deriva-ml 1.9.0__tar.gz → 1.9.1__tar.gz

{deriva_ml-1.9.0/src/deriva_ml.egg-info → deriva_ml-1.9.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: deriva-ml
-Version: 1.9.0
+Version: 1.9.1
 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
@@ -16,5 +16,14 @@ Requires-Dist: setuptools-scm<=6.0
 Requires-Dist: nbstripout
 Dynamic: license-file
 
-Deriva-ML is a python libary to simplify the process of creating and executing reproducible machine learning workflows
+# DerivaML
+Deriva-ML is a python library to simplify the process of creating and executing reproducible machine learning workflows
 using a deriva catalog.
+
+
+## Installing the GitHub CLI
+
+The script release.sh will create a new release tag in GitHub.  This script requires the 
+GitHUB CLI be installed. 
+
+See [https://cli.github.com](https://cli.github.com) for instructions on how to install and configure the CLI.

deriva_ml-1.9.1/README.md

@@ -0,0 +1,11 @@
+# DerivaML
+Deriva-ML is a python library to simplify the process of creating and executing reproducible machine learning workflows
+using a deriva catalog.
+
+
+## Installing the GitHub CLI
+
+The script release.sh will create a new release tag in GitHub.  This script requires the 
+GitHUB CLI be installed. 
+
+See [https://cli.github.com](https://cli.github.com) for instructions on how to install and configure the CLI.

{deriva_ml-1.9.0 → deriva_ml-1.9.1}/release.sh

@@ -9,6 +9,7 @@ fi
 
 # Default version bump is patch unless specified (patch, minor, or major)
 VERSION_TYPE=${1:-patch}
+
 echo "Bumping version: $VERSION_TYPE"
 
 # Bump the version using bump-my-version.
@@ -32,6 +33,6 @@ python -m build
 NEW_TAG=$(git describe --tags --abbrev=0)
 echo "New version tag: $NEW_TAG"
 
-twine upload "dist/*${NEW_TAG/v/}"
+twine upload dist/*${NEW_TAG/v/}
 
 echo "Release process complete!"

{deriva_ml-1.9.0 → deriva_ml-1.9.1}/src/deriva_ml/database_model.py

@@ -84,7 +84,7 @@ class DatabaseModel(DerivaModel, metaclass=DatabaseModelMeta):
         except KeyError:
             raise DerivaMLException(f"Dataset {dataset_rid} not found")
 
-    def __init__(self, minid: DatasetMinid, bag_path: Path):
+    def __init__(self, minid: DatasetMinid, bag_path: Path, dbase_path: Path):
         """Create a new DatabaseModel.
 
         Args:
@@ -95,8 +95,7 @@ class DatabaseModel(DerivaModel, metaclass=DatabaseModelMeta):
         self.bag_path = bag_path
         self.minid = minid
         self.dataset_rid = minid.dataset_rid
-        dir_path = bag_path.parent
-        self.dbase_file = dir_path / f"{minid.version_rid}.db"
+        self.dbase_file = dbase_path / f"{minid.version_rid}.db"
         self.dbase = sqlite3.connect(self.dbase_file)
 
         super().__init__(

{deriva_ml-1.9.0 → deriva_ml-1.9.1}/src/deriva_ml/dataset.py

@@ -67,11 +67,12 @@ class Dataset:
 
     _Logger = logging.getLogger("deriva_ml")
 
-    def __init__(self, model: DerivaModel, cache_dir: Path):
+    def __init__(self, model: DerivaModel, cache_dir: Path, working_dir: Path):
         self._model = model
         self._ml_schema = ML_SCHEMA
         self.dataset_table = self._model.schemas[self._ml_schema].tables["Dataset"]
         self._cache_dir = cache_dir
+        self._working_dir = working_dir
         self._logger = logging.getLogger("deriva_ml")
 
     def _is_dataset_rid(self, dataset_rid: RID, deleted: bool = False) -> bool:
@@ -783,7 +784,6 @@ class Dataset:
         snapshot: Optional[Dataset] = None,
         dataset_nesting_depth: Optional[int] = None,
     ) -> set[tuple[Table, ...]]:
-
         snapshot_catalog = snapshot if snapshot else self
 
         dataset_table = snapshot_catalog._model.schemas[self._ml_schema].tables[
@@ -831,9 +831,7 @@ class Dataset:
         nested_paths = set()
         if dataset_rid:
             for c in snapshot_catalog.list_dataset_children(dataset_rid=dataset_rid):
-                nested_paths |= self._collect_paths(
-                    c, snapshot=snapshot_catalog
-                )
+                nested_paths |= self._collect_paths(c, snapshot=snapshot_catalog)
         else:
             # Initialize nesting depth if not already provided.
             dataset_nesting_depth = (
@@ -979,7 +977,7 @@ class Dataset:
             if dataset.materialize
             else self._download_dataset_minid(minid)
         )
-        return DatabaseModel(minid, bag_path).get_dataset()
+        return DatabaseModel(minid, bag_path, self._working_dir).get_dataset()
 
     def _version_snapshot(self, dataset: DatasetSpec) -> str:
         """Return a catalog with snapshot for the specified dataset version"""

{deriva_ml-1.9.0 → deriva_ml-1.9.1}/src/deriva_ml/deriva_ml_base.py

@@ -163,7 +163,7 @@ class DerivaML(Dataset):
         self.cache_dir.mkdir(parents=True, exist_ok=True)
 
         # Initialize dataset class.
-        super().__init__(self.model, self.cache_dir)
+        super().__init__(self.model, self.cache_dir, self.working_dir)
         self._logger = logging.getLogger("deriva_ml")
         self._logger.setLevel(logging_level)
 
@@ -257,7 +257,7 @@ class DerivaML(Dataset):
     def _get_notebook_path(self) -> Path | None:
         """Return the absolute path of the current notebook."""
 
-        server, session = self._get_notebook_session()
+        server, session = DerivaML._get_notebook_session()
         if server and session:
             self._check_nbstrip_status()
             relative_path = session["notebook"]["path"]

{deriva_ml-1.9.0 → deriva_ml-1.9.1/src/deriva_ml.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: deriva-ml
-Version: 1.9.0
+Version: 1.9.1
 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
@@ -16,5 +16,14 @@ Requires-Dist: setuptools-scm<=6.0
 Requires-Dist: nbstripout
 Dynamic: license-file
 
-Deriva-ML is a python libary to simplify the process of creating and executing reproducible machine learning workflows
+# DerivaML
+Deriva-ML is a python library to simplify the process of creating and executing reproducible machine learning workflows
 using a deriva catalog.
+
+
+## Installing the GitHub CLI
+
+The script release.sh will create a new release tag in GitHub.  This script requires the 
+GitHUB CLI be installed. 
+
+See [https://cli.github.com](https://cli.github.com) for instructions on how to install and configure the CLI.

deriva_ml-1.9.0/README.md

@@ -1,2 +0,0 @@
-Deriva-ML is a python libary to simplify the process of creating and executing reproducible machine learning workflows
-using a deriva catalog.