wehub-resource-sync
204 lines
5.3 KiB
Plaintext
204 lines
5.3 KiB
Plaintext
# ML4T Technical Review - .gitignore
|
|
|
|
# Environment and secrets
|
|
.env
|
|
.env.local
|
|
.env.*.local
|
|
|
|
# Python
|
|
__pycache__/
|
|
*.py[cod]
|
|
*$py.class
|
|
*.so
|
|
*.egg
|
|
*.egg-info/
|
|
dist/
|
|
build/
|
|
eggs/
|
|
.eggs/
|
|
*.manifest
|
|
*.spec
|
|
|
|
# Virtual environments
|
|
.venv/
|
|
venv/
|
|
ENV/
|
|
|
|
# Package manager
|
|
pip-log.txt
|
|
|
|
# Claude Code
|
|
.claude/
|
|
.mcp.json
|
|
|
|
# IDE and editors
|
|
.idea/
|
|
.vscode/
|
|
*.swp
|
|
*.swo
|
|
*~
|
|
|
|
# Jupyter
|
|
.ipynb_checkpoints/
|
|
*.ipynb_checkpoints/
|
|
|
|
# NOTE: .ipynb files ARE committed (for reviewer convenience)
|
|
# Both .py (Jupytext source) and .ipynb (generated) are tracked
|
|
|
|
# Testing
|
|
.pytest_cache/
|
|
.coverage
|
|
htmlcov/
|
|
.tox/
|
|
.nox/
|
|
tests/_internal/notebook_catalog.db
|
|
|
|
# Linter caches
|
|
.ruff_cache/
|
|
|
|
# OS files
|
|
.DS_Store
|
|
Thumbs.db
|
|
|
|
# Data files (downloaded, not tracked)
|
|
# Download using: uv run python data/download_all.py
|
|
data/**/*.parquet
|
|
data/**/*.csv
|
|
data/**/*.h5
|
|
data/**/*.hdf5
|
|
data/**/*.gz
|
|
data/**/*.pkl
|
|
data/**/*.json
|
|
data/**/*.bin
|
|
data/**/*.pcap
|
|
data/**/*.npy
|
|
data/**/*.txt
|
|
data/**/*.xlsx
|
|
data/**/*.pdf
|
|
data/**/*.parquet.gzip
|
|
data/**/*.npz
|
|
data/**/*.meta
|
|
data/**/*.index
|
|
data/**/*.data-*
|
|
data/**/checkpoint
|
|
data/**/__MACOSX/
|
|
data/**/*.xml
|
|
data/**/*.zip
|
|
|
|
# Caches
|
|
data/**/__pycache__/
|
|
data/**/.cache/
|
|
|
|
# Chapter outputs (generated by notebooks)
|
|
*/output/
|
|
!*/output/.gitkeep
|
|
# Root-level output/ — notebooks run from repo root write chapter-relative
|
|
# output/ paths here; regenerable, never committed.
|
|
/output/
|
|
# Executed-state builder logs (scripts/build_executed_state.py)
|
|
scripts/executed_state_logs/
|
|
# Ch23 supply chain extraction cache (11KB, saves 25-min GPU re-run)
|
|
# Whitelist the parent path, then re-exclude all siblings of the cache pair below.
|
|
!23_knowledge_graphs/output/
|
|
23_knowledge_graphs/output/*
|
|
!23_knowledge_graphs/output/supply_chain_cache/
|
|
23_knowledge_graphs/output/supply_chain_cache/*
|
|
!23_knowledge_graphs/output/supply_chain_cache/extracted_triples.parquet
|
|
!23_knowledge_graphs/output/supply_chain_cache/extracted_triples.meta.json
|
|
|
|
# Figure outputs (regenerated by notebooks; publication figures live in book repo)
|
|
*/figures/
|
|
!*/figures/.gitkeep
|
|
case_studies/*/figures/
|
|
|
|
# Local notebook/model run artifacts
|
|
.deploy_source.json
|
|
.ml4t_risk_state.json
|
|
catalog.sqlite
|
|
catboost_info/
|
|
mlruns/
|
|
mlflow.db
|
|
lib/
|
|
tests/notebook_catalog.db
|
|
11_ml_pipeline/models/
|
|
|
|
# Test-status DB is the SSOT in the agents repo, not here — a stray run
|
|
# from the wrong cwd can drop an empty one at this repo root. Never track it.
|
|
test_status.db
|
|
|
|
# Pipeline artifacts (case study outputs — generated, not tracked)
|
|
case_studies/*/features/
|
|
case_studies/*/labels/
|
|
case_studies/*/models/
|
|
case_studies/*/synthesis/
|
|
case_studies/*/backtest/
|
|
case_studies/*/strategy/
|
|
case_studies/*/evaluation/
|
|
case_studies/*/exploration/
|
|
case_studies/*/config/exploration/
|
|
case_studies/*/config/cv_config.json
|
|
case_studies/*/eligibility.csv
|
|
case_studies/*/registry.db
|
|
case_studies/*/results/
|
|
case_studies/*/*_v1_contaminated/
|
|
|
|
# Unified registry and run artifacts — all gitignored
|
|
# registry.db is SSOT but too large for git (43-180 MB per case study)
|
|
# Regenerated from pipeline runs; not needed for readers
|
|
case_studies/*/run_log/
|
|
|
|
# Model checkpoints (from training notebooks)
|
|
**/trainer_great/
|
|
**/trainer_output/
|
|
**/checkpoint-*/
|
|
|
|
# Temporary files
|
|
*.tmp
|
|
*.temp
|
|
*.bak
|
|
*.log
|
|
/tmp/
|
|
|
|
# Executed notebooks (test artifacts)
|
|
_executed_*.ipynb
|
|
|
|
# Misc
|
|
FinFutYY.txt
|
|
f_year.txt
|
|
.test-output/
|
|
test_results/
|
|
|
|
# Notebook catalogs live in book repo
|
|
*/catalog/*.json
|
|
case_studies/*/catalog/*.json
|
|
|
|
# Chapter 25 deployment loop artefacts (regenerated by 02_etfs_deployment_loop)
|
|
25_live_trading/live_artifacts/
|
|
|
|
# Chapter 24 research-operator captured traces. The directory is ignored (live
|
|
# re-runs write throwaway traces here), EXCEPT the two canonical pinned traces
|
|
# 11_research_operator replays by default — those are committed (host home path
|
|
# normalized to ~) so the chapter reproduces deterministically on any clone.
|
|
24_autonomous_agents/operator_artifacts/*
|
|
!24_autonomous_agents/operator_artifacts/run_etfs_20260504T223150.json
|
|
!24_autonomous_agents/operator_artifacts/run_us_firm_characteristics_20260504T225521.json
|
|
|
|
# Chapter 24 forecasting run traces. The directory is ignored (live re-runs and
|
|
# CI smoke-tests write throwaway traces here), EXCEPT the canonical pinned traces
|
|
# the notebooks replay by default — those are committed (sanitized) so the
|
|
# chapter reproduces deterministically on any clone. See each notebook's
|
|
# PINNED_TRACE / PINNED_TRACES parameter.
|
|
24_autonomous_agents/forecast_traces/*
|
|
!24_autonomous_agents/forecast_traces/04_research_agent_20260609T141730Z_b694ab4d0453.json
|
|
!24_autonomous_agents/forecast_traces/06_multi_agent_research_20260609T141413Z_9fc4a2655471.json
|
|
!24_autonomous_agents/forecast_traces/07_adversarial_debate_20260609T141631Z_cf1ad76cf379.json
|
|
!24_autonomous_agents/forecast_traces/08_forecasting_pipeline_20260609T141954Z_ef5bca7b95bd.json
|
|
!24_autonomous_agents/forecast_traces/08_forecasting_pipeline_20260609T142158Z_24e083e7fe54.json
|
|
!24_autonomous_agents/forecast_traces/10_framework_comparison_20260609T150909Z_ba1855847f4c.json
|
|
!24_autonomous_agents/forecast_traces/10_framework_comparison_20260609T151202Z_c8cba3007562.json
|
|
!24_autonomous_agents/forecast_traces/01_react_reasoning_20260615T191047Z_04eb6e7c603d.json
|
|
!24_autonomous_agents/forecast_traces/09_evaluation_and_governance_20260615T191431Z_d5030378899c.json
|
|
|
|
# Review tooling config (dev-only)
|
|
.roborev.toml
|