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

src/scraper/api_football.py

@@ -0,0 +1,118 @@
+"""api-football integration via RapidAPI.
+
+Supplements FBref data with real-time injury info, expected goals (xG),
+expected assists (xA), and fixture data.
+
+Requires RAPIDAPI_KEY environment variable.
+"""
+
+import logging
+import os
+import time
+from pathlib import Path
+from typing import Optional
+
+import pandas as pd
+import requests
+
+logger = logging.getLogger(__name__)
+
+API_BASE = "https://api-football-v1.p.rapidapi.com/v3"
+LEAGUE_ID = 135  # Serie A
+
+
+class APIFootballClient:
+    def __init__(self, api_key: Optional[str] = None):
+        self.api_key = api_key or os.getenv("RAPIDAPI_KEY")
+        if not self.api_key:
+            logger.warning("No RAPIDAPI_KEY found. API calls will fail.")
+        self.session = requests.Session()
+        self.session.headers.update({
+            "x-rapidapi-key": self.api_key or "",
+            "x-rapidapi-host": "api-football-v1.p.rapidapi.com",
+        })
+
+    def _get(self, endpoint: str, params: Optional[dict] = None) -> dict:
+        if not self.api_key:
+            raise ValueError("RAPIDAPI_KEY not configured")
+        url = f"{API_BASE}/{endpoint}"
+        resp = self.session.get(url, params=params, timeout=15)
+        resp.raise_for_status()
+        data = resp.json()
+        if data.get("errors"):
+            logger.error(f"API error: {data['errors']}")
+        return data
+
+    def get_fixtures(self, season: int, matchday: Optional[int] = None) -> pd.DataFrame:
+        """Get Serie A fixtures for a season. Optionally filter by matchday."""
+        params = {"league": LEAGUE_ID, "season": season}
+        if matchday:
+            params["round"] = f"Regular Season - {matchday}"
+
+        data = self._get("fixtures", params)
+        fixtures = data.get("response", [])
+        rows = []
+        for fix in fixtures:
+            f = fix["fixture"]
+            teams = fix["teams"]
+            rows.append({
+                "fixture_id": f["id"],
+                "date": f["date"],
+                "matchday": f.get("round", "").replace("Regular Season - ", ""),
+                "home_team": teams["home"]["name"],
+                "away_team": teams["away"]["name"],
+                "home_goals": fix.get("goals", {}).get("home"),
+                "away_goals": fix.get("goals", {}).get("away"),
+            })
+        return pd.DataFrame(rows)
+
+    def get_team_statistics(self, season: int, team_id: int) -> dict:
+        """Get team-level statistics including xG, formations, etc."""
+        data = self._get("teams/statistics", {
+            "league": LEAGUE_ID, "season": season, "team": team_id,
+        })
+        return data.get("response", {})
+
+    def get_player_statistics(self, season: int, team_id: int, page: int = 1) -> pd.DataFrame:
+        """Get player statistics for a team in a given season."""
+        data = self._get("players", {
+            "league": LEAGUE_ID, "season": season, "team": team_id, "page": page,
+        })
+        players = data.get("response", [])
+        rows = []
+        for p in players:
+            player = p["player"]
+            stats = p["statistics"][0] if p.get("statistics") else {}
+            rows.append({
+                "player_id": player["id"],
+                "player_name": player["name"],
+                "position": stats.get("games", {}).get("position", ""),
+                "appearences": stats.get("games", {}).get("appearences", 0),
+                "minutes": stats.get("games", {}).get("minutes", 0),
+                "goals": stats.get("goals", {}).get("total", 0),
+                "assists": stats.get("goals", {}).get("assists", 0),
+                "yellow_cards": stats.get("cards", {}).get("yellow", 0),
+                "red_cards": stats.get("cards", {}).get("red", 0),
+            })
+        return pd.DataFrame(rows)
+
+    def get_injuries(self, season: int, team_id: Optional[int] = None) -> pd.DataFrame:
+        """Get current injury list."""
+        params = {"league": LEAGUE_ID, "season": season}
+        if team_id:
+            params["team"] = team_id
+
+        data = self._get("injuries", params)
+        injuries = data.get("response", [])
+        rows = []
+        for inj in injuries:
+            player = inj["player"]
+            row = {
+                "player_id": player["id"],
+                "player_name": player["name"],
+                "team": inj["team"]["name"],
+                "injury_type": inj.get("player", {}).get("type", ""),
+                "reason": inj.get("player", {}).get("reason", ""),
+            }
+            rows.append(row)
+        return pd.DataFrame(rows)