解决merge中的重复列名，修改traffic.csv中simTime倒序问题，增加交通灯与车辆航向角筛选交通灯

core/processors/built_in/lst.py

@@ -1061,131 +1061,6 @@ class FinalDataProcessor:
             traceback.print_exc()
             return False
 
-    # def _merge_optional_data(self, df_object: pd.DataFrame) -> pd.DataFrame:
-    #     """加载和合并可选数据"""
-    #     df_merged = df_object.copy()
-        
-    #     # 检查并删除重复列的函数
-    #     def clean_duplicate_columns(df):
-    #         # 查找带有 _x 或 _y 后缀的列
-    #         duplicate_cols = []
-    #         base_cols = {}
-            
-    #         for col in df.columns:
-    #             if col.endswith('_x') or col.endswith('_y'):
-    #                 base_name = col[:-2]  # 去掉后缀
-    #                 if base_name not in base_cols:
-    #                     base_cols[base_name] = []
-    #                 base_cols[base_name].append(col)
-            
-    #         # 对于每组重复列，检查数据是否相同，如果相同则只保留一个
-    #         for base_name, cols in base_cols.items():
-    #             if len(cols) > 1:
-    #                 # 检查这些列的数据是否相同
-    #                 is_identical = True
-    #                 first_col = cols[0]
-    #                 for col in cols[1:]:
-    #                     if not df[first_col].equals(df[col]):
-    #                         is_identical = False
-    #                         break
-                    
-    #                 if is_identical:
-    #                     # 数据相同，保留第一列并重命名为基本名称
-    #                     df = df.rename(columns={first_col: base_name})
-    #                     # 删除其他重复列
-    #                     for col in cols[1:]:
-    #                         duplicate_cols.append(col)
-    #                     print(f"列 {cols} 数据相同，保留为 {base_name}")
-    #                 else:
-    #                     print(f"列 {cols} 数据不同，保留所有列")
-            
-    #         # 删除重复列
-    #         if duplicate_cols:
-    #             df = df.drop(columns=duplicate_cols)
-    #             print(f"删除了重复列: {duplicate_cols}")
-            
-    #         return df
-
-    #     # --- 合并 EgoMap ---
-    #     egomap_path = self.output_dir / OUTPUT_CSV_EGOMAP
-    #     if egomap_path.exists() and egomap_path.stat().st_size > 0:
-    #         try:
-    #             df_ego = pd.read_csv(egomap_path, dtype={"simTime": float})
-    #             # 删除 simFrame 列，因为使用主数据的 simFrame
-    #             if 'simFrame' in df_ego.columns:
-    #                 df_ego = df_ego.drop(columns=['simFrame'])
-
-    #             # 按时间和ID排序
-    #             df_ego.sort_values(['simTime', 'playerId'], inplace=True)
-    #             df_merged.sort_values(['simTime', 'playerId'], inplace=True)
-
-    #             # 使用 merge_asof 进行就近合并，不包括 simFrame
-    #             df_merged = pd.merge_asof(
-    #                 df_merged,
-    #                 df_ego,
-    #                 on='simTime',
-    #                 by='playerId',
-    #                 direction='nearest',
-    #                 tolerance=0.01  # 10ms tolerance
-    #             )
-    #             print("EgoMap data merged.")
-    #         except Exception as e:
-    #             print(f"Warning: Could not merge EgoMap data from {egomap_path}: {e}")
-
-    #     # --- Merge Function ---
-    #     function_path = self.output_dir / OUTPUT_CSV_FUNCTION
-    #     if function_path.exists() and function_path.stat().st_size > 0:
-    #         try:
-    #             df_function = pd.read_csv(function_path, dtype={"timestamp": float}, low_memory=False).drop_duplicates()
-    #             # 删除 simFrame 列
-    #             if 'simFrame' in df_function.columns:
-    #                 df_function = df_function.drop(columns=['simFrame'])
-
-    #             if 'simTime' in df_function.columns:
-    #                 df_function['simTime'] = df_function['simTime'].round(2)
-    #                 df_function['time'] = df_function['simTime'].round(2).astype(float)
-    #                 df_merged['time'] = df_merged['simTime'].round(2).astype(float)
-
-    #                 common_cols = list(set(df_merged.columns) & set(df_function.columns) - {'time'})
-    #                 df_function.drop(columns=common_cols, inplace=True, errors='ignore')
-
-    #                 df_merged = pd.merge(df_merged, df_function, on=["time"], how="left")
-    #                 df_merged.drop(columns=['time'], inplace=True)
-    #                 print("Function data merged.")
-    #             else:
-    #                 print("Warning: 'simTime' column not found in Function.csv. Cannot merge.")
-    #         except Exception as e:
-    #             print(f"Warning: Could not merge Function data from {function_path}: {e}")
-    #     else:
-    #         print("Function data not found or empty, skipping merge.")
-
-    #     # --- Merge OBU ---
-    #     obu_path = self.output_dir / OUTPUT_CSV_OBU
-    #     if obu_path.exists() and obu_path.stat().st_size > 0:
-    #         try:
-    #             df_obu = pd.read_csv(obu_path, dtype={"simTime": float}, low_memory=False).drop_duplicates()
-    #             # 删除 simFrame 列
-    #             if 'simFrame' in df_obu.columns:
-    #                 df_obu = df_obu.drop(columns=['simFrame'])
-
-    #             df_obu['time'] = df_obu['simTime'].round(2).astype(float)
-    #             df_merged['time'] = df_merged['simTime'].round(2).astype(float)
-
-    #             common_cols = list(set(df_merged.columns) & set(df_obu.columns) - {'time'})
-    #             df_obu.drop(columns=common_cols, inplace=True, errors='ignore')
-
-    #             df_merged = pd.merge(df_merged, df_obu, on=["time"], how="left")
-    #             df_merged.drop(columns=['time'], inplace=True)
-    #             print("OBU data merged.")
-    #         except Exception as e:
-    #             print(f"Warning: Could not merge OBU data from {obu_path}: {e}")
-    #     else:
-    #         print("OBU data not found or empty, skipping merge.")
-
-    #     # 在所有合并完成后，清理重复列
-    #     df_merged = clean_duplicate_columns(df_merged)
-        
-    #     return df_merged
     def _merge_optional_data(self, df_object: pd.DataFrame) -> pd.DataFrame:
         """加载和合并可选数据"""
         df_merged = df_object.copy()