adds fine tuning notebook and sample datasets

.github/workflows/nightly-test.yml

@@ -16,22 +16,23 @@ jobs:
     runs-on: ubuntu-latest
     outputs:
       notebooks: ${{ steps.get_nbs.outputs.notebooks }}
+      has_notebooks: ${{ steps.get_nbs.outputs.has_notebooks }}
     steps:
-      - uses: actions/checkout@v2
+      - uses: actions/checkout@v3
 
       - id: get_nbs
         run: |
-          # 1) Read ignore patterns from .github/ignore-notebooks.txt
+          # 1) Find all available notebooks
+          NBS=$(find python-recipes -name '*.ipynb')
+
+          # 2) Load notebooks to ignore
           IGNORE_LIST=()
           while IFS= read -r skip_nb || [ -n "$skip_nb" ]; do
             # Skip empty lines or comment lines
             [[ -z "$skip_nb" || "$skip_nb" =~ ^# ]] && continue
             IGNORE_LIST+=("$skip_nb")
           done < .github/ignore-notebooks.txt
 
-          # 2) Find all .ipynb in python-recipes (or your path)
-          NBS=$(find python-recipes -name '*.ipynb')
-
           # 3) Filter out notebooks that match anything in IGNORE_LIST
           FILTERED_NBS=()
           for nb in $NBS; do
@@ -42,29 +43,36 @@ jobs:
                 break
               fi
             done
-
             if [ "$skip" = false ]; then
               FILTERED_NBS+=("$nb")
             fi
           done
 
-          # 4) Convert the final array to compact JSON for GitHub Actions
+          # 4) Stuff into a single-line JSON array
           NB_JSON=$(printf '%s\n' "${FILTERED_NBS[@]}" \
             | jq -R . \
             | jq -s -c .)
 
-          # 5) Default to an empty array if there's nothing left
           if [ -z "$NB_JSON" ] || [ "$NB_JSON" = "[]" ]; then
             NB_JSON="[]"
           fi
 
           echo "All valid notebooks: $NB_JSON"
+
+          # 5) Check if there's anything in FILTERED_NBS
+          if [ "${#FILTERED_NBS[@]}" -gt 0 ]; then
+            echo "has_notebooks=true" >> $GITHUB_OUTPUT
+          else
+            echo "has_notebooks=false" >> $GITHUB_OUTPUT
+          fi
+
           echo "notebooks=$NB_JSON" >> $GITHUB_OUTPUT
 
   # ---------------------------------------------------------
   # 2) Test all notebooks in parallel
   # ---------------------------------------------------------
   test_all_notebooks:
+    if: ${{ needs.gather_all_notebooks.outputs.has_notebooks == 'true' }}
     needs: gather_all_notebooks
     runs-on: ubuntu-latest
     strategy:
@@ -79,7 +87,7 @@ jobs:
           - 6379:6379
 
     steps:
-      - uses: actions/checkout@v2
+      - uses: actions/checkout@v3
 
       # Setup Python
       - uses: actions/setup-python@v4

.github/workflows/test.yml

@@ -17,28 +17,29 @@ jobs:
     runs-on: ubuntu-latest
     outputs:
       notebooks: ${{ steps.get_nbs.outputs.notebooks }}
+      has_notebooks: ${{ steps.get_nbs.outputs.has_notebooks }}
     steps:
-      - uses: actions/checkout@v2
+      - uses: actions/checkout@v3
 
-      - id: get_nbs
+      - name: Gather notebooks
+        id: get_nbs
         run: |
-          # Compare this commit/PR to 'main' and list changed .ipynb files
+          # 1) Compare this commit/PR to 'main' and list changed notebooks
           git fetch --depth=1 origin main
           CHANGED_NOTEBOOKS=$(git diff --name-only origin/main | grep '\.ipynb$' || true)
 
-          # 1) Read ignore patterns from .github/ignore-notebooks.txt
+          # 2) Load notebooks to ignore
           IGNORE_LIST=()
           while IFS= read -r skip_nb || [ -n "$skip_nb" ]; do
             # Skip empty lines or comment lines
             [[ -z "$skip_nb" || "$skip_nb" =~ ^# ]] && continue
             IGNORE_LIST+=("$skip_nb")
           done < .github/ignore-notebooks.txt
 
-          # 2) Filter out notebooks in CHANGED_NOTEBOOKS that match ignore patterns
+          # 3) Filter out ignored notebooks
           FILTERED_NBS=()
           for nb in $CHANGED_NOTEBOOKS; do
             skip=false
-
             # Check if in ignore list
             for ignore_nb in "${IGNORE_LIST[@]}"; do
               # Partial match:
@@ -47,33 +48,31 @@ jobs:
                 break
               fi
             done
-
             if [ "$skip" = false ]; then
               FILTERED_NBS+=("$nb")
             fi
           done
 
-          # 3) Build a single-line JSON array
+          # 4) Stuff into a single-line JSON array
           NB_JSON=$(printf '%s\n' "${FILTERED_NBS[@]}" \
             | jq -R . \
             | jq -s -c .)
 
-          # 4) Fallback to an empty array if there's nothing left
           if [ -z "$NB_JSON" ] || [ "$NB_JSON" = "[]" ]; then
             NB_JSON="[]"
           fi
 
           echo "All valid notebooks: $NB_JSON"
 
-          # 5) Write to $GITHUB_OUTPUT
-          if [ "$NB_JSON" != "[]" ]; then
+          # 5) Check if there's anything in FILTERED_NBS
+          if [ "${#FILTERED_NBS[@]}" -gt 0 ]; then
             echo "has_notebooks=true" >> $GITHUB_OUTPUT
           else
             echo "has_notebooks=false" >> $GITHUB_OUTPUT
           fi
 
           echo "notebooks=$NB_JSON" >> $GITHUB_OUTPUT
-      
+
   # ---------------------------------------------------------
   # 2) Test each changed notebook in parallel
   # ---------------------------------------------------------
@@ -93,7 +92,7 @@ jobs:
           - 6379:6379
 
     steps:
-      - uses: actions/checkout@v2
+      - uses: actions/checkout@v3
 
       # Setup Python
       - uses: actions/setup-python@v4

.gitignore

@@ -1,4 +1,222 @@
-.env
-node_modules/
+# Created by https://www.toptal.com/developers/gitignore/api/python,venv,macos
+# Edit at https://www.toptal.com/developers/gitignore?templates=python,venv,macos
+
+### macOS ###
+# General
 .DS_Store
-.pytest_cache/
+.AppleDouble
+.LSOverride
+
+# Icon must end with two \r
+Icon
+
+
+# Thumbnails
+._*
+
+# Files that might appear in the root of a volume
+.DocumentRevisions-V100
+.fseventsd
+.Spotlight-V100
+.TemporaryItems
+.Trashes
+.VolumeIcon.icns
+.com.apple.timemachine.donotpresent
+
+# Directories potentially created on remote AFP share
+.AppleDB
+.AppleDesktop
+Network Trash Folder
+Temporary Items
+.apdisk
+
+### macOS Patch ###
+# iCloud generated files
+*.icloud
+
+### Python ###
+# 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/
+
+### Python Patch ###
+# Poetry local configuration file - https://python-poetry.org/docs/configuration/#local-configuration
+poetry.toml
+
+# ruff
+.ruff_cache/
+
+# LSP config files
+pyrightconfig.json
+
+### venv ###
+# Virtualenv
+# http://iamzed.com/2009/05/07/a-primer-on-virtualenv/
+[Bb]in
+[Ii]nclude
+[Ll]ib
+[Ll]ib64
+[Ll]ocal
+pyvenv.cfg
+pip-selfcheck.json
+
+libs/redis/docs/.Trash*
+.python-version
+.idea/*

.python-version

@@ -1 +1 @@
-3.11.9
+3.11