deriva-ml 1.17.7__tar.gz → 1.17.10__tar.gz

{deriva_ml-1.17.7 → deriva_ml-1.17.10}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: deriva-ml
-Version: 1.17.7
+Version: 1.17.10
 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
@@ -12,7 +12,6 @@ Requires-Dist: deriva~=1.7.10
 Requires-Dist: deepdiff
 Requires-Dist: nbconvert
 Requires-Dist: pandas
-Requires-Dist: pip-system-certs
 Requires-Dist: pydantic>=2.11
 Requires-Dist: papermill
 Requires-Dist: pandas-stubs==2.2.3.250527

{deriva_ml-1.17.7 → deriva_ml-1.17.10}/pyproject.toml

@@ -14,7 +14,6 @@ dependencies = [
     "deepdiff",
     "nbconvert",
     "pandas",
-    "pip-system-certs",
     "pydantic>=2.11",
     "papermill",
     "pandas-stubs==2.2.3.250527",
@@ -35,6 +34,7 @@ deriva-ml-alter-annotation = "deriva_ml.schema_setup.alter_annotation:main"
 deriva-ml-run-notebook = "deriva_ml.run_notebook:main"
 deriva-ml-install-kernel = "deriva_ml.install_kernel:main"
 bump-version = "deriva_ml.bump_version:main"
+create-demo-catalog = "deriva_ml.demo_catalog:main"
 
 deriva-ml-check-catalog-schema = "deriva_ml.schema.check_schema:main"
 
@@ -111,10 +111,10 @@ dev = [
     "mkdocs-jupyter",
     "mkdocstrings[python]",
     "mkdocs-material",
+    "pip-system-certs",
     "pytest>=8.4.1",
     "pytest-mock",
     "pytest-coverage>=0.0",
-    "pip-system-certs",
     "ruff"
 ]
 lint = [

{deriva_ml-1.17.7 → deriva_ml-1.17.10}/src/deriva_ml/dataset/upload.py

@@ -295,7 +295,6 @@ def upload_directory(model: DerivaModel, directory: Path | str) -> dict[Any, Fil
     # Now upload the files by creating an upload spec and then calling the uploader.
     with TemporaryDirectory() as temp_dir:
         spec_file = Path(temp_dir) / "config.json"
-
         with spec_file.open("w+") as cfile:
             json.dump(bulk_upload_configuration(model), cfile)
         uploader = GenericUploader(

{deriva_ml-1.17.7 → deriva_ml-1.17.10}/src/deriva_ml/demo_catalog.py

@@ -3,6 +3,7 @@ from __future__ import annotations
 import atexit
 import itertools
 import logging
+import os
 import string
 from collections.abc import Iterator, Sequence
 from datetime import datetime
@@ -11,7 +12,7 @@ from pathlib import Path
 from random import choice, randint, random
 from tempfile import TemporaryDirectory
 
-from deriva.core import ErmrestCatalog
+from deriva.core import BaseCLI, ErmrestCatalog
 from deriva.core.ermrest_model import Column, Schema, Table, builtin_types
 from pydantic import BaseModel, ConfigDict
 from requests.exceptions import HTTPError
@@ -19,7 +20,7 @@ from requests.exceptions import HTTPError
 from deriva_ml import DerivaML, MLVocab
 from deriva_ml.core.definitions import RID, BuiltinTypes, ColumnDefinition
 from deriva_ml.dataset.aux_classes import DatasetVersion
-from deriva_ml.execution.execution import Execution
+from deriva_ml.execution.execution import Execution, Workflow
 from deriva_ml.execution.execution_configuration import ExecutionConfiguration
 from deriva_ml.schema import (
     create_ml_catalog,
@@ -48,11 +49,16 @@ def populate_demo_catalog(ml_instance: DerivaML) -> None:
         "Demo Catalog Creation",
         description="A workflow demonstrating how to create a demo catalog.",
     )
-    execution = ml_instance.create_execution(
-        ExecutionConfiguration(
-            workflow=ml_instance.create_workflow(name="Demo Catalog", workflow_type="Demo Catalog Creation")
-        )
+    workflow = Workflow(
+        name="Demo Catalog",
+        workflow_type="Demo Catalog Creation",
+        url="https://github.com/informatics-isi-edu/deriva-ml/blob/main/src/deriva_ml/demo_catalog.py",
+        version="1.0.0",
+        checksum="27",
+        git_root=Path(),
     )
+    execution = ml_instance.create_execution(ExecutionConfiguration(workflow=workflow))
+
     with execution.execute() as e:
         for s in ss:
             image_file = e.asset_file_path(
@@ -386,9 +392,12 @@ def create_demo_catalog(
     test_catalog = create_ml_catalog(hostname, project_name=project_name)
     if on_exit_delete:
         atexit.register(destroy_demo_catalog, test_catalog)
+
     try:
         with TemporaryDirectory() as tmpdir:
+            os.chdir(tmpdir)  # Do this so we don't get confused if running from a GitHub repo.
             create_domain_schema(test_catalog, domain_schema)
+
             ml_instance = DerivaML(
                 hostname,
                 catalog_id=test_catalog.catalog_id,
@@ -396,7 +405,6 @@ def create_demo_catalog(
                 working_dir=tmpdir,
                 logging_level=logging_level,
             )
-
             if populate or create_features or create_datasets:
                 populate_demo_catalog(ml_instance)
                 if create_features:
@@ -428,3 +436,60 @@ class DemoML(DerivaML):
             working_dir=working_dir,
             use_minid=use_minid,
         )
+
+
+class DerivaMLDemoCatalogCLI(BaseCLI):
+    """Main class to part command line arguments and call model"""
+
+    def __init__(self, description, epilog, **kwargs):
+        BaseCLI.__init__(self, description, epilog, **kwargs)
+        # Optional domain schema name for the demo catalog. Defaults to None if not provided.
+        self.parser.add_argument(
+            "--domain_schema",
+            type=str,
+            default="demo-schema",
+            help="Name of the domain schema to create/use for the demo catalog (default: demo-schema).",
+        )
+
+    @staticmethod
+    def _coerce_number(val: str):
+        """
+        Try to convert a string to int, then float; otherwise return str.
+        """
+        try:
+            return int(val)
+        except ValueError:
+            try:
+                return float(val)
+            except ValueError:
+                return val
+
+    def main(self) -> ErmrestCatalog:
+        """Parse arguments and set up execution environment."""
+        args = self.parse_cli()
+        if not args.host:
+            raise ValueError("Host must be specified.")
+        demo_catalog = create_demo_catalog(args.host, args.domain_schema)
+        return demo_catalog
+
+
+def main() -> None:
+    """Main entry point for the notebook runner CLI.
+
+    Creates and runs the DerivaMLRunNotebookCLI instance.
+
+    Returns:
+        None. Executes the CLI.
+    """
+    cli = DerivaMLDemoCatalogCLI(description="Create a Deriva ML Sample Catalog", epilog="")
+    catalog = cli.main()
+    print("Created catalog: {}".format(catalog._server_uri))
+
+
+if __name__ == "__main__":
+    try:
+        main()
+    except Exception as e:
+        print("Error creating catalog:")
+        print(e)
+        exit(1)

{deriva_ml-1.17.7 → deriva_ml-1.17.10}/src/deriva_ml/execution/execution.py

@@ -384,9 +384,9 @@ class Execution:
                 file_name="configuration.json",
                 asset_types=ExecMetadataType.execution_config.value,
             )
-            with Path(cfile).open("w", encoding="utf-8") as config_file:
-                json.dump(self.configuration.model_dump(), config_file)
 
+            with Path(cfile).open("w", encoding="utf-8") as config_file:
+                json.dump(self.configuration.model_dump(mode="json"), config_file)
             lock_file = Path(self.configuration.workflow.git_root) / "uv.lock"
             if lock_file.exists():
                 _ = self.asset_file_path(
@@ -920,8 +920,11 @@ class Execution:
 
         # Determine if we will need to rename an existing file as the asset.
         file_name = Path(file_name)
-        target_name = Path(rename_file) if file_name.exists() and rename_file else file_name
+        if file_name.name == "_implementations.log":
+            # There is a funny bug with S3 hatrac if we have the leading _ in the filename.
+            file_name = file_name.with_name("-implementations.log")
 
+        target_name = Path(rename_file) if file_name.exists() and rename_file else file_name
         asset_path = asset_file_path(
             prefix=self._working_dir,
             exec_rid=self.execution_rid,

{deriva_ml-1.17.7 → deriva_ml-1.17.10}/src/deriva_ml/execution/workflow.py

@@ -130,7 +130,7 @@ class Workflow(BaseModel):
             self.url, self.checksum = Workflow.get_url_and_checksum(path)
             self.git_root = Workflow._get_git_root(path)
 
-        self.version = Workflow.get_dynamic_version(root=str(self.git_root or Path.cwd()))
+        self.version = self.version or Workflow.get_dynamic_version(root=str(self.git_root or Path.cwd()))
         self._logger = logging.getLogger("deriva_ml")
         return self
 

{deriva_ml-1.17.7 → deriva_ml-1.17.10}/src/deriva_ml.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: deriva-ml
-Version: 1.17.7
+Version: 1.17.10
 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
@@ -12,7 +12,6 @@ Requires-Dist: deriva~=1.7.10
 Requires-Dist: deepdiff
 Requires-Dist: nbconvert
 Requires-Dist: pandas
-Requires-Dist: pip-system-certs
 Requires-Dist: pydantic>=2.11
 Requires-Dist: papermill
 Requires-Dist: pandas-stubs==2.2.3.250527

{deriva_ml-1.17.7 → deriva_ml-1.17.10}/src/deriva_ml.egg-info/entry_points.txt

@@ -1,5 +1,6 @@
 [console_scripts]
 bump-version = deriva_ml.bump_version:main
+create-demo-catalog = deriva_ml.demo_catalog:main
 deriva-ml-alter-annotation = deriva_ml.schema_setup.alter_annotation:main
 deriva-ml-check-catalog-schema = deriva_ml.schema.check_schema:main
 deriva-ml-create-schema = deriva_ml.schema_setup.create_schema:main

{deriva_ml-1.17.7 → deriva_ml-1.17.10}/src/deriva_ml.egg-info/requires.txt

@@ -4,7 +4,6 @@ deriva~=1.7.10
 deepdiff
 nbconvert
 pandas
-pip-system-certs
 pydantic>=2.11
 papermill
 pandas-stubs==2.2.3.250527

{deriva_ml-1.17.7 → deriva_ml-1.17.10}/uv.lock

@@ -22,13 +22,13 @@ name = "aiohttp"
 version = "3.13.2"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
-    { name = "aiohappyeyeballs", marker = "python_full_version >= '3.12'" },
-    { name = "aiosignal", marker = "python_full_version >= '3.12'" },
-    { name = "attrs", marker = "python_full_version >= '3.12'" },
-    { name = "frozenlist", marker = "python_full_version >= '3.12'" },
-    { name = "multidict", marker = "python_full_version >= '3.12'" },
-    { name = "propcache", marker = "python_full_version >= '3.12'" },
-    { name = "yarl", marker = "python_full_version >= '3.12'" },
+    { name = "aiohappyeyeballs", marker = "python_full_version >= '3.12' and python_full_version < '3.14'" },
+    { name = "aiosignal", marker = "python_full_version >= '3.12' and python_full_version < '3.14'" },
+    { name = "attrs", marker = "python_full_version >= '3.12' and python_full_version < '3.14'" },
+    { name = "frozenlist", marker = "python_full_version >= '3.12' and python_full_version < '3.14'" },
+    { name = "multidict", marker = "python_full_version >= '3.12' and python_full_version < '3.14'" },
+    { name = "propcache", marker = "python_full_version >= '3.12' and python_full_version < '3.14'" },
+    { name = "yarl", marker = "python_full_version >= '3.12' and python_full_version < '3.14'" },
 ]
 sdist = { url = "https://files.pythonhosted.org/packages/1c/ce/3b83ebba6b3207a7135e5fcaba49706f8a4b6008153b4e30540c982fae26/aiohttp-3.13.2.tar.gz", hash = "sha256:40176a52c186aefef6eb3cad2cdd30cd06e3afbe88fe8ab2af9c0b90f228daca", size = 7837994, upload-time = "2025-10-28T20:59:39.937Z" }
 wheels = [
@@ -141,7 +141,7 @@ name = "aiosignal"
 version = "1.4.0"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
-    { name = "frozenlist", marker = "python_full_version >= '3.12'" },
+    { name = "frozenlist", marker = "python_full_version >= '3.12' and python_full_version < '3.14'" },
     { name = "typing-extensions", marker = "python_full_version == '3.12.*'" },
 ]
 sdist = { url = "https://files.pythonhosted.org/packages/61/62/06741b579156360248d1ec624842ad0edf697050bbaf7c3e46394e106ad1/aiosignal-1.4.0.tar.gz", hash = "sha256:f47eecd9468083c2029cc99945502cb7708b082c232f9aca65da147157b251c7", size = 25007, upload-time = "2025-07-03T22:54:43.528Z" }
@@ -879,7 +879,6 @@ dependencies = [
     { name = "pandas" },
     { name = "pandas-stubs" },
     { name = "papermill" },
-    { name = "pip-system-certs" },
     { name = "pydantic" },
     { name = "pyyaml" },
     { name = "regex" },
@@ -919,7 +918,6 @@ requires-dist = [
     { name = "pandas" },
     { name = "pandas-stubs", specifier = "==2.2.3.250527" },
     { name = "papermill" },
-    { name = "pip-system-certs" },
     { name = "pydantic", specifier = ">=2.11" },
     { name = "pyyaml" },
     { name = "regex", specifier = "~=2024.7.24" },
@@ -4072,9 +4070,9 @@ name = "yarl"
 version = "1.22.0"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
-    { name = "idna", marker = "python_full_version >= '3.12'" },
-    { name = "multidict", marker = "python_full_version >= '3.12'" },
-    { name = "propcache", marker = "python_full_version >= '3.12'" },
+    { name = "idna", marker = "python_full_version >= '3.12' and python_full_version < '3.14'" },
+    { name = "multidict", marker = "python_full_version >= '3.12' and python_full_version < '3.14'" },
+    { name = "propcache", marker = "python_full_version >= '3.12' and python_full_version < '3.14'" },
 ]
 sdist = { url = "https://files.pythonhosted.org/packages/57/63/0c6ebca57330cd313f6102b16dd57ffaf3ec4c83403dcb45dbd15c6f3ea1/yarl-1.22.0.tar.gz", hash = "sha256:bebf8557577d4401ba8bd9ff33906f1376c877aa78d1fe216ad01b4d6745af71", size = 187169, upload-time = "2025-10-06T14:12:55.963Z" }
 wheels = [