init=False)
     """An instance of `RunCollectionInfo`."""
 
+    _data: RunCollectionData = field(init=False)
+    """An instance of `RunCollectionData`."""
+
     def __post_init__(self) -> None:
         self._info = RunCollectionInfo(self)
+        self._data = RunCollectionData(self)
 
     def __repr__(self) -> str:
         return f"{self.__class__.__name__}({len(self)})"
@@ -101,6 +107,11 @@ class RunCollection:
         """An instance of `RunCollectionInfo`."""
         return self._info
 
+    @property
+    def data(self) -> RunCollectionData:
+        """An instance of `RunCollectionData`."""
+        return self._data
+
     def take(self, n: int) -> RunCollection:
         """Take the first n runs from the collection.
 
@@ -371,7 +382,7 @@ class RunCollection:
             raise ValueError(msg)
 
     def try_get(self, config: object | None = None, **kwargs) -> Run | None:
-        """Try to retrieve a specific `Run` instance based on the provided config.
+        """Try to get a specific `Run` instance based on the provided configuration.
 
         This method filters the runs in the collection according to the
         specified configuration object and returns the run that matches the
@@ -505,7 +516,7 @@ class RunCollection:
             in the collection.
 
         """
-        return (func(config, *args, **kwargs) for config in self.info.config)
+        return (func(config, *args, **kwargs) for config in self.data.config)
 
     def map_uri(
         self,
@@ -584,6 +595,16 @@ class RunCollection:
 
         return {key: RunCollection(runs) for key, runs in grouped_runs.items()}
 
+    @property
+    def config(self) -> DataFrame:
+        """Get the runs' configurations as a polars DataFrame.
+
+        Returns:
+            A polars DataFrame containing the runs' configurations.
+
+        """
+        return DataFrame(self.map_config(collect_params))
+
 
 def _param_matches(run: Run, key: str, value: Any) -> bool:
     params = run.data.params
@@ -634,8 +655,10 @@ def filter_runs(
     """
     for key, value in chain(iter_params(config), kwargs.items()):
         runs = [run for run in runs if _param_matches(run, key, value)]
+        if not runs:
+            return []
 
-    if len(runs) == 0 or status is None:
+    if status is None:
         return runs
 
     return filter_runs_by_status(runs, status)

hydraflow/run_data.py

@@ -0,0 +1,56 @@
+"""Provide information about MLflow runs."""
+
+from __future__ import annotations
+
+from typing import TYPE_CHECKING
+
+from omegaconf import DictConfig, OmegaConf
+
+from hydraflow.run_info import get_artifact_dir
+
+if TYPE_CHECKING:
+    from mlflow.entities import Run
+
+    from hydraflow.run_collection import RunCollection
+
+
+class RunCollectionData:
+    """Provide information about MLflow runs."""
+
+    def __init__(self, runs: RunCollection) -> None:
+        self._runs = runs
+
+    @property
+    def params(self) -> list[dict[str, str]]:
+        """Get the parameters for each run in the collection."""
+        return [run.data.params for run in self._runs]
+
+    @property
+    def metrics(self) -> list[dict[str, float]]:
+        """Get the metrics for each run in the collection."""
+        return [run.data.metrics for run in self._runs]
+
+    @property
+    def config(self) -> list[DictConfig]:
+        """Get the configuration for each run in the collection."""
+        return [load_config(run) for run in self._runs]
+
+
+def load_config(run: Run) -> DictConfig:
+    """Load the configuration for a given run.
+
+    This function loads the configuration for the provided Run instance
+    by downloading the configuration file from the MLflow artifacts and
+    loading it using OmegaConf. It returns an empty config if
+    `.hydra/config.yaml` is not found in the run's artifact directory.
+
+    Args:
+        run (Run): The Run instance for which to load the configuration.
+
+    Returns:
+        The loaded configuration as a DictConfig object. Returns an empty
+        DictConfig if the configuration file is not found.
+
+    """
+    path = get_artifact_dir(run) / ".hydra/config.yaml"
+    return OmegaConf.load(path)  # type: ignore

hydraflow/{info.py → run_info.py}

@@ -8,7 +8,7 @@ from typing import TYPE_CHECKING
 import mlflow
 from hydra.core.hydra_config import HydraConfig
 from mlflow.tracking import artifact_utils
-from omegaconf import DictConfig, OmegaConf
+from omegaconf import OmegaConf
 
 if TYPE_CHECKING:
     from mlflow.entities import Run
@@ -27,16 +27,6 @@ class RunCollectionInfo:
         """Get the run ID for each run in the collection."""
         return [run.info.run_id for run in self._runs]
 
-    @property
-    def params(self) -> list[dict[str, str]]:
-        """Get the parameters for each run in the collection."""
-        return [run.data.params for run in self._runs]
-
-    @property
-    def metrics(self) -> list[dict[str, float]]:
-        """Get the metrics for each run in the collection."""
-        return [run.data.metrics for run in self._runs]
-
     @property
     def artifact_uri(self) -> list[str | None]:
         """Get the artifact URI for each run in the collection."""
@@ -47,11 +37,6 @@ class RunCollectionInfo:
         """Get the artifact directory for each run in the collection."""
         return [get_artifact_dir(run) for run in self._runs]
 
-    @property
-    def config(self) -> list[DictConfig]:
-        """Get the configuration for each run in the collection."""
-        return [load_config(run) for run in self._runs]
-
 
 def get_artifact_dir(run: Run | None = None) -> Path:
     """Retrieve the artifact directory for the given run.
@@ -104,23 +89,3 @@ def get_hydra_output_dir(run: Run | None = None) -> Path:
         return Path(hc.hydra.runtime.output_dir)
 
     raise FileNotFoundError
-
-
-def load_config(run: Run) -> DictConfig:
-    """Load the configuration for a given run.
-
-    This function loads the configuration for the provided Run instance
-    by downloading the configuration file from the MLflow artifacts and
-    loading it using OmegaConf. It returns an empty config if
-    `.hydra/config.yaml` is not found in the run's artifact directory.
-
-    Args:
-        run (Run): The Run instance for which to load the configuration.
-
-    Returns:
-        The loaded configuration as a DictConfig object. Returns an empty
-        DictConfig if the configuration file is not found.
-
-    """
-    path = get_artifact_dir(run) / ".hydra/config.yaml"
-    return OmegaConf.load(path)  # type: ignore

{hydraflow-0.2.18.dist-info → hydraflow-0.3.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: hydraflow
-Version: 0.2.18
+Version: 0.3.0
 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
@@ -17,6 +17,7 @@ Requires-Python: >=3.10
 Requires-Dist: hydra-core>=1.3
 Requires-Dist: joblib
 Requires-Dist: mlflow>=2.15
+Requires-Dist: polars
 Requires-Dist: rich
 Requires-Dist: watchdog
 Requires-Dist: watchfiles

hydraflow-0.3.0.dist-info/RECORD

@@ -0,0 +1,15 @@
+hydraflow/__init__.py,sha256=zlLTztJPXyBFJC5Z8G7_OnlfzAHJPRrfE1c2OoDvlTg,667
+hydraflow/asyncio.py,sha256=-i1C8KAmNDImrjHnk92Csaa1mpjdK8Vp4ZVaQV-l94s,6634
+hydraflow/config.py,sha256=Wx7jymwLVr5EfpzXBpvv3Ax3VhGhvWyA7Yy6EzsPYWk,2479
+hydraflow/context.py,sha256=IaDy-ZCdCfWwv95S-gyQNp062oBdtSVaz6dxGmO6Y8w,8226
+hydraflow/mlflow.py,sha256=GkOr_pXfpfY5USYBLrCigHcP13VgrAK_e9kheR1Wke4,8579
+hydraflow/param.py,sha256=dvIXcKgc_MPiju3WEk9qz5FOUeK5qSj-YWN2ophCpUM,1938
+hydraflow/progress.py,sha256=zvKX1HCN8_xDOsgYOEcLLhkhdPdep-U8vHrc0XZ-6SQ,6163
+hydraflow/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+hydraflow/run_collection.py,sha256=Xv6-KD5ac-vv-4Q3PZrzJy1x84H_g7UoP7ZqZ8_DQeQ,24973
+hydraflow/run_data.py,sha256=HgXGjV5oN6VxOAhrFRjubWz5ZiRqT1a2VdS5OcH2UQQ,1732
+hydraflow/run_info.py,sha256=4QrTmyPEQ_PVn7JKXJIa9NkXGAdqh8k5Sue1ggQS5aQ,2678
+hydraflow-0.3.0.dist-info/METADATA,sha256=DmC1Yjwuc3snUQiePCr5xvdtbfIevOapiA2sg8w6Aho,3840
+hydraflow-0.3.0.dist-info/WHEEL,sha256=1yFddiXMmvYK7QYTqtRNtX66WJ0Mz8PYEiEUoOUUxRY,87
+hydraflow-0.3.0.dist-info/licenses/LICENSE,sha256=IGdDrBPqz1O0v_UwCW-NJlbX9Hy9b3uJ11t28y2srmY,1062
+hydraflow-0.3.0.dist-info/RECORD,,

hydraflow-0.2.18.dist-info/RECORD

@@ -1,14 +0,0 @@
-hydraflow/__init__.py,sha256=B7rWSiGP5WwWjijcb41Bv9uuo5MQ6gbBbVWGAWYtK-k,598
-hydraflow/asyncio.py,sha256=-i1C8KAmNDImrjHnk92Csaa1mpjdK8Vp4ZVaQV-l94s,6634
-hydraflow/config.py,sha256=sBaEYPMAGSIOc_wdDsWm0k4y3AZyWIET8gqa_o95SDA,2089
-hydraflow/context.py,sha256=ih_jnexaHoToNq1dZ6sBzhJWFluPiQluOlYTYOzNEgk,8222
-hydraflow/info.py,sha256=Vzyz9dEWcU9ovRG3JWshxIazzod1cZoHF74bHhHL3AI,3946
-hydraflow/mlflow.py,sha256=GkOr_pXfpfY5USYBLrCigHcP13VgrAK_e9kheR1Wke4,8579
-hydraflow/param.py,sha256=dvIXcKgc_MPiju3WEk9qz5FOUeK5qSj-YWN2ophCpUM,1938
-hydraflow/progress.py,sha256=zvKX1HCN8_xDOsgYOEcLLhkhdPdep-U8vHrc0XZ-6SQ,6163
-hydraflow/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-hydraflow/run_collection.py,sha256=gsseBQ6a2YolNanISgEgkjei7o9U6ZGV-Tk50UYH850,24295
-hydraflow-0.2.18.dist-info/METADATA,sha256=roL3lGtlIibF6rHbCp4aXrCphhq-OkNe0JwLxM1xtBY,3819
-hydraflow-0.2.18.dist-info/WHEEL,sha256=1yFddiXMmvYK7QYTqtRNtX66WJ0Mz8PYEiEUoOUUxRY,87
-hydraflow-0.2.18.dist-info/licenses/LICENSE,sha256=IGdDrBPqz1O0v_UwCW-NJlbX9Hy9b3uJ11t28y2srmY,1062
-hydraflow-0.2.18.dist-info/RECORD,,