deriva-ml 1.12.0__tar.gz → 1.12.2__tar.gz

{deriva_ml-1.12.0/src/deriva_ml.egg-info → deriva_ml-1.12.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: deriva-ml
-Version: 1.12.0
+Version: 1.12.2
 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-1.12.2/docs/user-guide/file-assets.md

@@ -0,0 +1,3 @@
+#  File Assets
+
+

{deriva_ml-1.12.0 → deriva_ml-1.12.2}/src/deriva_ml/deriva_ml_base.py

@@ -193,11 +193,7 @@ class DerivaML(Dataset):
             pass
 
     def _check_nbstrip_status(self) -> None:
-        """Figure out if you are running in a Jupyter notebook
-
-        Returns:
-            A Path to the notebook file that is currently being executed.
-        """
+        """Check to see if nbstrip is installed"""
         try:
             if subprocess.run(
                 ["nbstripout", "--is-installed"],

{deriva_ml-1.12.0 → deriva_ml-1.12.2}/src/deriva_ml/execution.py

@@ -651,6 +651,7 @@ class Execution:
             ]  # Peel off the schema from the asset table
             asset_exe = self._model.find_association(asset_table_name, "Execution")
             asset_exe_path = pb.schemas[asset_exe.schema.name].tables[asset_exe.name]
+
             asset_exe_path.insert(
                 [
                     {
@@ -706,7 +707,7 @@ class Execution:
         """Return a pathlib Path to the directory in which to place files for the specified execution_asset type.
 
         Given the name of an asset table, and a file name, register the file for upload, and return a path to that
-        file in the upload directory.  In addition to the filename, additioal asset metadata and file asset types may
+        file in the upload directory.  In addition to the filename, additional asset metadata and file asset types may
         be specified.
 
         This routine has three modes, depending on if file_name refers to an existing file.  If it doesn't, a path

{deriva_ml-1.12.0 → deriva_ml-1.12.2}/src/deriva_ml/upload.py

@@ -74,17 +74,16 @@ feature_table_dir_regex = (
     + r"/(?P<schema>[-\w]+)/(?P<target_table>[-\w]+)/(?P<feature_name>[-\w]+)"
 )
 feature_value_regex = (
-    feature_table_dir_regex + r"/(?P=feature_name)[.](?P<file_ext>[(csv|json)]*)$"
+    feature_table_dir_regex + r"/(?P=feature_name)[.](?P<ext>[(csv|json)]*)$"
 )
 feature_asset_dir_regex = feature_table_dir_regex + r"/asset/(?P<asset_table>[-\w]+)"
 feature_asset_regex = (
-    feature_asset_dir_regex
-    + r"/(?P<file_name>[A-Za-z0-9_-]+)[.](?P<file_ext>[a-z0-9]*)$"
+    feature_asset_dir_regex + r"/(?P<file>[A-Za-z0-9_-]+)[.](?P<ext>[a-z0-9]*)$"
 )
 
 asset_path_regex = exec_dir_regex + r"/asset/(?P<schema>[-\w]+)/(?P<asset_table>[-\w]*)"
 
-asset_file_regex = r"(?P<file_name>[-\w]+)[.](?P<file_ext>[a-z0-9]*)$"
+asset_file_regex = r"(?P<file>[-\w]+)[.](?P<ext>[a-z0-9]*)$"
 
 table_regex = (
     exec_dir_regex
@@ -211,15 +210,16 @@ def asset_table_upload_spec(model: DerivaModel, asset_table: str | Table):
             "Filename": "{file_name}",
         }
         | {c: f"{{{c}}}" for c in metadata_columns},
-        "file_pattern": asset_path,  # Sets schema, asset_table, file_name, file_ext
+        "file_pattern": asset_path,  # Sets schema, asset_table, file
+        "asset_type": "file",
         "target_table": [schema, asset_table.name],
         "checksum_types": ["sha256", "md5"],
         "hatrac_options": {"versioned_urls": True},
         "hatrac_templates": {
-            "hatrac_uri": f"/hatrac/{asset_table.name}/{{md5}}.{{file_name}}.{{file_ext}}",
-            "content-disposition": "filename*=UTF-8''{file_name}.{file_ext}",
+            "hatrac_uri": f"/hatrac/{asset_table.name}/{{md5}}.{{file_name}}",
+            "content-disposition": "filename*=UTF-8''{file_name}",
         },
-        "record_query_template": "/entity/{target_table}/MD5={{md5}}&Filename={file_name}.{file_ext}",
+        "record_query_template": "/entity/{target_table}/MD5={md5}&Filename={file_name}",
     }
 
 
@@ -244,18 +244,18 @@ def bulk_upload_configuration(model: DerivaModel) -> dict[str, Any]:
                     "Length": "{file_size}",
                     "Filename": "{file_name}",
                 },
-                "asset_type": "fetch",
+                "asset_type": "file",
                 "target_table": ["{schema}", "{asset_table}"],
                 "file_pattern": asset_path_regex
                 + "/"
-                + asset_file_regex,  # Sets schema, asset_table, file_name, file_ext
+                + asset_file_regex,  # Sets schema, asset_table, name, ext
                 "checksum_types": ["sha256", "md5"],
                 "hatrac_options": {"versioned_urls": True},
                 "hatrac_templates": {
-                    "hatrac_uri": "/hatrac/{asset_table}/{md5}.{file_name}.{file_ext}",
-                    "content-disposition": "filename*=UTF-8''{file_name}.{file_ext}",
+                    "hatrac_uri": "/hatrac/{asset_table}/{md5}.{file_name}",
+                    "content-disposition": "filename*=UTF-8''{file_name}",
                 },
-                "record_query_template": "/entity/{target_table}/MD5={md5}&Filename={file_name}.{file_ext}",
+                "record_query_template": "/entity/{target_table}/MD5={md5}&Filename={file_name}",
             },
             # {
             #  Upload the records into a  table

{deriva_ml-1.12.0 → deriva_ml-1.12.2/src/deriva_ml.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: deriva-ml
-Version: 1.12.0
+Version: 1.12.2
 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-1.12.0 → deriva_ml-1.12.2}/src/deriva_ml.egg-info/SOURCES.txt

@@ -31,6 +31,7 @@ docs/code-docs/feature.md
 docs/code-docs/upload.md
 docs/user-guide/datasets.md
 docs/user-guide/execution-configuration.md
+docs/user-guide/file-assets.md
 docs/user-guide/identifiers.md
 docs/user-guide/install.md
 docs/user-guide/ml_workflow_instruction.md