Initial commit: добавление проекта predictV1

Включает модели ML для предсказаний, API маршруты, скрипты обучения и данные.

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>

start/parse_pro_details_match.py

@@ -0,0 +1,106 @@
+import requests
+import psycopg2
+import time
+from psycopg2.extras import RealDictCursor, execute_values
+
+# Подключение к базе данных
+conn = psycopg2.connect(
+    host="localhost",
+    port=5432,
+    database="korobka_db",
+    user="postgres",
+    password="postgres"
+)
+cursor = conn.cursor(cursor_factory=RealDictCursor)
+
+# Функция для определения позиции по lane и lane_role
+def get_position(lane, lane_role):
+    """
+    lane 2, lane_role 2 -> pos 2 (Mid Core)
+    lane 1, lane_role 1 -> pos 1 (Safe Lane Carry)
+    lane 1, lane_role 3 -> pos 5 (Safe Lane Support)
+    lane 3, lane_role 1 -> pos 3 (Offlane Core)
+    lane 3, lane_role 3 -> pos 4 (Offlane Support)
+    """
+    if lane == 2 and lane_role == 2:
+        return 2
+    elif lane == 1 and lane_role == 1:
+        return 1
+    elif lane == 1 and lane_role == 3:
+        return 5
+    elif lane == 3 and lane_role == 1:
+        return 3
+    elif lane == 3 and lane_role == 3:
+        return 4
+    else:
+        return -1  # Неизвестная комбинация
+
+# Получение ID матчей из БД
+cursor.execute("""
+select m.id
+from matches m
+left join details_match dm on dm.match_id = m.id
+where m."source" = 'pro' and dm.match_id is null
+""")
+matches = cursor.fetchall()
+match_ids = [match['id'] for match in matches]
+
+print(f"Получено {len(match_ids)} ID матчей из БД")
+
+# Запрос деталей для каждого матча
+for idx, match_id in enumerate(match_ids, 1):
+    url = f"https://api.opendota.com/api/matches/{match_id}"
+
+    try:
+        response = requests.get(url, timeout=30)
+
+        if response.status_code == 200:
+            match_data = response.json()
+            picks_bans = match_data.get('picks_bans', [])
+            players = match_data.get('players', [])
+
+            print(f"[{idx}/{len(match_ids)}] Match {match_id}: {len(picks_bans)} picks/bans, {len(players)} players")
+
+            # Создаем словари из players
+            hero_to_account = {player.get('hero_id'): player.get('account_id') for player in players if player.get('hero_id')}
+            hero_to_pos = {player.get('hero_id'): get_position(player.get('lane'), player.get('lane_role')) for player in players if player.get('hero_id')}
+
+            # Сохранение picks_bans в БД (только пики) с позициями
+            data = [
+                (
+                    match_id,
+                    pick_ban.get('hero_id'),
+                    pick_ban.get('team'),
+                    pick_ban.get('order'),
+                    hero_to_account.get(pick_ban.get('hero_id')),  # players_id
+                    hero_to_pos.get(pick_ban.get('hero_id'), -1),  # pos
+                    'pro'  # source
+                )
+                for pick_ban in picks_bans
+                if pick_ban.get('is_pick')
+            ]
+
+            print(f"Вставка {len(data)} записей для матча {match_id}")
+
+            execute_values(
+                cursor,
+                """INSERT INTO details_match (match_id, hero_id, team, "order", players_id, pos, source)
+                    VALUES %s""",
+                data
+            )
+            conn.commit()
+            time.sleep(1)  # пауза между запросами
+
+        else:
+            print(f"[{idx}/{len(match_ids)}] Ошибка для матча {match_id}: {response.status_code}")
+            if response.status_code == 429:
+                print("Превышен лимит запросов, ждем 10 секунд...")
+                time.sleep(10)
+
+    except Exception as e:
+        print(f"[{idx}/{len(match_ids)}] Исключение для матча {match_id}: {e}")
+
+cursor.close()
+conn.close()
+
+print("Завершено сохранение деталей матчей")

start/parse_pro_matches.py

@@ -0,0 +1,79 @@
+import requests
+import psycopg2
+from psycopg2.extras import execute_values
+
+PAGE = 10
+url = "https://api.opendota.com/api/proMatches"
+all_matches = []
+less_than_match_id = None
+
+# Разрешенные лиги
+ALLOWED_LEAGUES = [17420]  # Замените на нужные ID лиг
+
+for page in range(PAGE):
+    params = {}
+    if less_than_match_id:
+        params['less_than_match_id'] = less_than_match_id
+
+    response = requests.get(url, params=params)
+
+    if response.status_code == 200:
+        matches = response.json()
+        all_matches.extend(matches)
+        print(f"Страница {page + 1}: получено {len(matches)} матчей")
+
+        if matches:
+            less_than_match_id = matches[-1]['match_id']
+    else:
+        print(f"Ошибка на странице {page + 1}: {response.status_code}")
+        break
+
+print(f"\nВсего получено {len(all_matches)} матчей")
+
+# Подключение к базе данных
+conn = psycopg2.connect(
+    host="localhost",
+    port=5432,
+    database="korobka_db",
+    user="postgres",
+    password="postgres"
+)
+cursor = conn.cursor()
+
+# Подготовка данных для вставки (фильтр по leagueid)
+data = [
+    (
+        match['match_id'],
+        match.get('start_time'),
+        match.get('leagueid'),
+        match.get('radiant_team_id'),
+        match.get('dire_team_id'),
+        match.get('radiant_win'),
+        'pro'  # ← добавили source
+    )
+    for match in all_matches
+    if match.get('leagueid') in ALLOWED_LEAGUES
+]
+
+print(f"Отфильтровано {len(data)} матчей из {len(all_matches)} по разрешенным лигам")
+
+# Вставка данных в таблицу
+execute_values(
+    cursor,
+    """INSERT INTO matches (id, start_time, leagueid, radiant_team_id, dire_team_id, radiant_win, source)
+       VALUES %s
+       ON CONFLICT (id) DO UPDATE SET
+       start_time = EXCLUDED.start_time,
+       leagueid = EXCLUDED.leagueid,
+       radiant_team_id = EXCLUDED.radiant_team_id,
+       dire_team_id = EXCLUDED.dire_team_id,
+       radiant_win = EXCLUDED.radiant_win,
+       source = EXCLUDED.source""",
+    data
+)
+
+conn.commit()
+cursor.close()
+conn.close()
+
+print(f"Успешно сохранено {len(data)} матчей в БД")