deriva-ml 1.12.0__py3-none-any.whl → 1.12.2__py3-none-any.whl

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/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/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.dist-info → deriva_ml-1.12.2.dist-info}/METADATA

@@ -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.dist-info → deriva_ml-1.12.2.dist-info}/RECORD

@@ -5,23 +5,23 @@ deriva_ml/dataset_aux_classes.py,sha256=YxjQnu2kS9kK_f8bGqhmgE6ty9GNeitCxfvReT9v
 deriva_ml/dataset_bag.py,sha256=yS8oYVshfFtRDyhGPRqtbvxjyd3ZFF29lrB783OP4vM,11849
 deriva_ml/demo_catalog.py,sha256=9Qo3JD4bUIwnL3ngPctc2QBeWApvMR_5UyaK9ockTrY,11536
 deriva_ml/deriva_definitions.py,sha256=2eSbTFQ-9rpctphN4PLo8WdtkzMfhfZr3vJeywt6xPM,8897
-deriva_ml/deriva_ml_base.py,sha256=gixttnYm15BB-maC_PAPKoypu-ZGYs4wBwxMv-_N98o,46633
+deriva_ml/deriva_ml_base.py,sha256=rrImShp1RXvMuXVLft5GfTnxf_PfF1LONHgV1Ee_E9I,46517
 deriva_ml/deriva_model.py,sha256=wytGCAHutiUaRfnRKr80Ks_P6ci0_wXRU3vq3lthfYU,13260
-deriva_ml/execution.py,sha256=WXbr3Haw0_TPMd2YRUiPA5Tob0q76IIo5MWzMoZ0WmU,36018
+deriva_ml/execution.py,sha256=SggLMAfQevnkGyaixF6dRwn36qHO5s07wkLxQXmNCag,36020
 deriva_ml/execution_configuration.py,sha256=XQeXzPz9Gh_AGa_iYW8zF95niwHed3ojv4gnibB0thA,4082
 deriva_ml/execution_environment.py,sha256=bCRKrCELDbGQDo7_FKfw7e8iMzVjSRZK3baKkqH5-_0,3264
 deriva_ml/feature.py,sha256=07g0uSrhumdopJluWuWSRMrzagaikAOihqB09bzXBP4,5475
 deriva_ml/history.py,sha256=qTDLDs8Ow_6r7mDO0gZm0Fg81SWKOAgtCU5pzZoDRgM,2828
 deriva_ml/test_functions.py,sha256=-eqLHjjCQCLBNAr1ofbZekNiCOfMISSACRxT_YHER8I,4396
-deriva_ml/upload.py,sha256=Pehi_nXElbg6kdGY5Q7RjEMOyc7Ua26WK8-31FkSc_s,16182
+deriva_ml/upload.py,sha256=gHTGXAVlf56EwNzmw5zY0gbBf8h08eU2q2GBbb2FdVc,16087
 deriva_ml/schema_setup/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 deriva_ml/schema_setup/annotations.py,sha256=v0gTpmWYxRqsQ-bcnQzsr8WowGv2pi9pZUsO3WWnu1U,9528
 deriva_ml/schema_setup/create_schema.py,sha256=hNMc-v5tferd0UjfdB6nBw7Rc_o-Mg6NkPqQGie9YOw,11700
 deriva_ml/schema_setup/policy.json,sha256=77sf0Imy6CAQV0_VwwbA56_KROJ05WXsvT-Wjtkk538,1633
 deriva_ml/schema_setup/table_comments_utils.py,sha256=-2_ubEpoH7ViLVb-ZfW9wZbQ26DTKNgjkCABMzGu4i4,2140
-deriva_ml-1.12.0.dist-info/licenses/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
-deriva_ml-1.12.0.dist-info/METADATA,sha256=4XXYdBKEdcIExAtH1VQz5iGmhzdkc9tQIMAfU6bNwC4,974
-deriva_ml-1.12.0.dist-info/WHEEL,sha256=CmyFI0kx5cdEMTLiONQRbGQwjIoR1aIYB7eCAQ4KPJ0,91
-deriva_ml-1.12.0.dist-info/entry_points.txt,sha256=ZiOvrYj022x544TQwi018ujeHRRDahNmwJnzn5ThacM,242
-deriva_ml-1.12.0.dist-info/top_level.txt,sha256=I1Q1dkH96cRghdsFRVqwpa2M7IqJpR2QPUNNc5-Bnpw,10
-deriva_ml-1.12.0.dist-info/RECORD,,
+deriva_ml-1.12.2.dist-info/licenses/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+deriva_ml-1.12.2.dist-info/METADATA,sha256=EcMVbM-QX5myyijRGJnUmaQOjOCHhxHf-27T68A8P18,974
+deriva_ml-1.12.2.dist-info/WHEEL,sha256=CmyFI0kx5cdEMTLiONQRbGQwjIoR1aIYB7eCAQ4KPJ0,91
+deriva_ml-1.12.2.dist-info/entry_points.txt,sha256=ZiOvrYj022x544TQwi018ujeHRRDahNmwJnzn5ThacM,242
+deriva_ml-1.12.2.dist-info/top_level.txt,sha256=I1Q1dkH96cRghdsFRVqwpa2M7IqJpR2QPUNNc5-Bnpw,10
+deriva_ml-1.12.2.dist-info/RECORD,,