2025-05-12 22:26:25 | INFO | model_gen:main:80 - 性能监控状态: False
2025-05-12 22:26:25 | INFO | model_gen:main:83 - {'action': 'config_loaded', 'config': {'envs': {'env': {'mode': 'prod', 'enable_monitor': False, 'n_jobs': 1}, 'incremental': {'enabled': True, 'lookback_days': 20}, 'shard': {'num_shards': 1, 'shard_id': 0}}, 'time_bar': 5, 'compression': {'type': 'zstd', 'level': 3}, 'files': {'base_dir': 'output', 'data': 'data_5min.parquet', 'pctchg': 'pctchg_5min.parquet'}, 'epoch': {'start_date': '2015-01-01', 'end_date': 'today', 'freq': 'W'}, 'base_key': 'B8Wstats250412', 'task_config': {'selected_expr_mapping': 'B8Wstats250412', 'config_key': 'B8Wstats250412--combo52'}, 'feature': {'include_time_comd': True, 'additional_columns': []}, 'run': {'n_jobs': 1, 'retry_times': 3, 'retry_delay': 2}, 'config_key': 'None'}}
2025-05-12 22:26:25 | INFO | model_gen:main:86 - {'action': 'params_initialized', 'config_key': 'B8Wstats250412--combo52'}
2025-05-12 22:26:25 | INFO | model_gen:main:90 - {'action': 'epoch_list_generated', 'count': 3}
2025-05-12 22:26:25 | INFO | model_gen:main:99 - {'action': 'shard_tasks', 'count': 3, 'head': array([[0, Period('2025-04-21/2025-04-27', 'W-SUN')],
       [0, Period('2025-04-28/2025-05-04', 'W-SUN')],
       [0, Period('2025-05-05/2025-05-11', 'W-SUN')]], dtype=object)}
2025-05-12 22:26:25 | INFO | model_gen:main:101 - {'action': 'parallel_start', 'n_jobs': 1, 'retry_times': 3}
2025-05-12 23:41:36 | INFO | model_gen:main:118 - {'action': 'parallel_done', 'success_count': 3, 'fail_count': 0}
sort done
内存优化: 12362.74 MB -> 6390.16 MB, 节省 48.31%
训练数据处理耗时: 850.8205秒
sort done
内存优化: 12362.74 MB -> 6390.16 MB, 节省 48.31%
预测数据处理耗时: 610.7057秒
使用已保存的单一模型: /root/data/Research1//feature/module//B8Wstats250412_0--combo52/ALL/2025-04-21__2025-04-27.pkl
权重字典键: ['ALL']
组字典键数量: 1
模型训练和预测耗时: 17.3303秒
结果最后日期: 2025-04-30 15:15:00
结果保存耗时: 0.0842秒
every thing is done
sort done
内存优化: 12375.17 MB -> 6397.60 MB, 节省 48.30%
训练数据处理耗时: 532.2034秒
sort done
内存优化: 12375.17 MB -> 6397.60 MB, 节省 48.30%
预测数据处理耗时: 682.8168秒
使用已保存的单一模型: /root/data/Research1//feature/module//B8Wstats250412_0--combo52/ALL/2025-04-28__2025-05-04.pkl
权重字典键: ['ALL']
组字典键数量: 1
模型训练和预测耗时: 22.3735秒
结果最后日期: 2025-05-07 15:15:00
结果保存耗时: 0.0893秒
every thing is done
sort done
内存优化: 12375.17 MB -> 6397.60 MB, 节省 48.30%
训练数据处理耗时: 410.9833秒
sort done
内存优化: 12375.17 MB -> 6397.60 MB, 节省 48.30%
预测数据处理耗时: 631.7154秒
使用顺序模式运行 1 个模型...
应用组合函数: LGBMRegressor
[LightGBM] [Info] Auto-choosing col-wise multi-threading, the overhead of testing was 41.679210 seconds.
You can set `force_col_wise=true` to remove the overhead.
[LightGBM] [Info] Total Bins 18850
[LightGBM] [Info] Number of data points in the train set: 8529600, number of used features: 191
[LightGBM] [Info] Start training from score 0.001067
train_and_evaluate_pl: best_score {'TA': 0.009445476887872254, 'TH': 0.006897959427300604, 'TQ': 0.008571117958730097, 'autocorr': 0.926877328632255}
模型训练和预测耗时: 556.6632秒
结果最后日期: 2025-05-07 15:15:00
结果保存耗时: 0.0165秒
every thing is done