#!/usr/bin/env bash
set -euo pipefail

# ===========================
# Конфиг (меняйте по желанию)
# ===========================
PY=python3
VENV=".venv"

# Порт REST-сервиса:
PORT="${PORT:-8000}"

# Принудить IPv4 (полезно при проблемном IPv6 у провайдера):
FORCE_IPV4="${FORCE_IPV4:-1}"

# API-ключи (необязательно, но улучшает стабильность/квоты):
#   export OPENDOTA_API_KEY=...
#   export STRATZ_TOKEN=...
OPENDOTA_API_KEY="${OPENDOTA_API_KEY:-}"
STRATZ_TOKEN="${STRATZ_TOKEN:-}"

# Использовать STRATZ вместо OpenDota
#   только для шага 1 (список матчей): USE_STRATZ_LIST=1
#   только для шага 2 (детали/драфт):  USE_STRATZ_DETAILS=1
USE_STRATZ_LIST="${USE_STRATZ_LIST:-0}"
USE_STRATZ_DETAILS="${USE_STRATZ_DETAILS:-0}"

# Задержка после каждых 100 запросов (смягчить 429):
SLEEP_PER_100="${SLEEP_PER_100:-1.0}"

# ===========================
# Окружение и зависимости
# ===========================
if [ ! -d "$VENV" ]; then
  $PY -m venv "$VENV"
fi
# shellcheck disable=SC1091
source "$VENV/bin/activate"

pip install -U pip
pip install pandas pyarrow requests httpx "urllib3>=2.2" certifi catboost scikit-learn fastapi uvicorn

mkdir -p data artifacts

# ===========================
# Хелперы
# ===========================
export FORCE_IPV4
export OPENDOTA_API_KEY
export STRATZ_TOKEN
export PAGES
export SLEEP_PER_100

# ===========================
# [1/7] Список pub-матчей
# ===========================
# [1b] Паблики (high-rank)
$PY educationML/fetch_public_matches.py
# [2b] Детали пабликов (герои из players)
$PY educationML/fetch_public_details.py

# ===========================
# [2/7] Список pro-матчей
# ===========================
echo "[1/6] Fetch pro matches via OpenDota (pages=$PAGES)"
$PY educationML/fetch_pro_matches_opendota.py

# =========================================
# [2/6] Детали матча + драфт (устойчивый)
# =========================================
if [ "$USE_STRATZ_DETAILS" = "1" ]; then
  echo "[2/6] Fetch match details + draft via STRATZ"
  $PY - <<'PYCODE'

PYCODE

else
  echo "[2/6] Fetch match details + draft via OpenDota (robust)"
  $PY - <<'PYCODE'
import os, time, socket, sys, pandas as pd, requests, httpx
from urllib3.util.retry import Retry
from requests.adapters import HTTPAdapter

# IPv4-only (если FORCE_IPV4=1)
if os.getenv("FORCE_IPV4","1") == "1":
    _orig = socket.getaddrinfo
    def _v4(host, port, family=0, type=0, proto=0, flags=0):
        return _orig(host, port, socket.AF_INET, type, proto, flags)
    socket.getaddrinfo = _v4

API_KEY = os.getenv("OPENDOTA_API_KEY")
SLEEP_PER_100 = float(os.getenv("SLEEP_PER_100","1.0"))
BASE = "https://api.opendota.com/api/matches/{mid}"
headers = {"User-Agent":"korobkaGames/1.0","Accept":"application/json","Connection":"close"}

# список match_id
pro = pd.read_parquet("data/pro_matches.parquet")
match_ids = pro['match_id'].drop_duplicates().tolist()

# requests с Retry
sess = requests.Session()
retries = Retry(total=6, connect=6, read=6, backoff_factor=0.7,
                status_forcelist=[429,500,502,503,504],
                allowed_methods=frozenset(["GET"]))
sess.mount("https://", HTTPAdapter(max_retries=retries))

def fetch_one(mid: int):
    url = BASE.format(mid=mid)
    if API_KEY:
        url += f"?api_key={API_KEY}"
    try:
        r = sess.get(url, headers=headers, timeout=(5,40))
        r.raise_for_status()
        return r.json()
    except requests.exceptions.SSLError:
        # fallback: httpx http2 off
        with httpx.Client(http2=False, timeout=40, headers=headers) as client:
            resp = client.get(url)
            resp.raise_for_status()
            return resp.json()

match_rows, draft_rows, failed = [], [], []
for i, mid in enumerate(match_ids, 1):
    try:
        m = fetch_one(int(mid))
        match_rows.append({
            "match_id": int(mid),
            "date": pd.to_datetime(m.get("start_time",0), unit="s"),
            "patch": str(m.get("patch")),
            "radiant_win": bool(m.get("radiant_win")),
            "duration_sec": m.get("duration"),
            "league_id": (m.get("league") or {}).get("id"),
            "series_type": m.get("series_type"),
        })
        for pb in (m.get("picks_bans") or []):
            draft_rows.append({
                "match_id": int(mid),
                "is_pick": pb.get("is_pick", False),
                "team": pb.get("team"),
                "hero_id": pb.get("hero_id"),
                "order": pb.get("order")
            })
    except Exception:
        failed.append(int(mid))
    if i % 100 == 0:
        time.sleep(SLEEP_PER_100)

pd.DataFrame(match_rows).to_parquet("data/matches.parquet", index=False)
pd.DataFrame(draft_rows).to_parquet("data/draft.parquet", index=False)
pd.Series(failed, name="failed_match_id").to_csv("data/matches_failed.csv", index=False)
print(f"Saved via OpenDota: matches={len(match_rows)} draft_rows={len(draft_rows)} failed={len(failed)}")
if not match_rows:
    raise SystemExit("OpenDota details: ничего не скачано")
PYCODE
fi

# ===========================
# [3/6] Простой Elo baseline
# ===========================
echo "[3/6] Build Elo"
$PY - <<'PYCODE'
import pandas as pd
matches = pd.read_parquet("data/matches.parquet").sort_values("date")
pro = pd.read_parquet("data/pro_matches.parquet")[['match_id','radiant_name','dire_name']]
df = matches.merge(pro, on='match_id', how='left')

K = 24
elo = {}
def get_elo(t): return elo.get(t, 1500)
def expect(a,b): return 1.0/(1.0+10**((b-a)/400))

rows=[]
for _, r in df.iterrows():
    A, B = r['radiant_name'], r['dire_name']
    ra, rb = get_elo(A), get_elo(B)
    ea, eb = expect(ra,rb), expect(rb,ra)
    y = 1.0 if r['radiant_win'] else 0.0
    rows.append({
        'match_id': r['match_id'],
        'date': r['date'],
        'elo_radiant': ra, 'elo_dire': rb,
        'elo_diff_90': ra - rb  # упрощённо без окон
    })
    elo[A] = ra + K*(y-ea)
    elo[B] = rb + K*((1-y)-eb)

pd.DataFrame(rows).to_parquet("data/elo.parquet", index=False)
print("Saved data/elo.parquet")
PYCODE

# [4] вместо старого build_dataset_draft.py
$PY educationML/build_dataset_mixed.py

# ===========================
# [5/6] Обучение модели
# ===========================
echo "[5/6] Train CatBoost"
$PY - <<'PYCODE'
import pandas as pd
from catboost import CatBoostClassifier
from sklearn.model_selection import TimeSeriesSplit
from sklearn.metrics import log_loss, brier_score_loss

df = pd.read_parquet("data/dataset_mixed.parquet").sort_values("date")
cat_cols = ['patch','source','r_h1','r_h2','r_h3','r_h4','r_h5','d_h1','d_h2','d_h3','d_h4','d_h5']
X = df.drop(columns=['y','date','match_id']) if 'match_id' in df.columns else df.drop(columns=['y','date'])
y = df['y']
cat_idx = [X.columns.get_loc(c) for c in cat_cols]

tscv = TimeSeriesSplit(n_splits=5)
ll, br = [], []
for tr, te in tscv.split(X):
    model = CatBoostClassifier(
        depth=8, iterations=1200, learning_rate=0.03,
        loss_function='Logloss', eval_metric='Logloss', verbose=False
    )
    model.fit(X.iloc[tr], y.iloc[tr], cat_features=cat_idx)
    p = model.predict_proba(X.iloc[te])[:,1]
    ll.append(log_loss(y.iloc[te], p))
    br.append(brier_score_loss(y.iloc[te], p))
print("CV LogLoss=", sum(ll)/len(ll), " Brier=", sum(br)/len(br))

final = CatBoostClassifier(depth=8, iterations=1500, learning_rate=0.03,
                           loss_function='Logloss', verbose=False)
final.fit(X, y, cat_features=cat_idx)
final.save_model("artifacts/model_draft.cbm")
pd.Series(X.columns).to_csv("artifacts/feature_order.csv", index=False)
print("Saved artifacts/model_draft.cbm and artifacts/feature_order.csv")
PYCODE

# ===========================
# [6/6] REST-сервис предсказаний
# ===========================
echo "[6/6] Start API → http://127.0.0.1:$PORT"

exec uvicorn serve:app --host 0.0.0.0 --port "$PORT"