Major refactor: Fantabeto 26/27 — modular package, GBM ensemble, MILP/MCTS optimization

Phase 1: Data Engineering
- Refactored notebooks into src/{scraper,features,models,optimization,bot}
- FBref scraper with proxy rotation + Playwright Cloudflare bypass
- Fantacalcio.it integrated scraper (authenticated API + HTML fallback)
- api-football RapidAPI client for supplementary xG/xA/injuries
- RAG news pipeline: Gazzetta, Sky Sport, Di Marzio → injury/suspension/tactical extraction
- 26/27 season config: teams, scoring rules, name mappings, news sources

Phase 2: SOTA ML Architecture
- GBM Ensemble (LightGBM + CatBoost + XGBoost) with stacked blending
- Bootstrap ensemble for uncertainty quantification
- SinhArcsinh distribution head (ported from original TF Probability)
- Card classifiers (yellow/red), penalty model, goal probability (Poisson)
- Temporal GNN for player interaction modeling (crosses→goals, passes→assists)
- Optuna hyperparameter tuning with time-series CV

Phase 3: Operations Research
- Auction solver: MILP knapsack with PuLP (budget + role constraints)
- Grid Auction (Asta a Griglia): Minimax game theory bidding strategy
- Weekly lineup optimizer: MCTS maximizing win probability vs opponent
- Modificatore Difesa integration + captain selection
- Transfer market analyzer: buy-low/sell-high via xG regression to mean
- Opponent behavior modeling from historical lineage patterns

Phase 4: Agentic Workflow
- Telegram bot: auto-briefing (Friday + Sunday morning)
- Tactical briefing generator with start/sit recommendations
- GitHub Actions CI/CD: scheduled pipeline (scrape → predict → notify)

Infrastructure:
- 31 pytest unit tests (features, models, scraper, optimization)
- requirements.txt (lightgbm, catboost, xgboost, optuna, pulp, playwright, langchain)
- Makefile with install/test/lint/scrape/train/bot targets
- Jupyter notebook: 26_27_strategy.ipynb demonstrating auction + matchday 1 mockup
- Completely rewritten README.md with architecture diagram

Makefile

@@ -0,0 +1,48 @@
+.PHONY: help install test lint pipeline scrape train optimize predict bot clean
+
+help:
+	@echo "Fantabeto 26/27 Commands"
+	@echo "========================"
+	@echo "make install   - Install dependencies"
+	@echo "make test      - Run test suite"
+	@echo "make lint      - Run ruff linter"
+	@echo "make scrape    - Scrape FBref data for 2024-26 seasons"
+	@echo "make features  - Build feature datasets"
+	@echo "make train     - Train ML models"
+	@echo "make optimize  - Run auction + lineup optimization"
+	@echo "make predict   - Generate matchday predictions"
+	@echo "make pipeline  - Run full pipeline (scrape -> features -> train)"
+	@echo "make bot       - Send Telegram briefing"
+	@echo "make clean     - Remove generated data files"
+
+install:
+	pip install -r requirements.txt
+	playwright install chromium
+
+test:
+	python -m pytest tests/ -v
+
+lint:
+	ruff check src/ tests/
+
+scrape:
+	python -c "from src.pipeline import Pipeline; p = Pipeline(); p.scrape_fbref(['2024-2025','2025-2026'], current=True)"
+
+features:
+	python -c "from src.pipeline import Pipeline; p = Pipeline(); p.build_features()"
+
+train:
+	python -c "import pandas as pd; from src.pipeline import Pipeline; p = Pipeline(); df = pd.read_excel('data/match_dataset.xlsx'); y = df['fantavote']; X = df.drop(columns=['fantavote','vote','matchday','player','team','oppteam'], errors='ignore'); p.train_models(X,y)"
+
+predict:
+	python -c "from src.pipeline import Pipeline; p = Pipeline(); p.run_full_pipeline()"
+
+bot:
+	python -c "from src.bot.telegram_bot import TelegramBot; from src.bot.briefing import BriefingGenerator; bot = TelegramBot(); gen = BriefingGenerator(); print('Bot ready. Use send_briefing() to dispatch.')"
+
+pipeline: scrape features train
+
+clean:
+	rm -rf data/
+	find . -type d -name __pycache__ -exec rm -rf {} +
+	find . -type f -name "*.pyc" -delete