feat: 添加数据匹配分析脚本，计算 loops_power 与 g5 表的匹配覆盖率

database_test_python/check_matching_rate.py

@@ -0,0 +1,61 @@
+import os
+import pandas as pd
+from sqlalchemy import create_engine
+import urllib.parse
+from db_config import get_db_url
+
+def main():
+    print("正在连接数据库...")
+    url_80portal = get_db_url("PORTAL")
+    url_test = get_db_url("TARGET")
+    
+    engine_80portal = create_engine(url_80portal)
+    engine_test = create_engine(url_test)
+
+    print("\n[1/3] 从 15433 test 库提取 loops_power 的数据...")
+    df_loops = pd.read_sql('SELECT hotel_id, room_id FROM "wh_test"."loops_power"', engine_test)
+    
+    print("[2/3] 从 15434 log_platform 库提取 room_status_moment_g5 的数据...")
+    df_g5 = pd.read_sql('SELECT hotel_id, room_id FROM "room_status"."room_status_moment_g5"', engine_80portal)
+    
+    print("\n[3/3] 正在对齐类型并进行交集运算...")
+    # 彻底数据清洗，防止由于 PostgreSQL 类型或字符串空格导致匹配不上
+    df_loops['hotel_id'] = pd.to_numeric(df_loops['hotel_id'], errors='coerce').astype('Int64')
+    df_loops['room_id'] = df_loops['room_id'].astype(str).str.strip().str.replace('.0', '', regex=False)
+    
+    df_g5['hotel_id'] = pd.to_numeric(df_g5['hotel_id'], errors='coerce').astype('Int64')
+    df_g5['room_id'] = df_g5['room_id'].astype(str).str.strip().str.replace('.0', '', regex=False)
+    
+    # 针对 g5 表去重建立参考系
+    df_g5_unique = df_g5.drop_duplicates(subset=['hotel_id', 'room_id']).copy()
+    df_g5_unique['g5_exists'] = True
+    
+    # 分析覆盖情况
+    total_loops = len(df_loops)
+    
+    merged = pd.merge(df_loops, df_g5_unique, on=['hotel_id', 'room_id'], how='left')
+    matched_loops = merged['g5_exists'].sum()
+    
+    match_rate = (matched_loops / total_loops * 100) if total_loops > 0 else 0
+    
+    print("=======================================")
+    print("匹配结果报告:")
+    print("=======================================")
+    print(f"-> 提取的 loops_power 总记录: {total_loops} 条")
+    print(f"-> 在 g5 表中成功映射找到的记录:     {int(matched_loops)} 条")
+    print(f"-> 整体匹配覆盖率:                   {match_rate:.2f}%")
+    
+    # 挑出匹配上的数据
+    mapped = merged[merged['g5_exists'] == True]
+    if len(mapped) > 0:
+        print(f"\n[√] 成功匹配配对示例(前10种):")
+        print(mapped[['hotel_id', 'room_id']].drop_duplicates().head(10).to_string(index=False))
+
+    # 挑出无法在 G5 找到的烂数据
+    unmapped = merged[merged['g5_exists'] != True]
+    if len(unmapped) > 0:
+        print(f"\n[!] 发现 {len(unmapped)} 条扁平化回路未在 g5 表中找到对应的 hotel_id/room_id。以下为缺失配对示例(前10种):")
+        print(unmapped[['hotel_id', 'room_id']].drop_duplicates().head(10).to_string(index=False))
+
+if __name__ == "__main__":
+    main()