.gitignore

# Byte-compiled / optimized / DLL files
__pycache__/
*.py[codz]
*$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

# UV
#   Similar to Pipfile.lock, it is generally recommended to include uv.lock in version control.
#   This is especially recommended for binary packages to ensure reproducibility, and is more
#   commonly ignored for libraries.
#uv.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
#poetry.toml

# pdm
#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
#   pdm recommends including project-wide configuration in pdm.toml, but excluding .pdm-python.
#   https://pdm-project.org/en/latest/usage/project/#working-with-version-control
#pdm.lock
#pdm.toml
.pdm-python
.pdm-build/

# pixi
#   Similar to Pipfile.lock, it is generally recommended to include pixi.lock in version control.
#pixi.lock
#   Pixi creates a virtual environment in the .pixi directory, just like venv module creates one
#   in the .venv directory. It is recommended not to include this directory in version control.
.pixi

# 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
.envrc
.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/

# Abstra
# Abstra is an AI-powered process automation framework.
# Ignore directories containing user credentials, local state, and settings.
# Learn more at https://abstra.io/docs
.abstra/

# Visual Studio Code
#  Visual Studio Code specific template is maintained in a separate VisualStudioCode.gitignore 
#  that can be found at https://github.com/github/gitignore/blob/main/Global/VisualStudioCode.gitignore
#  and can be added to the global gitignore or merged into this file. However, if you prefer, 
#  you could uncomment the following to ignore the entire vscode folder
# .vscode/

# Ruff stuff:
.ruff_cache/

# PyPI configuration file
.pypirc

# Cursor
#  Cursor is an AI-powered code editor. `.cursorignore` specifies files/directories to
#  exclude from AI features like autocomplete and code analysis. Recommended for sensitive data
#  refer to https://docs.cursor.com/context/ignore-files
.cursorignore
.cursorindexingignore

# Marimo
marimo/_static/
marimo/_lsp/
__marimo__/


# -----------------------------
# Custom: Newsletter Project
# -----------------------------

# OS/editor cruft
.DS_Store

# Local public-release audit scratch files
xxx_*.md

# Raw data (original newsletter HTML files)
data_raw

# Local database backups; tracked historical manifests/files are unaffected.
data/supabase_backup/

# Large or intermediate processed files
*.csv
*.xlsx

# Optional: temporary working folders
data/tmp/


.env


# .ipynb_checkpoints/
**/.ipynb_checkpoints/


# -----------------------------
# AM1 Project Specific
# -----------------------------

# Model artifacts
*.pkl
analysis/models/

# MLflow
mlruns/

# Data: ignore dataset file contents under data/, but TRACK the code/apps/READMEs
# that now live there (labelling_app, document_check_app, link_resolver, sync scripts).
# (*.csv is already ignored globally above.)
data/**/*.parquet
data/**/*.feather
data/**/*.xlsx
data/**/*.xls
data/**/*.npz
data/**/*.faiss
data/tmp/

# Internal docs (not pushed to GitHub)
docs/internal/

# Dashboard snapshots (data files)
pipelines/nmf_baseline/dashboard/streamlit_nmf/snapshots/

# Credentials
credentials.json

# --- BERTopic artefacts (see ARTIFACTS.md) ---
# Embeddings: ~165MB, rebuildable via pipelines/bertopic_epoch/training/build_embeddings.py -> ignore.
pipelines/bertopic_epoch/models/embeddings/
# Regenerated analysis outputs -> ignore (canonical = frozen models + crosswalk).
pipelines/bertopic_epoch/outputs/
# ...EXCEPT the category scheme — it's a RUNTIME dependency of the inference API (the
# topic->category map read by inference.py + baked into the Docker image), so track it.
# This 3-line dance un-ignores just this one file inside the otherwise-ignored outputs/
# dir, and (being last + most specific) also beats the global *.csv rule above.
!pipelines/bertopic_epoch/outputs/
pipelines/bertopic_epoch/outputs/*
!pipelines/bertopic_epoch/outputs/final_topics_category_scheme.csv
# Frozen v1 topic_models (~19MB) are NOT ignored: commit them (load-bearing;
# topic IDs are referenced by docs/methods/category_scheme.csv).

# Local pre-restructure backups (never commit)
_backup_pre_restructure/

# MLflow local tracking (file-based)
experiments/mlruns/

.vscode/

# scraping pipeline data outputs
ingestion/data/
x_dll/

# PDFs (working docs, not part of the corpus)
*.pdf

# private company/commercialisation strategy — do not commit
planning/x_commercialisation_strategy.md
experiments/.numba_cache/
experiments/.matplotlib_cache/
*.pyc

# Guard: stray model tree if a notebook mis-resolves ROOT
pipelines/bertopic_epoch/notebooks/models/

# personal planning scratch (not for repo)
xxx_plan.md

# assessment working scratch (not for repo)
docs/assessment/business_metrics.md

# PSD assessment write-up + working drafts (personal, not for repo)
AM1 NOW/
docs/assessment/L6_MLengineer_PSD.docx

# editor/agent/OS junk
.claude/
.codex/
.agents/
.vscode/
**/.DS_Store

# Assessment working docs (kept local, not tracked)
X_ASSESSMENT/AIE PORTFOLIO QUESTIONS .docx
X_ASSESSMENT/L6_MLengineer_PSD_Draft_LY.docx

# Paper drafts (kept local, not tracked)
EMPIRICAL FLAGSHIP/

# Country briefs (kept local, not tracked)
country_briefs/
docs/briefs/

# EPOCH dashboard (old marketing-framed build; kept local, not tracked pending rebuild)
dashboard/epoch/

# TRACE dashboard WIP (kept local, not tracked)
July dashboard update/