hydraflow 0.18.3__tar.gz → 0.19.0__tar.gz

{hydraflow-0.18.3 → hydraflow-0.19.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: hydraflow
-Version: 0.18.3
+Version: 0.19.0
 Summary: HydraFlow seamlessly integrates Hydra and MLflow to streamline ML experiment management, combining Hydra's configuration management with MLflow's tracking capabilities.
 Project-URL: Documentation, https://daizutabi.github.io/hydraflow/
 Project-URL: Source, https://github.com/daizutabi/hydraflow

{hydraflow-0.18.3 → hydraflow-0.19.0}/docs/part3-analysis/run-class.md

@@ -191,22 +191,6 @@ run = Run[Config, AdvancedModelLoader](run_dir, AdvancedModelLoader)
 model = run.impl.load_model()  # Uses configuration information
 ```
 
-## Loading Multiple Runs
-
-The `load` class method can load both individual runs and collections of runs:
-
-```python
-# Load a single run
-run = Run.load("mlruns/exp_id/run_id")
-
-# Load multiple runs to create a RunCollection
-run_dirs = ["mlruns/exp_id/run_id1", "mlruns/exp_id/run_id2"]
-runs = Run.load(run_dirs)
-
-# Load runs with parallel processing
-runs = Run.load(run_dirs, n_jobs=4)  # Use 4 parallel jobs for loading
-runs = Run.load(run_dirs, n_jobs=-1)  # Use all available CPU cores
-```
 ## Converting to DataFrame
 
 To convert a Run instance to a Polars DataFrame, use the
@@ -231,12 +215,27 @@ df = run.to_frame(
 
 The `to_frame` method accepts the following parameters:
 
-- `func`: A function that takes a Run instance and returns a DataFrame
+- `function`: A function that takes a Run instance and returns a DataFrame
 - `*keys`: Keys for the Run's information to add. Accepts the following formats:
-  - String: A simple key (e.g., "run_id")
-  - Tuple: A tuple of (key, default value or function returning default value)
+    - String: A simple key (e.g., "run_id")
+    - Tuple: A tuple of (key, default value or function returning default value)
 
+## Loading Multiple Runs
+
+The `load` class method can load both individual runs and collections of runs:
+
+```python
+# Load a single run
+run = Run.load("mlruns/exp_id/run_id")
 
+# Load multiple runs to create a RunCollection
+run_dirs = ["mlruns/exp_id/run_id1", "mlruns/exp_id/run_id2"]
+runs = Run.load(run_dirs)
+
+# Load runs with parallel processing
+runs = Run.load(run_dirs, n_jobs=4)  # Use 4 parallel jobs for loading
+runs = Run.load(run_dirs, n_jobs=-1)  # Use all available CPU cores
+```
 
 ### Finding Runs with `iter_run_dirs`
 
@@ -294,4 +293,4 @@ based on experiment names or custom filtering criteria.
 The [`Run`][hydraflow.core.run.Run] class provides a powerful interface for
 working with experiment runs in HydraFlow. Its type-safe configuration access,
 custom implementation support, and convenient loading mechanisms make it easy
-to analyze and compare experiment results effectively.
+to analyze and compare experiment results effectively.

{hydraflow-0.18.3 → hydraflow-0.19.0}/docs/part3-analysis/run-collection.md

@@ -327,10 +327,10 @@ df = run_collection.concat(
 
 The `concat` method accepts the following parameters:
 
-- `func`: A function that takes each Run instance and returns a DataFrame
+- `function`: A function that takes each Run instance and returns a DataFrame
 - `*keys`: Keys for the Run's information to add. Accepts the following formats:
-  - String: A simple key (e.g., "run_id")
-  - Tuple: A tuple of (key, default value or function returning default value)
+    - String: A simple key (e.g., "run_id")
+    - Tuple: A tuple of (key, default value or function returning default value)
 
 ## Grouping Runs
 
@@ -468,4 +468,4 @@ filtering, grouping, and data extraction capabilities enable efficient extractio
 of insights from large sets of experiments, helping you identify optimal
 configurations and understand performance trends.
 
-[hydraflow.core.collection.Collection]: ../../api/hydraflow/core/collection.html#hydraflow.core.collection.Collection
+[hydraflow.core.collection.Collection]: ../../api/hydraflow/core/collection.html#hydraflow.core.collection.Collection

{hydraflow-0.18.3 → hydraflow-0.19.0}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "hydraflow"
-version = "0.18.3"
+version = "0.19.0"
 description = "HydraFlow seamlessly integrates Hydra and MLflow to streamline ML experiment management, combining Hydra's configuration management with MLflow's tracking capabilities."
 readme = "README.md"
 license = { file = "LICENSE" }
@@ -62,7 +62,7 @@ dev = [
   "pytest-xdist",
   "ruff>=0.11",
 ]
-docs = ["markdown-exec[ansi]", "mkapi", "mkdocs-material"]
+docs = ["markdown-exec[ansi]", "mkapi>=4.4", "mkdocs-material"]
 
 [tool.pytest.ini_options]
 addopts = [

{hydraflow-0.18.3 → hydraflow-0.19.0}/src/hydraflow/core/run.py

@@ -140,7 +140,7 @@ class Run[C, I = None]:
         impl_factory: Callable[[Path], I] | Callable[[Path, C], I] | None = None,
         *,
         n_jobs: int = 0,
-    ) -> RunCollection[Self, I]: ...
+    ) -> RunCollection[Self]: ...
 
     @classmethod
     def load(
@@ -149,7 +149,7 @@ class Run[C, I = None]:
         impl_factory: Callable[[Path], I] | Callable[[Path, C], I] | None = None,
         *,
         n_jobs: int = 0,
-    ) -> Self | RunCollection[Self, I]:
+    ) -> Self | RunCollection[Self]:
         """Load a Run from a run directory.
 
         Args:
@@ -343,13 +343,13 @@ class Run[C, I = None]:
 
     def to_frame(
         self,
-        func: Callable[[Self], DataFrame],
+        function: Callable[[Self], DataFrame],
         *keys: str | tuple[str, Any | Callable[[Self], Any]],
     ) -> DataFrame:
         """Convert the Run to a DataFrame.
 
         Args:
-            func (Callable[[Run], DataFrame]): A function that takes a Run
+            function (Callable[[Run], DataFrame]): A function that takes a Run
                 instance and returns a DataFrame.
             keys (str | tuple[str, Any | Callable[[Run], Any]]): The keys to
                 add to the DataFrame.
@@ -358,7 +358,7 @@ class Run[C, I = None]:
             DataFrame: A DataFrame representation of the Run.
 
         """
-        return func(self).with_columns(
+        return function(self).with_columns(
             self.lit(k) if isinstance(k, str) else self.lit(k[0], k[1]) for k in keys
         )
 

{hydraflow-0.18.3 → hydraflow-0.19.0}/src/hydraflow/core/run_collection.py

@@ -40,7 +40,6 @@ Note:
 
 from __future__ import annotations
 
-from functools import cached_property
 from typing import TYPE_CHECKING, overload
 
 import polars as pl
@@ -56,7 +55,7 @@ if TYPE_CHECKING:
     from polars import DataFrame
 
 
-class RunCollection[R: Run[Any, Any], I = None](Collection[R]):
+class RunCollection[R: Run[Any, Any]](Collection[R]):
     """A collection of Run instances that implements the Sequence protocol.
 
     RunCollection provides methods for filtering, sorting, grouping, and analyzing
@@ -174,7 +173,7 @@ class RunCollection[R: Run[Any, Any], I = None](Collection[R]):
 
     def concat(
         self,
-        func: Callable[[R], DataFrame],
+        function: Callable[[R], DataFrame],
         *keys: str | tuple[str, Any | Callable[[R], Any]],
     ) -> DataFrame:
         """Concatenate the results of a function applied to all runs in the collection.
@@ -183,26 +182,16 @@ class RunCollection[R: Run[Any, Any], I = None](Collection[R]):
         and concatenates the resulting DataFrames along the specified keys.
 
         Args:
-            func (Callable[[R], DataFrame]): A function that takes a Run
+            function (Callable[[R], DataFrame]): A function that takes a Run
                 instance and returns a DataFrame.
             keys (str | tuple[str, Any | Callable[[R], Any]]): The keys to
                 add to the DataFrame.
 
         Returns:
-            DataFrame: A DataFrame representation of the Run.
+            DataFrame: A DataFrame representation of the Run collection.
 
         """
-        return pl.concat(run.to_frame(func, *keys) for run in self)
-
-    @cached_property
-    def impls(self) -> Collection[I]:
-        """Get the implementation objects for all runs in the collection.
-
-        Returns:
-            Collection[I]: A collection of implementation objects for all runs.
-
-        """
-        return Collection(run.impl for run in self)
+        return pl.concat(run.to_frame(function, *keys) for run in self)
 
     def iterdir(self, relative_dir: str = "") -> Iterator[Path]:
         """Iterate over the artifact directories for all runs in the collection.

{hydraflow-0.18.3 → hydraflow-0.19.0}/tests/cli/test_run.py

@@ -97,19 +97,15 @@ def test_run_echo():
     assert result.exit_code == 0
     out = result.stdout
     lines = out.splitlines()
-    assert len(lines) == 5
-    assert "['a', 'b', 'c', '--multirun', 'name=a', 'count=1,2,3'" in lines[1]
-    assert "['a', 'b', 'c', '--multirun', 'name=b', 'count=1,2,3'" in lines[2]
-    assert "['a', 'b', 'c', '--multirun', 'name=c', 'count=4,5,6'" in lines[3]
-    assert "['a', 'b', 'c', '--multirun', 'name=d', 'count=4,5,6'" in lines[4]
+    assert "['a', 'b', 'c', '--multirun', 'name=a', 'count=1,2,3'" in lines[-4]
+    assert "['a', 'b', 'c', '--multirun', 'name=b', 'count=1,2,3'" in lines[-3]
+    assert "['a', 'b', 'c', '--multirun', 'name=c', 'count=4,5,6'" in lines[-2]
+    assert "['a', 'b', 'c', '--multirun', 'name=d', 'count=4,5,6'" in lines[-1]
 
 
 def test_submit():
     result = runner.invoke(app, ["run", "submit"])
     assert result.exit_code == 0
-    out = result.stdout
-    lines = out.splitlines()
-    assert len(lines) == 1
     run_dirs = list(iter_run_dirs("mlruns", "submit"))
     assert len(run_dirs) == 4
 

{hydraflow-0.18.3 → hydraflow-0.19.0}/tests/core/run/test_run_collection.py

@@ -53,7 +53,7 @@ def rc(run_factory):
     return RunCollection(runs, Run.get)
 
 
-type Rc = RunCollection[Run[Config, Impl], Impl]
+type Rc = RunCollection[Run[Config, Impl]]
 
 
 def test_repr(rc: Rc):
@@ -289,9 +289,3 @@ def test_concat(rc: Rc):
     assert df["size.width"].to_list()[-6:] == [10, 10, 20, 20, 30, 30]
     assert df["z"].to_list()[:6] == [20, 20, 20, 20, 20, 20]
     assert df["z"].to_list()[-6:] == [40, 40, 40, 40, 40, 40]
-
-
-def test_impls(rc: Rc):
-    impls = rc.impls
-    assert len(impls) == 12
-    assert len(impls.filter(lambda i: i.y[0] == "1")) == 6

{hydraflow-0.18.3 → hydraflow-0.19.0}/tests/core/test_group_by.py

@@ -52,7 +52,7 @@ def rc(run_factory):
     return RunCollection(runs, Run.get)
 
 
-type Rc = RunCollection[Run[Config, Impl], Impl]
+type Rc = RunCollection[Run[Config, Impl]]
 
 
 def test_getitem_key(rc: Rc):