Files
fantabeto/requirements.txt
T
ramseshk 35370c81f8 feat: PWA auction assistant — mobile-first progressive web app
FastAPI backend:
- /api/players — search/filter 505 Serie A players with calibrated prices
- /api/player/name — full detail with ML predictions (quantile P10/P50/P90,
  starter probability, bandit bid recommendation, opponent bid estimate)
- /api/roster — CRUD for live auction roster with budget tracking
- /api/stats — league-wide price distribution
- All ML models loaded on startup (quantile, survival, bandit, opponent, budget)

PWA frontend:
- Installable on iOS/Android via manifest.json + service worker
- Dark theme matching Fantabeto design system
- Player search with role filter, quick-scan list
- Detail sheet with ML intelligence cards
- One-tap bid buttons (market, ML rec, max)
- Live budget bar, roster management
- Works offline for cached assets
- Mobile-first (480px max-width)

Launch: uvicorn pwa.api:app --port 8601
Live at: http://localhost:8601
2026-08-12 12:38:00 +08:00

68 lines
972 B
Plaintext

# Fantabeto 2026/27 — Core dependencies
python-dateutil>=2.8
requests>=2.31
beautifulsoup4>=4.12
lxml>=5.0
# Data processing
pandas>=2.1
numpy>=1.26
openpyxl>=3.1
scipy>=1.11
pyyaml>=6.0
# ML models
lightgbm>=4.3
catboost>=1.2
xgboost>=2.0
scikit-learn>=1.4
# Hyperparameter tuning
optuna>=3.5
# Graph neural network (optional, for T-GNN)
torch>=2.2
torch-geometric>=2.5
# Optimization
pulp>=2.8
scikit-optimize>=0.9
# Bayesian modeling (optional)
pymc>=5.0
lifelines>=0.28
# Causal inference (optional)
econml>=0.15
# Browser automation (Playwright fallback for Cloudflare)
playwright>=1.42
# RAG & LLM (optional, for news pipeline)
langchain>=0.1
langchain-community>=0.1
chromadb>=0.4
feedparser>=6.0
# LLM providers (choose one)
openai>=1.12
# anthropic>=0.20
# ollama>=0.1
# Visualization
matplotlib>=3.8
seaborn>=0.13
plotly>=5.18
# Development
pytest>=8.0
black>=24.0
ruff>=0.3
# Bot
python-telegram-bot>=21.0
# PWA API
fastapi>=0.110
uvicorn>=0.29