yrtv/ETL/L3_Builder.py

import logging
import os
import sys

# Add parent directory to path to allow importing web module
sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))

from web.services.feature_service import FeatureService
from web.config import Config
from web.app import create_app
import sqlite3

# Setup logging
logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(levelname)s - %(message)s')
logger = logging.getLogger(__name__)

L3_DB_PATH = Config.DB_L3_PATH
SCHEMA_PATH = os.path.join(Config.BASE_DIR, 'database', 'L3', 'schema.sql')

def _get_existing_columns(conn, table_name):
    cur = conn.execute(f"PRAGMA table_info({table_name})")
    return {row[1] for row in cur.fetchall()}

def _ensure_columns(conn, table_name, columns):
    existing = _get_existing_columns(conn, table_name)
    for col, col_type in columns.items():
        if col in existing:
            continue
        conn.execute(f"ALTER TABLE {table_name} ADD COLUMN {col} {col_type}")

def init_db():
    l3_dir = os.path.dirname(L3_DB_PATH)
    if not os.path.exists(l3_dir):
        os.makedirs(l3_dir)
        
    conn = sqlite3.connect(L3_DB_PATH)
    with open(SCHEMA_PATH, 'r', encoding='utf-8') as f:
        conn.executescript(f.read())

    _ensure_columns(
        conn,
        "dm_player_features",
        {
            "rd_phase_kill_early_share": "REAL",
            "rd_phase_kill_mid_share": "REAL",
            "rd_phase_kill_late_share": "REAL",
            "rd_phase_death_early_share": "REAL",
            "rd_phase_death_mid_share": "REAL",
            "rd_phase_death_late_share": "REAL",
            "rd_phase_kill_early_share_t": "REAL",
            "rd_phase_kill_mid_share_t": "REAL",
            "rd_phase_kill_late_share_t": "REAL",
            "rd_phase_kill_early_share_ct": "REAL",
            "rd_phase_kill_mid_share_ct": "REAL",
            "rd_phase_kill_late_share_ct": "REAL",
            "rd_phase_death_early_share_t": "REAL",
            "rd_phase_death_mid_share_t": "REAL",
            "rd_phase_death_late_share_t": "REAL",
            "rd_phase_death_early_share_ct": "REAL",
            "rd_phase_death_mid_share_ct": "REAL",
            "rd_phase_death_late_share_ct": "REAL",
            "rd_firstdeath_team_first_death_rounds": "INTEGER",
            "rd_firstdeath_team_first_death_win_rate": "REAL",
            "rd_invalid_death_rounds": "INTEGER",
            "rd_invalid_death_rate": "REAL",
            "rd_pressure_kpr_ratio": "REAL",
            "rd_pressure_perf_ratio": "REAL",
            "rd_pressure_rounds_down3": "INTEGER",
            "rd_pressure_rounds_normal": "INTEGER",
            "rd_matchpoint_kpr_ratio": "REAL",
            "rd_matchpoint_perf_ratio": "REAL",
            "rd_matchpoint_rounds": "INTEGER",
            "rd_comeback_kill_share": "REAL",
            "rd_comeback_rounds": "INTEGER",
            "rd_trade_response_10s_rate": "REAL",
            "rd_weapon_top_json": "TEXT",
            "rd_roundtype_split_json": "TEXT",
            "map_stability_coef": "REAL",
            "basic_avg_knife_kill": "REAL",
            "basic_avg_zeus_kill": "REAL",
            "basic_zeus_pick_rate": "REAL",
        },
    )

    conn.commit()
    conn.close()
    logger.info("L3 DB Initialized/Updated with Schema.")

def main():
    logger.info("Starting L3 Builder (Delegating to FeatureService)...")
    
    # 1. Ensure Schema is up to date
    init_db()
    
    # 2. Rebuild Features using the centralized logic
    try:
        app = create_app()
        with app.app_context():
            count = FeatureService.rebuild_all_features()
            logger.info(f"Successfully rebuilt features for {count} players.")
    except Exception as e:
        logger.error(f"Error rebuilding features: {e}")
        import traceback
        traceback.print_exc()

if __name__ == "__main__":
    main()