deriva-ml 1.14.26__tar.gz → 1.14.28__tar.gz

{deriva_ml-1.14.26/src/deriva_ml.egg-info → deriva_ml-1.14.28}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: deriva-ml
-Version: 1.14.26
+Version: 1.14.28
 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-1.14.26 → deriva_ml-1.14.28}/release.sh

@@ -14,7 +14,7 @@ echo "Bumping version: $VERSION_TYPE"
 
 # Bump the version using bump-my-version.
 # This command should update version files, commit the changes, and create a Git tag.
-bump-my-version bump "$VERSION_TYPE" --verbose
+uv run bump-my-version bump "$VERSION_TYPE" --verbose
 
 # Push commits and tags to the remote repository.
 echo "Pushing changes to remote repository..."

{deriva_ml-1.14.26 → deriva_ml-1.14.28}/src/deriva_ml/dataset/dataset.py

@@ -211,6 +211,7 @@ class Dataset:
         dataset_path.update([{"RID": dataset, "Version": version["RID"]} for dataset, version in versions.items()])
 
     def _set_version_snapshot(self):
+        """Update the Snapshot column of the Dataset_Version table to the correct time."""
         dataset_version_path = self._model.catalog.getPathBuilder().schemas[self._ml_schema].tables["Dataset_Version"]
         versions = dataset_version_path.entities().fetch()
         dataset_version_path.update(
@@ -1023,7 +1024,7 @@ class Dataset:
                 self._logger.info(
                     "Downloading dataset %s for catalog: %s@%s"
                     % (
-                        'minid' if self._use_minid else 'bag',
+                        "minid" if self._use_minid else "bag",
                         dataset.rid,
                         str(dataset.version),
                     )

{deriva_ml-1.14.26 → deriva_ml-1.14.28}/src/deriva_ml/execution/workflow.py

@@ -2,6 +2,7 @@ import inspect
 import logging
 import os
 import subprocess
+import sys
 from pathlib import Path
 from typing import Any
 
@@ -297,22 +298,46 @@ class Workflow(BaseModel):
                 pass
         return None, None
 
+    @staticmethod
+    def _in_repl():
+        # Standard Python interactive mode
+        if hasattr(sys, "ps1"):
+            return True
+
+        # Interactive mode forced by -i
+        if sys.flags.interactive:
+            return True
+
+        # IPython / Jupyter detection
+        try:
+            from IPython import get_ipython
+
+            if get_ipython() is not None:
+                return True
+        except ImportError:
+            pass
+
+        return False
+
     @staticmethod
     def _get_python_script() -> tuple[Path, bool]:
         """Return the path to the currently executing script"""
         is_notebook = True
         if not (filename := Workflow._get_notebook_path()):
             is_notebook = False
-            stack = inspect.stack()
+            stack = [
+                s.filename
+                for s in inspect.stack()
+                if ("pycharm" not in s.filename) and ("site-packages" not in s.filename)
+            ]
+            # Get the caller's filename, which is two up the stack from here.
+            filename = Path(stack[-1])
+            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.
-            if len(stack) > 1:
-                filename = Path(stack[2].filename)
-                if not filename.exists():
-                    # Being called from the command line interpreter.
-                    filename = Path("REPL")
-                # Get the caller's filename, which is two up the stack from here.
-            else:
-                raise DerivaMLException("Looking for caller failed")  # Stack is too shallow
+        else:
+            raise DerivaMLException("Looking for caller failed")  # Stack is too shallow
         return filename, is_notebook
 
     @staticmethod
@@ -352,19 +377,20 @@ class Workflow(BaseModel):
                 cwd=executable_path.parent,
                 capture_output=True,
                 text=True,
-                check=True,
+                check=False,
             )
             is_dirty = bool("M " in result.stdout.strip())  # Returns True if the output indicates a modified file
         except subprocess.CalledProcessError:
             is_dirty = False  # If the Git command fails, assume no changes
 
         """Get SHA-1 hash of latest commit of the file in the repository"""
+
         result = subprocess.run(
             ["git", "log", "-n", "1", "--pretty=format:%H--", executable_path],
-            cwd=executable_path.parent,
+            cwd=repo_root,
             capture_output=True,
             text=True,
-            check=True,
+            check=False,
         )
         sha = result.stdout.strip()
         url = f"{github_url}/blob/{sha}/{executable_path.relative_to(repo_root)}"

{deriva_ml-1.14.26 → deriva_ml-1.14.28/src/deriva_ml.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: deriva-ml
-Version: 1.14.26
+Version: 1.14.28
 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-1.14.26 → deriva_ml-1.14.28}/src/deriva_ml.egg-info/SOURCES.txt

@@ -89,11 +89,17 @@ tests/core/test_basic_tables.py
 tests/core/test_file.py
 tests/core/test_vocabulary.py
 tests/dataset/__init__.py
+tests/dataset/demo-catalog-schema.json
+tests/dataset/deriva-ml-reference.json
+tests/dataset/eye-ai-catalog-schema.json
+tests/dataset/test_dataset_export.py
 tests/dataset/test_dataset_version.py
 tests/dataset/test_datasets.py
 tests/dataset/test_download.py
 tests/execution/__init__.py
 tests/execution/test_execution.py
+tests/execution/workflow-script.py
+tests/execution/workflow_test.ipynb
 tests/feature/test_features.py
 tests/model/__init__.py
 tests/model/test_database.py