deriva-ml 1.10.0__tar.gz → 1.10.1__tar.gz

{deriva_ml-1.10.0/src/deriva_ml.egg-info → deriva_ml-1.10.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: deriva-ml
-Version: 1.10.0
+Version: 1.10.1
 Summary: Utilities to simplify use of Dervia and Pandas to create reproducable ML pipelines
 Author-email: ISRD <isrd-dev@isi.edu>
 Requires-Python: >=3.10

{deriva_ml-1.10.0 → deriva_ml-1.10.1}/src/deriva_ml/deriva_ml_base.py

@@ -1249,7 +1249,7 @@ class DerivaML(Dataset):
 
     # @validate_call
     def create_execution(
-        self, configuration: ExecutionConfiguration, dryrun: bool = False
+        self, configuration: ExecutionConfiguration, dry_run: bool = False
     ) -> "Execution":
         """Create an execution object
 
@@ -1268,12 +1268,7 @@ class DerivaML(Dataset):
         """
         from .execution import Execution
 
-        if self._execution:
-            DerivaMLException(
-                "Only one execution can be created for a Deriva ML instance."
-            )
-        else:
-            self._execution = Execution(configuration, self, dryrun=dryrun)
+        self._execution = Execution(configuration, self, dry_run=dry_run)
         return self._execution
 
     # @validate_call

{deriva_ml-1.10.0 → deriva_ml-1.10.1}/src/deriva_ml/execution.py

@@ -18,6 +18,7 @@ from typing import Iterable, Any, Optional
 from deriva.core import format_exception
 from deriva.core.ermrest_model import Table
 from pydantic import validate_call, ConfigDict
+import sys
 
 from .deriva_definitions import MLVocab, ExecMetadataVocab
 from .deriva_definitions import (
@@ -113,9 +114,11 @@ class Execution:
         self.stop_time = None
         self.status = Status.created
         self.uploaded_assets: list[Path] = []
+        self.configuration.argv = sys.argv
 
         self.dataset_rids: list[RID] = []
         self.datasets: list[DatasetBag] = []
+        self.parameters = self.configuration.parameters
 
         self._working_dir = self._ml_object.working_dir
         self._cache_dir = self._ml_object.cache_dir

{deriva_ml-1.10.0 → deriva_ml-1.10.1}/src/deriva_ml/execution_configuration.py

@@ -1,14 +1,11 @@
 from __future__ import annotations
 
 import json
-from typing import Optional
+from typing import Optional, Any
 
-from pydantic import (
-    BaseModel,
-    conlist,
-    ConfigDict,
-)
+from pydantic import BaseModel, conlist, ConfigDict, field_validator, Field
 from pathlib import Path
+import sys
 
 
 from .dataset_aux_classes import DatasetSpec
@@ -43,6 +40,7 @@ class ExecutionConfiguration(BaseModel):
         datasets: List of dataset specifications which specify the dataset RID, version and if the dataset
             should be materialized.
         assets: List of assets to be downloaded prior to execution.  The values must be RIDs in an asset table
+        parameters: Either a dictionary or a path to a JSON file that contains configuration parameters for the execution.
         workflow: A RID for a workflow instance.  Must have a name, URI to the workflow instance, and a type.
         description: A description of the execution.  Can use Markdown format.
     """
@@ -50,10 +48,22 @@ class ExecutionConfiguration(BaseModel):
     datasets: conlist(DatasetSpec) = []
     assets: list[RID | str] = []  # List of RIDs to model files.
     workflow: RID | Workflow
+    parameters: dict[str, Any] = {}
     description: str = ""
+    argv: conlist(str) = Field(default_factory=lambda: sys.argv)
 
     model_config = ConfigDict(arbitrary_types_allowed=True)
 
+    @field_validator("parameters", mode="before")
+    @classmethod
+    def validate_parameters(cls, value: Any) -> Any:
+        """If parameter is a file, assume that it has JSON contents for configuration parameters"""
+        if isinstance(value, str) or isinstance(value, Path):
+            with open(value, "r") as f:
+                return json.load(f)
+        else:
+            return value
+
     @staticmethod
     def load_configuration(path: Path) -> ExecutionConfiguration:
         """Create a ExecutionConfiguration from a JSON configuration file.

{deriva_ml-1.10.0 → deriva_ml-1.10.1/src/deriva_ml.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: deriva-ml
-Version: 1.10.0
+Version: 1.10.1
 Summary: Utilities to simplify use of Dervia and Pandas to create reproducable ML pipelines
 Author-email: ISRD <isrd-dev@isi.edu>
 Requires-Python: >=3.10