2025-07-13 04:01:04 | WARNING | dataFuture:get_latest_valid_dir:99 - 使用的数据目录日期(2025-07-11)不是今天(2025-07-13)，可能不是最新数据
2025-07-13 04:01:05 | INFO | model_gen:main:87 - 性能监控状态: False
2025-07-13 04:01:05 | INFO | model_gen:main:90 - {'config': {'envs': {'env': {'mode': 'prod', 'enable_monitor': False, 'n_jobs': 1}, 'incremental': {'enabled': True, 'lookback_days': 20, 'start_date': None, 'end_date': 'today'}, 'run': {'n_jobs': 1, 'retry_times': 3, 'retry_delay': 2}, 'shard': {'num_shards': 1, 'shard_id': 0}}, 'strategy': {'time_bar': 5, 'pred_periods': 12, 'base_key': 'B8Wstats250412', 'task_config': {'selected_expr_mapping': 'B8Wstats250412', 'config_key': 'B8Wstats250412', 'combo_key': 'combo52', 'metric_key': ['B8Wstats250412'], 'versions_to_optimize': ['v7', 'v8']}}, 'compression': {'type': 'zstd', 'level': 3}, 'files': {'base_dir': 'output', 'data': 'data_5min.parquet', 'pctchg': 'pctchg_5min_pred12.parquet'}, 'feature': {'include_time_comd': True, 'additional_columns': []}, 'epoch': {'freq': 'W'}}}
2025-07-13 04:01:06 | INFO | model_gen:main:95 - {'action': 'params_initialized', 'config_key': 'B8Wstats250412', 'combo_key': 'combo52', 'time_bar': 5, 'pred_periods': 12, 'pctchg_path': 'pctchg_5min_pred12.parquet'}
2025-07-13 04:01:06 | INFO | model_gen:main:99 - {'action': 'epoch_list_generated', 'count': 3}
2025-07-13 04:01:06 | INFO | model_gen:main:108 - {'action': 'shard_tasks', 'count': 3, 'head': array([[0, Period('2025-06-23/2025-06-29', 'W-SUN')],
       [0, Period('2025-06-30/2025-07-06', 'W-SUN')],
       [0, Period('2025-07-07/2025-07-13', 'W-SUN')]], dtype=object)}
2025-07-13 04:01:06 | INFO | model_gen:main:110 - {'action': 'parallel_start', 'n_jobs': 1, 'retry_times': 3}
2025-07-13 05:35:06 | INFO | model_gen:main:127 - {'action': 'parallel_done', 'success_count': 3, 'fail_count': 0}
2025-07-13 05:35:06 | INFO | model_gen:main:132 - {'action': 'success', 'description': 'model_gen 完成'}
sort done
内存优化: 12634.55 MB -> 6531.69 MB, 节省 48.30%
训练数据处理耗时: 186.7839秒
sort done
内存优化: 12634.55 MB -> 6531.69 MB, 节省 48.30%
预测数据处理耗时: 1581.9468秒
使用已保存的单一模型: /root/data/Research1//feature/module//B8Wstats250412_0--combo52/ALL/2025-06-23__2025-06-29.pkl
权重字典键: ['ALL']
组字典键数量: 1
模型训练和预测耗时: 17.0300秒
结果最后日期: 2025-07-05 02:30:00
结果保存耗时: 0.1638秒
every thing is done
sort done
内存优化: 12663.62 MB -> 6546.72 MB, 节省 48.30%
训练数据处理耗时: 365.5797秒
sort done
内存优化: 12663.62 MB -> 6546.72 MB, 节省 48.30%
预测数据处理耗时: 1335.2379秒
使用已保存的单一模型: /root/data/Research1//feature/module//B8Wstats250412_0--combo52/ALL/2025-06-30__2025-07-06.pkl
权重字典键: ['ALL']
组字典键数量: 1
模型训练和预测耗时: 17.7043秒
结果最后日期: 2025-07-11 15:15:00
结果保存耗时: 0.1628秒
every thing is done
sort done
内存优化: 12663.62 MB -> 6546.72 MB, 节省 48.30%
训练数据处理耗时: 328.5719秒
sort done
内存优化: 12663.62 MB -> 6546.72 MB, 节省 48.30%
预测数据处理耗时: 1040.7764秒
使用顺序模式运行 1 个模型...
应用组合函数: LGBMRegressor
[LightGBM] [Info] Auto-choosing row-wise multi-threading, the overhead of testing was 0.775095 seconds.
You can set `force_row_wise=true` to remove the overhead.
And if memory is not enough, you can set `force_col_wise=true`.
[LightGBM] [Info] Total Bins 18860
[LightGBM] [Info] Number of data points in the train set: 8720827, number of used features: 191
[LightGBM] [Info] Start training from score 0.001172
train_and_evaluate_pl: best_score {'TA': 0.009151428128522253, 'TH': 0.006671852535278811, 'TQ': 0.0082942897024263, 'autocorr': 0.9260890872250959}
模型训练和预测耗时: 663.6277秒
结果最后日期: 2025-07-11 15:15:00
结果保存耗时: 0.1116秒
every thing is done