deriva-ml 1.14.37__tar.gz → 1.14.39__tar.gz

{deriva_ml-1.14.37 → deriva_ml-1.14.39}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: deriva-ml
-Version: 1.14.37
+Version: 1.14.39
 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-1.14.37 → deriva_ml-1.14.39}/src/deriva_ml/core/base.py

@@ -134,8 +134,10 @@ class DerivaML(Dataset):
                 this argument must be provided a value.
             ml_schema: Schema name for ML schema. Used if you have a non-standard configuration of deriva-ml.
             project_name: Project name. Defaults to name of domain schema.
-            cache_dir: Directory path for caching data downloaded from the Deriva server as bdbag.
-            working_dir: Directory path for storing data used by or generated by any computations.
+            cache_dir: Directory path for caching data downloaded from the Deriva server as bdbag. If not provided,
+                will default to working_dir.
+            working_dir: Directory path for storing data used by or generated by any computations. If no value is
+                provided, will default to  ${HOME}/deriva_ml
             use_minid: Use the MINID service when downloading dataset bags.
         """
         # Get or use provided credentials for server access

{deriva_ml-1.14.37 → deriva_ml-1.14.39}/src/deriva_ml/execution/workflow.py

@@ -320,6 +320,11 @@ class Workflow(BaseModel):
             if not (filename.exists() or Workflow._in_repl()):
                 # Being called from the command line interpreter.
                 filename = Path.cwd() / Path("REPL")
+            # Get the caller's filename, which is two up the stack from here.
+            elif "PYTEST_CURRENT_TEST" in os.environ:
+                filename = Path.cwd() / Path("pytest")
+            else:
+                raise DerivaMLException("Looking for caller failed")  # Stack is too shallow
         return filename, is_notebook
 
     @staticmethod

{deriva_ml-1.14.37 → deriva_ml-1.14.39}/src/deriva_ml/install_kernel.py

@@ -1,4 +1,3 @@
-# your_pkg/install_kernel.py
 import re
 import sys
 from argparse import ArgumentParser
@@ -60,7 +59,7 @@ def main() -> None:
         prefix_arg = {"prefix": sys.prefix}
 
     install_kernel(
-        user=False,  # write under sys.prefix (the active env)
+        user=True,  # write under sys.prefix (the active env)
         kernel_name=kernel_name,
         display_name=display_name,
         **prefix_arg,

{deriva_ml-1.14.37 → deriva_ml-1.14.39}/src/deriva_ml/model/database.py

@@ -326,7 +326,7 @@ class DatabaseModel(DerivaModel, metaclass=DatabaseModelMeta):
         except ValueError:
             tname = table
             for sname in [self.domain_schema, self.ml_schema, "WWW"]:  # Be careful of File table.
-                if table in self.model.schemas[sname].tables:
+                if sname in self.model.schemas and table in self.model.schemas[sname].tables:
                     break
         try:
             _ = self.model.schemas[sname].tables[tname]

{deriva_ml-1.14.37 → deriva_ml-1.14.39}/src/deriva_ml.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: deriva-ml
-Version: 1.14.37
+Version: 1.14.39
 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-1.14.37 → deriva_ml-1.14.39}/tests/execution/test_execution.py

@@ -7,6 +7,8 @@ from pathlib import Path
 from tempfile import TemporaryDirectory
 
 from deriva_ml import (
+    BuiltinTypes,
+    ColumnDefinition,
     DatasetSpec,
     DerivaML,
     ExecAssetType,
@@ -186,10 +188,48 @@ class TestExecution:
         # Create manual execution
         test_execution = ml_instance.create_execution(config)
         with test_execution.execute() as execution:
+            assert execution.asset_paths["Execution_Asset"][0].asset_types[0] == "Model_File"
             assert 1 == len(execution.asset_paths)
             assert 1 == len(execution.datasets)
             assert execution.datasets[0].dataset_rid == dataset_rid
 
+    def test_download_asset(self, test_ml, tmp_path):
+        ml_instance = test_ml
+
+        # Create a workflow
+        ml_instance.add_term(vc.asset_type, "Test Model", description="Model for our Test workflow")
+        ml_instance.add_term(vc.workflow_type, "Test Workflow", description="A ML Workflow that uses Deriva ML API")
+        api_workflow = ml_instance.create_workflow(
+            name="Test Workflow One",
+            workflow_type="Test Workflow",
+            description="A test operation",
+        )
+        ml_instance.create_asset(
+            "BarAsset",
+            column_defs=[ColumnDefinition(name="foo", type=BuiltinTypes.int4)],
+        )
+        manual_execution = ml_instance.create_execution(
+            ExecutionConfiguration(description="Sample Execution", workflow=api_workflow)
+        )
+
+        with manual_execution.execute() as execution:
+            model_file = execution.asset_file_path(
+                "BarAsset", "API_Model/modelfile.txt", asset_types=ExecAssetType.model_file, foo=23
+            )
+            print(model_file)
+            with model_file.open("w") as fp:
+                fp.write("My model")
+            # Now upload the file and retrieve the RID of the new asset from the returned results.
+        uploaded_assets = manual_execution.upload_execution_outputs()
+        print(uploaded_assets)
+        assert 1 == len(uploaded_assets["deriva-ml/Execution_Asset"])
+
+        file = manual_execution.download_asset(asset_rid, tmpdir, update_catalog=False)
+        assert file.name == "modelfile.txt"
+
+        assert "BarAsset" in [a.name for a in ml_instance.model.find_assets()]
+        assert ml_instance.model.asset_metadata("BarAsset") == {"foo"}
+
     @staticmethod
     def create_execution_asset(ml_instance: DerivaML, api_workflow):
         manual_execution = ml_instance.create_execution(