# Python
__pycache__/
*.py[cod]
*$py.class
.pytest_cache/
.hypothesis/

# Environment
.env
.venv/
venv/

# Database
*.db
*.db-shm
*.db-wal
*.sqlite3

# Models (general pkl ignored, but production models are tracked)
*.pkl
!backend/diabetes_model.pkl
!backend/heart_disease_model.pkl
!backend/kidney_model.pkl
!backend/kidney_scaler.pkl
!backend/liver_disease_model.pkl
!backend/liver_scaler.pkl
!backend/lungs_model.pkl
!backend/lungs_scaler.pkl

# Logs & Temp
*.log
session.json
.coverage
htmlcov/
pytest_output.txt
tmp/
output/

# Local drafts
README_DATA_ENGINEERING.md
README_ENHANCED.md
RESUME_*.tex

# IDE & AI Tools
.cursor/
.cursorrules
.antigravity/
.gemini/
.idea/
.vscode/
.kiro/
CLAUDE.md
GEMINI.md

# Antigravity / Agent brain data (NEVER commit)
brain/

# Streamlit config
.streamlit/

# Build
dist/
build/
*.egg-info/
node_modules/
.next/
playwright-report/
test-results/

# RAG vector store (generated at runtime)
models/vector_store.*

# Airflow
airflow/logs/
airflow/airflow.db

# OS
.DS_Store
Thumbs.db

# Legacy/dead frontends
frontend_legacy/
frontend_v2/

# Loose scripts (moved to scripts/)
seed_data.py
seed_doctor.py
start_servers.bat

# Personal/interview docs
docs/interview-guide/
docs/delta-lake-architecture.md
docs/scd_*.md
docs/time_travel_*.md
docs/optimal_dual_layer_architecture.md
docs/ZERO_CAPITAL_GUIDE.md
docs/GITHUB_METADATA.md
# Data Lake layers (Bronze, Silver, Gold Parquet files)
data/bronze/
data/silver/
data/gold/
# Keep only the Gold Analyst Report JSON file tracked in git for deployment
!data/gold/analyst_report.json

# Spark Telemetry stream & checkpoint directories
data/telemetry_stream/
data/checkpoints/
.hadoop/


# Catboost
catboost_info/
