deriva-ml 1.8.4__tar.gz → 1.8.10__tar.gz

deriva_ml-1.8.10/.github/workflows/publish-docs.yml

@@ -0,0 +1,29 @@
+name: DerivaML 
+on:
+  push:
+    branches:
+      - master 
+      - main
+permissions:
+  contents: write
+jobs:
+  deploy:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - name: Configure Git Credentials
+        run: |
+          git config user.name github-actions[bot]
+          git config user.email 41898282+github-actions[bot]@users.noreply.github.com
+      - uses: actions/setup-python@v5
+        with:
+          python-version: 3.x
+      - run: echo "cache_id=$(date --utc '+%V')" >> $GITHUB_ENV 
+      - uses: actions/cache@v4
+        with:
+          key: mkdocs-material-${{ env.cache_id }}
+          path: .cache
+          restore-keys: |
+            mkdocs-material-
+      - run: pip install mkdocs-material mkdocstrings[python] mkdocs-jupyter ruff semver
+      - run: mkdocs gh-deploy --force

deriva_ml-1.8.10/.gitignore

@@ -0,0 +1,160 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+.idea/

{deriva_ml-1.8.4/src/deriva_ml.egg-info → deriva_ml-1.8.10}/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.2
+Metadata-Version: 2.4
 Name: deriva-ml
-Version: 1.8.4
+Version: 1.8.10
 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
@@ -11,8 +11,10 @@ Requires-Dist: pandas
 Requires-Dist: regex~=2024.7.24
 Requires-Dist: pydantic>=2.10.6
 Requires-Dist: semver>3.0.0
-Requires-Dist: setuptools-git-versioning<3,>=2.0
+Requires-Dist: setuptools>=64
+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
 using a deriva catalog.

deriva_ml-1.8.10/docs/Notebooks/DerivaML Create Notes.ipynb

@@ -0,0 +1,248 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "94ffee41-4986-4196-b35d-b38b6e10490a",
+   "metadata": {},
+   "source": [
+    "DerivaML is a class library built on the Deriva Scientific Asset management system that is designed to help simplify a number of the basic operations associated with building and testing ML libraries based on common toolkits such as TensorFlow.  This notebook reviews the basic features of the DerivaML library."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "id": "ff605747-195b-40a1-b915-0e799f8d0748",
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2025-02-25T21:48:28.351714Z",
+     "start_time": "2025-02-25T21:48:28.337684Z"
+    }
+   },
+   "source": [
+    "%load_ext autoreload\n",
+    "%autoreload 2"
+   ],
+   "outputs": [],
+   "execution_count": 1
+  },
+  {
+   "cell_type": "code",
+   "id": "9493a5ef-86b9-490b-a1d5-f461fdcd68ef",
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2025-02-25T21:48:34.419914Z",
+     "start_time": "2025-02-25T21:48:33.686305Z"
+    }
+   },
+   "source": [
+    "import builtins\n",
+    "from demo_catalog import create_demo_catalog, DemoML\n",
+    "from deriva.core.utils.globus_auth_utils import GlobusNativeLogin\n",
+    "from IPython.display import display, Markdown, HTML, IFrame\n"
+   ],
+   "outputs": [],
+   "execution_count": 2
+  },
+  {
+   "cell_type": "markdown",
+   "id": "ba06990f-6dc5-4805-9e82-0881a524bfef",
+   "metadata": {},
+   "source": [
+    "Set the details for the catalog we want and authenticate to the server if needed."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "id": "9ee79ab7-a3f7-4c69-9c80-336871c13ec2",
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-11-29T21:26:58.015044Z",
+     "start_time": "2024-11-29T21:26:57.868191Z"
+    }
+   },
+   "source": [
+    "hostname = 'dev.eye-ai.org'\n",
+    "domain_schema = 'demo-schema'\n",
+    "\n",
+    "gnl = GlobusNativeLogin(host=hostname)\n",
+    "if gnl.is_logged_in([hostname]):\n",
+    "    print(\"You are already logged in.\")\n",
+    "else:\n",
+    "    gnl.login([hostname], no_local_server=True, no_browser=True, refresh_tokens=True, update_bdbag_keychain=True)\n",
+    "    print(\"Login Successful\")\n"
+   ],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "You are already logged in.\n"
+     ]
+    }
+   ],
+   "execution_count": 6
+  },
+  {
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2025-02-25T21:55:24.227032Z",
+     "start_time": "2025-02-25T21:55:24.201465Z"
+    }
+   },
+   "cell_type": "code",
+   "source": [
+    "import json\n",
+    "import os\n",
+    "import ipykernel\n",
+    "import requests\n",
+    "\n",
+    "def get_notebook_filename():\n",
+    "    \"\"\"Returns the current Jupyter Notebook filename.\"\"\"\n",
+    "    try:\n",
+    "        # Get the kernel ID\n",
+    "        kernel_id = ipykernel.connect.get_connection_file().split('-')[1].split('.')[0]\n",
+    "        print(kernel_id)\n",
+    "        # Get running notebook servers\n",
+    "        response = requests.get('http://127.0.0.1:8888/api/sessions', headers={'Authorization': ''})\n",
+    "        sessions = json.loads(response.text)\n",
+    "        print(sessions)\n",
+    "        # Match the kernel ID to find the notebook name\n",
+    "        for session in sessions:\n",
+    "            print(session)\n",
+    "            if session['kernel']['id'] == kernel_id:\n",
+    "                return session['name']  # Returns the filename\n",
+    "    except Exception as e:\n",
+    "        return f\"Error: {e}\"\n",
+    "\n",
+    "# Usage\n",
+    "notebook_file = get_notebook_filename()\n",
+    "print(f\"Current Notebook: {notebook_file}\")"
+   ],
+   "id": "94d9b590bc04d3fa",
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "23f783f8\n",
+      "{'message': 'Forbidden', 'reason': None}\n",
+      "message\n",
+      "Current Notebook: Error: string indices must be integers\n"
+     ]
+    }
+   ],
+   "execution_count": 8
+  },
+  {
+   "cell_type": "code",
+   "id": "e9bddcf0-27ea-40b3-a388-b77635586fad",
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-11-29T21:27:24.811146Z",
+     "start_time": "2024-11-29T21:27:01.353095Z"
+    }
+   },
+   "source": [
+    "test_catalog = create_demo_catalog(hostname, domain_schema)\n",
+    "ml_instance = DemoML(hostname, test_catalog.catalog_id)"
+   ],
+   "outputs": [],
+   "execution_count": 7
+  },
+  {
+   "cell_type": "markdown",
+   "id": "92416df1-e3f9-4097-bc19-b24712dc7242",
+   "metadata": {},
+   "source": [
+    "Now using TestFeatureClass, we can create some instances of the feature and add it.  We must have a exeuction_rid in order to define the feature."
+   ]
+  },
+  {
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-11-29T21:44:32.359769Z",
+     "start_time": "2024-11-29T21:44:32.301145Z"
+    }
+   },
+   "cell_type": "code",
+   "source": "display(IFrame(ml_instance.chaise_url('Page'), 500, 500))\n",
+   "id": "4a7c313481859e78",
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "<IPython.lib.display.IFrame at 0x17b5d6b10>"
+      ],
+      "text/html": [
+       "\n",
+       "        <iframe\n",
+       "            width=\"500\"\n",
+       "            height=\"500\"\n",
+       "            src=\"https://dev.eye-ai.org/chaise/recordset/#631/www%3APage\"\n",
+       "            frameborder=\"0\"\n",
+       "            allowfullscreen\n",
+       "            \n",
+       "        ></iframe>\n",
+       "        "
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "execution_count": 21
+  },
+  {
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-11-29T21:49:30.725063Z",
+     "start_time": "2024-11-29T21:49:29.753350Z"
+    }
+   },
+   "cell_type": "code",
+   "source": "ml_instance.chaise_url('Page')",
+   "id": "ea200c3f5ff4d39f",
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'https://dev.eye-ai.org/chaise/recordset/#631/www:Page'"
+      ]
+     },
+     "execution_count": 23,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "execution_count": 23
+  },
+  {
+   "metadata": {},
+   "cell_type": "code",
+   "source": "test_catalog.delete_ermrest_catalog(really=True)",
+   "id": "79aa46cf32c2db00",
+   "outputs": [],
+   "execution_count": null
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.12.2"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}