2025-10-06 06:50:32,936 - main.py - DEBUG - 99 - loading sales data..
2025-10-06 06:50:33,790 - reading_data.py - DEBUG - 129 - start date: 2022-03-01 00:00:00 end date: 2025-06-30 00:00:00
2025-10-06 06:51:35,435 - functions.py - INFO - 274 - Fetched prediction months:
('2023-12-7', (2024, 1))
('2024-01-7', (2024, 2))
('2024-02-7', (2024, 3))
('2024-03-7', (2024, 4))
('2024-04-7', (2024, 5))
('2024-05-7', (2024, 6))
('2024-06-7', (2024, 7))
('2024-07-7', (2024, 8))
('2024-08-7', (2024, 9))
('2024-09-7', (2024, 10))
('2024-10-7', (2024, 11))
('2024-11-7', (2024, 12))
('2024-12-7', (2025, 1))
('2025-01-7', (2025, 2))
('2025-02-7', (2025, 3))
('2025-03-7', (2025, 4))
('2025-04-7', (2025, 6))
('2025-04-7', (2025, 5))
2025-10-06 06:51:35,830 - algorithm.py - DEBUG - 72 - start training with xgboost...
2025-10-06 06:51:35,929 - algorithm.py - DEBUG - 78 - shape: (52587, 279) start: 2022-05-02 00:00:00 end: 2023-12-06 00:00:00
2025-10-06 06:51:43,734 - algorithm.py - INFO - 122 - parameters {'objective': 'reg:squarederror', 'base_score': None, 'booster': None, 'callbacks': None, 'colsample_bylevel': None, 'colsample_bynode': None, 'colsample_bytree': 0.8, 'device': None, 'early_stopping_rounds': None, 'enable_categorical': True, 'eval_metric': <function mean_squared_error at 0x7f560d4d9670>, 'feature_types': None, 'gamma': None, 'grow_policy': None, 'importance_type': None, 'interaction_constraints': None, 'learning_rate': 0.01, 'max_bin': None, 'max_cat_threshold': None, 'max_cat_to_onehot': None, 'max_delta_step': None, 'max_depth': 7, 'max_leaves': None, 'min_child_weight': None, 'missing': nan, 'monotone_constraints': None, 'multi_strategy': None, 'n_estimators': 1250, 'n_jobs': -1, 'num_parallel_tree': None, 'random_state': 42, 'reg_alpha': 0.05, 'reg_lambda': 1.0, 'sampling_method': None, 'scale_pos_weight': None, 'subsample': 0.8, 'tree_method': 'hist', 'validate_parameters': None, 'verbosity': None}
2025-10-06 06:51:43,735 - algorithm.py - INFO - 130 - parameters:
{ 'colsample_bytree': 0.8,
'enable_categorical': True,
'eval_metric': <function mean_squared_error at 0x7f560d4d9670>,
'learning_rate': 0.01,
'max_depth': 7,
'missing': nan,
'n_estimators': 1250,
'n_jobs': -1,
'objective': 'reg:squarederror',
'random_state': 42,
'reg_alpha': 0.05,
'reg_lambda': 1.0,
'subsample': 0.8,
'tree_method': 'hist'}
2025-10-06 06:51:43,735 - algorithm.py - INFO - 131 - indep vars:
['ladenvkpmean', 'ladenvkpmin', 'ladenvkpmax', 'ladenvkpstd', 'fg_bl_BW', 'fg_bl_BY', 'fg_bl_HE', 'fg_bl_NW', 'fg_bl_RP', 'weekdayname_Monday', 'weekdayname_Tuesday', 'weekdayname_Wednesday', 'weekdayname_Thursday', 'weekdayname_Friday', 'weekdayname_Saturday', 'isoweek_1', 'isoweek_2', 'isoweek_3', 'isoweek_4', 'isoweek_5', 'isoweek_6', 'isoweek_7', 'isoweek_8', 'isoweek_9', 'isoweek_10', 'isoweek_11', 'isoweek_12', 'isoweek_13', 'isoweek_14', 'isoweek_15', 'isoweek_16', 'isoweek_17', 'isoweek_18', 'isoweek_19', 'isoweek_20', 'isoweek_21', 'isoweek_22', 'isoweek_23', 'isoweek_24', 'isoweek_25', 'isoweek_26', 'isoweek_27', 'isoweek_28', 'isoweek_29', 'isoweek_30', 'isoweek_31', 'isoweek_32', 'isoweek_33', 'isoweek_34', 'isoweek_35', 'isoweek_36', 'isoweek_37', 'isoweek_38', 'isoweek_39', 'isoweek_40', 'isoweek_41', 'isoweek_42', 'isoweek_43', 'isoweek_44', 'isoweek_45', 'isoweek_46', 'isoweek_47', 'isoweek_48', 'isoweek_49', 'isoweek_50', 'isoweek_51', 'isoweek_52', 'month_1', 'month_2', 'month_3', 'month_4', 'month_5', 'month_6', 'month_7', 'month_8', 'month_9', 'month_10', 'month_11', 'month_12', 'year_2022', 'year_2023', 'year_2024', 'fg_sg_1', 'fg_sg_2', 'fg_sg_3', 'fg_sg_9', 'fg_sg_19', 'fg_sg_21', 'fg_sg_24', 'fg_sg_26', 'fg_sg_27', 'fg_sg_28', 'fg_sg_29', 'fg_sg_31', 'fg_sg_34', 'fg_sg_40', 'fg_sg_41', 'fg_sg_43', 'fg_sg_44', 'fg_sg_52', 'fg_sg_55', 'fg_sg_57', 'fg_sg_58', 'fg_sg_61', 'fg_sg_62', 'fg_sg_63', 'fg_sg_64', 'fg_sg_65', 'fg_sg_66', 'fg_sg_68', 'fg_sg_69', 'fg_sg_71', 'fg_sg_73', 'fg_sg_74', 'fg_sg_76', 'fg_sg_77', 'fg_sg_80', 'fg_sg_81', 'fg_sg_82', 'fg_sg_83', 'fg_sg_85', 'fg_sg_88', 'fg_sg_89', 'fg_sg_91', 'fg_sg_92', 'fg_sg_96', 'fg_sg_97', 'fg_sg_99', 'fg_sg_101', 'fg_sg_103', 'fg_sg_104', 'fg_sg_105', 'fg_sg_107', 'fg_sg_108', 'fg_sg_109', 'fg_sg_110', 'fg_sg_111', 'fg_sg_112', 'fg_sg_113', 'fg_sg_117', 'fg_sg_118', 'fg_sg_120', 'fg_sg_125', 'fg_sg_126', 'fg_sg_128', 'fg_sg_130', 'fg_sg_131', 'fg_sg_133', 'fg_sg_134', 'fg_sg_136', 'fg_sg_139', 'fg_sg_141', 'fg_sg_142', 'fg_sg_143', 'fg_sg_146', 'fg_sg_147', 'fg_sg_148', 'fg_sg_149', 'fg_sg_150', 'fg_sg_151', 'fg_sg_153', 'fg_sg_154', 'fg_sg_155', 'fg_sg_157', 'fg_sg_159', 'fg_sg_160', 'fg_sg_161', 'fg_sg_162', 'fg_sg_164', 'fg_sg_165', 'fg_sg_166', 'fg_sg_167', 'fg_sg_168', 'fg_sg_169', 'fg_sg_170', 'fg_sg_171', 'fg_sg_172', 'fg_sg_173', 'fg_sg_174', 'fg_sg_176', 'fg_sg_177', 'fg_sg_179', 'fg_sg_181', 'fg_sg_182', 'fg_sg_183', 'fg_sg_185', 'fg_sg_187', 'fg_sg_188', 'fg_sg_189', 'fg_sg_190', 'fg_sg_191', 'fg_sg_192', 'fg_sg_193', 'psv_starts', 'psv', 'salesday', 'presales', 'postsales', 'bridge_days', 'outlet', 'store_opening', 'weiberfasching_2022', 'faschingsfreitag_2022', 'faschingssamstag_2022', 'rosenmontag_2022', 'faschingdienstag_2022', 'weiberfasching', 'faschingsfreitag', 'faschingssamstag', 'pre_christmas_peaks', 'valentines_day', 'interaction', 'market_Montags', 'market_Dienstags', 'market_Mittwochs', 'market_Donnerstags', 'market_Freitags', 'market_Samstags', 'population', 'shop_area', 'dist_from_weiden', 'ratio', 'average', 'shop_count', 'weekday_special', 'weekend_special', 'x_coord', 'y_coord', 'dayofmonth', 'isoweek', 'month', 'dayofyear', 'dayofseason', 'season_month']
2025-10-06 06:51:43,737 - main.py - INFO - 137 - Successfully trained xgb9 xgboost for month (2024, 1) training data to: 2023-12-7
2025-10-06 06:51:43,737 - prediction_task.py - DEBUG - 21 - predictions starting...
2025-10-06 06:51:53,698 - prediction_task.py - DEBUG - 31 - test data not found for 194 Michelfeld in period (2024, 1)
2025-10-06 06:51:53,701 - prediction_task.py - DEBUG - 31 - test data not found for 195 Kelheim in period (2024, 1)
2025-10-06 06:51:53,701 - main.py - INFO - 145 - Successfully predicted with xgb9 xgboost for month (2024, 1)
2025-10-06 06:51:53,701 - main.py - INFO - 137 - Successfully trained agp agp for month (2024, 1) training data to: 2023-12-7
2025-10-06 06:51:53,701 - prediction_task.py - DEBUG - 21 - predictions starting...
2025-10-06 06:51:54,190 - prediction_task.py - DEBUG - 31 - test data not found for 194 Michelfeld in period (2024, 1)
2025-10-06 06:51:54,193 - prediction_task.py - DEBUG - 31 - test data not found for 195 Kelheim in period (2024, 1)
2025-10-06 06:51:54,193 - main.py - INFO - 145 - Successfully predicted with agp agp for month (2024, 1)
2025-10-06 06:51:54,193 - algorithm.py - DEBUG - 72 - start training with xgboost...
2025-10-06 06:51:54,301 - algorithm.py - DEBUG - 78 - shape: (55164, 279) start: 2022-05-02 00:00:00 end: 2024-01-06 00:00:00
2025-10-06 06:52:02,204 - algorithm.py - INFO - 122 - parameters {'objective': 'reg:squarederror', 'base_score': None, 'booster': None, 'callbacks': None, 'colsample_bylevel': None, 'colsample_bynode': None, 'colsample_bytree': 0.8, 'device': None, 'early_stopping_rounds': None, 'enable_categorical': True, 'eval_metric': <function mean_squared_error at 0x7f560d4d9670>, 'feature_types': None, 'gamma': None, 'grow_policy': None, 'importance_type': None, 'interaction_constraints': None, 'learning_rate': 0.01, 'max_bin': None, 'max_cat_threshold': None, 'max_cat_to_onehot': None, 'max_delta_step': None, 'max_depth': 7, 'max_leaves': None, 'min_child_weight': None, 'missing': nan, 'monotone_constraints': None, 'multi_strategy': None, 'n_estimators': 1250, 'n_jobs': -1, 'num_parallel_tree': None, 'random_state': 42, 'reg_alpha': 0.05, 'reg_lambda': 1.0, 'sampling_method': None, 'scale_pos_weight': None, 'subsample': 0.8, 'tree_method': 'hist', 'validate_parameters': None, 'verbosity': None}
2025-10-06 06:52:02,205 - algorithm.py - INFO - 130 - parameters:
{ 'colsample_bytree': 0.8,
'enable_categorical': True,
'eval_metric': <function mean_squared_error at 0x7f560d4d9670>,
'learning_rate': 0.01,
'max_depth': 7,
'missing': nan,
'n_estimators': 1250,
'n_jobs': -1,
'objective': 'reg:squarederror',
'random_state': 42,
'reg_alpha': 0.05,
'reg_lambda': 1.0,
'subsample': 0.8,
'tree_method': 'hist'}
2025-10-06 06:52:02,205 - algorithm.py - INFO - 131 - indep vars:
['ladenvkpmean', 'ladenvkpmin', 'ladenvkpmax', 'ladenvkpstd', 'fg_bl_BW', 'fg_bl_BY', 'fg_bl_HE', 'fg_bl_NW', 'fg_bl_RP', 'weekdayname_Monday', 'weekdayname_Tuesday', 'weekdayname_Wednesday', 'weekdayname_Thursday', 'weekdayname_Friday', 'weekdayname_Saturday', 'isoweek_1', 'isoweek_2', 'isoweek_3', 'isoweek_4', 'isoweek_5', 'isoweek_6', 'isoweek_7', 'isoweek_8', 'isoweek_9', 'isoweek_10', 'isoweek_11', 'isoweek_12', 'isoweek_13', 'isoweek_14', 'isoweek_15', 'isoweek_16', 'isoweek_17', 'isoweek_18', 'isoweek_19', 'isoweek_20', 'isoweek_21', 'isoweek_22', 'isoweek_23', 'isoweek_24', 'isoweek_25', 'isoweek_26', 'isoweek_27', 'isoweek_28', 'isoweek_29', 'isoweek_30', 'isoweek_31', 'isoweek_32', 'isoweek_33', 'isoweek_34', 'isoweek_35', 'isoweek_36', 'isoweek_37', 'isoweek_38', 'isoweek_39', 'isoweek_40', 'isoweek_41', 'isoweek_42', 'isoweek_43', 'isoweek_44', 'isoweek_45', 'isoweek_46', 'isoweek_47', 'isoweek_48', 'isoweek_49', 'isoweek_50', 'isoweek_51', 'isoweek_52', 'month_1', 'month_2', 'month_3', 'month_4', 'month_5', 'month_6', 'month_7', 'month_8', 'month_9', 'month_10', 'month_11', 'month_12', 'year_2022', 'year_2023', 'year_2024', 'fg_sg_1', 'fg_sg_2', 'fg_sg_3', 'fg_sg_9', 'fg_sg_19', 'fg_sg_21', 'fg_sg_24', 'fg_sg_26', 'fg_sg_27', 'fg_sg_28', 'fg_sg_29', 'fg_sg_31', 'fg_sg_34', 'fg_sg_40', 'fg_sg_41', 'fg_sg_43', 'fg_sg_44', 'fg_sg_52', 'fg_sg_55', 'fg_sg_57', 'fg_sg_58', 'fg_sg_61', 'fg_sg_62', 'fg_sg_63', 'fg_sg_64', 'fg_sg_65', 'fg_sg_66', 'fg_sg_68', 'fg_sg_69', 'fg_sg_71', 'fg_sg_73', 'fg_sg_74', 'fg_sg_76', 'fg_sg_77', 'fg_sg_80', 'fg_sg_81', 'fg_sg_82', 'fg_sg_83', 'fg_sg_85', 'fg_sg_88', 'fg_sg_89', 'fg_sg_91', 'fg_sg_92', 'fg_sg_96', 'fg_sg_97', 'fg_sg_99', 'fg_sg_101', 'fg_sg_103', 'fg_sg_104', 'fg_sg_105', 'fg_sg_107', 'fg_sg_108', 'fg_sg_109', 'fg_sg_110', 'fg_sg_111', 'fg_sg_112', 'fg_sg_113', 'fg_sg_117', 'fg_sg_118', 'fg_sg_120', 'fg_sg_125', 'fg_sg_126', 'fg_sg_128', 'fg_sg_130', 'fg_sg_131', 'fg_sg_133', 'fg_sg_134', 'fg_sg_136', 'fg_sg_139', 'fg_sg_141', 'fg_sg_142', 'fg_sg_143', 'fg_sg_146', 'fg_sg_147', 'fg_sg_148', 'fg_sg_149', 'fg_sg_150', 'fg_sg_151', 'fg_sg_153', 'fg_sg_154', 'fg_sg_155', 'fg_sg_157', 'fg_sg_159', 'fg_sg_160', 'fg_sg_161', 'fg_sg_162', 'fg_sg_164', 'fg_sg_165', 'fg_sg_166', 'fg_sg_167', 'fg_sg_168', 'fg_sg_169', 'fg_sg_170', 'fg_sg_171', 'fg_sg_172', 'fg_sg_173', 'fg_sg_174', 'fg_sg_176', 'fg_sg_177', 'fg_sg_179', 'fg_sg_181', 'fg_sg_182', 'fg_sg_183', 'fg_sg_185', 'fg_sg_187', 'fg_sg_188', 'fg_sg_189', 'fg_sg_190', 'fg_sg_191', 'fg_sg_192', 'fg_sg_193', 'psv_starts', 'psv', 'salesday', 'presales', 'postsales', 'bridge_days', 'outlet', 'store_opening', 'weiberfasching_2022', 'faschingsfreitag_2022', 'faschingssamstag_2022', 'rosenmontag_2022', 'faschingdienstag_2022', 'weiberfasching', 'faschingsfreitag', 'faschingssamstag', 'pre_christmas_peaks', 'valentines_day', 'interaction', 'market_Montags', 'market_Dienstags', 'market_Mittwochs', 'market_Donnerstags', 'market_Freitags', 'market_Samstags', 'population', 'shop_area', 'dist_from_weiden', 'ratio', 'average', 'shop_count', 'weekday_special', 'weekend_special', 'x_coord', 'y_coord', 'dayofmonth', 'isoweek', 'month', 'dayofyear', 'dayofseason', 'season_month']
2025-10-06 06:52:02,207 - main.py - INFO - 137 - Successfully trained xgb9 xgboost for month (2024, 2) training data to: 2024-01-7
2025-10-06 06:52:02,208 - prediction_task.py - DEBUG - 21 - predictions starting...
2025-10-06 06:52:12,058 - prediction_task.py - DEBUG - 31 - test data not found for 194 Michelfeld in period (2024, 2)
2025-10-06 06:52:12,061 - prediction_task.py - DEBUG - 31 - test data not found for 195 Kelheim in period (2024, 2)
2025-10-06 06:52:12,061 - main.py - INFO - 145 - Successfully predicted with xgb9 xgboost for month (2024, 2)
2025-10-06 06:52:12,061 - main.py - INFO - 137 - Successfully trained agp agp for month (2024, 2) training data to: 2024-01-7
2025-10-06 06:52:12,061 - prediction_task.py - DEBUG - 21 - predictions starting...
2025-10-06 06:52:12,542 - prediction_task.py - DEBUG - 31 - test data not found for 194 Michelfeld in period (2024, 2)
2025-10-06 06:52:12,545 - prediction_task.py - DEBUG - 31 - test data not found for 195 Kelheim in period (2024, 2)
2025-10-06 06:52:12,545 - main.py - INFO - 145 - Successfully predicted with agp agp for month (2024, 2)
2025-10-06 06:52:12,545 - algorithm.py - DEBUG - 72 - start training with xgboost...
2025-10-06 06:52:12,652 - algorithm.py - DEBUG - 78 - shape: (58048, 279) start: 2022-05-02 00:00:00 end: 2024-02-06 00:00:00
2025-10-06 06:52:21,246 - algorithm.py - INFO - 122 - parameters {'objective': 'reg:squarederror', 'base_score': None, 'booster': None, 'callbacks': None, 'colsample_bylevel': None, 'colsample_bynode': None, 'colsample_bytree': 0.8, 'device': None, 'early_stopping_rounds': None, 'enable_categorical': True, 'eval_metric': <function mean_squared_error at 0x7f560d4d9670>, 'feature_types': None, 'gamma': None, 'grow_policy': None, 'importance_type': None, 'interaction_constraints': None, 'learning_rate': 0.01, 'max_bin': None, 'max_cat_threshold': None, 'max_cat_to_onehot': None, 'max_delta_step': None, 'max_depth': 7, 'max_leaves': None, 'min_child_weight': None, 'missing': nan, 'monotone_constraints': None, 'multi_strategy': None, 'n_estimators': 1250, 'n_jobs': -1, 'num_parallel_tree': None, 'random_state': 42, 'reg_alpha': 0.05, 'reg_lambda': 1.0, 'sampling_method': None, 'scale_pos_weight': None, 'subsample': 0.8, 'tree_method': 'hist', 'validate_parameters': None, 'verbosity': None}
2025-10-06 06:52:21,247 - algorithm.py - INFO - 130 - parameters:
{ 'colsample_bytree': 0.8,
'enable_categorical': True,
'eval_metric': <function mean_squared_error at 0x7f560d4d9670>,
'learning_rate': 0.01,
'max_depth': 7,
'missing': nan,
'n_estimators': 1250,
'n_jobs': -1,
'objective': 'reg:squarederror',
'random_state': 42,
'reg_alpha': 0.05,
'reg_lambda': 1.0,
'subsample': 0.8,
'tree_method': 'hist'}
2025-10-06 06:52:21,248 - algorithm.py - INFO - 131 - indep vars:
['ladenvkpmean', 'ladenvkpmin', 'ladenvkpmax', 'ladenvkpstd', 'fg_bl_BW', 'fg_bl_BY', 'fg_bl_HE', 'fg_bl_NW', 'fg_bl_RP', 'weekdayname_Monday', 'weekdayname_Tuesday', 'weekdayname_Wednesday', 'weekdayname_Thursday', 'weekdayname_Friday', 'weekdayname_Saturday', 'isoweek_1', 'isoweek_2', 'isoweek_3', 'isoweek_4', 'isoweek_5', 'isoweek_6', 'isoweek_7', 'isoweek_8', 'isoweek_9', 'isoweek_10', 'isoweek_11', 'isoweek_12', 'isoweek_13', 'isoweek_14', 'isoweek_15', 'isoweek_16', 'isoweek_17', 'isoweek_18', 'isoweek_19', 'isoweek_20', 'isoweek_21', 'isoweek_22', 'isoweek_23', 'isoweek_24', 'isoweek_25', 'isoweek_26', 'isoweek_27', 'isoweek_28', 'isoweek_29', 'isoweek_30', 'isoweek_31', 'isoweek_32', 'isoweek_33', 'isoweek_34', 'isoweek_35', 'isoweek_36', 'isoweek_37', 'isoweek_38', 'isoweek_39', 'isoweek_40', 'isoweek_41', 'isoweek_42', 'isoweek_43', 'isoweek_44', 'isoweek_45', 'isoweek_46', 'isoweek_47', 'isoweek_48', 'isoweek_49', 'isoweek_50', 'isoweek_51', 'isoweek_52', 'month_1', 'month_2', 'month_3', 'month_4', 'month_5', 'month_6', 'month_7', 'month_8', 'month_9', 'month_10', 'month_11', 'month_12', 'year_2022', 'year_2023', 'year_2024', 'fg_sg_1', 'fg_sg_2', 'fg_sg_3', 'fg_sg_9', 'fg_sg_19', 'fg_sg_21', 'fg_sg_24', 'fg_sg_26', 'fg_sg_27', 'fg_sg_28', 'fg_sg_29', 'fg_sg_31', 'fg_sg_34', 'fg_sg_40', 'fg_sg_41', 'fg_sg_43', 'fg_sg_44', 'fg_sg_52', 'fg_sg_55', 'fg_sg_57', 'fg_sg_58', 'fg_sg_61', 'fg_sg_62', 'fg_sg_63', 'fg_sg_64', 'fg_sg_65', 'fg_sg_66', 'fg_sg_68', 'fg_sg_69', 'fg_sg_71', 'fg_sg_73', 'fg_sg_74', 'fg_sg_76', 'fg_sg_77', 'fg_sg_80', 'fg_sg_81', 'fg_sg_82', 'fg_sg_83', 'fg_sg_85', 'fg_sg_88', 'fg_sg_89', 'fg_sg_91', 'fg_sg_92', 'fg_sg_96', 'fg_sg_97', 'fg_sg_99', 'fg_sg_101', 'fg_sg_103', 'fg_sg_104', 'fg_sg_105', 'fg_sg_107', 'fg_sg_108', 'fg_sg_109', 'fg_sg_110', 'fg_sg_111', 'fg_sg_112', 'fg_sg_113', 'fg_sg_117', 'fg_sg_118', 'fg_sg_120', 'fg_sg_125', 'fg_sg_126', 'fg_sg_128', 'fg_sg_130', 'fg_sg_131', 'fg_sg_133', 'fg_sg_134', 'fg_sg_136', 'fg_sg_139', 'fg_sg_141', 'fg_sg_142', 'fg_sg_143', 'fg_sg_146', 'fg_sg_147', 'fg_sg_148', 'fg_sg_149', 'fg_sg_150', 'fg_sg_151', 'fg_sg_153', 'fg_sg_154', 'fg_sg_155', 'fg_sg_157', 'fg_sg_159', 'fg_sg_160', 'fg_sg_161', 'fg_sg_162', 'fg_sg_164', 'fg_sg_165', 'fg_sg_166', 'fg_sg_167', 'fg_sg_168', 'fg_sg_169', 'fg_sg_170', 'fg_sg_171', 'fg_sg_172', 'fg_sg_173', 'fg_sg_174', 'fg_sg_176', 'fg_sg_177', 'fg_sg_179', 'fg_sg_181', 'fg_sg_182', 'fg_sg_183', 'fg_sg_185', 'fg_sg_187', 'fg_sg_188', 'fg_sg_189', 'fg_sg_190', 'fg_sg_191', 'fg_sg_192', 'fg_sg_193', 'psv_starts', 'psv', 'salesday', 'presales', 'postsales', 'bridge_days', 'outlet', 'store_opening', 'weiberfasching_2022', 'faschingsfreitag_2022', 'faschingssamstag_2022', 'rosenmontag_2022', 'faschingdienstag_2022', 'weiberfasching', 'faschingsfreitag', 'faschingssamstag', 'pre_christmas_peaks', 'valentines_day', 'interaction', 'market_Montags', 'market_Dienstags', 'market_Mittwochs', 'market_Donnerstags', 'market_Freitags', 'market_Samstags', 'population', 'shop_area', 'dist_from_weiden', 'ratio', 'average', 'shop_count', 'weekday_special', 'weekend_special', 'x_coord', 'y_coord', 'dayofmonth', 'isoweek', 'month', 'dayofyear', 'dayofseason', 'season_month']
2025-10-06 06:52:21,250 - main.py - INFO - 137 - Successfully trained xgb9 xgboost for month (2024, 3) training data to: 2024-02-7
2025-10-06 06:52:21,250 - prediction_task.py - DEBUG - 21 - predictions starting...
2025-10-06 06:52:31,153 - prediction_task.py - DEBUG - 31 - test data not found for 194 Michelfeld in period (2024, 3)
2025-10-06 06:52:31,156 - prediction_task.py - DEBUG - 31 - test data not found for 195 Kelheim in period (2024, 3)
2025-10-06 06:52:31,156 - main.py - INFO - 145 - Successfully predicted with xgb9 xgboost for month (2024, 3)
2025-10-06 06:52:31,156 - main.py - INFO - 137 - Successfully trained agp agp for month (2024, 3) training data to: 2024-02-7
2025-10-06 06:52:31,157 - prediction_task.py - DEBUG - 21 - predictions starting...
2025-10-06 06:52:31,638 - prediction_task.py - DEBUG - 31 - test data not found for 194 Michelfeld in period (2024, 3)
2025-10-06 06:52:31,641 - prediction_task.py - DEBUG - 31 - test data not found for 195 Kelheim in period (2024, 3)
2025-10-06 06:52:31,641 - main.py - INFO - 145 - Successfully predicted with agp agp for month (2024, 3)
2025-10-06 06:52:31,641 - algorithm.py - DEBUG - 72 - start training with xgboost...
2025-10-06 06:52:31,754 - algorithm.py - DEBUG - 78 - shape: (60793, 279) start: 2022-05-02 00:00:00 end: 2024-03-06 00:00:00
2025-10-06 06:52:40,216 - algorithm.py - INFO - 122 - parameters {'objective': 'reg:squarederror', 'base_score': None, 'booster': None, 'callbacks': None, 'colsample_bylevel': None, 'colsample_bynode': None, 'colsample_bytree': 0.8, 'device': None, 'early_stopping_rounds': None, 'enable_categorical': True, 'eval_metric': <function mean_squared_error at 0x7f560d4d9670>, 'feature_types': None, 'gamma': None, 'grow_policy': None, 'importance_type': None, 'interaction_constraints': None, 'learning_rate': 0.01, 'max_bin': None, 'max_cat_threshold': None, 'max_cat_to_onehot': None, 'max_delta_step': None, 'max_depth': 7, 'max_leaves': None, 'min_child_weight': None, 'missing': nan, 'monotone_constraints': None, 'multi_strategy': None, 'n_estimators': 1250, 'n_jobs': -1, 'num_parallel_tree': None, 'random_state': 42, 'reg_alpha': 0.05, 'reg_lambda': 1.0, 'sampling_method': None, 'scale_pos_weight': None, 'subsample': 0.8, 'tree_method': 'hist', 'validate_parameters': None, 'verbosity': None}
2025-10-06 06:52:40,217 - algorithm.py - INFO - 130 - parameters:
{ 'colsample_bytree': 0.8,
'enable_categorical': True,
'eval_metric': <function mean_squared_error at 0x7f560d4d9670>,
'learning_rate': 0.01,
'max_depth': 7,
'missing': nan,
'n_estimators': 1250,
'n_jobs': -1,
'objective': 'reg:squarederror',
'random_state': 42,
'reg_alpha': 0.05,
'reg_lambda': 1.0,
'subsample': 0.8,
'tree_method': 'hist'}
2025-10-06 06:52:40,217 - algorithm.py - INFO - 131 - indep vars:
['ladenvkpmean', 'ladenvkpmin', 'ladenvkpmax', 'ladenvkpstd', 'fg_bl_BW', 'fg_bl_BY', 'fg_bl_HE', 'fg_bl_NW', 'fg_bl_RP', 'weekdayname_Monday', 'weekdayname_Tuesday', 'weekdayname_Wednesday', 'weekdayname_Thursday', 'weekdayname_Friday', 'weekdayname_Saturday', 'isoweek_1', 'isoweek_2', 'isoweek_3', 'isoweek_4', 'isoweek_5', 'isoweek_6', 'isoweek_7', 'isoweek_8', 'isoweek_9', 'isoweek_10', 'isoweek_11', 'isoweek_12', 'isoweek_13', 'isoweek_14', 'isoweek_15', 'isoweek_16', 'isoweek_17', 'isoweek_18', 'isoweek_19', 'isoweek_20', 'isoweek_21', 'isoweek_22', 'isoweek_23', 'isoweek_24', 'isoweek_25', 'isoweek_26', 'isoweek_27', 'isoweek_28', 'isoweek_29', 'isoweek_30', 'isoweek_31', 'isoweek_32', 'isoweek_33', 'isoweek_34', 'isoweek_35', 'isoweek_36', 'isoweek_37', 'isoweek_38', 'isoweek_39', 'isoweek_40', 'isoweek_41', 'isoweek_42', 'isoweek_43', 'isoweek_44', 'isoweek_45', 'isoweek_46', 'isoweek_47', 'isoweek_48', 'isoweek_49', 'isoweek_50', 'isoweek_51', 'isoweek_52', 'month_1', 'month_2', 'month_3', 'month_4', 'month_5', 'month_6', 'month_7', 'month_8', 'month_9', 'month_10', 'month_11', 'month_12', 'year_2022', 'year_2023', 'year_2024', 'fg_sg_1', 'fg_sg_2', 'fg_sg_3', 'fg_sg_9', 'fg_sg_19', 'fg_sg_21', 'fg_sg_24', 'fg_sg_26', 'fg_sg_27', 'fg_sg_28', 'fg_sg_29', 'fg_sg_31', 'fg_sg_34', 'fg_sg_40', 'fg_sg_41', 'fg_sg_43', 'fg_sg_44', 'fg_sg_52', 'fg_sg_55', 'fg_sg_57', 'fg_sg_58', 'fg_sg_61', 'fg_sg_62', 'fg_sg_63', 'fg_sg_64', 'fg_sg_65', 'fg_sg_66', 'fg_sg_68', 'fg_sg_69', 'fg_sg_71', 'fg_sg_73', 'fg_sg_74', 'fg_sg_76', 'fg_sg_77', 'fg_sg_80', 'fg_sg_81', 'fg_sg_82', 'fg_sg_83', 'fg_sg_85', 'fg_sg_88', 'fg_sg_89', 'fg_sg_91', 'fg_sg_92', 'fg_sg_96', 'fg_sg_97', 'fg_sg_99', 'fg_sg_101', 'fg_sg_103', 'fg_sg_104', 'fg_sg_105', 'fg_sg_107', 'fg_sg_108', 'fg_sg_109', 'fg_sg_110', 'fg_sg_111', 'fg_sg_112', 'fg_sg_113', 'fg_sg_117', 'fg_sg_118', 'fg_sg_120', 'fg_sg_125', 'fg_sg_126', 'fg_sg_128', 'fg_sg_130', 'fg_sg_131', 'fg_sg_133', 'fg_sg_134', 'fg_sg_136', 'fg_sg_139', 'fg_sg_141', 'fg_sg_142', 'fg_sg_143', 'fg_sg_146', 'fg_sg_147', 'fg_sg_148', 'fg_sg_149', 'fg_sg_150', 'fg_sg_151', 'fg_sg_153', 'fg_sg_154', 'fg_sg_155', 'fg_sg_157', 'fg_sg_159', 'fg_sg_160', 'fg_sg_161', 'fg_sg_162', 'fg_sg_164', 'fg_sg_165', 'fg_sg_166', 'fg_sg_167', 'fg_sg_168', 'fg_sg_169', 'fg_sg_170', 'fg_sg_171', 'fg_sg_172', 'fg_sg_173', 'fg_sg_174', 'fg_sg_176', 'fg_sg_177', 'fg_sg_179', 'fg_sg_181', 'fg_sg_182', 'fg_sg_183', 'fg_sg_185', 'fg_sg_187', 'fg_sg_188', 'fg_sg_189', 'fg_sg_190', 'fg_sg_191', 'fg_sg_192', 'fg_sg_193', 'psv_starts', 'psv', 'salesday', 'presales', 'postsales', 'bridge_days', 'outlet', 'store_opening', 'weiberfasching_2022', 'faschingsfreitag_2022', 'faschingssamstag_2022', 'rosenmontag_2022', 'faschingdienstag_2022', 'weiberfasching', 'faschingsfreitag', 'faschingssamstag', 'pre_christmas_peaks', 'valentines_day', 'interaction', 'market_Montags', 'market_Dienstags', 'market_Mittwochs', 'market_Donnerstags', 'market_Freitags', 'market_Samstags', 'population', 'shop_area', 'dist_from_weiden', 'ratio', 'average', 'shop_count', 'weekday_special', 'weekend_special', 'x_coord', 'y_coord', 'dayofmonth', 'isoweek', 'month', 'dayofyear', 'dayofseason', 'season_month']
2025-10-06 06:52:40,220 - main.py - INFO - 137 - Successfully trained xgb9 xgboost for month (2024, 4) training data to: 2024-03-7
2025-10-06 06:52:40,220 - prediction_task.py - DEBUG - 21 - predictions starting...
2025-10-06 06:52:49,933 - prediction_task.py - DEBUG - 31 - test data not found for 194 Michelfeld in period (2024, 4)
2025-10-06 06:52:49,935 - prediction_task.py - DEBUG - 31 - test data not found for 195 Kelheim in period (2024, 4)
2025-10-06 06:52:49,936 - main.py - INFO - 145 - Successfully predicted with xgb9 xgboost for month (2024, 4)
2025-10-06 06:52:49,936 - main.py - INFO - 137 - Successfully trained agp agp for month (2024, 4) training data to: 2024-03-7
2025-10-06 06:52:49,936 - prediction_task.py - DEBUG - 21 - predictions starting...
2025-10-06 06:52:50,402 - prediction_task.py - DEBUG - 31 - test data not found for 194 Michelfeld in period (2024, 4)
2025-10-06 06:52:50,404 - prediction_task.py - DEBUG - 31 - test data not found for 195 Kelheim in period (2024, 4)
2025-10-06 06:52:50,404 - main.py - INFO - 145 - Successfully predicted with agp agp for month (2024, 4)
2025-10-06 06:52:50,404 - algorithm.py - DEBUG - 72 - start training with xgboost...
2025-10-06 06:52:50,525 - algorithm.py - DEBUG - 78 - shape: (63568, 279) start: 2022-05-02 00:00:00 end: 2024-04-06 00:00:00
2025-10-06 06:52:59,111 - algorithm.py - INFO - 122 - parameters {'objective': 'reg:squarederror', 'base_score': None, 'booster': None, 'callbacks': None, 'colsample_bylevel': None, 'colsample_bynode': None, 'colsample_bytree': 0.8, 'device': None, 'early_stopping_rounds': None, 'enable_categorical': True, 'eval_metric': <function mean_squared_error at 0x7f560d4d9670>, 'feature_types': None, 'gamma': None, 'grow_policy': None, 'importance_type': None, 'interaction_constraints': None, 'learning_rate': 0.01, 'max_bin': None, 'max_cat_threshold': None, 'max_cat_to_onehot': None, 'max_delta_step': None, 'max_depth': 7, 'max_leaves': None, 'min_child_weight': None, 'missing': nan, 'monotone_constraints': None, 'multi_strategy': None, 'n_estimators': 1250, 'n_jobs': -1, 'num_parallel_tree': None, 'random_state': 42, 'reg_alpha': 0.05, 'reg_lambda': 1.0, 'sampling_method': None, 'scale_pos_weight': None, 'subsample': 0.8, 'tree_method': 'hist', 'validate_parameters': None, 'verbosity': None}
2025-10-06 06:52:59,112 - algorithm.py - INFO - 130 - parameters:
{ 'colsample_bytree': 0.8,
'enable_categorical': True,
'eval_metric': <function mean_squared_error at 0x7f560d4d9670>,
'learning_rate': 0.01,
'max_depth': 7,
'missing': nan,
'n_estimators': 1250,
'n_jobs': -1,
'objective': 'reg:squarederror',
'random_state': 42,
'reg_alpha': 0.05,
'reg_lambda': 1.0,
'subsample': 0.8,
'tree_method': 'hist'}
2025-10-06 06:52:59,112 - algorithm.py - INFO - 131 - indep vars:
['ladenvkpmean', 'ladenvkpmin', 'ladenvkpmax', 'ladenvkpstd', 'fg_bl_BW', 'fg_bl_BY', 'fg_bl_HE', 'fg_bl_NW', 'fg_bl_RP', 'weekdayname_Monday', 'weekdayname_Tuesday', 'weekdayname_Wednesday', 'weekdayname_Thursday', 'weekdayname_Friday', 'weekdayname_Saturday', 'isoweek_1', 'isoweek_2', 'isoweek_3', 'isoweek_4', 'isoweek_5', 'isoweek_6', 'isoweek_7', 'isoweek_8', 'isoweek_9', 'isoweek_10', 'isoweek_11', 'isoweek_12', 'isoweek_13', 'isoweek_14', 'isoweek_15', 'isoweek_16', 'isoweek_17', 'isoweek_18', 'isoweek_19', 'isoweek_20', 'isoweek_21', 'isoweek_22', 'isoweek_23', 'isoweek_24', 'isoweek_25', 'isoweek_26', 'isoweek_27', 'isoweek_28', 'isoweek_29', 'isoweek_30', 'isoweek_31', 'isoweek_32', 'isoweek_33', 'isoweek_34', 'isoweek_35', 'isoweek_36', 'isoweek_37', 'isoweek_38', 'isoweek_39', 'isoweek_40', 'isoweek_41', 'isoweek_42', 'isoweek_43', 'isoweek_44', 'isoweek_45', 'isoweek_46', 'isoweek_47', 'isoweek_48', 'isoweek_49', 'isoweek_50', 'isoweek_51', 'isoweek_52', 'month_1', 'month_2', 'month_3', 'month_4', 'month_5', 'month_6', 'month_7', 'month_8', 'month_9', 'month_10', 'month_11', 'month_12', 'year_2022', 'year_2023', 'year_2024', 'fg_sg_1', 'fg_sg_2', 'fg_sg_3', 'fg_sg_9', 'fg_sg_19', 'fg_sg_21', 'fg_sg_24', 'fg_sg_26', 'fg_sg_27', 'fg_sg_28', 'fg_sg_29', 'fg_sg_31', 'fg_sg_34', 'fg_sg_40', 'fg_sg_41', 'fg_sg_43', 'fg_sg_44', 'fg_sg_52', 'fg_sg_55', 'fg_sg_57', 'fg_sg_58', 'fg_sg_61', 'fg_sg_62', 'fg_sg_63', 'fg_sg_64', 'fg_sg_65', 'fg_sg_66', 'fg_sg_68', 'fg_sg_69', 'fg_sg_71', 'fg_sg_73', 'fg_sg_74', 'fg_sg_76', 'fg_sg_77', 'fg_sg_80', 'fg_sg_81', 'fg_sg_82', 'fg_sg_83', 'fg_sg_85', 'fg_sg_88', 'fg_sg_89', 'fg_sg_91', 'fg_sg_92', 'fg_sg_96', 'fg_sg_97', 'fg_sg_99', 'fg_sg_101', 'fg_sg_103', 'fg_sg_104', 'fg_sg_105', 'fg_sg_107', 'fg_sg_108', 'fg_sg_109', 'fg_sg_110', 'fg_sg_111', 'fg_sg_112', 'fg_sg_113', 'fg_sg_117', 'fg_sg_118', 'fg_sg_120', 'fg_sg_125', 'fg_sg_126', 'fg_sg_128', 'fg_sg_130', 'fg_sg_131', 'fg_sg_133', 'fg_sg_134', 'fg_sg_136', 'fg_sg_139', 'fg_sg_141', 'fg_sg_142', 'fg_sg_143', 'fg_sg_146', 'fg_sg_147', 'fg_sg_148', 'fg_sg_149', 'fg_sg_150', 'fg_sg_151', 'fg_sg_153', 'fg_sg_154', 'fg_sg_155', 'fg_sg_157', 'fg_sg_159', 'fg_sg_160', 'fg_sg_161', 'fg_sg_162', 'fg_sg_164', 'fg_sg_165', 'fg_sg_166', 'fg_sg_167', 'fg_sg_168', 'fg_sg_169', 'fg_sg_170', 'fg_sg_171', 'fg_sg_172', 'fg_sg_173', 'fg_sg_174', 'fg_sg_176', 'fg_sg_177', 'fg_sg_179', 'fg_sg_181', 'fg_sg_182', 'fg_sg_183', 'fg_sg_185', 'fg_sg_187', 'fg_sg_188', 'fg_sg_189', 'fg_sg_190', 'fg_sg_191', 'fg_sg_192', 'fg_sg_193', 'psv_starts', 'psv', 'salesday', 'presales', 'postsales', 'bridge_days', 'outlet', 'store_opening', 'weiberfasching_2022', 'faschingsfreitag_2022', 'faschingssamstag_2022', 'rosenmontag_2022', 'faschingdienstag_2022', 'weiberfasching', 'faschingsfreitag', 'faschingssamstag', 'pre_christmas_peaks', 'valentines_day', 'interaction', 'market_Montags', 'market_Dienstags', 'market_Mittwochs', 'market_Donnerstags', 'market_Freitags', 'market_Samstags', 'population', 'shop_area', 'dist_from_weiden', 'ratio', 'average', 'shop_count', 'weekday_special', 'weekend_special', 'x_coord', 'y_coord', 'dayofmonth', 'isoweek', 'month', 'dayofyear', 'dayofseason', 'season_month']
2025-10-06 06:52:59,114 - main.py - INFO - 137 - Successfully trained xgb9 xgboost for month (2024, 5) training data to: 2024-04-7
2025-10-06 06:52:59,114 - prediction_task.py - DEBUG - 21 - predictions starting...
2025-10-06 06:53:08,765 - prediction_task.py - DEBUG - 31 - test data not found for 194 Michelfeld in period (2024, 5)
2025-10-06 06:53:08,767 - prediction_task.py - DEBUG - 31 - test data not found for 195 Kelheim in period (2024, 5)
2025-10-06 06:53:08,767 - main.py - INFO - 145 - Successfully predicted with xgb9 xgboost for month (2024, 5)
2025-10-06 06:53:08,768 - main.py - INFO - 137 - Successfully trained agp agp for month (2024, 5) training data to: 2024-04-7
2025-10-06 06:53:08,768 - prediction_task.py - DEBUG - 21 - predictions starting...
2025-10-06 06:53:09,249 - prediction_task.py - DEBUG - 31 - test data not found for 194 Michelfeld in period (2024, 5)
2025-10-06 06:53:09,251 - prediction_task.py - DEBUG - 31 - test data not found for 195 Kelheim in period (2024, 5)
2025-10-06 06:53:09,252 - main.py - INFO - 145 - Successfully predicted with agp agp for month (2024, 5)
2025-10-06 06:53:09,252 - algorithm.py - DEBUG - 72 - start training with xgboost...
2025-10-06 06:53:09,378 - algorithm.py - DEBUG - 78 - shape: (66230, 279) start: 2022-05-02 00:00:00 end: 2024-05-06 00:00:00
2025-10-06 06:53:18,264 - algorithm.py - INFO - 122 - parameters {'objective': 'reg:squarederror', 'base_score': None, 'booster': None, 'callbacks': None, 'colsample_bylevel': None, 'colsample_bynode': None, 'colsample_bytree': 0.8, 'device': None, 'early_stopping_rounds': None, 'enable_categorical': True, 'eval_metric': <function mean_squared_error at 0x7f560d4d9670>, 'feature_types': None, 'gamma': None, 'grow_policy': None, 'importance_type': None, 'interaction_constraints': None, 'learning_rate': 0.01, 'max_bin': None, 'max_cat_threshold': None, 'max_cat_to_onehot': None, 'max_delta_step': None, 'max_depth': 7, 'max_leaves': None, 'min_child_weight': None, 'missing': nan, 'monotone_constraints': None, 'multi_strategy': None, 'n_estimators': 1250, 'n_jobs': -1, 'num_parallel_tree': None, 'random_state': 42, 'reg_alpha': 0.05, 'reg_lambda': 1.0, 'sampling_method': None, 'scale_pos_weight': None, 'subsample': 0.8, 'tree_method': 'hist', 'validate_parameters': None, 'verbosity': None}
2025-10-06 06:53:18,264 - algorithm.py - INFO - 130 - parameters:
{ 'colsample_bytree': 0.8,
'enable_categorical': True,
'eval_metric': <function mean_squared_error at 0x7f560d4d9670>,
'learning_rate': 0.01,
'max_depth': 7,
'missing': nan,
'n_estimators': 1250,
'n_jobs': -1,
'objective': 'reg:squarederror',
'random_state': 42,
'reg_alpha': 0.05,
'reg_lambda': 1.0,
'subsample': 0.8,
'tree_method': 'hist'}
2025-10-06 06:53:18,265 - algorithm.py - INFO - 131 - indep vars:
['ladenvkpmean', 'ladenvkpmin', 'ladenvkpmax', 'ladenvkpstd', 'fg_bl_BW', 'fg_bl_BY', 'fg_bl_HE', 'fg_bl_NW', 'fg_bl_RP', 'weekdayname_Monday', 'weekdayname_Tuesday', 'weekdayname_Wednesday', 'weekdayname_Thursday', 'weekdayname_Friday', 'weekdayname_Saturday', 'isoweek_1', 'isoweek_2', 'isoweek_3', 'isoweek_4', 'isoweek_5', 'isoweek_6', 'isoweek_7', 'isoweek_8', 'isoweek_9', 'isoweek_10', 'isoweek_11', 'isoweek_12', 'isoweek_13', 'isoweek_14', 'isoweek_15', 'isoweek_16', 'isoweek_17', 'isoweek_18', 'isoweek_19', 'isoweek_20', 'isoweek_21', 'isoweek_22', 'isoweek_23', 'isoweek_24', 'isoweek_25', 'isoweek_26', 'isoweek_27', 'isoweek_28', 'isoweek_29', 'isoweek_30', 'isoweek_31', 'isoweek_32', 'isoweek_33', 'isoweek_34', 'isoweek_35', 'isoweek_36', 'isoweek_37', 'isoweek_38', 'isoweek_39', 'isoweek_40', 'isoweek_41', 'isoweek_42', 'isoweek_43', 'isoweek_44', 'isoweek_45', 'isoweek_46', 'isoweek_47', 'isoweek_48', 'isoweek_49', 'isoweek_50', 'isoweek_51', 'isoweek_52', 'month_1', 'month_2', 'month_3', 'month_4', 'month_5', 'month_6', 'month_7', 'month_8', 'month_9', 'month_10', 'month_11', 'month_12', 'year_2022', 'year_2023', 'year_2024', 'fg_sg_1', 'fg_sg_2', 'fg_sg_3', 'fg_sg_9', 'fg_sg_19', 'fg_sg_21', 'fg_sg_24', 'fg_sg_26', 'fg_sg_27', 'fg_sg_28', 'fg_sg_29', 'fg_sg_31', 'fg_sg_34', 'fg_sg_40', 'fg_sg_41', 'fg_sg_43', 'fg_sg_44', 'fg_sg_52', 'fg_sg_55', 'fg_sg_57', 'fg_sg_58', 'fg_sg_61', 'fg_sg_62', 'fg_sg_63', 'fg_sg_64', 'fg_sg_65', 'fg_sg_66', 'fg_sg_68', 'fg_sg_69', 'fg_sg_71', 'fg_sg_73', 'fg_sg_74', 'fg_sg_76', 'fg_sg_77', 'fg_sg_80', 'fg_sg_81', 'fg_sg_82', 'fg_sg_83', 'fg_sg_85', 'fg_sg_88', 'fg_sg_89', 'fg_sg_91', 'fg_sg_92', 'fg_sg_96', 'fg_sg_97', 'fg_sg_99', 'fg_sg_101', 'fg_sg_103', 'fg_sg_104', 'fg_sg_105', 'fg_sg_107', 'fg_sg_108', 'fg_sg_109', 'fg_sg_110', 'fg_sg_111', 'fg_sg_112', 'fg_sg_113', 'fg_sg_117', 'fg_sg_118', 'fg_sg_120', 'fg_sg_125', 'fg_sg_126', 'fg_sg_128', 'fg_sg_130', 'fg_sg_131', 'fg_sg_133', 'fg_sg_134', 'fg_sg_136', 'fg_sg_139', 'fg_sg_141', 'fg_sg_142', 'fg_sg_143', 'fg_sg_146', 'fg_sg_147', 'fg_sg_148', 'fg_sg_149', 'fg_sg_150', 'fg_sg_151', 'fg_sg_153', 'fg_sg_154', 'fg_sg_155', 'fg_sg_157', 'fg_sg_159', 'fg_sg_160', 'fg_sg_161', 'fg_sg_162', 'fg_sg_164', 'fg_sg_165', 'fg_sg_166', 'fg_sg_167', 'fg_sg_168', 'fg_sg_169', 'fg_sg_170', 'fg_sg_171', 'fg_sg_172', 'fg_sg_173', 'fg_sg_174', 'fg_sg_176', 'fg_sg_177', 'fg_sg_179', 'fg_sg_181', 'fg_sg_182', 'fg_sg_183', 'fg_sg_185', 'fg_sg_187', 'fg_sg_188', 'fg_sg_189', 'fg_sg_190', 'fg_sg_191', 'fg_sg_192', 'fg_sg_193', 'psv_starts', 'psv', 'salesday', 'presales', 'postsales', 'bridge_days', 'outlet', 'store_opening', 'weiberfasching_2022', 'faschingsfreitag_2022', 'faschingssamstag_2022', 'rosenmontag_2022', 'faschingdienstag_2022', 'weiberfasching', 'faschingsfreitag', 'faschingssamstag', 'pre_christmas_peaks', 'valentines_day', 'interaction', 'market_Montags', 'market_Dienstags', 'market_Mittwochs', 'market_Donnerstags', 'market_Freitags', 'market_Samstags', 'population', 'shop_area', 'dist_from_weiden', 'ratio', 'average', 'shop_count', 'weekday_special', 'weekend_special', 'x_coord', 'y_coord', 'dayofmonth', 'isoweek', 'month', 'dayofyear', 'dayofseason', 'season_month']
2025-10-06 06:53:18,267 - main.py - INFO - 137 - Successfully trained xgb9 xgboost for month (2024, 6) training data to: 2024-05-7
2025-10-06 06:53:18,267 - prediction_task.py - DEBUG - 21 - predictions starting...
2025-10-06 06:53:28,077 - prediction_task.py - DEBUG - 31 - test data not found for 194 Michelfeld in period (2024, 6)
2025-10-06 06:53:28,080 - prediction_task.py - DEBUG - 31 - test data not found for 195 Kelheim in period (2024, 6)
2025-10-06 06:53:28,080 - main.py - INFO - 145 - Successfully predicted with xgb9 xgboost for month (2024, 6)
2025-10-06 06:53:28,080 - main.py - INFO - 137 - Successfully trained agp agp for month (2024, 6) training data to: 2024-05-7
2025-10-06 06:53:28,080 - prediction_task.py - DEBUG - 21 - predictions starting...
2025-10-06 06:53:28,557 - prediction_task.py - DEBUG - 31 - test data not found for 194 Michelfeld in period (2024, 6)
2025-10-06 06:53:28,559 - prediction_task.py - DEBUG - 31 - test data not found for 195 Kelheim in period (2024, 6)
2025-10-06 06:53:28,559 - main.py - INFO - 145 - Successfully predicted with agp agp for month (2024, 6)
2025-10-06 06:53:28,559 - algorithm.py - DEBUG - 72 - start training with xgboost...
2025-10-06 06:53:28,691 - algorithm.py - DEBUG - 78 - shape: (68894, 279) start: 2022-05-02 00:00:00 end: 2024-06-06 00:00:00
2025-10-06 06:53:37,574 - algorithm.py - INFO - 122 - parameters {'objective': 'reg:squarederror', 'base_score': None, 'booster': None, 'callbacks': None, 'colsample_bylevel': None, 'colsample_bynode': None, 'colsample_bytree': 0.8, 'device': None, 'early_stopping_rounds': None, 'enable_categorical': True, 'eval_metric': <function mean_squared_error at 0x7f560d4d9670>, 'feature_types': None, 'gamma': None, 'grow_policy': None, 'importance_type': None, 'interaction_constraints': None, 'learning_rate': 0.01, 'max_bin': None, 'max_cat_threshold': None, 'max_cat_to_onehot': None, 'max_delta_step': None, 'max_depth': 7, 'max_leaves': None, 'min_child_weight': None, 'missing': nan, 'monotone_constraints': None, 'multi_strategy': None, 'n_estimators': 1250, 'n_jobs': -1, 'num_parallel_tree': None, 'random_state': 42, 'reg_alpha': 0.05, 'reg_lambda': 1.0, 'sampling_method': None, 'scale_pos_weight': None, 'subsample': 0.8, 'tree_method': 'hist', 'validate_parameters': None, 'verbosity': None}
2025-10-06 06:53:37,574 - algorithm.py - INFO - 130 - parameters:
{ 'colsample_bytree': 0.8,
'enable_categorical': True,
'eval_metric': <function mean_squared_error at 0x7f560d4d9670>,
'learning_rate': 0.01,
'max_depth': 7,
'missing': nan,
'n_estimators': 1250,
'n_jobs': -1,
'objective': 'reg:squarederror',
'random_state': 42,
'reg_alpha': 0.05,
'reg_lambda': 1.0,
'subsample': 0.8,
'tree_method': 'hist'}
2025-10-06 06:53:37,575 - algorithm.py - INFO - 131 - indep vars:
['ladenvkpmean', 'ladenvkpmin', 'ladenvkpmax', 'ladenvkpstd', 'fg_bl_BW', 'fg_bl_BY', 'fg_bl_HE', 'fg_bl_NW', 'fg_bl_RP', 'weekdayname_Monday', 'weekdayname_Tuesday', 'weekdayname_Wednesday', 'weekdayname_Thursday', 'weekdayname_Friday', 'weekdayname_Saturday', 'isoweek_1', 'isoweek_2', 'isoweek_3', 'isoweek_4', 'isoweek_5', 'isoweek_6', 'isoweek_7', 'isoweek_8', 'isoweek_9', 'isoweek_10', 'isoweek_11', 'isoweek_12', 'isoweek_13', 'isoweek_14', 'isoweek_15', 'isoweek_16', 'isoweek_17', 'isoweek_18', 'isoweek_19', 'isoweek_20', 'isoweek_21', 'isoweek_22', 'isoweek_23', 'isoweek_24', 'isoweek_25', 'isoweek_26', 'isoweek_27', 'isoweek_28', 'isoweek_29', 'isoweek_30', 'isoweek_31', 'isoweek_32', 'isoweek_33', 'isoweek_34', 'isoweek_35', 'isoweek_36', 'isoweek_37', 'isoweek_38', 'isoweek_39', 'isoweek_40', 'isoweek_41', 'isoweek_42', 'isoweek_43', 'isoweek_44', 'isoweek_45', 'isoweek_46', 'isoweek_47', 'isoweek_48', 'isoweek_49', 'isoweek_50', 'isoweek_51', 'isoweek_52', 'month_1', 'month_2', 'month_3', 'month_4', 'month_5', 'month_6', 'month_7', 'month_8', 'month_9', 'month_10', 'month_11', 'month_12', 'year_2022', 'year_2023', 'year_2024', 'fg_sg_1', 'fg_sg_2', 'fg_sg_3', 'fg_sg_9', 'fg_sg_19', 'fg_sg_21', 'fg_sg_24', 'fg_sg_26', 'fg_sg_27', 'fg_sg_28', 'fg_sg_29', 'fg_sg_31', 'fg_sg_34', 'fg_sg_40', 'fg_sg_41', 'fg_sg_43', 'fg_sg_44', 'fg_sg_52', 'fg_sg_55', 'fg_sg_57', 'fg_sg_58', 'fg_sg_61', 'fg_sg_62', 'fg_sg_63', 'fg_sg_64', 'fg_sg_65', 'fg_sg_66', 'fg_sg_68', 'fg_sg_69', 'fg_sg_71', 'fg_sg_73', 'fg_sg_74', 'fg_sg_76', 'fg_sg_77', 'fg_sg_80', 'fg_sg_81', 'fg_sg_82', 'fg_sg_83', 'fg_sg_85', 'fg_sg_88', 'fg_sg_89', 'fg_sg_91', 'fg_sg_92', 'fg_sg_96', 'fg_sg_97', 'fg_sg_99', 'fg_sg_101', 'fg_sg_103', 'fg_sg_104', 'fg_sg_105', 'fg_sg_107', 'fg_sg_108', 'fg_sg_109', 'fg_sg_110', 'fg_sg_111', 'fg_sg_112', 'fg_sg_113', 'fg_sg_117', 'fg_sg_118', 'fg_sg_120', 'fg_sg_125', 'fg_sg_126', 'fg_sg_128', 'fg_sg_130', 'fg_sg_131', 'fg_sg_133', 'fg_sg_134', 'fg_sg_136', 'fg_sg_139', 'fg_sg_141', 'fg_sg_142', 'fg_sg_143', 'fg_sg_146', 'fg_sg_147', 'fg_sg_148', 'fg_sg_149', 'fg_sg_150', 'fg_sg_151', 'fg_sg_153', 'fg_sg_154', 'fg_sg_155', 'fg_sg_157', 'fg_sg_159', 'fg_sg_160', 'fg_sg_161', 'fg_sg_162', 'fg_sg_164', 'fg_sg_165', 'fg_sg_166', 'fg_sg_167', 'fg_sg_168', 'fg_sg_169', 'fg_sg_170', 'fg_sg_171', 'fg_sg_172', 'fg_sg_173', 'fg_sg_174', 'fg_sg_176', 'fg_sg_177', 'fg_sg_179', 'fg_sg_181', 'fg_sg_182', 'fg_sg_183', 'fg_sg_185', 'fg_sg_187', 'fg_sg_188', 'fg_sg_189', 'fg_sg_190', 'fg_sg_191', 'fg_sg_192', 'fg_sg_193', 'psv_starts', 'psv', 'salesday', 'presales', 'postsales', 'bridge_days', 'outlet', 'store_opening', 'weiberfasching_2022', 'faschingsfreitag_2022', 'faschingssamstag_2022', 'rosenmontag_2022', 'faschingdienstag_2022', 'weiberfasching', 'faschingsfreitag', 'faschingssamstag', 'pre_christmas_peaks', 'valentines_day', 'interaction', 'market_Montags', 'market_Dienstags', 'market_Mittwochs', 'market_Donnerstags', 'market_Freitags', 'market_Samstags', 'population', 'shop_area', 'dist_from_weiden', 'ratio', 'average', 'shop_count', 'weekday_special', 'weekend_special', 'x_coord', 'y_coord', 'dayofmonth', 'isoweek', 'month', 'dayofyear', 'dayofseason', 'season_month']
2025-10-06 06:53:37,577 - main.py - INFO - 137 - Successfully trained xgb9 xgboost for month (2024, 7) training data to: 2024-06-7
2025-10-06 06:53:37,577 - prediction_task.py - DEBUG - 21 - predictions starting...
2025-10-06 06:53:47,243 - prediction_task.py - DEBUG - 31 - test data not found for 194 Michelfeld in period (2024, 7)
2025-10-06 06:53:47,246 - prediction_task.py - DEBUG - 31 - test data not found for 195 Kelheim in period (2024, 7)
2025-10-06 06:53:47,246 - main.py - INFO - 145 - Successfully predicted with xgb9 xgboost for month (2024, 7)
2025-10-06 06:53:47,246 - main.py - INFO - 137 - Successfully trained agp agp for month (2024, 7) training data to: 2024-06-7
2025-10-06 06:53:47,246 - prediction_task.py - DEBUG - 21 - predictions starting...
2025-10-06 06:53:47,898 - prediction_task.py - DEBUG - 31 - test data not found for 194 Michelfeld in period (2024, 7)
2025-10-06 06:53:47,900 - prediction_task.py - DEBUG - 31 - test data not found for 195 Kelheim in period (2024, 7)
2025-10-06 06:53:47,900 - main.py - INFO - 145 - Successfully predicted with agp agp for month (2024, 7)
2025-10-06 06:53:47,900 - algorithm.py - DEBUG - 72 - start training with xgboost...
2025-10-06 06:53:48,033 - algorithm.py - DEBUG - 78 - shape: (71778, 279) start: 2022-05-02 00:00:00 end: 2024-07-06 00:00:00
2025-10-06 06:53:57,493 - algorithm.py - INFO - 122 - parameters {'objective': 'reg:squarederror', 'base_score': None, 'booster': None, 'callbacks': None, 'colsample_bylevel': None, 'colsample_bynode': None, 'colsample_bytree': 0.8, 'device': None, 'early_stopping_rounds': None, 'enable_categorical': True, 'eval_metric': <function mean_squared_error at 0x7f560d4d9670>, 'feature_types': None, 'gamma': None, 'grow_policy': None, 'importance_type': None, 'interaction_constraints': None, 'learning_rate': 0.01, 'max_bin': None, 'max_cat_threshold': None, 'max_cat_to_onehot': None, 'max_delta_step': None, 'max_depth': 7, 'max_leaves': None, 'min_child_weight': None, 'missing': nan, 'monotone_constraints': None, 'multi_strategy': None, 'n_estimators': 1250, 'n_jobs': -1, 'num_parallel_tree': None, 'random_state': 42, 'reg_alpha': 0.05, 'reg_lambda': 1.0, 'sampling_method': None, 'scale_pos_weight': None, 'subsample': 0.8, 'tree_method': 'hist', 'validate_parameters': None, 'verbosity': None}
2025-10-06 06:53:57,493 - algorithm.py - INFO - 130 - parameters:
{ 'colsample_bytree': 0.8,
'enable_categorical': True,
'eval_metric': <function mean_squared_error at 0x7f560d4d9670>,
'learning_rate': 0.01,
'max_depth': 7,
'missing': nan,
'n_estimators': 1250,
'n_jobs': -1,
'objective': 'reg:squarederror',
'random_state': 42,
'reg_alpha': 0.05,
'reg_lambda': 1.0,
'subsample': 0.8,
'tree_method': 'hist'}
2025-10-06 06:53:57,494 - algorithm.py - INFO - 131 - indep vars:
['ladenvkpmean', 'ladenvkpmin', 'ladenvkpmax', 'ladenvkpstd', 'fg_bl_BW', 'fg_bl_BY', 'fg_bl_HE', 'fg_bl_NW', 'fg_bl_RP', 'weekdayname_Monday', 'weekdayname_Tuesday', 'weekdayname_Wednesday', 'weekdayname_Thursday', 'weekdayname_Friday', 'weekdayname_Saturday', 'isoweek_1', 'isoweek_2', 'isoweek_3', 'isoweek_4', 'isoweek_5', 'isoweek_6', 'isoweek_7', 'isoweek_8', 'isoweek_9', 'isoweek_10', 'isoweek_11', 'isoweek_12', 'isoweek_13', 'isoweek_14', 'isoweek_15', 'isoweek_16', 'isoweek_17', 'isoweek_18', 'isoweek_19', 'isoweek_20', 'isoweek_21', 'isoweek_22', 'isoweek_23', 'isoweek_24', 'isoweek_25', 'isoweek_26', 'isoweek_27', 'isoweek_28', 'isoweek_29', 'isoweek_30', 'isoweek_31', 'isoweek_32', 'isoweek_33', 'isoweek_34', 'isoweek_35', 'isoweek_36', 'isoweek_37', 'isoweek_38', 'isoweek_39', 'isoweek_40', 'isoweek_41', 'isoweek_42', 'isoweek_43', 'isoweek_44', 'isoweek_45', 'isoweek_46', 'isoweek_47', 'isoweek_48', 'isoweek_49', 'isoweek_50', 'isoweek_51', 'isoweek_52', 'month_1', 'month_2', 'month_3', 'month_4', 'month_5', 'month_6', 'month_7', 'month_8', 'month_9', 'month_10', 'month_11', 'month_12', 'year_2022', 'year_2023', 'year_2024', 'fg_sg_1', 'fg_sg_2', 'fg_sg_3', 'fg_sg_9', 'fg_sg_19', 'fg_sg_21', 'fg_sg_24', 'fg_sg_26', 'fg_sg_27', 'fg_sg_28', 'fg_sg_29', 'fg_sg_31', 'fg_sg_34', 'fg_sg_40', 'fg_sg_41', 'fg_sg_43', 'fg_sg_44', 'fg_sg_52', 'fg_sg_55', 'fg_sg_57', 'fg_sg_58', 'fg_sg_61', 'fg_sg_62', 'fg_sg_63', 'fg_sg_64', 'fg_sg_65', 'fg_sg_66', 'fg_sg_68', 'fg_sg_69', 'fg_sg_71', 'fg_sg_73', 'fg_sg_74', 'fg_sg_76', 'fg_sg_77', 'fg_sg_80', 'fg_sg_81', 'fg_sg_82', 'fg_sg_83', 'fg_sg_85', 'fg_sg_88', 'fg_sg_89', 'fg_sg_91', 'fg_sg_92', 'fg_sg_96', 'fg_sg_97', 'fg_sg_99', 'fg_sg_101', 'fg_sg_103', 'fg_sg_104', 'fg_sg_105', 'fg_sg_107', 'fg_sg_108', 'fg_sg_109', 'fg_sg_110', 'fg_sg_111', 'fg_sg_112', 'fg_sg_113', 'fg_sg_117', 'fg_sg_118', 'fg_sg_120', 'fg_sg_125', 'fg_sg_126', 'fg_sg_128', 'fg_sg_130', 'fg_sg_131', 'fg_sg_133', 'fg_sg_134', 'fg_sg_136', 'fg_sg_139', 'fg_sg_141', 'fg_sg_142', 'fg_sg_143', 'fg_sg_146', 'fg_sg_147', 'fg_sg_148', 'fg_sg_149', 'fg_sg_150', 'fg_sg_151', 'fg_sg_153', 'fg_sg_154', 'fg_sg_155', 'fg_sg_157', 'fg_sg_159', 'fg_sg_160', 'fg_sg_161', 'fg_sg_162', 'fg_sg_164', 'fg_sg_165', 'fg_sg_166', 'fg_sg_167', 'fg_sg_168', 'fg_sg_169', 'fg_sg_170', 'fg_sg_171', 'fg_sg_172', 'fg_sg_173', 'fg_sg_174', 'fg_sg_176', 'fg_sg_177', 'fg_sg_179', 'fg_sg_181', 'fg_sg_182', 'fg_sg_183', 'fg_sg_185', 'fg_sg_187', 'fg_sg_188', 'fg_sg_189', 'fg_sg_190', 'fg_sg_191', 'fg_sg_192', 'fg_sg_193', 'psv_starts', 'psv', 'salesday', 'presales', 'postsales', 'bridge_days', 'outlet', 'store_opening', 'weiberfasching_2022', 'faschingsfreitag_2022', 'faschingssamstag_2022', 'rosenmontag_2022', 'faschingdienstag_2022', 'weiberfasching', 'faschingsfreitag', 'faschingssamstag', 'pre_christmas_peaks', 'valentines_day', 'interaction', 'market_Montags', 'market_Dienstags', 'market_Mittwochs', 'market_Donnerstags', 'market_Freitags', 'market_Samstags', 'population', 'shop_area', 'dist_from_weiden', 'ratio', 'average', 'shop_count', 'weekday_special', 'weekend_special', 'x_coord', 'y_coord', 'dayofmonth', 'isoweek', 'month', 'dayofyear', 'dayofseason', 'season_month']
2025-10-06 06:53:57,497 - main.py - INFO - 137 - Successfully trained xgb9 xgboost for month (2024, 8) training data to: 2024-07-7
2025-10-06 06:53:57,497 - prediction_task.py - DEBUG - 21 - predictions starting...
2025-10-06 06:54:07,441 - prediction_task.py - DEBUG - 31 - test data not found for 194 Michelfeld in period (2024, 8)
2025-10-06 06:54:07,444 - prediction_task.py - DEBUG - 31 - test data not found for 195 Kelheim in period (2024, 8)
2025-10-06 06:54:07,444 - main.py - INFO - 145 - Successfully predicted with xgb9 xgboost for month (2024, 8)
2025-10-06 06:54:07,444 - main.py - INFO - 137 - Successfully trained agp agp for month (2024, 8) training data to: 2024-07-7
2025-10-06 06:54:07,444 - prediction_task.py - DEBUG - 21 - predictions starting...
2025-10-06 06:54:07,946 - prediction_task.py - DEBUG - 31 - test data not found for 194 Michelfeld in period (2024, 8)
2025-10-06 06:54:07,948 - prediction_task.py - DEBUG - 31 - test data not found for 195 Kelheim in period (2024, 8)
2025-10-06 06:54:07,948 - main.py - INFO - 145 - Successfully predicted with agp agp for month (2024, 8)
2025-10-06 06:54:07,949 - algorithm.py - DEBUG - 72 - start training with xgboost...
2025-10-06 06:54:08,092 - algorithm.py - DEBUG - 78 - shape: (74647, 279) start: 2022-05-02 00:00:00 end: 2024-08-06 00:00:00
2025-10-06 06:54:17,947 - algorithm.py - INFO - 122 - parameters {'objective': 'reg:squarederror', 'base_score': None, 'booster': None, 'callbacks': None, 'colsample_bylevel': None, 'colsample_bynode': None, 'colsample_bytree': 0.8, 'device': None, 'early_stopping_rounds': None, 'enable_categorical': True, 'eval_metric': <function mean_squared_error at 0x7f560d4d9670>, 'feature_types': None, 'gamma': None, 'grow_policy': None, 'importance_type': None, 'interaction_constraints': None, 'learning_rate': 0.01, 'max_bin': None, 'max_cat_threshold': None, 'max_cat_to_onehot': None, 'max_delta_step': None, 'max_depth': 7, 'max_leaves': None, 'min_child_weight': None, 'missing': nan, 'monotone_constraints': None, 'multi_strategy': None, 'n_estimators': 1250, 'n_jobs': -1, 'num_parallel_tree': None, 'random_state': 42, 'reg_alpha': 0.05, 'reg_lambda': 1.0, 'sampling_method': None, 'scale_pos_weight': None, 'subsample': 0.8, 'tree_method': 'hist', 'validate_parameters': None, 'verbosity': None}
2025-10-06 06:54:17,947 - algorithm.py - INFO - 130 - parameters:
{ 'colsample_bytree': 0.8,
'enable_categorical': True,
'eval_metric': <function mean_squared_error at 0x7f560d4d9670>,
'learning_rate': 0.01,
'max_depth': 7,
'missing': nan,
'n_estimators': 1250,
'n_jobs': -1,
'objective': 'reg:squarederror',
'random_state': 42,
'reg_alpha': 0.05,
'reg_lambda': 1.0,
'subsample': 0.8,
'tree_method': 'hist'}
2025-10-06 06:54:17,947 - algorithm.py - INFO - 131 - indep vars:
['ladenvkpmean', 'ladenvkpmin', 'ladenvkpmax', 'ladenvkpstd', 'fg_bl_BW', 'fg_bl_BY', 'fg_bl_HE', 'fg_bl_NW', 'fg_bl_RP', 'weekdayname_Monday', 'weekdayname_Tuesday', 'weekdayname_Wednesday', 'weekdayname_Thursday', 'weekdayname_Friday', 'weekdayname_Saturday', 'isoweek_1', 'isoweek_2', 'isoweek_3', 'isoweek_4', 'isoweek_5', 'isoweek_6', 'isoweek_7', 'isoweek_8', 'isoweek_9', 'isoweek_10', 'isoweek_11', 'isoweek_12', 'isoweek_13', 'isoweek_14', 'isoweek_15', 'isoweek_16', 'isoweek_17', 'isoweek_18', 'isoweek_19', 'isoweek_20', 'isoweek_21', 'isoweek_22', 'isoweek_23', 'isoweek_24', 'isoweek_25', 'isoweek_26', 'isoweek_27', 'isoweek_28', 'isoweek_29', 'isoweek_30', 'isoweek_31', 'isoweek_32', 'isoweek_33', 'isoweek_34', 'isoweek_35', 'isoweek_36', 'isoweek_37', 'isoweek_38', 'isoweek_39', 'isoweek_40', 'isoweek_41', 'isoweek_42', 'isoweek_43', 'isoweek_44', 'isoweek_45', 'isoweek_46', 'isoweek_47', 'isoweek_48', 'isoweek_49', 'isoweek_50', 'isoweek_51', 'isoweek_52', 'month_1', 'month_2', 'month_3', 'month_4', 'month_5', 'month_6', 'month_7', 'month_8', 'month_9', 'month_10', 'month_11', 'month_12', 'year_2022', 'year_2023', 'year_2024', 'fg_sg_1', 'fg_sg_2', 'fg_sg_3', 'fg_sg_9', 'fg_sg_19', 'fg_sg_21', 'fg_sg_24', 'fg_sg_26', 'fg_sg_27', 'fg_sg_28', 'fg_sg_29', 'fg_sg_31', 'fg_sg_34', 'fg_sg_40', 'fg_sg_41', 'fg_sg_43', 'fg_sg_44', 'fg_sg_52', 'fg_sg_55', 'fg_sg_57', 'fg_sg_58', 'fg_sg_61', 'fg_sg_62', 'fg_sg_63', 'fg_sg_64', 'fg_sg_65', 'fg_sg_66', 'fg_sg_68', 'fg_sg_69', 'fg_sg_71', 'fg_sg_73', 'fg_sg_74', 'fg_sg_76', 'fg_sg_77', 'fg_sg_80', 'fg_sg_81', 'fg_sg_82', 'fg_sg_83', 'fg_sg_85', 'fg_sg_88', 'fg_sg_89', 'fg_sg_91', 'fg_sg_92', 'fg_sg_96', 'fg_sg_97', 'fg_sg_99', 'fg_sg_101', 'fg_sg_103', 'fg_sg_104', 'fg_sg_105', 'fg_sg_107', 'fg_sg_108', 'fg_sg_109', 'fg_sg_110', 'fg_sg_111', 'fg_sg_112', 'fg_sg_113', 'fg_sg_117', 'fg_sg_118', 'fg_sg_120', 'fg_sg_125', 'fg_sg_126', 'fg_sg_128', 'fg_sg_130', 'fg_sg_131', 'fg_sg_133', 'fg_sg_134', 'fg_sg_136', 'fg_sg_139', 'fg_sg_141', 'fg_sg_142', 'fg_sg_143', 'fg_sg_146', 'fg_sg_147', 'fg_sg_148', 'fg_sg_149', 'fg_sg_150', 'fg_sg_151', 'fg_sg_153', 'fg_sg_154', 'fg_sg_155', 'fg_sg_157', 'fg_sg_159', 'fg_sg_160', 'fg_sg_161', 'fg_sg_162', 'fg_sg_164', 'fg_sg_165', 'fg_sg_166', 'fg_sg_167', 'fg_sg_168', 'fg_sg_169', 'fg_sg_170', 'fg_sg_171', 'fg_sg_172', 'fg_sg_173', 'fg_sg_174', 'fg_sg_176', 'fg_sg_177', 'fg_sg_179', 'fg_sg_181', 'fg_sg_182', 'fg_sg_183', 'fg_sg_185', 'fg_sg_187', 'fg_sg_188', 'fg_sg_189', 'fg_sg_190', 'fg_sg_191', 'fg_sg_192', 'fg_sg_193', 'psv_starts', 'psv', 'salesday', 'presales', 'postsales', 'bridge_days', 'outlet', 'store_opening', 'weiberfasching_2022', 'faschingsfreitag_2022', 'faschingssamstag_2022', 'rosenmontag_2022', 'faschingdienstag_2022', 'weiberfasching', 'faschingsfreitag', 'faschingssamstag', 'pre_christmas_peaks', 'valentines_day', 'interaction', 'market_Montags', 'market_Dienstags', 'market_Mittwochs', 'market_Donnerstags', 'market_Freitags', 'market_Samstags', 'population', 'shop_area', 'dist_from_weiden', 'ratio', 'average', 'shop_count', 'weekday_special', 'weekend_special', 'x_coord', 'y_coord', 'dayofmonth', 'isoweek', 'month', 'dayofyear', 'dayofseason', 'season_month']
2025-10-06 06:54:17,950 - main.py - INFO - 137 - Successfully trained xgb9 xgboost for month (2024, 9) training data to: 2024-08-7
2025-10-06 06:54:17,950 - prediction_task.py - DEBUG - 21 - predictions starting...
2025-10-06 06:54:28,015 - prediction_task.py - DEBUG - 31 - test data not found for 194 Michelfeld in period (2024, 9)
2025-10-06 06:54:28,018 - prediction_task.py - DEBUG - 31 - test data not found for 195 Kelheim in period (2024, 9)
2025-10-06 06:54:28,018 - main.py - INFO - 145 - Successfully predicted with xgb9 xgboost for month (2024, 9)
2025-10-06 06:54:28,018 - main.py - INFO - 137 - Successfully trained agp agp for month (2024, 9) training data to: 2024-08-7
2025-10-06 06:54:28,018 - prediction_task.py - DEBUG - 21 - predictions starting...
2025-10-06 06:54:28,504 - prediction_task.py - DEBUG - 31 - test data not found for 194 Michelfeld in period (2024, 9)
2025-10-06 06:54:28,506 - prediction_task.py - DEBUG - 31 - test data not found for 195 Kelheim in period (2024, 9)
2025-10-06 06:54:28,506 - main.py - INFO - 145 - Successfully predicted with agp agp for month (2024, 9)
2025-10-06 06:54:28,506 - algorithm.py - DEBUG - 72 - start training with xgboost...
2025-10-06 06:54:28,648 - algorithm.py - DEBUG - 78 - shape: (77566, 279) start: 2022-05-02 00:00:00 end: 2024-09-06 00:00:00
2025-10-06 06:54:38,775 - algorithm.py - INFO - 122 - parameters {'objective': 'reg:squarederror', 'base_score': None, 'booster': None, 'callbacks': None, 'colsample_bylevel': None, 'colsample_bynode': None, 'colsample_bytree': 0.8, 'device': None, 'early_stopping_rounds': None, 'enable_categorical': True, 'eval_metric': <function mean_squared_error at 0x7f560d4d9670>, 'feature_types': None, 'gamma': None, 'grow_policy': None, 'importance_type': None, 'interaction_constraints': None, 'learning_rate': 0.01, 'max_bin': None, 'max_cat_threshold': None, 'max_cat_to_onehot': None, 'max_delta_step': None, 'max_depth': 7, 'max_leaves': None, 'min_child_weight': None, 'missing': nan, 'monotone_constraints': None, 'multi_strategy': None, 'n_estimators': 1250, 'n_jobs': -1, 'num_parallel_tree': None, 'random_state': 42, 'reg_alpha': 0.05, 'reg_lambda': 1.0, 'sampling_method': None, 'scale_pos_weight': None, 'subsample': 0.8, 'tree_method': 'hist', 'validate_parameters': None, 'verbosity': None}
2025-10-06 06:54:38,775 - algorithm.py - INFO - 130 - parameters:
{ 'colsample_bytree': 0.8,
'enable_categorical': True,
'eval_metric': <function mean_squared_error at 0x7f560d4d9670>,
'learning_rate': 0.01,
'max_depth': 7,
'missing': nan,
'n_estimators': 1250,
'n_jobs': -1,
'objective': 'reg:squarederror',
'random_state': 42,
'reg_alpha': 0.05,
'reg_lambda': 1.0,
'subsample': 0.8,
'tree_method': 'hist'}
2025-10-06 06:54:38,778 - algorithm.py - INFO - 131 - indep vars:
['ladenvkpmean', 'ladenvkpmin', 'ladenvkpmax', 'ladenvkpstd', 'fg_bl_BW', 'fg_bl_BY', 'fg_bl_HE', 'fg_bl_NW', 'fg_bl_RP', 'weekdayname_Monday', 'weekdayname_Tuesday', 'weekdayname_Wednesday', 'weekdayname_Thursday', 'weekdayname_Friday', 'weekdayname_Saturday', 'isoweek_1', 'isoweek_2', 'isoweek_3', 'isoweek_4', 'isoweek_5', 'isoweek_6', 'isoweek_7', 'isoweek_8', 'isoweek_9', 'isoweek_10', 'isoweek_11', 'isoweek_12', 'isoweek_13', 'isoweek_14', 'isoweek_15', 'isoweek_16', 'isoweek_17', 'isoweek_18', 'isoweek_19', 'isoweek_20', 'isoweek_21', 'isoweek_22', 'isoweek_23', 'isoweek_24', 'isoweek_25', 'isoweek_26', 'isoweek_27', 'isoweek_28', 'isoweek_29', 'isoweek_30', 'isoweek_31', 'isoweek_32', 'isoweek_33', 'isoweek_34', 'isoweek_35', 'isoweek_36', 'isoweek_37', 'isoweek_38', 'isoweek_39', 'isoweek_40', 'isoweek_41', 'isoweek_42', 'isoweek_43', 'isoweek_44', 'isoweek_45', 'isoweek_46', 'isoweek_47', 'isoweek_48', 'isoweek_49', 'isoweek_50', 'isoweek_51', 'isoweek_52', 'month_1', 'month_2', 'month_3', 'month_4', 'month_5', 'month_6', 'month_7', 'month_8', 'month_9', 'month_10', 'month_11', 'month_12', 'year_2022', 'year_2023', 'year_2024', 'fg_sg_1', 'fg_sg_2', 'fg_sg_3', 'fg_sg_9', 'fg_sg_19', 'fg_sg_21', 'fg_sg_24', 'fg_sg_26', 'fg_sg_27', 'fg_sg_28', 'fg_sg_29', 'fg_sg_31', 'fg_sg_34', 'fg_sg_40', 'fg_sg_41', 'fg_sg_43', 'fg_sg_44', 'fg_sg_52', 'fg_sg_55', 'fg_sg_57', 'fg_sg_58', 'fg_sg_61', 'fg_sg_62', 'fg_sg_63', 'fg_sg_64', 'fg_sg_65', 'fg_sg_66', 'fg_sg_68', 'fg_sg_69', 'fg_sg_71', 'fg_sg_73', 'fg_sg_74', 'fg_sg_76', 'fg_sg_77', 'fg_sg_80', 'fg_sg_81', 'fg_sg_82', 'fg_sg_83', 'fg_sg_85', 'fg_sg_88', 'fg_sg_89', 'fg_sg_91', 'fg_sg_92', 'fg_sg_96', 'fg_sg_97', 'fg_sg_99', 'fg_sg_101', 'fg_sg_103', 'fg_sg_104', 'fg_sg_105', 'fg_sg_107', 'fg_sg_108', 'fg_sg_109', 'fg_sg_110', 'fg_sg_111', 'fg_sg_112', 'fg_sg_113', 'fg_sg_117', 'fg_sg_118', 'fg_sg_120', 'fg_sg_125', 'fg_sg_126', 'fg_sg_128', 'fg_sg_130', 'fg_sg_131', 'fg_sg_133', 'fg_sg_134', 'fg_sg_136', 'fg_sg_139', 'fg_sg_141', 'fg_sg_142', 'fg_sg_143', 'fg_sg_146', 'fg_sg_147', 'fg_sg_148', 'fg_sg_149', 'fg_sg_150', 'fg_sg_151', 'fg_sg_153', 'fg_sg_154', 'fg_sg_155', 'fg_sg_157', 'fg_sg_159', 'fg_sg_160', 'fg_sg_161', 'fg_sg_162', 'fg_sg_164', 'fg_sg_165', 'fg_sg_166', 'fg_sg_167', 'fg_sg_168', 'fg_sg_169', 'fg_sg_170', 'fg_sg_171', 'fg_sg_172', 'fg_sg_173', 'fg_sg_174', 'fg_sg_176', 'fg_sg_177', 'fg_sg_179', 'fg_sg_181', 'fg_sg_182', 'fg_sg_183', 'fg_sg_185', 'fg_sg_187', 'fg_sg_188', 'fg_sg_189', 'fg_sg_190', 'fg_sg_191', 'fg_sg_192', 'fg_sg_193', 'psv_starts', 'psv', 'salesday', 'presales', 'postsales', 'bridge_days', 'outlet', 'store_opening', 'weiberfasching_2022', 'faschingsfreitag_2022', 'faschingssamstag_2022', 'rosenmontag_2022', 'faschingdienstag_2022', 'weiberfasching', 'faschingsfreitag', 'faschingssamstag', 'pre_christmas_peaks', 'valentines_day', 'interaction', 'market_Montags', 'market_Dienstags', 'market_Mittwochs', 'market_Donnerstags', 'market_Freitags', 'market_Samstags', 'population', 'shop_area', 'dist_from_weiden', 'ratio', 'average', 'shop_count', 'weekday_special', 'weekend_special', 'x_coord', 'y_coord', 'dayofmonth', 'isoweek', 'month', 'dayofyear', 'dayofseason', 'season_month']
2025-10-06 06:54:38,781 - main.py - INFO - 137 - Successfully trained xgb9 xgboost for month (2024, 10) training data to: 2024-09-7
2025-10-06 06:54:38,781 - prediction_task.py - DEBUG - 21 - predictions starting...
2025-10-06 06:54:39,665 - prediction_task.py - DEBUG - 31 - test data not found for 29 Kelheim II in period (2024, 10)
2025-10-06 06:54:48,604 - prediction_task.py - DEBUG - 31 - test data not found for 194 Michelfeld in period (2024, 10)
2025-10-06 06:54:48,606 - prediction_task.py - DEBUG - 31 - test data not found for 195 Kelheim in period (2024, 10)
2025-10-06 06:54:48,606 - main.py - INFO - 145 - Successfully predicted with xgb9 xgboost for month (2024, 10)
2025-10-06 06:54:48,606 - main.py - INFO - 137 - Successfully trained agp agp for month (2024, 10) training data to: 2024-09-7
2025-10-06 06:54:48,607 - prediction_task.py - DEBUG - 21 - predictions starting...
2025-10-06 06:54:48,653 - prediction_task.py - DEBUG - 31 - test data not found for 29 Kelheim II in period (2024, 10)
2025-10-06 06:54:49,083 - prediction_task.py - DEBUG - 31 - test data not found for 194 Michelfeld in period (2024, 10)
2025-10-06 06:54:49,085 - prediction_task.py - DEBUG - 31 - test data not found for 195 Kelheim in period (2024, 10)
2025-10-06 06:54:49,085 - main.py - INFO - 145 - Successfully predicted with agp agp for month (2024, 10)
2025-10-06 06:54:49,085 - algorithm.py - DEBUG - 72 - start training with xgboost...
2025-10-06 06:54:49,228 - algorithm.py - DEBUG - 78 - shape: (80206, 279) start: 2022-05-02 00:00:00 end: 2024-10-05 00:00:00
2025-10-06 06:54:59,419 - algorithm.py - INFO - 122 - parameters {'objective': 'reg:squarederror', 'base_score': None, 'booster': None, 'callbacks': None, 'colsample_bylevel': None, 'colsample_bynode': None, 'colsample_bytree': 0.8, 'device': None, 'early_stopping_rounds': None, 'enable_categorical': True, 'eval_metric': <function mean_squared_error at 0x7f560d4d9670>, 'feature_types': None, 'gamma': None, 'grow_policy': None, 'importance_type': None, 'interaction_constraints': None, 'learning_rate': 0.01, 'max_bin': None, 'max_cat_threshold': None, 'max_cat_to_onehot': None, 'max_delta_step': None, 'max_depth': 7, 'max_leaves': None, 'min_child_weight': None, 'missing': nan, 'monotone_constraints': None, 'multi_strategy': None, 'n_estimators': 1250, 'n_jobs': -1, 'num_parallel_tree': None, 'random_state': 42, 'reg_alpha': 0.05, 'reg_lambda': 1.0, 'sampling_method': None, 'scale_pos_weight': None, 'subsample': 0.8, 'tree_method': 'hist', 'validate_parameters': None, 'verbosity': None}
2025-10-06 06:54:59,419 - algorithm.py - INFO - 130 - parameters:
{ 'colsample_bytree': 0.8,
'enable_categorical': True,
'eval_metric': <function mean_squared_error at 0x7f560d4d9670>,
'learning_rate': 0.01,
'max_depth': 7,
'missing': nan,
'n_estimators': 1250,
'n_jobs': -1,
'objective': 'reg:squarederror',
'random_state': 42,
'reg_alpha': 0.05,
'reg_lambda': 1.0,
'subsample': 0.8,
'tree_method': 'hist'}
2025-10-06 06:54:59,420 - algorithm.py - INFO - 131 - indep vars:
['ladenvkpmean', 'ladenvkpmin', 'ladenvkpmax', 'ladenvkpstd', 'fg_bl_BW', 'fg_bl_BY', 'fg_bl_HE', 'fg_bl_NW', 'fg_bl_RP', 'weekdayname_Monday', 'weekdayname_Tuesday', 'weekdayname_Wednesday', 'weekdayname_Thursday', 'weekdayname_Friday', 'weekdayname_Saturday', 'isoweek_1', 'isoweek_2', 'isoweek_3', 'isoweek_4', 'isoweek_5', 'isoweek_6', 'isoweek_7', 'isoweek_8', 'isoweek_9', 'isoweek_10', 'isoweek_11', 'isoweek_12', 'isoweek_13', 'isoweek_14', 'isoweek_15', 'isoweek_16', 'isoweek_17', 'isoweek_18', 'isoweek_19', 'isoweek_20', 'isoweek_21', 'isoweek_22', 'isoweek_23', 'isoweek_24', 'isoweek_25', 'isoweek_26', 'isoweek_27', 'isoweek_28', 'isoweek_29', 'isoweek_30', 'isoweek_31', 'isoweek_32', 'isoweek_33', 'isoweek_34', 'isoweek_35', 'isoweek_36', 'isoweek_37', 'isoweek_38', 'isoweek_39', 'isoweek_40', 'isoweek_41', 'isoweek_42', 'isoweek_43', 'isoweek_44', 'isoweek_45', 'isoweek_46', 'isoweek_47', 'isoweek_48', 'isoweek_49', 'isoweek_50', 'isoweek_51', 'isoweek_52', 'month_1', 'month_2', 'month_3', 'month_4', 'month_5', 'month_6', 'month_7', 'month_8', 'month_9', 'month_10', 'month_11', 'month_12', 'year_2022', 'year_2023', 'year_2024', 'fg_sg_1', 'fg_sg_2', 'fg_sg_3', 'fg_sg_9', 'fg_sg_19', 'fg_sg_21', 'fg_sg_24', 'fg_sg_26', 'fg_sg_27', 'fg_sg_28', 'fg_sg_29', 'fg_sg_31', 'fg_sg_34', 'fg_sg_40', 'fg_sg_41', 'fg_sg_43', 'fg_sg_44', 'fg_sg_52', 'fg_sg_55', 'fg_sg_57', 'fg_sg_58', 'fg_sg_61', 'fg_sg_62', 'fg_sg_63', 'fg_sg_64', 'fg_sg_65', 'fg_sg_66', 'fg_sg_68', 'fg_sg_69', 'fg_sg_71', 'fg_sg_73', 'fg_sg_74', 'fg_sg_76', 'fg_sg_77', 'fg_sg_80', 'fg_sg_81', 'fg_sg_82', 'fg_sg_83', 'fg_sg_85', 'fg_sg_88', 'fg_sg_89', 'fg_sg_91', 'fg_sg_92', 'fg_sg_96', 'fg_sg_97', 'fg_sg_99', 'fg_sg_101', 'fg_sg_103', 'fg_sg_104', 'fg_sg_105', 'fg_sg_107', 'fg_sg_108', 'fg_sg_109', 'fg_sg_110', 'fg_sg_111', 'fg_sg_112', 'fg_sg_113', 'fg_sg_117', 'fg_sg_118', 'fg_sg_120', 'fg_sg_125', 'fg_sg_126', 'fg_sg_128', 'fg_sg_130', 'fg_sg_131', 'fg_sg_133', 'fg_sg_134', 'fg_sg_136', 'fg_sg_139', 'fg_sg_141', 'fg_sg_142', 'fg_sg_143', 'fg_sg_146', 'fg_sg_147', 'fg_sg_148', 'fg_sg_149', 'fg_sg_150', 'fg_sg_151', 'fg_sg_153', 'fg_sg_154', 'fg_sg_155', 'fg_sg_157', 'fg_sg_159', 'fg_sg_160', 'fg_sg_161', 'fg_sg_162', 'fg_sg_164', 'fg_sg_165', 'fg_sg_166', 'fg_sg_167', 'fg_sg_168', 'fg_sg_169', 'fg_sg_170', 'fg_sg_171', 'fg_sg_172', 'fg_sg_173', 'fg_sg_174', 'fg_sg_176', 'fg_sg_177', 'fg_sg_179', 'fg_sg_181', 'fg_sg_182', 'fg_sg_183', 'fg_sg_185', 'fg_sg_187', 'fg_sg_188', 'fg_sg_189', 'fg_sg_190', 'fg_sg_191', 'fg_sg_192', 'fg_sg_193', 'psv_starts', 'psv', 'salesday', 'presales', 'postsales', 'bridge_days', 'outlet', 'store_opening', 'weiberfasching_2022', 'faschingsfreitag_2022', 'faschingssamstag_2022', 'rosenmontag_2022', 'faschingdienstag_2022', 'weiberfasching', 'faschingsfreitag', 'faschingssamstag', 'pre_christmas_peaks', 'valentines_day', 'interaction', 'market_Montags', 'market_Dienstags', 'market_Mittwochs', 'market_Donnerstags', 'market_Freitags', 'market_Samstags', 'population', 'shop_area', 'dist_from_weiden', 'ratio', 'average', 'shop_count', 'weekday_special', 'weekend_special', 'x_coord', 'y_coord', 'dayofmonth', 'isoweek', 'month', 'dayofyear', 'dayofseason', 'season_month']
2025-10-06 06:54:59,424 - main.py - INFO - 137 - Successfully trained xgb9 xgboost for month (2024, 11) training data to: 2024-10-7
2025-10-06 06:54:59,424 - prediction_task.py - DEBUG - 21 - predictions starting...
2025-10-06 06:55:00,311 - prediction_task.py - DEBUG - 31 - test data not found for 29 Kelheim II in period (2024, 11)
2025-10-06 06:55:09,282 - prediction_task.py - DEBUG - 31 - test data not found for 194 Michelfeld in period (2024, 11)
2025-10-06 06:55:09,369 - main.py - INFO - 145 - Successfully predicted with xgb9 xgboost for month (2024, 11)
2025-10-06 06:55:09,369 - main.py - INFO - 137 - Successfully trained agp agp for month (2024, 11) training data to: 2024-10-7
2025-10-06 06:55:09,369 - prediction_task.py - DEBUG - 21 - predictions starting...
2025-10-06 06:55:09,417 - prediction_task.py - DEBUG - 31 - test data not found for 29 Kelheim II in period (2024, 11)
2025-10-06 06:55:09,857 - prediction_task.py - DEBUG - 31 - test data not found for 194 Michelfeld in period (2024, 11)
2025-10-06 06:55:09,862 - main.py - INFO - 145 - Successfully predicted with agp agp for month (2024, 11)
2025-10-06 06:55:09,863 - algorithm.py - DEBUG - 72 - start training with xgboost...
2025-10-06 06:55:10,022 - algorithm.py - DEBUG - 78 - shape: (83073, 279) start: 2022-05-02 00:00:00 end: 2024-11-06 00:00:00
2025-10-06 06:55:20,322 - algorithm.py - INFO - 122 - parameters {'objective': 'reg:squarederror', 'base_score': None, 'booster': None, 'callbacks': None, 'colsample_bylevel': None, 'colsample_bynode': None, 'colsample_bytree': 0.8, 'device': None, 'early_stopping_rounds': None, 'enable_categorical': True, 'eval_metric': <function mean_squared_error at 0x7f560d4d9670>, 'feature_types': None, 'gamma': None, 'grow_policy': None, 'importance_type': None, 'interaction_constraints': None, 'learning_rate': 0.01, 'max_bin': None, 'max_cat_threshold': None, 'max_cat_to_onehot': None, 'max_delta_step': None, 'max_depth': 7, 'max_leaves': None, 'min_child_weight': None, 'missing': nan, 'monotone_constraints': None, 'multi_strategy': None, 'n_estimators': 1250, 'n_jobs': -1, 'num_parallel_tree': None, 'random_state': 42, 'reg_alpha': 0.05, 'reg_lambda': 1.0, 'sampling_method': None, 'scale_pos_weight': None, 'subsample': 0.8, 'tree_method': 'hist', 'validate_parameters': None, 'verbosity': None}
2025-10-06 06:55:20,323 - algorithm.py - INFO - 130 - parameters:
{ 'colsample_bytree': 0.8,
'enable_categorical': True,
'eval_metric': <function mean_squared_error at 0x7f560d4d9670>,
'learning_rate': 0.01,
'max_depth': 7,
'missing': nan,
'n_estimators': 1250,
'n_jobs': -1,
'objective': 'reg:squarederror',
'random_state': 42,
'reg_alpha': 0.05,
'reg_lambda': 1.0,
'subsample': 0.8,
'tree_method': 'hist'}
2025-10-06 06:55:20,324 - algorithm.py - INFO - 131 - indep vars:
['ladenvkpmean', 'ladenvkpmin', 'ladenvkpmax', 'ladenvkpstd', 'fg_bl_BW', 'fg_bl_BY', 'fg_bl_HE', 'fg_bl_NW', 'fg_bl_RP', 'weekdayname_Monday', 'weekdayname_Tuesday', 'weekdayname_Wednesday', 'weekdayname_Thursday', 'weekdayname_Friday', 'weekdayname_Saturday', 'isoweek_1', 'isoweek_2', 'isoweek_3', 'isoweek_4', 'isoweek_5', 'isoweek_6', 'isoweek_7', 'isoweek_8', 'isoweek_9', 'isoweek_10', 'isoweek_11', 'isoweek_12', 'isoweek_13', 'isoweek_14', 'isoweek_15', 'isoweek_16', 'isoweek_17', 'isoweek_18', 'isoweek_19', 'isoweek_20', 'isoweek_21', 'isoweek_22', 'isoweek_23', 'isoweek_24', 'isoweek_25', 'isoweek_26', 'isoweek_27', 'isoweek_28', 'isoweek_29', 'isoweek_30', 'isoweek_31', 'isoweek_32', 'isoweek_33', 'isoweek_34', 'isoweek_35', 'isoweek_36', 'isoweek_37', 'isoweek_38', 'isoweek_39', 'isoweek_40', 'isoweek_41', 'isoweek_42', 'isoweek_43', 'isoweek_44', 'isoweek_45', 'isoweek_46', 'isoweek_47', 'isoweek_48', 'isoweek_49', 'isoweek_50', 'isoweek_51', 'isoweek_52', 'month_1', 'month_2', 'month_3', 'month_4', 'month_5', 'month_6', 'month_7', 'month_8', 'month_9', 'month_10', 'month_11', 'month_12', 'year_2022', 'year_2023', 'year_2024', 'fg_sg_1', 'fg_sg_2', 'fg_sg_3', 'fg_sg_9', 'fg_sg_19', 'fg_sg_21', 'fg_sg_24', 'fg_sg_26', 'fg_sg_27', 'fg_sg_28', 'fg_sg_29', 'fg_sg_31', 'fg_sg_34', 'fg_sg_40', 'fg_sg_41', 'fg_sg_43', 'fg_sg_44', 'fg_sg_52', 'fg_sg_55', 'fg_sg_57', 'fg_sg_58', 'fg_sg_61', 'fg_sg_62', 'fg_sg_63', 'fg_sg_64', 'fg_sg_65', 'fg_sg_66', 'fg_sg_68', 'fg_sg_69', 'fg_sg_71', 'fg_sg_73', 'fg_sg_74', 'fg_sg_76', 'fg_sg_77', 'fg_sg_80', 'fg_sg_81', 'fg_sg_82', 'fg_sg_83', 'fg_sg_85', 'fg_sg_88', 'fg_sg_89', 'fg_sg_91', 'fg_sg_92', 'fg_sg_96', 'fg_sg_97', 'fg_sg_99', 'fg_sg_101', 'fg_sg_103', 'fg_sg_104', 'fg_sg_105', 'fg_sg_107', 'fg_sg_108', 'fg_sg_109', 'fg_sg_110', 'fg_sg_111', 'fg_sg_112', 'fg_sg_113', 'fg_sg_117', 'fg_sg_118', 'fg_sg_120', 'fg_sg_125', 'fg_sg_126', 'fg_sg_128', 'fg_sg_130', 'fg_sg_131', 'fg_sg_133', 'fg_sg_134', 'fg_sg_136', 'fg_sg_139', 'fg_sg_141', 'fg_sg_142', 'fg_sg_143', 'fg_sg_146', 'fg_sg_147', 'fg_sg_148', 'fg_sg_149', 'fg_sg_150', 'fg_sg_151', 'fg_sg_153', 'fg_sg_154', 'fg_sg_155', 'fg_sg_157', 'fg_sg_159', 'fg_sg_160', 'fg_sg_161', 'fg_sg_162', 'fg_sg_164', 'fg_sg_165', 'fg_sg_166', 'fg_sg_167', 'fg_sg_168', 'fg_sg_169', 'fg_sg_170', 'fg_sg_171', 'fg_sg_172', 'fg_sg_173', 'fg_sg_174', 'fg_sg_176', 'fg_sg_177', 'fg_sg_179', 'fg_sg_181', 'fg_sg_182', 'fg_sg_183', 'fg_sg_185', 'fg_sg_187', 'fg_sg_188', 'fg_sg_189', 'fg_sg_190', 'fg_sg_191', 'fg_sg_192', 'fg_sg_193', 'psv_starts', 'psv', 'salesday', 'presales', 'postsales', 'bridge_days', 'outlet', 'store_opening', 'weiberfasching_2022', 'faschingsfreitag_2022', 'faschingssamstag_2022', 'rosenmontag_2022', 'faschingdienstag_2022', 'weiberfasching', 'faschingsfreitag', 'faschingssamstag', 'pre_christmas_peaks', 'valentines_day', 'interaction', 'market_Montags', 'market_Dienstags', 'market_Mittwochs', 'market_Donnerstags', 'market_Freitags', 'market_Samstags', 'population', 'shop_area', 'dist_from_weiden', 'ratio', 'average', 'shop_count', 'weekday_special', 'weekend_special', 'x_coord', 'y_coord', 'dayofmonth', 'isoweek', 'month', 'dayofyear', 'dayofseason', 'season_month']
2025-10-06 06:55:20,327 - main.py - INFO - 137 - Successfully trained xgb9 xgboost for month (2024, 12) training data to: 2024-11-7
2025-10-06 06:55:20,327 - prediction_task.py - DEBUG - 21 - predictions starting...
2025-10-06 06:55:21,204 - prediction_task.py - DEBUG - 31 - test data not found for 29 Kelheim II in period (2024, 12)
2025-10-06 06:55:30,074 - main.py - INFO - 145 - Successfully predicted with xgb9 xgboost for month (2024, 12)
2025-10-06 06:55:30,074 - main.py - INFO - 137 - Successfully trained agp agp for month (2024, 12) training data to: 2024-11-7
2025-10-06 06:55:30,074 - prediction_task.py - DEBUG - 21 - predictions starting...
2025-10-06 06:55:30,122 - prediction_task.py - DEBUG - 31 - test data not found for 29 Kelheim II in period (2024, 12)
2025-10-06 06:55:30,562 - main.py - INFO - 145 - Successfully predicted with agp agp for month (2024, 12)
2025-10-06 06:55:30,563 - algorithm.py - DEBUG - 72 - start training with xgboost...
2025-10-06 06:55:30,719 - algorithm.py - DEBUG - 78 - shape: (85947, 279) start: 2022-05-02 00:00:00 end: 2024-12-06 00:00:00
2025-10-06 06:55:41,220 - algorithm.py - INFO - 122 - parameters {'objective': 'reg:squarederror', 'base_score': None, 'booster': None, 'callbacks': None, 'colsample_bylevel': None, 'colsample_bynode': None, 'colsample_bytree': 0.8, 'device': None, 'early_stopping_rounds': None, 'enable_categorical': True, 'eval_metric': <function mean_squared_error at 0x7f560d4d9670>, 'feature_types': None, 'gamma': None, 'grow_policy': None, 'importance_type': None, 'interaction_constraints': None, 'learning_rate': 0.01, 'max_bin': None, 'max_cat_threshold': None, 'max_cat_to_onehot': None, 'max_delta_step': None, 'max_depth': 7, 'max_leaves': None, 'min_child_weight': None, 'missing': nan, 'monotone_constraints': None, 'multi_strategy': None, 'n_estimators': 1250, 'n_jobs': -1, 'num_parallel_tree': None, 'random_state': 42, 'reg_alpha': 0.05, 'reg_lambda': 1.0, 'sampling_method': None, 'scale_pos_weight': None, 'subsample': 0.8, 'tree_method': 'hist', 'validate_parameters': None, 'verbosity': None}
2025-10-06 06:55:41,220 - algorithm.py - INFO - 130 - parameters:
{ 'colsample_bytree': 0.8,
'enable_categorical': True,
'eval_metric': <function mean_squared_error at 0x7f560d4d9670>,
'learning_rate': 0.01,
'max_depth': 7,
'missing': nan,
'n_estimators': 1250,
'n_jobs': -1,
'objective': 'reg:squarederror',
'random_state': 42,
'reg_alpha': 0.05,
'reg_lambda': 1.0,
'subsample': 0.8,
'tree_method': 'hist'}
2025-10-06 06:55:41,221 - algorithm.py - INFO - 131 - indep vars:
['ladenvkpmean', 'ladenvkpmin', 'ladenvkpmax', 'ladenvkpstd', 'fg_bl_BW', 'fg_bl_BY', 'fg_bl_HE', 'fg_bl_NW', 'fg_bl_RP', 'weekdayname_Monday', 'weekdayname_Tuesday', 'weekdayname_Wednesday', 'weekdayname_Thursday', 'weekdayname_Friday', 'weekdayname_Saturday', 'isoweek_1', 'isoweek_2', 'isoweek_3', 'isoweek_4', 'isoweek_5', 'isoweek_6', 'isoweek_7', 'isoweek_8', 'isoweek_9', 'isoweek_10', 'isoweek_11', 'isoweek_12', 'isoweek_13', 'isoweek_14', 'isoweek_15', 'isoweek_16', 'isoweek_17', 'isoweek_18', 'isoweek_19', 'isoweek_20', 'isoweek_21', 'isoweek_22', 'isoweek_23', 'isoweek_24', 'isoweek_25', 'isoweek_26', 'isoweek_27', 'isoweek_28', 'isoweek_29', 'isoweek_30', 'isoweek_31', 'isoweek_32', 'isoweek_33', 'isoweek_34', 'isoweek_35', 'isoweek_36', 'isoweek_37', 'isoweek_38', 'isoweek_39', 'isoweek_40', 'isoweek_41', 'isoweek_42', 'isoweek_43', 'isoweek_44', 'isoweek_45', 'isoweek_46', 'isoweek_47', 'isoweek_48', 'isoweek_49', 'isoweek_50', 'isoweek_51', 'isoweek_52', 'month_1', 'month_2', 'month_3', 'month_4', 'month_5', 'month_6', 'month_7', 'month_8', 'month_9', 'month_10', 'month_11', 'month_12', 'year_2022', 'year_2023', 'year_2024', 'fg_sg_1', 'fg_sg_2', 'fg_sg_3', 'fg_sg_9', 'fg_sg_19', 'fg_sg_21', 'fg_sg_24', 'fg_sg_26', 'fg_sg_27', 'fg_sg_28', 'fg_sg_29', 'fg_sg_31', 'fg_sg_34', 'fg_sg_40', 'fg_sg_41', 'fg_sg_43', 'fg_sg_44', 'fg_sg_52', 'fg_sg_55', 'fg_sg_57', 'fg_sg_58', 'fg_sg_61', 'fg_sg_62', 'fg_sg_63', 'fg_sg_64', 'fg_sg_65', 'fg_sg_66', 'fg_sg_68', 'fg_sg_69', 'fg_sg_71', 'fg_sg_73', 'fg_sg_74', 'fg_sg_76', 'fg_sg_77', 'fg_sg_80', 'fg_sg_81', 'fg_sg_82', 'fg_sg_83', 'fg_sg_85', 'fg_sg_88', 'fg_sg_89', 'fg_sg_91', 'fg_sg_92', 'fg_sg_96', 'fg_sg_97', 'fg_sg_99', 'fg_sg_101', 'fg_sg_103', 'fg_sg_104', 'fg_sg_105', 'fg_sg_107', 'fg_sg_108', 'fg_sg_109', 'fg_sg_110', 'fg_sg_111', 'fg_sg_112', 'fg_sg_113', 'fg_sg_117', 'fg_sg_118', 'fg_sg_120', 'fg_sg_125', 'fg_sg_126', 'fg_sg_128', 'fg_sg_130', 'fg_sg_131', 'fg_sg_133', 'fg_sg_134', 'fg_sg_136', 'fg_sg_139', 'fg_sg_141', 'fg_sg_142', 'fg_sg_143', 'fg_sg_146', 'fg_sg_147', 'fg_sg_148', 'fg_sg_149', 'fg_sg_150', 'fg_sg_151', 'fg_sg_153', 'fg_sg_154', 'fg_sg_155', 'fg_sg_157', 'fg_sg_159', 'fg_sg_160', 'fg_sg_161', 'fg_sg_162', 'fg_sg_164', 'fg_sg_165', 'fg_sg_166', 'fg_sg_167', 'fg_sg_168', 'fg_sg_169', 'fg_sg_170', 'fg_sg_171', 'fg_sg_172', 'fg_sg_173', 'fg_sg_174', 'fg_sg_176', 'fg_sg_177', 'fg_sg_179', 'fg_sg_181', 'fg_sg_182', 'fg_sg_183', 'fg_sg_185', 'fg_sg_187', 'fg_sg_188', 'fg_sg_189', 'fg_sg_190', 'fg_sg_191', 'fg_sg_192', 'fg_sg_193', 'psv_starts', 'psv', 'salesday', 'presales', 'postsales', 'bridge_days', 'outlet', 'store_opening', 'weiberfasching_2022', 'faschingsfreitag_2022', 'faschingssamstag_2022', 'rosenmontag_2022', 'faschingdienstag_2022', 'weiberfasching', 'faschingsfreitag', 'faschingssamstag', 'pre_christmas_peaks', 'valentines_day', 'interaction', 'market_Montags', 'market_Dienstags', 'market_Mittwochs', 'market_Donnerstags', 'market_Freitags', 'market_Samstags', 'population', 'shop_area', 'dist_from_weiden', 'ratio', 'average', 'shop_count', 'weekday_special', 'weekend_special', 'x_coord', 'y_coord', 'dayofmonth', 'isoweek', 'month', 'dayofyear', 'dayofseason', 'season_month']
2025-10-06 06:55:41,223 - main.py - INFO - 137 - Successfully trained xgb9 xgboost for month (2025, 1) training data to: 2024-12-7
2025-10-06 06:55:41,224 - prediction_task.py - DEBUG - 21 - predictions starting...
2025-10-06 06:55:42,076 - prediction_task.py - DEBUG - 31 - test data not found for 29 Kelheim II in period (2025, 1)
2025-10-06 06:55:44,848 - prediction_task.py - DEBUG - 31 - test data not found for 96 Hof in period (2025, 1)
2025-10-06 06:55:51,013 - main.py - INFO - 145 - Successfully predicted with xgb9 xgboost for month (2025, 1)
2025-10-06 06:55:51,013 - main.py - INFO - 137 - Successfully trained agp agp for month (2025, 1) training data to: 2024-12-7
2025-10-06 06:55:51,013 - prediction_task.py - DEBUG - 21 - predictions starting...
2025-10-06 06:55:51,062 - prediction_task.py - DEBUG - 31 - test data not found for 29 Kelheim II in period (2025, 1)
2025-10-06 06:55:51,206 - prediction_task.py - DEBUG - 31 - test data not found for 96 Hof in period (2025, 1)
2025-10-06 06:55:51,509 - main.py - INFO - 145 - Successfully predicted with agp agp for month (2025, 1)
2025-10-06 06:55:51,509 - algorithm.py - DEBUG - 72 - start training with xgboost...
2025-10-06 06:55:51,662 - algorithm.py - DEBUG - 78 - shape: (88432, 279) start: 2022-05-02 00:00:00 end: 2025-01-06 00:00:00
2025-10-06 06:56:02,112 - algorithm.py - INFO - 122 - parameters {'objective': 'reg:squarederror', 'base_score': None, 'booster': None, 'callbacks': None, 'colsample_bylevel': None, 'colsample_bynode': None, 'colsample_bytree': 0.8, 'device': None, 'early_stopping_rounds': None, 'enable_categorical': True, 'eval_metric': <function mean_squared_error at 0x7f560d4d9670>, 'feature_types': None, 'gamma': None, 'grow_policy': None, 'importance_type': None, 'interaction_constraints': None, 'learning_rate': 0.01, 'max_bin': None, 'max_cat_threshold': None, 'max_cat_to_onehot': None, 'max_delta_step': None, 'max_depth': 7, 'max_leaves': None, 'min_child_weight': None, 'missing': nan, 'monotone_constraints': None, 'multi_strategy': None, 'n_estimators': 1250, 'n_jobs': -1, 'num_parallel_tree': None, 'random_state': 42, 'reg_alpha': 0.05, 'reg_lambda': 1.0, 'sampling_method': None, 'scale_pos_weight': None, 'subsample': 0.8, 'tree_method': 'hist', 'validate_parameters': None, 'verbosity': None}
2025-10-06 06:56:02,113 - algorithm.py - INFO - 130 - parameters:
{ 'colsample_bytree': 0.8,
'enable_categorical': True,
'eval_metric': <function mean_squared_error at 0x7f560d4d9670>,
'learning_rate': 0.01,
'max_depth': 7,
'missing': nan,
'n_estimators': 1250,
'n_jobs': -1,
'objective': 'reg:squarederror',
'random_state': 42,
'reg_alpha': 0.05,
'reg_lambda': 1.0,
'subsample': 0.8,
'tree_method': 'hist'}
2025-10-06 06:56:02,113 - algorithm.py - INFO - 131 - indep vars:
['ladenvkpmean', 'ladenvkpmin', 'ladenvkpmax', 'ladenvkpstd', 'fg_bl_BW', 'fg_bl_BY', 'fg_bl_HE', 'fg_bl_NW', 'fg_bl_RP', 'weekdayname_Monday', 'weekdayname_Tuesday', 'weekdayname_Wednesday', 'weekdayname_Thursday', 'weekdayname_Friday', 'weekdayname_Saturday', 'isoweek_1', 'isoweek_2', 'isoweek_3', 'isoweek_4', 'isoweek_5', 'isoweek_6', 'isoweek_7', 'isoweek_8', 'isoweek_9', 'isoweek_10', 'isoweek_11', 'isoweek_12', 'isoweek_13', 'isoweek_14', 'isoweek_15', 'isoweek_16', 'isoweek_17', 'isoweek_18', 'isoweek_19', 'isoweek_20', 'isoweek_21', 'isoweek_22', 'isoweek_23', 'isoweek_24', 'isoweek_25', 'isoweek_26', 'isoweek_27', 'isoweek_28', 'isoweek_29', 'isoweek_30', 'isoweek_31', 'isoweek_32', 'isoweek_33', 'isoweek_34', 'isoweek_35', 'isoweek_36', 'isoweek_37', 'isoweek_38', 'isoweek_39', 'isoweek_40', 'isoweek_41', 'isoweek_42', 'isoweek_43', 'isoweek_44', 'isoweek_45', 'isoweek_46', 'isoweek_47', 'isoweek_48', 'isoweek_49', 'isoweek_50', 'isoweek_51', 'isoweek_52', 'month_1', 'month_2', 'month_3', 'month_4', 'month_5', 'month_6', 'month_7', 'month_8', 'month_9', 'month_10', 'month_11', 'month_12', 'year_2022', 'year_2023', 'year_2024', 'fg_sg_1', 'fg_sg_2', 'fg_sg_3', 'fg_sg_9', 'fg_sg_19', 'fg_sg_21', 'fg_sg_24', 'fg_sg_26', 'fg_sg_27', 'fg_sg_28', 'fg_sg_29', 'fg_sg_31', 'fg_sg_34', 'fg_sg_40', 'fg_sg_41', 'fg_sg_43', 'fg_sg_44', 'fg_sg_52', 'fg_sg_55', 'fg_sg_57', 'fg_sg_58', 'fg_sg_61', 'fg_sg_62', 'fg_sg_63', 'fg_sg_64', 'fg_sg_65', 'fg_sg_66', 'fg_sg_68', 'fg_sg_69', 'fg_sg_71', 'fg_sg_73', 'fg_sg_74', 'fg_sg_76', 'fg_sg_77', 'fg_sg_80', 'fg_sg_81', 'fg_sg_82', 'fg_sg_83', 'fg_sg_85', 'fg_sg_88', 'fg_sg_89', 'fg_sg_91', 'fg_sg_92', 'fg_sg_96', 'fg_sg_97', 'fg_sg_99', 'fg_sg_101', 'fg_sg_103', 'fg_sg_104', 'fg_sg_105', 'fg_sg_107', 'fg_sg_108', 'fg_sg_109', 'fg_sg_110', 'fg_sg_111', 'fg_sg_112', 'fg_sg_113', 'fg_sg_117', 'fg_sg_118', 'fg_sg_120', 'fg_sg_125', 'fg_sg_126', 'fg_sg_128', 'fg_sg_130', 'fg_sg_131', 'fg_sg_133', 'fg_sg_134', 'fg_sg_136', 'fg_sg_139', 'fg_sg_141', 'fg_sg_142', 'fg_sg_143', 'fg_sg_146', 'fg_sg_147', 'fg_sg_148', 'fg_sg_149', 'fg_sg_150', 'fg_sg_151', 'fg_sg_153', 'fg_sg_154', 'fg_sg_155', 'fg_sg_157', 'fg_sg_159', 'fg_sg_160', 'fg_sg_161', 'fg_sg_162', 'fg_sg_164', 'fg_sg_165', 'fg_sg_166', 'fg_sg_167', 'fg_sg_168', 'fg_sg_169', 'fg_sg_170', 'fg_sg_171', 'fg_sg_172', 'fg_sg_173', 'fg_sg_174', 'fg_sg_176', 'fg_sg_177', 'fg_sg_179', 'fg_sg_181', 'fg_sg_182', 'fg_sg_183', 'fg_sg_185', 'fg_sg_187', 'fg_sg_188', 'fg_sg_189', 'fg_sg_190', 'fg_sg_191', 'fg_sg_192', 'fg_sg_193', 'psv_starts', 'psv', 'salesday', 'presales', 'postsales', 'bridge_days', 'outlet', 'store_opening', 'weiberfasching_2022', 'faschingsfreitag_2022', 'faschingssamstag_2022', 'rosenmontag_2022', 'faschingdienstag_2022', 'weiberfasching', 'faschingsfreitag', 'faschingssamstag', 'pre_christmas_peaks', 'valentines_day', 'interaction', 'market_Montags', 'market_Dienstags', 'market_Mittwochs', 'market_Donnerstags', 'market_Freitags', 'market_Samstags', 'population', 'shop_area', 'dist_from_weiden', 'ratio', 'average', 'shop_count', 'weekday_special', 'weekend_special', 'x_coord', 'y_coord', 'dayofmonth', 'isoweek', 'month', 'dayofyear', 'dayofseason', 'season_month']
2025-10-06 06:56:02,116 - main.py - INFO - 137 - Successfully trained xgb9 xgboost for month (2025, 2) training data to: 2025-01-7
2025-10-06 06:56:02,116 - prediction_task.py - DEBUG - 21 - predictions starting...
2025-10-06 06:56:02,968 - prediction_task.py - DEBUG - 31 - test data not found for 29 Kelheim II in period (2025, 2)
2025-10-06 06:56:05,701 - prediction_task.py - DEBUG - 31 - test data not found for 96 Hof in period (2025, 2)
2025-10-06 06:56:11,643 - main.py - INFO - 145 - Successfully predicted with xgb9 xgboost for month (2025, 2)
2025-10-06 06:56:11,643 - main.py - INFO - 137 - Successfully trained agp agp for month (2025, 2) training data to: 2025-01-7
2025-10-06 06:56:11,643 - prediction_task.py - DEBUG - 21 - predictions starting...
2025-10-06 06:56:11,691 - prediction_task.py - DEBUG - 31 - test data not found for 29 Kelheim II in period (2025, 2)
2025-10-06 06:56:11,831 - prediction_task.py - DEBUG - 31 - test data not found for 96 Hof in period (2025, 2)
2025-10-06 06:56:12,351 - main.py - INFO - 145 - Successfully predicted with agp agp for month (2025, 2)
2025-10-06 06:56:12,351 - algorithm.py - DEBUG - 72 - start training with xgboost...
2025-10-06 06:56:12,519 - algorithm.py - DEBUG - 78 - shape: (91428, 279) start: 2022-05-02 00:00:00 end: 2025-02-06 00:00:00
2025-10-06 06:56:24,963 - algorithm.py - INFO - 122 - parameters {'objective': 'reg:squarederror', 'base_score': None, 'booster': None, 'callbacks': None, 'colsample_bylevel': None, 'colsample_bynode': None, 'colsample_bytree': 0.8, 'device': None, 'early_stopping_rounds': None, 'enable_categorical': True, 'eval_metric': <function mean_squared_error at 0x7f560d4d9670>, 'feature_types': None, 'gamma': None, 'grow_policy': None, 'importance_type': None, 'interaction_constraints': None, 'learning_rate': 0.01, 'max_bin': None, 'max_cat_threshold': None, 'max_cat_to_onehot': None, 'max_delta_step': None, 'max_depth': 7, 'max_leaves': None, 'min_child_weight': None, 'missing': nan, 'monotone_constraints': None, 'multi_strategy': None, 'n_estimators': 1250, 'n_jobs': -1, 'num_parallel_tree': None, 'random_state': 42, 'reg_alpha': 0.05, 'reg_lambda': 1.0, 'sampling_method': None, 'scale_pos_weight': None, 'subsample': 0.8, 'tree_method': 'hist', 'validate_parameters': None, 'verbosity': None}
2025-10-06 06:56:24,964 - algorithm.py - INFO - 130 - parameters:
{ 'colsample_bytree': 0.8,
'enable_categorical': True,
'eval_metric': <function mean_squared_error at 0x7f560d4d9670>,
'learning_rate': 0.01,
'max_depth': 7,
'missing': nan,
'n_estimators': 1250,
'n_jobs': -1,
'objective': 'reg:squarederror',
'random_state': 42,
'reg_alpha': 0.05,
'reg_lambda': 1.0,
'subsample': 0.8,
'tree_method': 'hist'}
2025-10-06 06:56:24,966 - algorithm.py - INFO - 131 - indep vars:
['ladenvkpmean', 'ladenvkpmin', 'ladenvkpmax', 'ladenvkpstd', 'fg_bl_BW', 'fg_bl_BY', 'fg_bl_HE', 'fg_bl_NW', 'fg_bl_RP', 'weekdayname_Monday', 'weekdayname_Tuesday', 'weekdayname_Wednesday', 'weekdayname_Thursday', 'weekdayname_Friday', 'weekdayname_Saturday', 'isoweek_1', 'isoweek_2', 'isoweek_3', 'isoweek_4', 'isoweek_5', 'isoweek_6', 'isoweek_7', 'isoweek_8', 'isoweek_9', 'isoweek_10', 'isoweek_11', 'isoweek_12', 'isoweek_13', 'isoweek_14', 'isoweek_15', 'isoweek_16', 'isoweek_17', 'isoweek_18', 'isoweek_19', 'isoweek_20', 'isoweek_21', 'isoweek_22', 'isoweek_23', 'isoweek_24', 'isoweek_25', 'isoweek_26', 'isoweek_27', 'isoweek_28', 'isoweek_29', 'isoweek_30', 'isoweek_31', 'isoweek_32', 'isoweek_33', 'isoweek_34', 'isoweek_35', 'isoweek_36', 'isoweek_37', 'isoweek_38', 'isoweek_39', 'isoweek_40', 'isoweek_41', 'isoweek_42', 'isoweek_43', 'isoweek_44', 'isoweek_45', 'isoweek_46', 'isoweek_47', 'isoweek_48', 'isoweek_49', 'isoweek_50', 'isoweek_51', 'isoweek_52', 'month_1', 'month_2', 'month_3', 'month_4', 'month_5', 'month_6', 'month_7', 'month_8', 'month_9', 'month_10', 'month_11', 'month_12', 'year_2022', 'year_2023', 'year_2024', 'fg_sg_1', 'fg_sg_2', 'fg_sg_3', 'fg_sg_9', 'fg_sg_19', 'fg_sg_21', 'fg_sg_24', 'fg_sg_26', 'fg_sg_27', 'fg_sg_28', 'fg_sg_29', 'fg_sg_31', 'fg_sg_34', 'fg_sg_40', 'fg_sg_41', 'fg_sg_43', 'fg_sg_44', 'fg_sg_52', 'fg_sg_55', 'fg_sg_57', 'fg_sg_58', 'fg_sg_61', 'fg_sg_62', 'fg_sg_63', 'fg_sg_64', 'fg_sg_65', 'fg_sg_66', 'fg_sg_68', 'fg_sg_69', 'fg_sg_71', 'fg_sg_73', 'fg_sg_74', 'fg_sg_76', 'fg_sg_77', 'fg_sg_80', 'fg_sg_81', 'fg_sg_82', 'fg_sg_83', 'fg_sg_85', 'fg_sg_88', 'fg_sg_89', 'fg_sg_91', 'fg_sg_92', 'fg_sg_96', 'fg_sg_97', 'fg_sg_99', 'fg_sg_101', 'fg_sg_103', 'fg_sg_104', 'fg_sg_105', 'fg_sg_107', 'fg_sg_108', 'fg_sg_109', 'fg_sg_110', 'fg_sg_111', 'fg_sg_112', 'fg_sg_113', 'fg_sg_117', 'fg_sg_118', 'fg_sg_120', 'fg_sg_125', 'fg_sg_126', 'fg_sg_128', 'fg_sg_130', 'fg_sg_131', 'fg_sg_133', 'fg_sg_134', 'fg_sg_136', 'fg_sg_139', 'fg_sg_141', 'fg_sg_142', 'fg_sg_143', 'fg_sg_146', 'fg_sg_147', 'fg_sg_148', 'fg_sg_149', 'fg_sg_150', 'fg_sg_151', 'fg_sg_153', 'fg_sg_154', 'fg_sg_155', 'fg_sg_157', 'fg_sg_159', 'fg_sg_160', 'fg_sg_161', 'fg_sg_162', 'fg_sg_164', 'fg_sg_165', 'fg_sg_166', 'fg_sg_167', 'fg_sg_168', 'fg_sg_169', 'fg_sg_170', 'fg_sg_171', 'fg_sg_172', 'fg_sg_173', 'fg_sg_174', 'fg_sg_176', 'fg_sg_177', 'fg_sg_179', 'fg_sg_181', 'fg_sg_182', 'fg_sg_183', 'fg_sg_185', 'fg_sg_187', 'fg_sg_188', 'fg_sg_189', 'fg_sg_190', 'fg_sg_191', 'fg_sg_192', 'fg_sg_193', 'psv_starts', 'psv', 'salesday', 'presales', 'postsales', 'bridge_days', 'outlet', 'store_opening', 'weiberfasching_2022', 'faschingsfreitag_2022', 'faschingssamstag_2022', 'rosenmontag_2022', 'faschingdienstag_2022', 'weiberfasching', 'faschingsfreitag', 'faschingssamstag', 'pre_christmas_peaks', 'valentines_day', 'interaction', 'market_Montags', 'market_Dienstags', 'market_Mittwochs', 'market_Donnerstags', 'market_Freitags', 'market_Samstags', 'population', 'shop_area', 'dist_from_weiden', 'ratio', 'average', 'shop_count', 'weekday_special', 'weekend_special', 'x_coord', 'y_coord', 'dayofmonth', 'isoweek', 'month', 'dayofyear', 'dayofseason', 'season_month']
2025-10-06 06:56:24,969 - main.py - INFO - 137 - Successfully trained xgb9 xgboost for month (2025, 3) training data to: 2025-02-7
2025-10-06 06:56:24,969 - prediction_task.py - DEBUG - 21 - predictions starting...
2025-10-06 06:56:25,822 - prediction_task.py - DEBUG - 31 - test data not found for 29 Kelheim II in period (2025, 3)
2025-10-06 06:56:28,556 - prediction_task.py - DEBUG - 31 - test data not found for 96 Hof in period (2025, 3)
2025-10-06 06:56:34,464 - main.py - INFO - 145 - Successfully predicted with xgb9 xgboost for month (2025, 3)
2025-10-06 06:56:34,464 - main.py - INFO - 137 - Successfully trained agp agp for month (2025, 3) training data to: 2025-02-7
2025-10-06 06:56:34,464 - prediction_task.py - DEBUG - 21 - predictions starting...
2025-10-06 06:56:34,511 - prediction_task.py - DEBUG - 31 - test data not found for 29 Kelheim II in period (2025, 3)
2025-10-06 06:56:34,650 - prediction_task.py - DEBUG - 31 - test data not found for 96 Hof in period (2025, 3)
2025-10-06 06:56:34,946 - main.py - INFO - 145 - Successfully predicted with agp agp for month (2025, 3)
2025-10-06 06:56:34,946 - algorithm.py - DEBUG - 72 - start training with xgboost...
2025-10-06 06:56:35,110 - algorithm.py - DEBUG - 78 - shape: (94067, 279) start: 2022-05-02 00:00:00 end: 2025-03-06 00:00:00
2025-10-06 06:56:45,938 - algorithm.py - INFO - 122 - parameters {'objective': 'reg:squarederror', 'base_score': None, 'booster': None, 'callbacks': None, 'colsample_bylevel': None, 'colsample_bynode': None, 'colsample_bytree': 0.8, 'device': None, 'early_stopping_rounds': None, 'enable_categorical': True, 'eval_metric': <function mean_squared_error at 0x7f560d4d9670>, 'feature_types': None, 'gamma': None, 'grow_policy': None, 'importance_type': None, 'interaction_constraints': None, 'learning_rate': 0.01, 'max_bin': None, 'max_cat_threshold': None, 'max_cat_to_onehot': None, 'max_delta_step': None, 'max_depth': 7, 'max_leaves': None, 'min_child_weight': None, 'missing': nan, 'monotone_constraints': None, 'multi_strategy': None, 'n_estimators': 1250, 'n_jobs': -1, 'num_parallel_tree': None, 'random_state': 42, 'reg_alpha': 0.05, 'reg_lambda': 1.0, 'sampling_method': None, 'scale_pos_weight': None, 'subsample': 0.8, 'tree_method': 'hist', 'validate_parameters': None, 'verbosity': None}
2025-10-06 06:56:45,938 - algorithm.py - INFO - 130 - parameters:
{ 'colsample_bytree': 0.8,
'enable_categorical': True,
'eval_metric': <function mean_squared_error at 0x7f560d4d9670>,
'learning_rate': 0.01,
'max_depth': 7,
'missing': nan,
'n_estimators': 1250,
'n_jobs': -1,
'objective': 'reg:squarederror',
'random_state': 42,
'reg_alpha': 0.05,
'reg_lambda': 1.0,
'subsample': 0.8,
'tree_method': 'hist'}
2025-10-06 06:56:45,939 - algorithm.py - INFO - 131 - indep vars:
['ladenvkpmean', 'ladenvkpmin', 'ladenvkpmax', 'ladenvkpstd', 'fg_bl_BW', 'fg_bl_BY', 'fg_bl_HE', 'fg_bl_NW', 'fg_bl_RP', 'weekdayname_Monday', 'weekdayname_Tuesday', 'weekdayname_Wednesday', 'weekdayname_Thursday', 'weekdayname_Friday', 'weekdayname_Saturday', 'isoweek_1', 'isoweek_2', 'isoweek_3', 'isoweek_4', 'isoweek_5', 'isoweek_6', 'isoweek_7', 'isoweek_8', 'isoweek_9', 'isoweek_10', 'isoweek_11', 'isoweek_12', 'isoweek_13', 'isoweek_14', 'isoweek_15', 'isoweek_16', 'isoweek_17', 'isoweek_18', 'isoweek_19', 'isoweek_20', 'isoweek_21', 'isoweek_22', 'isoweek_23', 'isoweek_24', 'isoweek_25', 'isoweek_26', 'isoweek_27', 'isoweek_28', 'isoweek_29', 'isoweek_30', 'isoweek_31', 'isoweek_32', 'isoweek_33', 'isoweek_34', 'isoweek_35', 'isoweek_36', 'isoweek_37', 'isoweek_38', 'isoweek_39', 'isoweek_40', 'isoweek_41', 'isoweek_42', 'isoweek_43', 'isoweek_44', 'isoweek_45', 'isoweek_46', 'isoweek_47', 'isoweek_48', 'isoweek_49', 'isoweek_50', 'isoweek_51', 'isoweek_52', 'month_1', 'month_2', 'month_3', 'month_4', 'month_5', 'month_6', 'month_7', 'month_8', 'month_9', 'month_10', 'month_11', 'month_12', 'year_2022', 'year_2023', 'year_2024', 'fg_sg_1', 'fg_sg_2', 'fg_sg_3', 'fg_sg_9', 'fg_sg_19', 'fg_sg_21', 'fg_sg_24', 'fg_sg_26', 'fg_sg_27', 'fg_sg_28', 'fg_sg_29', 'fg_sg_31', 'fg_sg_34', 'fg_sg_40', 'fg_sg_41', 'fg_sg_43', 'fg_sg_44', 'fg_sg_52', 'fg_sg_55', 'fg_sg_57', 'fg_sg_58', 'fg_sg_61', 'fg_sg_62', 'fg_sg_63', 'fg_sg_64', 'fg_sg_65', 'fg_sg_66', 'fg_sg_68', 'fg_sg_69', 'fg_sg_71', 'fg_sg_73', 'fg_sg_74', 'fg_sg_76', 'fg_sg_77', 'fg_sg_80', 'fg_sg_81', 'fg_sg_82', 'fg_sg_83', 'fg_sg_85', 'fg_sg_88', 'fg_sg_89', 'fg_sg_91', 'fg_sg_92', 'fg_sg_96', 'fg_sg_97', 'fg_sg_99', 'fg_sg_101', 'fg_sg_103', 'fg_sg_104', 'fg_sg_105', 'fg_sg_107', 'fg_sg_108', 'fg_sg_109', 'fg_sg_110', 'fg_sg_111', 'fg_sg_112', 'fg_sg_113', 'fg_sg_117', 'fg_sg_118', 'fg_sg_120', 'fg_sg_125', 'fg_sg_126', 'fg_sg_128', 'fg_sg_130', 'fg_sg_131', 'fg_sg_133', 'fg_sg_134', 'fg_sg_136', 'fg_sg_139', 'fg_sg_141', 'fg_sg_142', 'fg_sg_143', 'fg_sg_146', 'fg_sg_147', 'fg_sg_148', 'fg_sg_149', 'fg_sg_150', 'fg_sg_151', 'fg_sg_153', 'fg_sg_154', 'fg_sg_155', 'fg_sg_157', 'fg_sg_159', 'fg_sg_160', 'fg_sg_161', 'fg_sg_162', 'fg_sg_164', 'fg_sg_165', 'fg_sg_166', 'fg_sg_167', 'fg_sg_168', 'fg_sg_169', 'fg_sg_170', 'fg_sg_171', 'fg_sg_172', 'fg_sg_173', 'fg_sg_174', 'fg_sg_176', 'fg_sg_177', 'fg_sg_179', 'fg_sg_181', 'fg_sg_182', 'fg_sg_183', 'fg_sg_185', 'fg_sg_187', 'fg_sg_188', 'fg_sg_189', 'fg_sg_190', 'fg_sg_191', 'fg_sg_192', 'fg_sg_193', 'psv_starts', 'psv', 'salesday', 'presales', 'postsales', 'bridge_days', 'outlet', 'store_opening', 'weiberfasching_2022', 'faschingsfreitag_2022', 'faschingssamstag_2022', 'rosenmontag_2022', 'faschingdienstag_2022', 'weiberfasching', 'faschingsfreitag', 'faschingssamstag', 'pre_christmas_peaks', 'valentines_day', 'interaction', 'market_Montags', 'market_Dienstags', 'market_Mittwochs', 'market_Donnerstags', 'market_Freitags', 'market_Samstags', 'population', 'shop_area', 'dist_from_weiden', 'ratio', 'average', 'shop_count', 'weekday_special', 'weekend_special', 'x_coord', 'y_coord', 'dayofmonth', 'isoweek', 'month', 'dayofyear', 'dayofseason', 'season_month']
2025-10-06 06:56:45,942 - main.py - INFO - 137 - Successfully trained xgb9 xgboost for month (2025, 4) training data to: 2025-03-7
2025-10-06 06:56:45,942 - prediction_task.py - DEBUG - 21 - predictions starting...
2025-10-06 06:56:46,808 - prediction_task.py - DEBUG - 31 - test data not found for 29 Kelheim II in period (2025, 4)
2025-10-06 06:56:49,573 - prediction_task.py - DEBUG - 31 - test data not found for 96 Hof in period (2025, 4)
2025-10-06 06:56:55,599 - main.py - INFO - 145 - Successfully predicted with xgb9 xgboost for month (2025, 4)
2025-10-06 06:56:55,599 - main.py - INFO - 137 - Successfully trained agp agp for month (2025, 4) training data to: 2025-03-7
2025-10-06 06:56:55,599 - prediction_task.py - DEBUG - 21 - predictions starting...
2025-10-06 06:56:55,648 - prediction_task.py - DEBUG - 31 - test data not found for 29 Kelheim II in period (2025, 4)
2025-10-06 06:56:55,789 - prediction_task.py - DEBUG - 31 - test data not found for 96 Hof in period (2025, 4)
2025-10-06 06:56:56,092 - main.py - INFO - 145 - Successfully predicted with agp agp for month (2025, 4)
2025-10-06 06:56:56,092 - algorithm.py - DEBUG - 72 - start training with xgboost...
2025-10-06 06:56:56,268 - algorithm.py - DEBUG - 78 - shape: (96946, 279) start: 2022-05-02 00:00:00 end: 2025-04-05 00:00:00
2025-10-06 06:57:07,748 - algorithm.py - INFO - 122 - parameters {'objective': 'reg:squarederror', 'base_score': None, 'booster': None, 'callbacks': None, 'colsample_bylevel': None, 'colsample_bynode': None, 'colsample_bytree': 0.8, 'device': None, 'early_stopping_rounds': None, 'enable_categorical': True, 'eval_metric': <function mean_squared_error at 0x7f560d4d9670>, 'feature_types': None, 'gamma': None, 'grow_policy': None, 'importance_type': None, 'interaction_constraints': None, 'learning_rate': 0.01, 'max_bin': None, 'max_cat_threshold': None, 'max_cat_to_onehot': None, 'max_delta_step': None, 'max_depth': 7, 'max_leaves': None, 'min_child_weight': None, 'missing': nan, 'monotone_constraints': None, 'multi_strategy': None, 'n_estimators': 1250, 'n_jobs': -1, 'num_parallel_tree': None, 'random_state': 42, 'reg_alpha': 0.05, 'reg_lambda': 1.0, 'sampling_method': None, 'scale_pos_weight': None, 'subsample': 0.8, 'tree_method': 'hist', 'validate_parameters': None, 'verbosity': None}
2025-10-06 06:57:07,749 - algorithm.py - INFO - 130 - parameters:
{ 'colsample_bytree': 0.8,
'enable_categorical': True,
'eval_metric': <function mean_squared_error at 0x7f560d4d9670>,
'learning_rate': 0.01,
'max_depth': 7,
'missing': nan,
'n_estimators': 1250,
'n_jobs': -1,
'objective': 'reg:squarederror',
'random_state': 42,
'reg_alpha': 0.05,
'reg_lambda': 1.0,
'subsample': 0.8,
'tree_method': 'hist'}
2025-10-06 06:57:07,750 - algorithm.py - INFO - 131 - indep vars:
['ladenvkpmean', 'ladenvkpmin', 'ladenvkpmax', 'ladenvkpstd', 'fg_bl_BW', 'fg_bl_BY', 'fg_bl_HE', 'fg_bl_NW', 'fg_bl_RP', 'weekdayname_Monday', 'weekdayname_Tuesday', 'weekdayname_Wednesday', 'weekdayname_Thursday', 'weekdayname_Friday', 'weekdayname_Saturday', 'isoweek_1', 'isoweek_2', 'isoweek_3', 'isoweek_4', 'isoweek_5', 'isoweek_6', 'isoweek_7', 'isoweek_8', 'isoweek_9', 'isoweek_10', 'isoweek_11', 'isoweek_12', 'isoweek_13', 'isoweek_14', 'isoweek_15', 'isoweek_16', 'isoweek_17', 'isoweek_18', 'isoweek_19', 'isoweek_20', 'isoweek_21', 'isoweek_22', 'isoweek_23', 'isoweek_24', 'isoweek_25', 'isoweek_26', 'isoweek_27', 'isoweek_28', 'isoweek_29', 'isoweek_30', 'isoweek_31', 'isoweek_32', 'isoweek_33', 'isoweek_34', 'isoweek_35', 'isoweek_36', 'isoweek_37', 'isoweek_38', 'isoweek_39', 'isoweek_40', 'isoweek_41', 'isoweek_42', 'isoweek_43', 'isoweek_44', 'isoweek_45', 'isoweek_46', 'isoweek_47', 'isoweek_48', 'isoweek_49', 'isoweek_50', 'isoweek_51', 'isoweek_52', 'month_1', 'month_2', 'month_3', 'month_4', 'month_5', 'month_6', 'month_7', 'month_8', 'month_9', 'month_10', 'month_11', 'month_12', 'year_2022', 'year_2023', 'year_2024', 'fg_sg_1', 'fg_sg_2', 'fg_sg_3', 'fg_sg_9', 'fg_sg_19', 'fg_sg_21', 'fg_sg_24', 'fg_sg_26', 'fg_sg_27', 'fg_sg_28', 'fg_sg_29', 'fg_sg_31', 'fg_sg_34', 'fg_sg_40', 'fg_sg_41', 'fg_sg_43', 'fg_sg_44', 'fg_sg_52', 'fg_sg_55', 'fg_sg_57', 'fg_sg_58', 'fg_sg_61', 'fg_sg_62', 'fg_sg_63', 'fg_sg_64', 'fg_sg_65', 'fg_sg_66', 'fg_sg_68', 'fg_sg_69', 'fg_sg_71', 'fg_sg_73', 'fg_sg_74', 'fg_sg_76', 'fg_sg_77', 'fg_sg_80', 'fg_sg_81', 'fg_sg_82', 'fg_sg_83', 'fg_sg_85', 'fg_sg_88', 'fg_sg_89', 'fg_sg_91', 'fg_sg_92', 'fg_sg_96', 'fg_sg_97', 'fg_sg_99', 'fg_sg_101', 'fg_sg_103', 'fg_sg_104', 'fg_sg_105', 'fg_sg_107', 'fg_sg_108', 'fg_sg_109', 'fg_sg_110', 'fg_sg_111', 'fg_sg_112', 'fg_sg_113', 'fg_sg_117', 'fg_sg_118', 'fg_sg_120', 'fg_sg_125', 'fg_sg_126', 'fg_sg_128', 'fg_sg_130', 'fg_sg_131', 'fg_sg_133', 'fg_sg_134', 'fg_sg_136', 'fg_sg_139', 'fg_sg_141', 'fg_sg_142', 'fg_sg_143', 'fg_sg_146', 'fg_sg_147', 'fg_sg_148', 'fg_sg_149', 'fg_sg_150', 'fg_sg_151', 'fg_sg_153', 'fg_sg_154', 'fg_sg_155', 'fg_sg_157', 'fg_sg_159', 'fg_sg_160', 'fg_sg_161', 'fg_sg_162', 'fg_sg_164', 'fg_sg_165', 'fg_sg_166', 'fg_sg_167', 'fg_sg_168', 'fg_sg_169', 'fg_sg_170', 'fg_sg_171', 'fg_sg_172', 'fg_sg_173', 'fg_sg_174', 'fg_sg_176', 'fg_sg_177', 'fg_sg_179', 'fg_sg_181', 'fg_sg_182', 'fg_sg_183', 'fg_sg_185', 'fg_sg_187', 'fg_sg_188', 'fg_sg_189', 'fg_sg_190', 'fg_sg_191', 'fg_sg_192', 'fg_sg_193', 'psv_starts', 'psv', 'salesday', 'presales', 'postsales', 'bridge_days', 'outlet', 'store_opening', 'weiberfasching_2022', 'faschingsfreitag_2022', 'faschingssamstag_2022', 'rosenmontag_2022', 'faschingdienstag_2022', 'weiberfasching', 'faschingsfreitag', 'faschingssamstag', 'pre_christmas_peaks', 'valentines_day', 'interaction', 'market_Montags', 'market_Dienstags', 'market_Mittwochs', 'market_Donnerstags', 'market_Freitags', 'market_Samstags', 'population', 'shop_area', 'dist_from_weiden', 'ratio', 'average', 'shop_count', 'weekday_special', 'weekend_special', 'x_coord', 'y_coord', 'dayofmonth', 'isoweek', 'month', 'dayofyear', 'dayofseason', 'season_month']
2025-10-06 06:57:07,753 - main.py - INFO - 137 - Successfully trained xgb9 xgboost for month (2025, 5) training data to: 2025-04-7
2025-10-06 06:57:07,753 - prediction_task.py - DEBUG - 21 - predictions starting...
2025-10-06 06:57:08,874 - prediction_task.py - DEBUG - 31 - test data not found for 29 Kelheim II in period (2025, 5)
2025-10-06 06:57:09,829 - prediction_task.py - DEBUG - 31 - test data not found for 62 Heidenheim in period (2025, 5)
2025-10-06 06:57:11,549 - prediction_task.py - DEBUG - 31 - test data not found for 96 Hof in period (2025, 5)
2025-10-06 06:57:17,794 - main.py - INFO - 145 - Successfully predicted with xgb9 xgboost for month (2025, 5)
2025-10-06 06:57:17,795 - main.py - INFO - 137 - Successfully trained agp agp for month (2025, 5) training data to: 2025-04-7
2025-10-06 06:57:17,795 - prediction_task.py - DEBUG - 21 - predictions starting...
2025-10-06 06:57:17,843 - prediction_task.py - DEBUG - 31 - test data not found for 29 Kelheim II in period (2025, 5)
2025-10-06 06:57:17,892 - prediction_task.py - DEBUG - 31 - test data not found for 62 Heidenheim in period (2025, 5)
2025-10-06 06:57:17,981 - prediction_task.py - DEBUG - 31 - test data not found for 96 Hof in period (2025, 5)
2025-10-06 06:57:18,277 - main.py - INFO - 145 - Successfully predicted with agp agp for month (2025, 5)
2025-10-06 06:57:18,277 - algorithm.py - DEBUG - 72 - start training with xgboost...
2025-10-06 06:57:18,444 - algorithm.py - DEBUG - 78 - shape: (96946, 279) start: 2022-05-02 00:00:00 end: 2025-04-05 00:00:00
2025-10-06 06:57:29,363 - algorithm.py - INFO - 122 - parameters {'objective': 'reg:squarederror', 'base_score': None, 'booster': None, 'callbacks': None, 'colsample_bylevel': None, 'colsample_bynode': None, 'colsample_bytree': 0.8, 'device': None, 'early_stopping_rounds': None, 'enable_categorical': True, 'eval_metric': <function mean_squared_error at 0x7f560d4d9670>, 'feature_types': None, 'gamma': None, 'grow_policy': None, 'importance_type': None, 'interaction_constraints': None, 'learning_rate': 0.01, 'max_bin': None, 'max_cat_threshold': None, 'max_cat_to_onehot': None, 'max_delta_step': None, 'max_depth': 7, 'max_leaves': None, 'min_child_weight': None, 'missing': nan, 'monotone_constraints': None, 'multi_strategy': None, 'n_estimators': 1250, 'n_jobs': -1, 'num_parallel_tree': None, 'random_state': 42, 'reg_alpha': 0.05, 'reg_lambda': 1.0, 'sampling_method': None, 'scale_pos_weight': None, 'subsample': 0.8, 'tree_method': 'hist', 'validate_parameters': None, 'verbosity': None}
2025-10-06 06:57:29,363 - algorithm.py - INFO - 130 - parameters:
{ 'colsample_bytree': 0.8,
'enable_categorical': True,
'eval_metric': <function mean_squared_error at 0x7f560d4d9670>,
'learning_rate': 0.01,
'max_depth': 7,
'missing': nan,
'n_estimators': 1250,
'n_jobs': -1,
'objective': 'reg:squarederror',
'random_state': 42,
'reg_alpha': 0.05,
'reg_lambda': 1.0,
'subsample': 0.8,
'tree_method': 'hist'}
2025-10-06 06:57:29,363 - algorithm.py - INFO - 131 - indep vars:
['ladenvkpmean', 'ladenvkpmin', 'ladenvkpmax', 'ladenvkpstd', 'fg_bl_BW', 'fg_bl_BY', 'fg_bl_HE', 'fg_bl_NW', 'fg_bl_RP', 'weekdayname_Monday', 'weekdayname_Tuesday', 'weekdayname_Wednesday', 'weekdayname_Thursday', 'weekdayname_Friday', 'weekdayname_Saturday', 'isoweek_1', 'isoweek_2', 'isoweek_3', 'isoweek_4', 'isoweek_5', 'isoweek_6', 'isoweek_7', 'isoweek_8', 'isoweek_9', 'isoweek_10', 'isoweek_11', 'isoweek_12', 'isoweek_13', 'isoweek_14', 'isoweek_15', 'isoweek_16', 'isoweek_17', 'isoweek_18', 'isoweek_19', 'isoweek_20', 'isoweek_21', 'isoweek_22', 'isoweek_23', 'isoweek_24', 'isoweek_25', 'isoweek_26', 'isoweek_27', 'isoweek_28', 'isoweek_29', 'isoweek_30', 'isoweek_31', 'isoweek_32', 'isoweek_33', 'isoweek_34', 'isoweek_35', 'isoweek_36', 'isoweek_37', 'isoweek_38', 'isoweek_39', 'isoweek_40', 'isoweek_41', 'isoweek_42', 'isoweek_43', 'isoweek_44', 'isoweek_45', 'isoweek_46', 'isoweek_47', 'isoweek_48', 'isoweek_49', 'isoweek_50', 'isoweek_51', 'isoweek_52', 'month_1', 'month_2', 'month_3', 'month_4', 'month_5', 'month_6', 'month_7', 'month_8', 'month_9', 'month_10', 'month_11', 'month_12', 'year_2022', 'year_2023', 'year_2024', 'fg_sg_1', 'fg_sg_2', 'fg_sg_3', 'fg_sg_9', 'fg_sg_19', 'fg_sg_21', 'fg_sg_24', 'fg_sg_26', 'fg_sg_27', 'fg_sg_28', 'fg_sg_29', 'fg_sg_31', 'fg_sg_34', 'fg_sg_40', 'fg_sg_41', 'fg_sg_43', 'fg_sg_44', 'fg_sg_52', 'fg_sg_55', 'fg_sg_57', 'fg_sg_58', 'fg_sg_61', 'fg_sg_62', 'fg_sg_63', 'fg_sg_64', 'fg_sg_65', 'fg_sg_66', 'fg_sg_68', 'fg_sg_69', 'fg_sg_71', 'fg_sg_73', 'fg_sg_74', 'fg_sg_76', 'fg_sg_77', 'fg_sg_80', 'fg_sg_81', 'fg_sg_82', 'fg_sg_83', 'fg_sg_85', 'fg_sg_88', 'fg_sg_89', 'fg_sg_91', 'fg_sg_92', 'fg_sg_96', 'fg_sg_97', 'fg_sg_99', 'fg_sg_101', 'fg_sg_103', 'fg_sg_104', 'fg_sg_105', 'fg_sg_107', 'fg_sg_108', 'fg_sg_109', 'fg_sg_110', 'fg_sg_111', 'fg_sg_112', 'fg_sg_113', 'fg_sg_117', 'fg_sg_118', 'fg_sg_120', 'fg_sg_125', 'fg_sg_126', 'fg_sg_128', 'fg_sg_130', 'fg_sg_131', 'fg_sg_133', 'fg_sg_134', 'fg_sg_136', 'fg_sg_139', 'fg_sg_141', 'fg_sg_142', 'fg_sg_143', 'fg_sg_146', 'fg_sg_147', 'fg_sg_148', 'fg_sg_149', 'fg_sg_150', 'fg_sg_151', 'fg_sg_153', 'fg_sg_154', 'fg_sg_155', 'fg_sg_157', 'fg_sg_159', 'fg_sg_160', 'fg_sg_161', 'fg_sg_162', 'fg_sg_164', 'fg_sg_165', 'fg_sg_166', 'fg_sg_167', 'fg_sg_168', 'fg_sg_169', 'fg_sg_170', 'fg_sg_171', 'fg_sg_172', 'fg_sg_173', 'fg_sg_174', 'fg_sg_176', 'fg_sg_177', 'fg_sg_179', 'fg_sg_181', 'fg_sg_182', 'fg_sg_183', 'fg_sg_185', 'fg_sg_187', 'fg_sg_188', 'fg_sg_189', 'fg_sg_190', 'fg_sg_191', 'fg_sg_192', 'fg_sg_193', 'psv_starts', 'psv', 'salesday', 'presales', 'postsales', 'bridge_days', 'outlet', 'store_opening', 'weiberfasching_2022', 'faschingsfreitag_2022', 'faschingssamstag_2022', 'rosenmontag_2022', 'faschingdienstag_2022', 'weiberfasching', 'faschingsfreitag', 'faschingssamstag', 'pre_christmas_peaks', 'valentines_day', 'interaction', 'market_Montags', 'market_Dienstags', 'market_Mittwochs', 'market_Donnerstags', 'market_Freitags', 'market_Samstags', 'population', 'shop_area', 'dist_from_weiden', 'ratio', 'average', 'shop_count', 'weekday_special', 'weekend_special', 'x_coord', 'y_coord', 'dayofmonth', 'isoweek', 'month', 'dayofyear', 'dayofseason', 'season_month']
2025-10-06 06:57:29,367 - main.py - INFO - 137 - Successfully trained xgb9 xgboost for month (2025, 6) training data to: 2025-04-7
2025-10-06 06:57:29,367 - prediction_task.py - DEBUG - 21 - predictions starting...
2025-10-06 06:57:30,230 - prediction_task.py - DEBUG - 31 - test data not found for 29 Kelheim II in period (2025, 6)
2025-10-06 06:57:31,174 - prediction_task.py - DEBUG - 31 - test data not found for 62 Heidenheim in period (2025, 6)
2025-10-06 06:57:32,878 - prediction_task.py - DEBUG - 31 - test data not found for 96 Hof in period (2025, 6)
2025-10-06 06:57:38,839 - main.py - INFO - 145 - Successfully predicted with xgb9 xgboost for month (2025, 6)
2025-10-06 06:57:38,839 - main.py - INFO - 137 - Successfully trained agp agp for month (2025, 6) training data to: 2025-04-7
2025-10-06 06:57:38,839 - prediction_task.py - DEBUG - 21 - predictions starting...
2025-10-06 06:57:38,887 - prediction_task.py - DEBUG - 31 - test data not found for 29 Kelheim II in period (2025, 6)
2025-10-06 06:57:38,935 - prediction_task.py - DEBUG - 31 - test data not found for 62 Heidenheim in period (2025, 6)
2025-10-06 06:57:39,024 - prediction_task.py - DEBUG - 31 - test data not found for 96 Hof in period (2025, 6)
2025-10-06 06:57:39,610 - main.py - INFO - 145 - Successfully predicted with agp agp for month (2025, 6)
2025-10-06 06:57:39,610 - functions.py - INFO - 425 - NB: using calibrate2 to meet AGP monthly totals
2025-10-06 06:58:06,053 - functions.py - INFO - 87 - No duplicates found in predictions.
2025-10-06 06:58:40,348 - functions.py - DEBUG - 207 - metric: mae
2025-10-06 06:58:48,175 - functions.py - DEBUG - 207 - metric: mape
2025-10-06 06:58:55,432 - functions.py - DEBUG - 207 - metric: jensen_shannon
2025-10-06 06:59:02,718 - functions.py - DEBUG - 207 - metric: kullback_leibler
2025-10-06 06:59:11,484 - conversion_functions.py - DEBUG - 168 - business hours file: (1332, 9) Index(['fg_sg', 'fg_bez', 'Bundesland', 'year', 'month', 'weekday_hours', 'saturday_hours', 'weekday_hours_extra', 'saturday_hours_extra'], dtype='object')
2025-10-06 06:59:11,732 - conversion_functions.py - DEBUG - 168 - business hours file: (2664, 9) Index(['fg_sg', 'fg_bez', 'Bundesland', 'year', 'month', 'weekday_hours', 'saturday_hours', 'weekday_hours_extra', 'saturday_hours_extra'], dtype='object')
2025-10-06 06:59:11,979 - conversion_functions.py - DEBUG - 168 - business hours file: (3996, 9) Index(['fg_sg', 'fg_bez', 'Bundesland', 'year', 'month', 'weekday_hours', 'saturday_hours', 'weekday_hours_extra', 'saturday_hours_extra'], dtype='object')
2025-10-06 06:59:12,072 - conversion_functions.py - DEBUG - 168 - business hours file: (4662, 10) Index(['fg_sg', 'fg_bez', 'Bundesland', 'year', 'month', 'weekday_hours', 'saturday_hours', 'weekday_hours_extra', 'saturday_hours_extra', 'season'], dtype='object')