2025-07-06 21:50:05 | WARNING | dataFuture:get_latest_valid_dir:99 - 使用的数据目录日期(2025-07-04)不是今天(2025-07-06)，可能不是最新数据
2025-07-06 21:50:07 | INFO | model_gen:main:87 - 性能监控状态: False
2025-07-06 21:50:07 | 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'}}}
2025-07-06 21:50:07 | 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'}
2025-07-06 21:50:07 | INFO | model_gen:main:99 - {'action': 'epoch_list_generated', 'count': 3}
2025-07-06 21:50:07 | INFO | model_gen:main:108 - {'action': 'shard_tasks', 'count': 3, 'head': array([[0, Period('2025-06-16/2025-06-22', 'W-SUN')],
       [0, Period('2025-06-23/2025-06-29', 'W-SUN')],
       [0, Period('2025-06-30/2025-07-06', 'W-SUN')]], dtype=object)}
2025-07-06 21:50:07 | INFO | model_gen:main:110 - {'action': 'parallel_start', 'n_jobs': 1, 'retry_times': 3}
2025-07-06 23:22:37 | INFO | model_gen:main:127 - {'action': 'parallel_done', 'success_count': 3, 'fail_count': 0}
2025-07-06 23:22:37 | INFO | model_gen:main:132 - {'action': 'success', 'description': 'model_gen 完成'}
sort done
内存优化: 12595.72 MB -> 6511.62 MB, 节省 48.30%
训练数据处理耗时: 171.5895秒
sort done
内存优化: 12595.72 MB -> 6511.62 MB, 节省 48.30%
预测数据处理耗时: 1770.8206秒
使用已保存的单一模型: /root/data/Research1//feature/module//B8Wstats250412_0--combo52/ALL/2025-06-16__2025-06-22.pkl
权重字典键: ['ALL']
组字典键数量: 1
模型训练和预测耗时: 19.3586秒
结果最后日期: 2025-06-28 01:00:00
结果保存耗时: 0.1838秒
every thing is done
sort done
内存优化: 12623.89 MB -> 6526.19 MB, 节省 48.30%
训练数据处理耗时: 281.4832秒
sort done
内存优化: 12623.89 MB -> 6526.19 MB, 节省 48.30%
预测数据处理耗时: 984.0253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: 22.4874秒
结果最后日期: 2025-07-04 15:15:00
结果保存耗时: 0.1810秒
every thing is done
sort done
内存优化: 12623.89 MB -> 6526.19 MB, 节省 48.30%
训练数据处理耗时: 355.1588秒
sort done
内存优化: 12623.89 MB -> 6526.19 MB, 节省 48.30%
预测数据处理耗时: 1201.2261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 0.834632 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 18856
[LightGBM] [Info] Number of data points in the train set: 8699697, number of used features: 191
[LightGBM] [Info] Start training from score 0.001141
train_and_evaluate_pl: best_score {'TA': 0.009230491508274569, 'TH': 0.006752945110898227, 'TQ': 0.008381803923096067, 'autocorr': 0.9251563319449682}
模型训练和预测耗时: 632.0512秒
结果最后日期: 2025-07-04 15:15:00
结果保存耗时: 0.0165秒
every thing is done