bong9513 commited on
Commit
f681006
ยท
1 Parent(s): 9b3b83f

checkpoint

Browse files
Files changed (44) hide show
  1. Analysis_code/5.optima/deepgbm_ctgan10000/deepgbm_ctgan10000_daegu.py +97 -0
  2. Analysis_code/5.optima/deepgbm_ctgan10000/deepgbm_ctgan10000_daejeon.py +97 -0
  3. Analysis_code/5.optima/deepgbm_ctgan10000/deepgbm_ctgan10000_gwangju.py +97 -0
  4. Analysis_code/5.optima/deepgbm_ctgan10000/deepgbm_ctgan10000_incheon.py +97 -0
  5. Analysis_code/5.optima/deepgbm_ctgan10000/deepgbm_ctgan10000_seoul.py +97 -0
  6. Analysis_code/5.optima/ft_transformer_ctgan10000/ft_transformer_ctgan10000_daegu.py +96 -0
  7. Analysis_code/5.optima/ft_transformer_ctgan10000/ft_transformer_ctgan10000_daejeon.py +96 -0
  8. Analysis_code/5.optima/ft_transformer_ctgan10000/ft_transformer_ctgan10000_gwangju.py +96 -0
  9. Analysis_code/5.optima/ft_transformer_ctgan10000/ft_transformer_ctgan10000_incheon.py +96 -0
  10. Analysis_code/5.optima/ft_transformer_ctgan10000/ft_transformer_ctgan10000_seoul.py +96 -0
  11. Analysis_code/5.optima/lgb_ctgan10000/LGB_ctgan10000_daegu.py +317 -0
  12. Analysis_code/5.optima/lgb_ctgan10000/LGB_ctgan10000_daejeon.py +317 -0
  13. Analysis_code/5.optima/lgb_ctgan10000/LGB_ctgan10000_gwangju.py +317 -0
  14. Analysis_code/5.optima/lgb_ctgan10000/LGB_ctgan10000_incheon.py +317 -0
  15. Analysis_code/5.optima/lgb_ctgan10000/LGB_ctgan10000_seoul.py +317 -0
  16. Analysis_code/5.optima/resnet_like_ctgan10000/resnet_like_ctgan10000_daegu.py +97 -0
  17. Analysis_code/5.optima/resnet_like_ctgan10000/resnet_like_ctgan10000_daejeon.py +97 -0
  18. Analysis_code/5.optima/resnet_like_ctgan10000/resnet_like_ctgan10000_gwangju.py +97 -0
  19. Analysis_code/5.optima/resnet_like_ctgan10000/resnet_like_ctgan10000_incheon.py +97 -0
  20. Analysis_code/5.optima/resnet_like_ctgan10000/resnet_like_ctgan10000_seoul.py +97 -0
  21. Analysis_code/5.optima/run_bash/deepgbm/deepgbm_ctgan10000 +0 -0
  22. Analysis_code/5.optima/run_bash/deepgbm/deepgbm_ctgan10000.log +0 -0
  23. Analysis_code/5.optima/run_bash/deepgbm/run_deepgbm_ctgan10000.sh +5 -0
  24. Analysis_code/5.optima/run_bash/ft_transformer/ft_transformer_ctgan10000 +0 -0
  25. Analysis_code/5.optima/run_bash/ft_transformer/ft_transformer_ctgan10000.log +0 -0
  26. Analysis_code/5.optima/run_bash/ft_transformer/run_ft_transformer_ctgan10000.sh +5 -0
  27. Analysis_code/5.optima/run_bash/lgb/lgb_ctgan10000.log +219 -156
  28. Analysis_code/5.optima/run_bash/lgb/run_lgb_ctgan10000.sh +1 -1
  29. Analysis_code/5.optima/run_bash/resnet_like/resnet_like_ctgan10000 +0 -0
  30. Analysis_code/5.optima/run_bash/resnet_like/resnet_like_ctgan10000.log +0 -0
  31. Analysis_code/5.optima/run_bash/resnet_like/run_resnet_like_ctgan10000.sh +5 -0
  32. Analysis_code/5.optima/run_bash/xgb/xgb_ctgan10000.log +219 -156
  33. Analysis_code/5.optima/xgb_ctgan10000/XGB_ctgan10000_daegu.py +305 -0
  34. Analysis_code/5.optima/xgb_ctgan10000/XGB_ctgan10000_daejeon.py +305 -0
  35. Analysis_code/5.optima/xgb_ctgan10000/XGB_ctgan10000_gwangju.py +305 -0
  36. Analysis_code/5.optima/xgb_ctgan10000/XGB_ctgan10000_incheon.py +305 -0
  37. Analysis_code/5.optima/xgb_ctgan10000/XGB_ctgan10000_seoul.py +305 -0
  38. Analysis_code/6.optima_models_analysis/analysis_for_.ipynb +0 -0
  39. Analysis_code/6.optima_models_analysis/best_samples_best_datasample_per_model_per_region.csv +31 -0
  40. Analysis_code/6.optima_models_analysis/extract_result.ipynb +0 -690
  41. Analysis_code/6.optima_models_analysis/extract_result_from_omptimized_models.ipynb +0 -0
  42. Analysis_code/6.optima_models_analysis/optimization_result.csv +121 -0
  43. Analysis_code/6.optima_models_analysis/utils.py +1077 -0
  44. Analysis_code/find_reason/wasserstein_distance.ipynb +46 -35
Analysis_code/5.optima/deepgbm_ctgan10000/deepgbm_ctgan10000_daegu.py ADDED
@@ -0,0 +1,97 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ import optuna
2
+ import numpy as np
3
+ import random
4
+ import pandas as pd
5
+ import joblib
6
+ import os
7
+ import torch
8
+ from utils import *
9
+ # Python ๋ฐ Numpy ์‹œ๋“œ ๊ณ ์ •
10
+ seed = 42
11
+ random.seed(seed)
12
+ np.random.seed(seed)
13
+
14
+
15
+ # 1. Study ์ƒ์„ฑ ์‹œ 'maximize'๋กœ ์„ค์ •
16
+ study = optuna.create_study(
17
+ direction="maximize", # CSI ์ ์ˆ˜๊ฐ€ ๋†’์„์ˆ˜๋ก ์ข‹์œผ๋ฏ€๋กœ maximize
18
+ pruner=optuna.pruners.MedianPruner(n_warmup_steps=10) # ์ดˆ๋ฐ˜ 10์—ํญ์€ ์ง€์ผœ๋ณด๊ณ  ์ดํ›„ ๊ฐ€์ง€์น˜๊ธฐ
19
+ )
20
+ # Trial ์™„๋ฃŒ ์‹œ ์ƒ์„ธ ์ •๋ณด ์ถœ๋ ฅํ•˜๋Š” callback ํ•จ์ˆ˜
21
+ def print_trial_callback(study, trial):
22
+ """๊ฐ trial ์™„๋ฃŒ ์‹œ best value๋ฅผ ํฌํ•จํ•œ ์ƒ์„ธ ์ •๋ณด ์ถœ๋ ฅ"""
23
+ print(f"\n{'='*80}")
24
+ print(f"Trial {trial.number} ์™„๋ฃŒ")
25
+ print(f" Value (CSI): {trial.value:.6f}" if trial.value is not None else f" Value: {trial.value}")
26
+ print(f" Parameters: {trial.params}")
27
+ print(f" Best Value (CSI): {study.best_value:.6f}" if study.best_value is not None else f" Best Value: {study.best_value}")
28
+ print(f" Best Trial: {study.best_trial.number}")
29
+ print(f" Best Parameters: {study.best_params}")
30
+ print(f"{'='*80}\n")
31
+
32
+
33
+
34
+ # 2. ์ตœ์ ํ™” ์‹คํ–‰
35
+ study.optimize(
36
+ lambda trial: objective(trial, model_choose="deepgbm", region="daegu", data_sample='ctgan10000'),
37
+ n_trials=100
38
+ ,
39
+ callbacks=[print_trial_callback]
40
+ )
41
+
42
+ # 3. ๊ฒฐ๊ณผ ํ™•์ธ ๋ฐ ์š”์•ฝ
43
+ print(f"\n์ตœ์ ํ™” ์™„๋ฃŒ.")
44
+ print(f"Best CSI Score: {study.best_value:.4f}")
45
+ print(f"Best Hyperparameters: {study.best_params}")
46
+
47
+ try:
48
+ # ๋ชจ๋“  trial์˜ CSI ์ ์ˆ˜ ์ถ”์ถœ
49
+ csi_scores = [trial.value for trial in study.trials if trial.value is not None]
50
+
51
+ if len(csi_scores) > 0:
52
+ print(f"\n์ตœ์ ํ™” ๊ณผ์ • ์š”์•ฝ:")
53
+ print(f" - ์ด ์‹œ๋„ ํšŸ์ˆ˜: {len(study.trials)}")
54
+ print(f" - ์„ฑ๊ณตํ•œ ์‹œ๋„: {len(csi_scores)}")
55
+ print(f" - ์ตœ์ดˆ CSI: {csi_scores[0]:.4f}")
56
+ print(f" - ์ตœ์ข… CSI: {csi_scores[-1]:.4f}")
57
+ print(f" - ์ตœ๊ณ  CSI: {max(csi_scores):.4f}")
58
+ print(f" - ์ตœ์ € CSI: {min(csi_scores):.4f}")
59
+ print(f" - ํ‰๊ท  CSI: {np.mean(csi_scores):.4f}")
60
+
61
+ # Study ๊ฐ์ฒด ์ €์žฅ
62
+ # ํŒŒ์ผ ์œ„์น˜ ๊ธฐ๋ฐ˜์œผ๋กœ base ๋””๋ ‰ํ† ๋ฆฌ ๊ฒฝ๋กœ ์„ค์ •
63
+ current_file_dir = os.path.dirname(os.path.abspath(__file__))
64
+ base_dir = os.path.dirname(os.path.dirname(current_file_dir)) # 5.optima ๋””๋ ‰ํ† ๋ฆฌ
65
+ os.makedirs(os.path.join(base_dir, "optimization_history"), exist_ok=True)
66
+ study_path = os.path.join(base_dir, "optimization_history/deepgbm_ctgan10000_daegu_trials.pkl")
67
+ joblib.dump(study, study_path)
68
+ print(f"\n์ตœ์ ํ™” Study ๊ฐ์ฒด๊ฐ€ {study_path}์— ์ €์žฅ๋˜์—ˆ์Šต๋‹ˆ๋‹ค.")
69
+
70
+ # ์ตœ์ ํ™”๋œ ํ•˜์ดํผํŒŒ๋ผ๋ฏธํ„ฐ๋กœ ์ตœ์ข… ๋ชจ๋ธ ํ•™์Šต ๋ฐ ์ €์žฅ
71
+ print("\n" + "="*50)
72
+ print("์ตœ์ ํ™”๋œ ํ•˜์ดํผํŒŒ๋ผ๋ฏธํ„ฐ๋กœ ์ตœ์ข… ๋ชจ๋ธ ํ•™์Šต ์‹œ์ž‘")
73
+ print("="*50)
74
+
75
+ best_params = study.best_params
76
+ model_path = train_final_model(
77
+ best_params=best_params,
78
+ model_choose="deepgbm",
79
+ region="daegu",
80
+ data_sample='ctgan10000',
81
+ target='multi',
82
+ n_folds=3,
83
+ random_state=seed
84
+ )
85
+
86
+ print(f"\n์ตœ์ข… ๋ชจ๋ธ ํ•™์Šต ๋ฐ ์ €์žฅ ์™„๋ฃŒ!")
87
+ print(f"์ €์žฅ๋œ ๋ชจ๋ธ ๊ฒฝ๋กœ: {model_path}")
88
+
89
+ except Exception as e:
90
+ print(f"\nโš ๏ธ ์ตœ์ ํ™” ๊ฒฐ๊ณผ ๋ถ„์„ ์ค‘ ์˜ค๋ฅ˜ ๋ฐœ์ƒ: {e}")
91
+ import traceback
92
+ traceback.print_exc()
93
+
94
+ # ์ •์ƒ ์ข…๋ฃŒ
95
+ import sys
96
+ sys.exit(0)
97
+
Analysis_code/5.optima/deepgbm_ctgan10000/deepgbm_ctgan10000_daejeon.py ADDED
@@ -0,0 +1,97 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ import optuna
2
+ import numpy as np
3
+ import random
4
+ import pandas as pd
5
+ import joblib
6
+ import os
7
+ import torch
8
+ from utils import *
9
+ # Python ๋ฐ Numpy ์‹œ๋“œ ๊ณ ์ •
10
+ seed = 42
11
+ random.seed(seed)
12
+ np.random.seed(seed)
13
+
14
+
15
+ # 1. Study ์ƒ์„ฑ ์‹œ 'maximize'๋กœ ์„ค์ •
16
+ study = optuna.create_study(
17
+ direction="maximize", # CSI ์ ์ˆ˜๊ฐ€ ๋†’์„์ˆ˜๋ก ์ข‹์œผ๋ฏ€๋กœ maximize
18
+ pruner=optuna.pruners.MedianPruner(n_warmup_steps=10) # ์ดˆ๋ฐ˜ 10์—ํญ์€ ์ง€์ผœ๋ณด๊ณ  ์ดํ›„ ๊ฐ€์ง€์น˜๊ธฐ
19
+ )
20
+ # Trial ์™„๋ฃŒ ์‹œ ์ƒ์„ธ ์ •๋ณด ์ถœ๋ ฅํ•˜๋Š” callback ํ•จ์ˆ˜
21
+ def print_trial_callback(study, trial):
22
+ """๊ฐ trial ์™„๋ฃŒ ์‹œ best value๋ฅผ ํฌํ•จํ•œ ์ƒ์„ธ ์ •๋ณด ์ถœ๋ ฅ"""
23
+ print(f"\n{'='*80}")
24
+ print(f"Trial {trial.number} ์™„๋ฃŒ")
25
+ print(f" Value (CSI): {trial.value:.6f}" if trial.value is not None else f" Value: {trial.value}")
26
+ print(f" Parameters: {trial.params}")
27
+ print(f" Best Value (CSI): {study.best_value:.6f}" if study.best_value is not None else f" Best Value: {study.best_value}")
28
+ print(f" Best Trial: {study.best_trial.number}")
29
+ print(f" Best Parameters: {study.best_params}")
30
+ print(f"{'='*80}\n")
31
+
32
+
33
+
34
+ # 2. ์ตœ์ ํ™” ์‹คํ–‰
35
+ study.optimize(
36
+ lambda trial: objective(trial, model_choose="deepgbm", region="daejeon", data_sample='ctgan10000'),
37
+ n_trials=100
38
+ ,
39
+ callbacks=[print_trial_callback]
40
+ )
41
+
42
+ # 3. ๊ฒฐ๊ณผ ํ™•์ธ ๋ฐ ์š”์•ฝ
43
+ print(f"\n์ตœ์ ํ™” ์™„๋ฃŒ.")
44
+ print(f"Best CSI Score: {study.best_value:.4f}")
45
+ print(f"Best Hyperparameters: {study.best_params}")
46
+
47
+ try:
48
+ # ๋ชจ๋“  trial์˜ CSI ์ ์ˆ˜ ์ถ”์ถœ
49
+ csi_scores = [trial.value for trial in study.trials if trial.value is not None]
50
+
51
+ if len(csi_scores) > 0:
52
+ print(f"\n์ตœ์ ํ™” ๊ณผ์ • ์š”์•ฝ:")
53
+ print(f" - ์ด ์‹œ๋„ ํšŸ์ˆ˜: {len(study.trials)}")
54
+ print(f" - ์„ฑ๊ณตํ•œ ์‹œ๋„: {len(csi_scores)}")
55
+ print(f" - ์ตœ์ดˆ CSI: {csi_scores[0]:.4f}")
56
+ print(f" - ์ตœ์ข… CSI: {csi_scores[-1]:.4f}")
57
+ print(f" - ์ตœ๊ณ  CSI: {max(csi_scores):.4f}")
58
+ print(f" - ์ตœ์ € CSI: {min(csi_scores):.4f}")
59
+ print(f" - ํ‰๊ท  CSI: {np.mean(csi_scores):.4f}")
60
+
61
+ # Study ๊ฐ์ฒด ์ €์žฅ
62
+ # ํŒŒ์ผ ์œ„์น˜ ๊ธฐ๋ฐ˜์œผ๋กœ base ๋””๋ ‰ํ† ๋ฆฌ ๊ฒฝ๋กœ ์„ค์ •
63
+ current_file_dir = os.path.dirname(os.path.abspath(__file__))
64
+ base_dir = os.path.dirname(os.path.dirname(current_file_dir)) # 5.optima ๋””๋ ‰ํ† ๋ฆฌ
65
+ os.makedirs(os.path.join(base_dir, "optimization_history"), exist_ok=True)
66
+ study_path = os.path.join(base_dir, "optimization_history/deepgbm_ctgan10000_daejeon_trials.pkl")
67
+ joblib.dump(study, study_path)
68
+ print(f"\n์ตœ์ ํ™” Study ๊ฐ์ฒด๊ฐ€ {study_path}์— ์ €์žฅ๋˜์—ˆ์Šต๋‹ˆ๋‹ค.")
69
+
70
+ # ์ตœ์ ํ™”๋œ ํ•˜์ดํผํŒŒ๋ผ๋ฏธํ„ฐ๋กœ ์ตœ์ข… ๋ชจ๋ธ ํ•™์Šต ๋ฐ ์ €์žฅ
71
+ print("\n" + "="*50)
72
+ print("์ตœ์ ํ™”๋œ ํ•˜์ดํผํŒŒ๋ผ๋ฏธํ„ฐ๋กœ ์ตœ์ข… ๋ชจ๋ธ ํ•™์Šต ์‹œ์ž‘")
73
+ print("="*50)
74
+
75
+ best_params = study.best_params
76
+ model_path = train_final_model(
77
+ best_params=best_params,
78
+ model_choose="deepgbm",
79
+ region="daejeon",
80
+ data_sample='ctgan10000',
81
+ target='multi',
82
+ n_folds=3,
83
+ random_state=seed
84
+ )
85
+
86
+ print(f"\n์ตœ์ข… ๋ชจ๋ธ ํ•™์Šต ๋ฐ ์ €์žฅ ์™„๋ฃŒ!")
87
+ print(f"์ €์žฅ๋œ ๋ชจ๋ธ ๊ฒฝ๋กœ: {model_path}")
88
+
89
+ except Exception as e:
90
+ print(f"\nโš ๏ธ ์ตœ์ ํ™” ๊ฒฐ๊ณผ ๋ถ„์„ ์ค‘ ์˜ค๋ฅ˜ ๋ฐœ์ƒ: {e}")
91
+ import traceback
92
+ traceback.print_exc()
93
+
94
+ # ์ •์ƒ ์ข…๋ฃŒ
95
+ import sys
96
+ sys.exit(0)
97
+
Analysis_code/5.optima/deepgbm_ctgan10000/deepgbm_ctgan10000_gwangju.py ADDED
@@ -0,0 +1,97 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ import optuna
2
+ import numpy as np
3
+ import random
4
+ import pandas as pd
5
+ import joblib
6
+ import os
7
+ import torch
8
+ from utils import *
9
+ # Python ๋ฐ Numpy ์‹œ๋“œ ๊ณ ์ •
10
+ seed = 42
11
+ random.seed(seed)
12
+ np.random.seed(seed)
13
+
14
+
15
+ # 1. Study ์ƒ์„ฑ ์‹œ 'maximize'๋กœ ์„ค์ •
16
+ study = optuna.create_study(
17
+ direction="maximize", # CSI ์ ์ˆ˜๊ฐ€ ๋†’์„์ˆ˜๋ก ์ข‹์œผ๋ฏ€๋กœ maximize
18
+ pruner=optuna.pruners.MedianPruner(n_warmup_steps=10) # ์ดˆ๋ฐ˜ 10์—ํญ์€ ์ง€์ผœ๋ณด๊ณ  ์ดํ›„ ๊ฐ€์ง€์น˜๊ธฐ
19
+ )
20
+ # Trial ์™„๋ฃŒ ์‹œ ์ƒ์„ธ ์ •๋ณด ์ถœ๋ ฅํ•˜๋Š” callback ํ•จ์ˆ˜
21
+ def print_trial_callback(study, trial):
22
+ """๊ฐ trial ์™„๋ฃŒ ์‹œ best value๋ฅผ ํฌํ•จํ•œ ์ƒ์„ธ ์ •๋ณด ์ถœ๋ ฅ"""
23
+ print(f"\n{'='*80}")
24
+ print(f"Trial {trial.number} ์™„๋ฃŒ")
25
+ print(f" Value (CSI): {trial.value:.6f}" if trial.value is not None else f" Value: {trial.value}")
26
+ print(f" Parameters: {trial.params}")
27
+ print(f" Best Value (CSI): {study.best_value:.6f}" if study.best_value is not None else f" Best Value: {study.best_value}")
28
+ print(f" Best Trial: {study.best_trial.number}")
29
+ print(f" Best Parameters: {study.best_params}")
30
+ print(f"{'='*80}\n")
31
+
32
+
33
+
34
+ # 2. ์ตœ์ ํ™” ์‹คํ–‰
35
+ study.optimize(
36
+ lambda trial: objective(trial, model_choose="deepgbm", region="gwangju", data_sample='ctgan10000'),
37
+ n_trials=100
38
+ ,
39
+ callbacks=[print_trial_callback]
40
+ )
41
+
42
+ # 3. ๊ฒฐ๊ณผ ํ™•์ธ ๋ฐ ์š”์•ฝ
43
+ print(f"\n์ตœ์ ํ™” ์™„๋ฃŒ.")
44
+ print(f"Best CSI Score: {study.best_value:.4f}")
45
+ print(f"Best Hyperparameters: {study.best_params}")
46
+
47
+ try:
48
+ # ๋ชจ๋“  trial์˜ CSI ์ ์ˆ˜ ์ถ”์ถœ
49
+ csi_scores = [trial.value for trial in study.trials if trial.value is not None]
50
+
51
+ if len(csi_scores) > 0:
52
+ print(f"\n์ตœ์ ํ™” ๊ณผ์ • ์š”์•ฝ:")
53
+ print(f" - ์ด ์‹œ๋„ ํšŸ์ˆ˜: {len(study.trials)}")
54
+ print(f" - ์„ฑ๊ณตํ•œ ์‹œ๋„: {len(csi_scores)}")
55
+ print(f" - ์ตœ์ดˆ CSI: {csi_scores[0]:.4f}")
56
+ print(f" - ์ตœ์ข… CSI: {csi_scores[-1]:.4f}")
57
+ print(f" - ์ตœ๊ณ  CSI: {max(csi_scores):.4f}")
58
+ print(f" - ์ตœ์ € CSI: {min(csi_scores):.4f}")
59
+ print(f" - ํ‰๊ท  CSI: {np.mean(csi_scores):.4f}")
60
+
61
+ # Study ๊ฐ์ฒด ์ €์žฅ
62
+ # ํŒŒ์ผ ์œ„์น˜ ๊ธฐ๋ฐ˜์œผ๋กœ base ๋””๋ ‰ํ† ๋ฆฌ ๊ฒฝ๋กœ ์„ค์ •
63
+ current_file_dir = os.path.dirname(os.path.abspath(__file__))
64
+ base_dir = os.path.dirname(os.path.dirname(current_file_dir)) # 5.optima ๋””๋ ‰ํ† ๋ฆฌ
65
+ os.makedirs(os.path.join(base_dir, "optimization_history"), exist_ok=True)
66
+ study_path = os.path.join(base_dir, "optimization_history/deepgbm_ctgan10000_gwangju_trials.pkl")
67
+ joblib.dump(study, study_path)
68
+ print(f"\n์ตœ์ ํ™” Study ๊ฐ์ฒด๊ฐ€ {study_path}์— ์ €์žฅ๋˜์—ˆ์Šต๋‹ˆ๋‹ค.")
69
+
70
+ # ์ตœ์ ํ™”๋œ ํ•˜์ดํผํŒŒ๋ผ๋ฏธํ„ฐ๋กœ ์ตœ์ข… ๋ชจ๋ธ ํ•™์Šต ๋ฐ ์ €์žฅ
71
+ print("\n" + "="*50)
72
+ print("์ตœ์ ํ™”๋œ ํ•˜์ดํผํŒŒ๋ผ๋ฏธํ„ฐ๋กœ ์ตœ์ข… ๋ชจ๋ธ ํ•™์Šต ์‹œ์ž‘")
73
+ print("="*50)
74
+
75
+ best_params = study.best_params
76
+ model_path = train_final_model(
77
+ best_params=best_params,
78
+ model_choose="deepgbm",
79
+ region="gwangju",
80
+ data_sample='ctgan10000',
81
+ target='multi',
82
+ n_folds=3,
83
+ random_state=seed
84
+ )
85
+
86
+ print(f"\n์ตœ์ข… ๋ชจ๋ธ ํ•™์Šต ๋ฐ ์ €์žฅ ์™„๋ฃŒ!")
87
+ print(f"์ €์žฅ๋œ ๋ชจ๋ธ ๊ฒฝ๋กœ: {model_path}")
88
+
89
+ except Exception as e:
90
+ print(f"\nโš ๏ธ ์ตœ์ ํ™” ๊ฒฐ๊ณผ ๋ถ„์„ ์ค‘ ์˜ค๋ฅ˜ ๋ฐœ์ƒ: {e}")
91
+ import traceback
92
+ traceback.print_exc()
93
+
94
+ # ์ •์ƒ ์ข…๋ฃŒ
95
+ import sys
96
+ sys.exit(0)
97
+
Analysis_code/5.optima/deepgbm_ctgan10000/deepgbm_ctgan10000_incheon.py ADDED
@@ -0,0 +1,97 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ import optuna
2
+ import numpy as np
3
+ import random
4
+ import pandas as pd
5
+ import joblib
6
+ import os
7
+ import torch
8
+ from utils import *
9
+ # Python ๋ฐ Numpy ์‹œ๋“œ ๊ณ ์ •
10
+ seed = 42
11
+ random.seed(seed)
12
+ np.random.seed(seed)
13
+
14
+
15
+ # 1. Study ์ƒ์„ฑ ์‹œ 'maximize'๋กœ ์„ค์ •
16
+ study = optuna.create_study(
17
+ direction="maximize", # CSI ์ ์ˆ˜๊ฐ€ ๋†’์„์ˆ˜๋ก ์ข‹์œผ๋ฏ€๋กœ maximize
18
+ pruner=optuna.pruners.MedianPruner(n_warmup_steps=10) # ์ดˆ๋ฐ˜ 10์—ํญ์€ ์ง€์ผœ๋ณด๊ณ  ์ดํ›„ ๊ฐ€์ง€์น˜๊ธฐ
19
+ )
20
+ # Trial ์™„๋ฃŒ ์‹œ ์ƒ์„ธ ์ •๋ณด ์ถœ๋ ฅํ•˜๋Š” callback ํ•จ์ˆ˜
21
+ def print_trial_callback(study, trial):
22
+ """๊ฐ trial ์™„๋ฃŒ ์‹œ best value๋ฅผ ํฌํ•จํ•œ ์ƒ์„ธ ์ •๋ณด ์ถœ๋ ฅ"""
23
+ print(f"\n{'='*80}")
24
+ print(f"Trial {trial.number} ์™„๋ฃŒ")
25
+ print(f" Value (CSI): {trial.value:.6f}" if trial.value is not None else f" Value: {trial.value}")
26
+ print(f" Parameters: {trial.params}")
27
+ print(f" Best Value (CSI): {study.best_value:.6f}" if study.best_value is not None else f" Best Value: {study.best_value}")
28
+ print(f" Best Trial: {study.best_trial.number}")
29
+ print(f" Best Parameters: {study.best_params}")
30
+ print(f"{'='*80}\n")
31
+
32
+
33
+
34
+ # 2. ์ตœ์ ํ™” ์‹คํ–‰
35
+ study.optimize(
36
+ lambda trial: objective(trial, model_choose="deepgbm", region="incheon", data_sample='ctgan10000'),
37
+ n_trials=100
38
+ ,
39
+ callbacks=[print_trial_callback]
40
+ )
41
+
42
+ # 3. ๊ฒฐ๊ณผ ํ™•์ธ ๋ฐ ์š”์•ฝ
43
+ print(f"\n์ตœ์ ํ™” ์™„๋ฃŒ.")
44
+ print(f"Best CSI Score: {study.best_value:.4f}")
45
+ print(f"Best Hyperparameters: {study.best_params}")
46
+
47
+ try:
48
+ # ๋ชจ๋“  trial์˜ CSI ์ ์ˆ˜ ์ถ”์ถœ
49
+ csi_scores = [trial.value for trial in study.trials if trial.value is not None]
50
+
51
+ if len(csi_scores) > 0:
52
+ print(f"\n์ตœ์ ํ™” ๊ณผ์ • ์š”์•ฝ:")
53
+ print(f" - ์ด ์‹œ๋„ ํšŸ์ˆ˜: {len(study.trials)}")
54
+ print(f" - ์„ฑ๊ณตํ•œ ์‹œ๋„: {len(csi_scores)}")
55
+ print(f" - ์ตœ์ดˆ CSI: {csi_scores[0]:.4f}")
56
+ print(f" - ์ตœ์ข… CSI: {csi_scores[-1]:.4f}")
57
+ print(f" - ์ตœ๊ณ  CSI: {max(csi_scores):.4f}")
58
+ print(f" - ์ตœ์ € CSI: {min(csi_scores):.4f}")
59
+ print(f" - ํ‰๊ท  CSI: {np.mean(csi_scores):.4f}")
60
+
61
+ # Study ๊ฐ์ฒด ์ €์žฅ
62
+ # ํŒŒ์ผ ์œ„์น˜ ๊ธฐ๋ฐ˜์œผ๋กœ base ๋””๋ ‰ํ† ๋ฆฌ ๊ฒฝ๋กœ ์„ค์ •
63
+ current_file_dir = os.path.dirname(os.path.abspath(__file__))
64
+ base_dir = os.path.dirname(os.path.dirname(current_file_dir)) # 5.optima ๋””๋ ‰ํ† ๋ฆฌ
65
+ os.makedirs(os.path.join(base_dir, "optimization_history"), exist_ok=True)
66
+ study_path = os.path.join(base_dir, "optimization_history/deepgbm_ctgan10000_incheon_trials.pkl")
67
+ joblib.dump(study, study_path)
68
+ print(f"\n์ตœ์ ํ™” Study ๊ฐ์ฒด๊ฐ€ {study_path}์— ์ €์žฅ๋˜์—ˆ์Šต๋‹ˆ๋‹ค.")
69
+
70
+ # ์ตœ์ ํ™”๋œ ํ•˜์ดํผํŒŒ๋ผ๋ฏธํ„ฐ๋กœ ์ตœ์ข… ๋ชจ๋ธ ํ•™์Šต ๋ฐ ์ €์žฅ
71
+ print("\n" + "="*50)
72
+ print("์ตœ์ ํ™”๋œ ํ•˜์ดํผํŒŒ๋ผ๋ฏธํ„ฐ๋กœ ์ตœ์ข… ๋ชจ๋ธ ํ•™์Šต ์‹œ์ž‘")
73
+ print("="*50)
74
+
75
+ best_params = study.best_params
76
+ model_path = train_final_model(
77
+ best_params=best_params,
78
+ model_choose="deepgbm",
79
+ region="incheon",
80
+ data_sample='ctgan10000',
81
+ target='multi',
82
+ n_folds=3,
83
+ random_state=seed
84
+ )
85
+
86
+ print(f"\n์ตœ์ข… ๋ชจ๋ธ ํ•™์Šต ๋ฐ ์ €์žฅ ์™„๋ฃŒ!")
87
+ print(f"์ €์žฅ๋œ ๋ชจ๋ธ ๊ฒฝ๋กœ: {model_path}")
88
+
89
+ except Exception as e:
90
+ print(f"\nโš ๏ธ ์ตœ์ ํ™” ๊ฒฐ๊ณผ ๋ถ„์„ ์ค‘ ์˜ค๋ฅ˜ ๋ฐœ์ƒ: {e}")
91
+ import traceback
92
+ traceback.print_exc()
93
+
94
+ # ์ •์ƒ ์ข…๋ฃŒ
95
+ import sys
96
+ sys.exit(0)
97
+
Analysis_code/5.optima/deepgbm_ctgan10000/deepgbm_ctgan10000_seoul.py ADDED
@@ -0,0 +1,97 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ import optuna
2
+ import numpy as np
3
+ import random
4
+ import pandas as pd
5
+ import joblib
6
+ import os
7
+ import torch
8
+ from utils import *
9
+ # Python ๋ฐ Numpy ์‹œ๋“œ ๊ณ ์ •
10
+ seed = 42
11
+ random.seed(seed)
12
+ np.random.seed(seed)
13
+
14
+
15
+ # 1. Study ์ƒ์„ฑ ์‹œ 'maximize'๋กœ ์„ค์ •
16
+ study = optuna.create_study(
17
+ direction="maximize", # CSI ์ ์ˆ˜๊ฐ€ ๋†’์„์ˆ˜๋ก ์ข‹์œผ๋ฏ€๋กœ maximize
18
+ pruner=optuna.pruners.MedianPruner(n_warmup_steps=10) # ์ดˆ๋ฐ˜ 10์—ํญ์€ ์ง€์ผœ๋ณด๊ณ  ์ดํ›„ ๊ฐ€์ง€์น˜๊ธฐ
19
+ )
20
+ # Trial ์™„๋ฃŒ ์‹œ ์ƒ์„ธ ์ •๋ณด ์ถœ๋ ฅํ•˜๋Š” callback ํ•จ์ˆ˜
21
+ def print_trial_callback(study, trial):
22
+ """๊ฐ trial ์™„๋ฃŒ ์‹œ best value๋ฅผ ํฌํ•จํ•œ ์ƒ์„ธ ์ •๋ณด ์ถœ๋ ฅ"""
23
+ print(f"\n{'='*80}")
24
+ print(f"Trial {trial.number} ์™„๋ฃŒ")
25
+ print(f" Value (CSI): {trial.value:.6f}" if trial.value is not None else f" Value: {trial.value}")
26
+ print(f" Parameters: {trial.params}")
27
+ print(f" Best Value (CSI): {study.best_value:.6f}" if study.best_value is not None else f" Best Value: {study.best_value}")
28
+ print(f" Best Trial: {study.best_trial.number}")
29
+ print(f" Best Parameters: {study.best_params}")
30
+ print(f"{'='*80}\n")
31
+
32
+
33
+
34
+ # 2. ์ตœ์ ํ™” ์‹คํ–‰
35
+ study.optimize(
36
+ lambda trial: objective(trial, model_choose="deepgbm", region="seoul", data_sample='ctgan10000'),
37
+ n_trials=100
38
+ ,
39
+ callbacks=[print_trial_callback]
40
+ )
41
+
42
+ # 3. ๊ฒฐ๊ณผ ํ™•์ธ ๋ฐ ์š”์•ฝ
43
+ print(f"\n์ตœ์ ํ™” ์™„๋ฃŒ.")
44
+ print(f"Best CSI Score: {study.best_value:.4f}")
45
+ print(f"Best Hyperparameters: {study.best_params}")
46
+
47
+ try:
48
+ # ๋ชจ๋“  trial์˜ CSI ์ ์ˆ˜ ์ถ”์ถœ
49
+ csi_scores = [trial.value for trial in study.trials if trial.value is not None]
50
+
51
+ if len(csi_scores) > 0:
52
+ print(f"\n์ตœ์ ํ™” ๊ณผ์ • ์š”์•ฝ:")
53
+ print(f" - ์ด ์‹œ๋„ ํšŸ์ˆ˜: {len(study.trials)}")
54
+ print(f" - ์„ฑ๊ณตํ•œ ์‹œ๋„: {len(csi_scores)}")
55
+ print(f" - ์ตœ์ดˆ CSI: {csi_scores[0]:.4f}")
56
+ print(f" - ์ตœ์ข… CSI: {csi_scores[-1]:.4f}")
57
+ print(f" - ์ตœ๊ณ  CSI: {max(csi_scores):.4f}")
58
+ print(f" - ์ตœ์ € CSI: {min(csi_scores):.4f}")
59
+ print(f" - ํ‰๊ท  CSI: {np.mean(csi_scores):.4f}")
60
+
61
+ # Study ๊ฐ์ฒด ์ €์žฅ
62
+ # ํŒŒ์ผ ์œ„์น˜ ๊ธฐ๋ฐ˜์œผ๋กœ base ๋””๋ ‰ํ† ๋ฆฌ ๊ฒฝ๋กœ ์„ค์ •
63
+ current_file_dir = os.path.dirname(os.path.abspath(__file__))
64
+ base_dir = os.path.dirname(os.path.dirname(current_file_dir)) # 5.optima ๋””๋ ‰ํ† ๋ฆฌ
65
+ os.makedirs(os.path.join(base_dir, "optimization_history"), exist_ok=True)
66
+ study_path = os.path.join(base_dir, "optimization_history/deepgbm_ctgan10000_seoul_trials.pkl")
67
+ joblib.dump(study, study_path)
68
+ print(f"\n์ตœ์ ํ™” Study ๊ฐ์ฒด๊ฐ€ {study_path}์— ์ €์žฅ๋˜์—ˆ์Šต๋‹ˆ๋‹ค.")
69
+
70
+ # ์ตœ์ ํ™”๋œ ํ•˜์ดํผํŒŒ๋ผ๋ฏธํ„ฐ๋กœ ์ตœ์ข… ๋ชจ๋ธ ํ•™์Šต ๋ฐ ์ €์žฅ
71
+ print("\n" + "="*50)
72
+ print("์ตœ์ ํ™”๋œ ํ•˜์ดํผํŒŒ๋ผ๋ฏธํ„ฐ๋กœ ์ตœ์ข… ๋ชจ๋ธ ํ•™์Šต ์‹œ์ž‘")
73
+ print("="*50)
74
+
75
+ best_params = study.best_params
76
+ model_path = train_final_model(
77
+ best_params=best_params,
78
+ model_choose="deepgbm",
79
+ region="seoul",
80
+ data_sample='ctgan10000',
81
+ target='multi',
82
+ n_folds=3,
83
+ random_state=seed
84
+ )
85
+
86
+ print(f"\n์ตœ์ข… ๋ชจ๋ธ ํ•™์Šต ๋ฐ ์ €์žฅ ์™„๋ฃŒ!")
87
+ print(f"์ €์žฅ๋œ ๋ชจ๋ธ ๊ฒฝ๋กœ: {model_path}")
88
+
89
+ except Exception as e:
90
+ print(f"\nโš ๏ธ ์ตœ์ ํ™” ๊ฒฐ๊ณผ ๋ถ„์„ ์ค‘ ์˜ค๋ฅ˜ ๋ฐœ์ƒ: {e}")
91
+ import traceback
92
+ traceback.print_exc()
93
+
94
+ # ์ •์ƒ ์ข…๋ฃŒ
95
+ import sys
96
+ sys.exit(0)
97
+
Analysis_code/5.optima/ft_transformer_ctgan10000/ft_transformer_ctgan10000_daegu.py ADDED
@@ -0,0 +1,96 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ import optuna
2
+ import numpy as np
3
+ import random
4
+ import pandas as pd
5
+ import joblib
6
+ import os
7
+ import torch
8
+ from utils import *
9
+ # Python ๋ฐ Numpy ์‹œ๋“œ ๊ณ ์ •
10
+ seed = 42
11
+ random.seed(seed)
12
+ np.random.seed(seed)
13
+
14
+
15
+ # Trial ์™„๋ฃŒ ์‹œ ์ƒ์„ธ ์ •๋ณด ์ถœ๋ ฅํ•˜๋Š” callback ํ•จ์ˆ˜
16
+ def print_trial_callback(study, trial):
17
+ """๊ฐ trial ์™„๋ฃŒ ์‹œ best value๋ฅผ ํฌํ•จํ•œ ์ƒ์„ธ ์ •๋ณด ์ถœ๋ ฅ"""
18
+ print(f"\n{'='*80}")
19
+ print(f"Trial {trial.number} ์™„๋ฃŒ")
20
+ print(f" Value (CSI): {trial.value:.6f}" if trial.value is not None else f" Value: {trial.value}")
21
+ print(f" Parameters: {trial.params}")
22
+ print(f" Best Value (CSI): {study.best_value:.6f}" if study.best_value is not None else f" Best Value: {study.best_value}")
23
+ print(f" Best Trial: {study.best_trial.number}")
24
+ print(f" Best Parameters: {study.best_params}")
25
+ print(f"{'='*80}\n")
26
+
27
+
28
+ # 1. Study ์ƒ์„ฑ ์‹œ 'maximize'๋กœ ์„ค์ •
29
+ study = optuna.create_study(
30
+ direction="maximize", # CSI ์ ์ˆ˜๊ฐ€ ๋†’์„์ˆ˜๋ก ์ข‹์œผ๋ฏ€๋กœ maximize
31
+ pruner=optuna.pruners.MedianPruner(n_warmup_steps=10) # ์ดˆ๋ฐ˜ 10์—ํญ์€ ์ง€์ผœ๋ณด๊ณ  ์ดํ›„ ๊ฐ€์ง€์น˜๊ธฐ
32
+ )
33
+
34
+ # 2. ์ตœ์ ํ™” ์‹คํ–‰
35
+ study.optimize(
36
+ lambda trial: objective(trial, model_choose="ft_transformer", region="daegu", data_sample='ctgan10000'),
37
+ n_trials=100,
38
+ callbacks=[print_trial_callback]
39
+ )
40
+
41
+ # 3. ๊ฒฐ๊ณผ ํ™•์ธ ๋ฐ ์š”์•ฝ
42
+ print(f"\n์ตœ์ ํ™” ์™„๋ฃŒ.")
43
+ print(f"Best CSI Score: {study.best_value:.4f}")
44
+ print(f"Best Hyperparameters: {study.best_params}")
45
+
46
+ try:
47
+ # ๋ชจ๋“  trial์˜ CSI ์ ์ˆ˜ ์ถ”์ถœ
48
+ csi_scores = [trial.value for trial in study.trials if trial.value is not None]
49
+
50
+ if len(csi_scores) > 0:
51
+ print(f"\n์ตœ์ ํ™” ๊ณผ์ • ์š”์•ฝ:")
52
+ print(f" - ์ด ์‹œ๋„ ํšŸ์ˆ˜: {len(study.trials)}")
53
+ print(f" - ์„ฑ๊ณตํ•œ ์‹œ๋„: {len(csi_scores)}")
54
+ print(f" - ์ตœ์ดˆ CSI: {csi_scores[0]:.4f}")
55
+ print(f" - ์ตœ์ข… CSI: {csi_scores[-1]:.4f}")
56
+ print(f" - ์ตœ๊ณ  CSI: {max(csi_scores):.4f}")
57
+ print(f" - ์ตœ์ € CSI: {min(csi_scores):.4f}")
58
+ print(f" - ํ‰๊ท  CSI: {np.mean(csi_scores):.4f}")
59
+
60
+ # Study ๊ฐ์ฒด ์ €์žฅ
61
+ # ํŒŒ์ผ ์œ„์น˜ ๊ธฐ๋ฐ˜์œผ๋กœ base ๋””๋ ‰ํ† ๋ฆฌ ๊ฒฝ๋กœ ์„ค์ •
62
+ current_file_dir = os.path.dirname(os.path.abspath(__file__))
63
+ base_dir = os.path.dirname(os.path.dirname(current_file_dir)) # 5.optima ๋””๋ ‰ํ† ๋ฆฌ
64
+ os.makedirs(os.path.join(base_dir, "optimization_history"), exist_ok=True)
65
+ study_path = os.path.join(base_dir, "optimization_history/ft_transformer_ctgan10000_daegu_trials.pkl")
66
+ joblib.dump(study, study_path)
67
+ print(f"\n์ตœ์ ํ™” Study ๊ฐ์ฒด๊ฐ€ {study_path}์— ์ €์žฅ๋˜์—ˆ์Šต๋‹ˆ๋‹ค.")
68
+
69
+ # ์ตœ์ ํ™”๋œ ํ•˜์ดํผํŒŒ๋ผ๋ฏธํ„ฐ๋กœ ์ตœ์ข… ๋ชจ๋ธ ํ•™์Šต ๋ฐ ์ €์žฅ
70
+ print("\n" + "="*50)
71
+ print("์ตœ์ ํ™”๋œ ํ•˜์ดํผํŒŒ๋ผ๋ฏธํ„ฐ๋กœ ์ตœ์ข… ๋ชจ๋ธ ํ•™์Šต ์‹œ์ž‘")
72
+ print("="*50)
73
+
74
+ best_params = study.best_params
75
+ model_path = train_final_model(
76
+ best_params=best_params,
77
+ model_choose="ft_transformer",
78
+ region="daegu",
79
+ data_sample='ctgan10000',
80
+ target='multi',
81
+ n_folds=3,
82
+ random_state=seed
83
+ )
84
+
85
+ print(f"\n์ตœ์ข… ๋ชจ๋ธ ํ•™์Šต ๋ฐ ์ €์žฅ ์™„๋ฃŒ!")
86
+ print(f"์ €์žฅ๋œ ๋ชจ๋ธ ๊ฒฝ๋กœ: {model_path}")
87
+
88
+ except Exception as e:
89
+ print(f"\nโš ๏ธ ์ตœ์ ํ™” ๊ฒฐ๊ณผ ๋ถ„์„ ์ค‘ ์˜ค๋ฅ˜ ๋ฐœ์ƒ: {e}")
90
+ import traceback
91
+ traceback.print_exc()
92
+
93
+ # ์ •์ƒ ์ข…๋ฃŒ
94
+ import sys
95
+ sys.exit(0)
96
+
Analysis_code/5.optima/ft_transformer_ctgan10000/ft_transformer_ctgan10000_daejeon.py ADDED
@@ -0,0 +1,96 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ import optuna
2
+ import numpy as np
3
+ import random
4
+ import pandas as pd
5
+ import joblib
6
+ import os
7
+ import torch
8
+ from utils import *
9
+ # Python ๋ฐ Numpy ์‹œ๋“œ ๊ณ ์ •
10
+ seed = 42
11
+ random.seed(seed)
12
+ np.random.seed(seed)
13
+
14
+
15
+ # Trial ์™„๋ฃŒ ์‹œ ์ƒ์„ธ ์ •๋ณด ์ถœ๋ ฅํ•˜๋Š” callback ํ•จ์ˆ˜
16
+ def print_trial_callback(study, trial):
17
+ """๊ฐ trial ์™„๋ฃŒ ์‹œ best value๋ฅผ ํฌํ•จํ•œ ์ƒ์„ธ ์ •๋ณด ์ถœ๋ ฅ"""
18
+ print(f"\n{'='*80}")
19
+ print(f"Trial {trial.number} ์™„๋ฃŒ")
20
+ print(f" Value (CSI): {trial.value:.6f}" if trial.value is not None else f" Value: {trial.value}")
21
+ print(f" Parameters: {trial.params}")
22
+ print(f" Best Value (CSI): {study.best_value:.6f}" if study.best_value is not None else f" Best Value: {study.best_value}")
23
+ print(f" Best Trial: {study.best_trial.number}")
24
+ print(f" Best Parameters: {study.best_params}")
25
+ print(f"{'='*80}\n")
26
+
27
+
28
+ # 1. Study ์ƒ์„ฑ ์‹œ 'maximize'๋กœ ์„ค์ •
29
+ study = optuna.create_study(
30
+ direction="maximize", # CSI ์ ์ˆ˜๊ฐ€ ๋†’์„์ˆ˜๋ก ์ข‹์œผ๋ฏ€๋กœ maximize
31
+ pruner=optuna.pruners.MedianPruner(n_warmup_steps=10) # ์ดˆ๋ฐ˜ 10์—ํญ์€ ์ง€์ผœ๋ณด๊ณ  ์ดํ›„ ๊ฐ€์ง€์น˜๊ธฐ
32
+ )
33
+
34
+ # 2. ์ตœ์ ํ™” ์‹คํ–‰
35
+ study.optimize(
36
+ lambda trial: objective(trial, model_choose="ft_transformer", region="daejeon", data_sample='ctgan10000'),
37
+ n_trials=100,
38
+ callbacks=[print_trial_callback]
39
+ )
40
+
41
+ # 3. ๊ฒฐ๊ณผ ํ™•์ธ ๋ฐ ์š”์•ฝ
42
+ print(f"\n์ตœ์ ํ™” ์™„๋ฃŒ.")
43
+ print(f"Best CSI Score: {study.best_value:.4f}")
44
+ print(f"Best Hyperparameters: {study.best_params}")
45
+
46
+ try:
47
+ # ๋ชจ๋“  trial์˜ CSI ์ ์ˆ˜ ์ถ”์ถœ
48
+ csi_scores = [trial.value for trial in study.trials if trial.value is not None]
49
+
50
+ if len(csi_scores) > 0:
51
+ print(f"\n์ตœ์ ํ™” ๊ณผ์ • ์š”์•ฝ:")
52
+ print(f" - ์ด ์‹œ๋„ ํšŸ์ˆ˜: {len(study.trials)}")
53
+ print(f" - ์„ฑ๊ณตํ•œ ์‹œ๋„: {len(csi_scores)}")
54
+ print(f" - ์ตœ์ดˆ CSI: {csi_scores[0]:.4f}")
55
+ print(f" - ์ตœ์ข… CSI: {csi_scores[-1]:.4f}")
56
+ print(f" - ์ตœ๊ณ  CSI: {max(csi_scores):.4f}")
57
+ print(f" - ์ตœ์ € CSI: {min(csi_scores):.4f}")
58
+ print(f" - ํ‰๊ท  CSI: {np.mean(csi_scores):.4f}")
59
+
60
+ # Study ๊ฐ์ฒด ์ €์žฅ
61
+ # ํŒŒ์ผ ์œ„์น˜ ๊ธฐ๋ฐ˜์œผ๋กœ base ๋””๋ ‰ํ† ๋ฆฌ ๊ฒฝ๋กœ ์„ค์ •
62
+ current_file_dir = os.path.dirname(os.path.abspath(__file__))
63
+ base_dir = os.path.dirname(os.path.dirname(current_file_dir)) # 5.optima ๋””๋ ‰ํ† ๋ฆฌ
64
+ os.makedirs(os.path.join(base_dir, "optimization_history"), exist_ok=True)
65
+ study_path = os.path.join(base_dir, "optimization_history/ft_transformer_ctgan10000_daejeon_trials.pkl")
66
+ joblib.dump(study, study_path)
67
+ print(f"\n์ตœ์ ํ™” Study ๊ฐ์ฒด๊ฐ€ {study_path}์— ์ €์žฅ๋˜์—ˆ์Šต๋‹ˆ๋‹ค.")
68
+
69
+ # ์ตœ์ ํ™”๋œ ํ•˜์ดํผํŒŒ๋ผ๋ฏธํ„ฐ๋กœ ์ตœ์ข… ๋ชจ๋ธ ํ•™์Šต ๋ฐ ์ €์žฅ
70
+ print("\n" + "="*50)
71
+ print("์ตœ์ ํ™”๋œ ํ•˜์ดํผํŒŒ๋ผ๋ฏธํ„ฐ๋กœ ์ตœ์ข… ๋ชจ๋ธ ํ•™์Šต ์‹œ์ž‘")
72
+ print("="*50)
73
+
74
+ best_params = study.best_params
75
+ model_path = train_final_model(
76
+ best_params=best_params,
77
+ model_choose="ft_transformer",
78
+ region="daejeon",
79
+ data_sample='ctgan10000',
80
+ target='multi',
81
+ n_folds=3,
82
+ random_state=seed
83
+ )
84
+
85
+ print(f"\n์ตœ์ข… ๋ชจ๋ธ ํ•™์Šต ๋ฐ ์ €์žฅ ์™„๋ฃŒ!")
86
+ print(f"์ €์žฅ๋œ ๋ชจ๋ธ ๊ฒฝ๋กœ: {model_path}")
87
+
88
+ except Exception as e:
89
+ print(f"\nโš ๏ธ ์ตœ์ ํ™” ๊ฒฐ๊ณผ ๋ถ„์„ ์ค‘ ์˜ค๋ฅ˜ ๋ฐœ์ƒ: {e}")
90
+ import traceback
91
+ traceback.print_exc()
92
+
93
+ # ์ •์ƒ ์ข…๋ฃŒ
94
+ import sys
95
+ sys.exit(0)
96
+
Analysis_code/5.optima/ft_transformer_ctgan10000/ft_transformer_ctgan10000_gwangju.py ADDED
@@ -0,0 +1,96 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ import optuna
2
+ import numpy as np
3
+ import random
4
+ import pandas as pd
5
+ import joblib
6
+ import os
7
+ import torch
8
+ from utils import *
9
+ # Python ๋ฐ Numpy ์‹œ๋“œ ๊ณ ์ •
10
+ seed = 42
11
+ random.seed(seed)
12
+ np.random.seed(seed)
13
+
14
+
15
+ # Trial ์™„๋ฃŒ ์‹œ ์ƒ์„ธ ์ •๋ณด ์ถœ๋ ฅํ•˜๋Š” callback ํ•จ์ˆ˜
16
+ def print_trial_callback(study, trial):
17
+ """๊ฐ trial ์™„๋ฃŒ ์‹œ best value๋ฅผ ํฌํ•จํ•œ ์ƒ์„ธ ์ •๋ณด ์ถœ๋ ฅ"""
18
+ print(f"\n{'='*80}")
19
+ print(f"Trial {trial.number} ์™„๋ฃŒ")
20
+ print(f" Value (CSI): {trial.value:.6f}" if trial.value is not None else f" Value: {trial.value}")
21
+ print(f" Parameters: {trial.params}")
22
+ print(f" Best Value (CSI): {study.best_value:.6f}" if study.best_value is not None else f" Best Value: {study.best_value}")
23
+ print(f" Best Trial: {study.best_trial.number}")
24
+ print(f" Best Parameters: {study.best_params}")
25
+ print(f"{'='*80}\n")
26
+
27
+
28
+ # 1. Study ์ƒ์„ฑ ์‹œ 'maximize'๋กœ ์„ค์ •
29
+ study = optuna.create_study(
30
+ direction="maximize", # CSI ์ ์ˆ˜๊ฐ€ ๋†’์„์ˆ˜๋ก ์ข‹์œผ๋ฏ€๋กœ maximize
31
+ pruner=optuna.pruners.MedianPruner(n_warmup_steps=10) # ์ดˆ๋ฐ˜ 10์—ํญ์€ ์ง€์ผœ๋ณด๊ณ  ์ดํ›„ ๊ฐ€์ง€์น˜๊ธฐ
32
+ )
33
+
34
+ # 2. ์ตœ์ ํ™” ์‹คํ–‰
35
+ study.optimize(
36
+ lambda trial: objective(trial, model_choose="ft_transformer", region="gwangju", data_sample='ctgan10000'),
37
+ n_trials=100,
38
+ callbacks=[print_trial_callback]
39
+ )
40
+
41
+ # 3. ๊ฒฐ๊ณผ ํ™•์ธ ๋ฐ ์š”์•ฝ
42
+ print(f"\n์ตœ์ ํ™” ์™„๋ฃŒ.")
43
+ print(f"Best CSI Score: {study.best_value:.4f}")
44
+ print(f"Best Hyperparameters: {study.best_params}")
45
+
46
+ try:
47
+ # ๋ชจ๋“  trial์˜ CSI ์ ์ˆ˜ ์ถ”์ถœ
48
+ csi_scores = [trial.value for trial in study.trials if trial.value is not None]
49
+
50
+ if len(csi_scores) > 0:
51
+ print(f"\n์ตœ์ ํ™” ๊ณผ์ • ์š”์•ฝ:")
52
+ print(f" - ์ด ์‹œ๋„ ํšŸ์ˆ˜: {len(study.trials)}")
53
+ print(f" - ์„ฑ๊ณตํ•œ ์‹œ๋„: {len(csi_scores)}")
54
+ print(f" - ์ตœ์ดˆ CSI: {csi_scores[0]:.4f}")
55
+ print(f" - ์ตœ์ข… CSI: {csi_scores[-1]:.4f}")
56
+ print(f" - ์ตœ๊ณ  CSI: {max(csi_scores):.4f}")
57
+ print(f" - ์ตœ์ € CSI: {min(csi_scores):.4f}")
58
+ print(f" - ํ‰๊ท  CSI: {np.mean(csi_scores):.4f}")
59
+
60
+ # Study ๊ฐ์ฒด ์ €์žฅ
61
+ # ํŒŒ์ผ ์œ„์น˜ ๊ธฐ๋ฐ˜์œผ๋กœ base ๋””๋ ‰ํ† ๋ฆฌ ๊ฒฝ๋กœ ์„ค์ •
62
+ current_file_dir = os.path.dirname(os.path.abspath(__file__))
63
+ base_dir = os.path.dirname(os.path.dirname(current_file_dir)) # 5.optima ๋””๋ ‰ํ† ๋ฆฌ
64
+ os.makedirs(os.path.join(base_dir, "optimization_history"), exist_ok=True)
65
+ study_path = os.path.join(base_dir, "optimization_history/ft_transformer_ctgan10000_gwangju_trials.pkl")
66
+ joblib.dump(study, study_path)
67
+ print(f"\n์ตœ์ ํ™” Study ๊ฐ์ฒด๊ฐ€ {study_path}์— ์ €์žฅ๋˜์—ˆ์Šต๋‹ˆ๋‹ค.")
68
+
69
+ # ์ตœ์ ํ™”๋œ ํ•˜์ดํผํŒŒ๋ผ๋ฏธํ„ฐ๋กœ ์ตœ์ข… ๋ชจ๋ธ ํ•™์Šต ๋ฐ ์ €์žฅ
70
+ print("\n" + "="*50)
71
+ print("์ตœ์ ํ™”๋œ ํ•˜์ดํผํŒŒ๋ผ๋ฏธํ„ฐ๋กœ ์ตœ์ข… ๋ชจ๋ธ ํ•™์Šต ์‹œ์ž‘")
72
+ print("="*50)
73
+
74
+ best_params = study.best_params
75
+ model_path = train_final_model(
76
+ best_params=best_params,
77
+ model_choose="ft_transformer",
78
+ region="gwangju",
79
+ data_sample='ctgan10000',
80
+ target='multi',
81
+ n_folds=3,
82
+ random_state=seed
83
+ )
84
+
85
+ print(f"\n์ตœ์ข… ๋ชจ๋ธ ํ•™์Šต ๋ฐ ์ €์žฅ ์™„๋ฃŒ!")
86
+ print(f"์ €์žฅ๋œ ๋ชจ๋ธ ๊ฒฝ๋กœ: {model_path}")
87
+
88
+ except Exception as e:
89
+ print(f"\nโš ๏ธ ์ตœ์ ํ™” ๊ฒฐ๊ณผ ๋ถ„์„ ์ค‘ ์˜ค๋ฅ˜ ๋ฐœ์ƒ: {e}")
90
+ import traceback
91
+ traceback.print_exc()
92
+
93
+ # ์ •์ƒ ์ข…๋ฃŒ
94
+ import sys
95
+ sys.exit(0)
96
+
Analysis_code/5.optima/ft_transformer_ctgan10000/ft_transformer_ctgan10000_incheon.py ADDED
@@ -0,0 +1,96 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ import optuna
2
+ import numpy as np
3
+ import random
4
+ import pandas as pd
5
+ import joblib
6
+ import os
7
+ import torch
8
+ from utils import *
9
+ # Python ๋ฐ Numpy ์‹œ๋“œ ๊ณ ์ •
10
+ seed = 42
11
+ random.seed(seed)
12
+ np.random.seed(seed)
13
+
14
+
15
+ # Trial ์™„๋ฃŒ ์‹œ ์ƒ์„ธ ์ •๋ณด ์ถœ๋ ฅํ•˜๋Š” callback ํ•จ์ˆ˜
16
+ def print_trial_callback(study, trial):
17
+ """๊ฐ trial ์™„๋ฃŒ ์‹œ best value๋ฅผ ํฌํ•จํ•œ ์ƒ์„ธ ์ •๋ณด ์ถœ๋ ฅ"""
18
+ print(f"\n{'='*80}")
19
+ print(f"Trial {trial.number} ์™„๋ฃŒ")
20
+ print(f" Value (CSI): {trial.value:.6f}" if trial.value is not None else f" Value: {trial.value}")
21
+ print(f" Parameters: {trial.params}")
22
+ print(f" Best Value (CSI): {study.best_value:.6f}" if study.best_value is not None else f" Best Value: {study.best_value}")
23
+ print(f" Best Trial: {study.best_trial.number}")
24
+ print(f" Best Parameters: {study.best_params}")
25
+ print(f"{'='*80}\n")
26
+
27
+
28
+ # 1. Study ์ƒ์„ฑ ์‹œ 'maximize'๋กœ ์„ค์ •
29
+ study = optuna.create_study(
30
+ direction="maximize", # CSI ์ ์ˆ˜๊ฐ€ ๋†’์„์ˆ˜๋ก ์ข‹์œผ๋ฏ€๋กœ maximize
31
+ pruner=optuna.pruners.MedianPruner(n_warmup_steps=10) # ์ดˆ๋ฐ˜ 10์—ํญ์€ ์ง€์ผœ๋ณด๊ณ  ์ดํ›„ ๊ฐ€์ง€์น˜๊ธฐ
32
+ )
33
+
34
+ # 2. ์ตœ์ ํ™” ์‹คํ–‰
35
+ study.optimize(
36
+ lambda trial: objective(trial, model_choose="ft_transformer", region="incheon", data_sample='ctgan10000'),
37
+ n_trials=100,
38
+ callbacks=[print_trial_callback]
39
+ )
40
+
41
+ # 3. ๊ฒฐ๊ณผ ํ™•์ธ ๋ฐ ์š”์•ฝ
42
+ print(f"\n์ตœ์ ํ™” ์™„๋ฃŒ.")
43
+ print(f"Best CSI Score: {study.best_value:.4f}")
44
+ print(f"Best Hyperparameters: {study.best_params}")
45
+
46
+ try:
47
+ # ๋ชจ๋“  trial์˜ CSI ์ ์ˆ˜ ์ถ”์ถœ
48
+ csi_scores = [trial.value for trial in study.trials if trial.value is not None]
49
+
50
+ if len(csi_scores) > 0:
51
+ print(f"\n์ตœ์ ํ™” ๊ณผ์ • ์š”์•ฝ:")
52
+ print(f" - ์ด ์‹œ๋„ ํšŸ์ˆ˜: {len(study.trials)}")
53
+ print(f" - ์„ฑ๊ณตํ•œ ์‹œ๋„: {len(csi_scores)}")
54
+ print(f" - ์ตœ์ดˆ CSI: {csi_scores[0]:.4f}")
55
+ print(f" - ์ตœ์ข… CSI: {csi_scores[-1]:.4f}")
56
+ print(f" - ์ตœ๊ณ  CSI: {max(csi_scores):.4f}")
57
+ print(f" - ์ตœ์ € CSI: {min(csi_scores):.4f}")
58
+ print(f" - ํ‰๊ท  CSI: {np.mean(csi_scores):.4f}")
59
+
60
+ # Study ๊ฐ์ฒด ์ €์žฅ
61
+ # ํŒŒ์ผ ์œ„์น˜ ๊ธฐ๋ฐ˜์œผ๋กœ base ๋””๋ ‰ํ† ๋ฆฌ ๊ฒฝ๋กœ ์„ค์ •
62
+ current_file_dir = os.path.dirname(os.path.abspath(__file__))
63
+ base_dir = os.path.dirname(os.path.dirname(current_file_dir)) # 5.optima ๋””๋ ‰ํ† ๋ฆฌ
64
+ os.makedirs(os.path.join(base_dir, "optimization_history"), exist_ok=True)
65
+ study_path = os.path.join(base_dir, "optimization_history/ft_transformer_ctgan10000_incheon_trials.pkl")
66
+ joblib.dump(study, study_path)
67
+ print(f"\n์ตœ์ ํ™” Study ๊ฐ์ฒด๊ฐ€ {study_path}์— ์ €์žฅ๋˜์—ˆ์Šต๋‹ˆ๋‹ค.")
68
+
69
+ # ์ตœ์ ํ™”๋œ ํ•˜์ดํผํŒŒ๋ผ๋ฏธํ„ฐ๋กœ ์ตœ์ข… ๋ชจ๋ธ ํ•™์Šต ๋ฐ ์ €์žฅ
70
+ print("\n" + "="*50)
71
+ print("์ตœ์ ํ™”๋œ ํ•˜์ดํผํŒŒ๋ผ๋ฏธํ„ฐ๋กœ ์ตœ์ข… ๋ชจ๋ธ ํ•™์Šต ์‹œ์ž‘")
72
+ print("="*50)
73
+
74
+ best_params = study.best_params
75
+ model_path = train_final_model(
76
+ best_params=best_params,
77
+ model_choose="ft_transformer",
78
+ region="incheon",
79
+ data_sample='ctgan10000',
80
+ target='multi',
81
+ n_folds=3,
82
+ random_state=seed
83
+ )
84
+
85
+ print(f"\n์ตœ์ข… ๋ชจ๋ธ ํ•™์Šต ๋ฐ ์ €์žฅ ์™„๋ฃŒ!")
86
+ print(f"์ €์žฅ๋œ ๋ชจ๋ธ ๊ฒฝ๋กœ: {model_path}")
87
+
88
+ except Exception as e:
89
+ print(f"\nโš ๏ธ ์ตœ์ ํ™” ๊ฒฐ๊ณผ ๋ถ„์„ ์ค‘ ์˜ค๋ฅ˜ ๋ฐœ์ƒ: {e}")
90
+ import traceback
91
+ traceback.print_exc()
92
+
93
+ # ์ •์ƒ ์ข…๋ฃŒ
94
+ import sys
95
+ sys.exit(0)
96
+
Analysis_code/5.optima/ft_transformer_ctgan10000/ft_transformer_ctgan10000_seoul.py ADDED
@@ -0,0 +1,96 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ import optuna
2
+ import numpy as np
3
+ import random
4
+ import pandas as pd
5
+ import joblib
6
+ import os
7
+ import torch
8
+ from utils import *
9
+ # Python ๋ฐ Numpy ์‹œ๋“œ ๊ณ ์ •
10
+ seed = 42
11
+ random.seed(seed)
12
+ np.random.seed(seed)
13
+
14
+
15
+ # Trial ์™„๋ฃŒ ์‹œ ์ƒ์„ธ ์ •๋ณด ์ถœ๋ ฅํ•˜๋Š” callback ํ•จ์ˆ˜
16
+ def print_trial_callback(study, trial):
17
+ """๊ฐ trial ์™„๋ฃŒ ์‹œ best value๋ฅผ ํฌํ•จํ•œ ์ƒ์„ธ ์ •๋ณด ์ถœ๋ ฅ"""
18
+ print(f"\n{'='*80}")
19
+ print(f"Trial {trial.number} ์™„๋ฃŒ")
20
+ print(f" Value (CSI): {trial.value:.6f}" if trial.value is not None else f" Value: {trial.value}")
21
+ print(f" Parameters: {trial.params}")
22
+ print(f" Best Value (CSI): {study.best_value:.6f}" if study.best_value is not None else f" Best Value: {study.best_value}")
23
+ print(f" Best Trial: {study.best_trial.number}")
24
+ print(f" Best Parameters: {study.best_params}")
25
+ print(f"{'='*80}\n")
26
+
27
+
28
+ # 1. Study ์ƒ์„ฑ ์‹œ 'maximize'๋กœ ์„ค์ •
29
+ study = optuna.create_study(
30
+ direction="maximize", # CSI ์ ์ˆ˜๊ฐ€ ๋†’์„์ˆ˜๋ก ์ข‹์œผ๋ฏ€๋กœ maximize
31
+ pruner=optuna.pruners.MedianPruner(n_warmup_steps=10) # ์ดˆ๋ฐ˜ 10์—ํญ์€ ์ง€์ผœ๋ณด๊ณ  ์ดํ›„ ๊ฐ€์ง€์น˜๊ธฐ
32
+ )
33
+
34
+ # 2. ์ตœ์ ํ™” ์‹คํ–‰
35
+ study.optimize(
36
+ lambda trial: objective(trial, model_choose="ft_transformer", region="seoul", data_sample='ctgan10000'),
37
+ n_trials=100,
38
+ callbacks=[print_trial_callback]
39
+ )
40
+
41
+ # 3. ๊ฒฐ๊ณผ ํ™•์ธ ๋ฐ ์š”์•ฝ
42
+ print(f"\n์ตœ์ ํ™” ์™„๋ฃŒ.")
43
+ print(f"Best CSI Score: {study.best_value:.4f}")
44
+ print(f"Best Hyperparameters: {study.best_params}")
45
+
46
+ try:
47
+ # ๋ชจ๋“  trial์˜ CSI ์ ์ˆ˜ ์ถ”์ถœ
48
+ csi_scores = [trial.value for trial in study.trials if trial.value is not None]
49
+
50
+ if len(csi_scores) > 0:
51
+ print(f"\n์ตœ์ ํ™” ๊ณผ์ • ์š”์•ฝ:")
52
+ print(f" - ์ด ์‹œ๋„ ํšŸ์ˆ˜: {len(study.trials)}")
53
+ print(f" - ์„ฑ๊ณตํ•œ ์‹œ๋„: {len(csi_scores)}")
54
+ print(f" - ์ตœ์ดˆ CSI: {csi_scores[0]:.4f}")
55
+ print(f" - ์ตœ์ข… CSI: {csi_scores[-1]:.4f}")
56
+ print(f" - ์ตœ๊ณ  CSI: {max(csi_scores):.4f}")
57
+ print(f" - ์ตœ์ € CSI: {min(csi_scores):.4f}")
58
+ print(f" - ํ‰๊ท  CSI: {np.mean(csi_scores):.4f}")
59
+
60
+ # Study ๊ฐ์ฒด ์ €์žฅ
61
+ # ํŒŒ์ผ ์œ„์น˜ ๊ธฐ๋ฐ˜์œผ๋กœ base ๋””๋ ‰ํ† ๋ฆฌ ๊ฒฝ๋กœ ์„ค์ •
62
+ current_file_dir = os.path.dirname(os.path.abspath(__file__))
63
+ base_dir = os.path.dirname(os.path.dirname(current_file_dir)) # 5.optima ๋””๋ ‰ํ† ๋ฆฌ
64
+ os.makedirs(os.path.join(base_dir, "optimization_history"), exist_ok=True)
65
+ study_path = os.path.join(base_dir, "optimization_history/ft_transformer_ctgan10000_seoul_trials.pkl")
66
+ joblib.dump(study, study_path)
67
+ print(f"\n์ตœ์ ํ™” Study ๊ฐ์ฒด๊ฐ€ {study_path}์— ์ €์žฅ๋˜์—ˆ์Šต๋‹ˆ๋‹ค.")
68
+
69
+ # ์ตœ์ ํ™”๋œ ํ•˜์ดํผํŒŒ๋ผ๋ฏธํ„ฐ๋กœ ์ตœ์ข… ๋ชจ๋ธ ํ•™์Šต ๋ฐ ์ €์žฅ
70
+ print("\n" + "="*50)
71
+ print("์ตœ์ ํ™”๋œ ํ•˜์ดํผํŒŒ๋ผ๋ฏธํ„ฐ๋กœ ์ตœ์ข… ๋ชจ๋ธ ํ•™์Šต ์‹œ์ž‘")
72
+ print("="*50)
73
+
74
+ best_params = study.best_params
75
+ model_path = train_final_model(
76
+ best_params=best_params,
77
+ model_choose="ft_transformer",
78
+ region="seoul",
79
+ data_sample='ctgan10000',
80
+ target='multi',
81
+ n_folds=3,
82
+ random_state=seed
83
+ )
84
+
85
+ print(f"\n์ตœ์ข… ๋ชจ๋ธ ํ•™์Šต ๋ฐ ์ €์žฅ ์™„๋ฃŒ!")
86
+ print(f"์ €์žฅ๋œ ๋ชจ๋ธ ๊ฒฝ๋กœ: {model_path}")
87
+
88
+ except Exception as e:
89
+ print(f"\nโš ๏ธ ์ตœ์ ํ™” ๊ฒฐ๊ณผ ๋ถ„์„ ์ค‘ ์˜ค๋ฅ˜ ๋ฐœ์ƒ: {e}")
90
+ import traceback
91
+ traceback.print_exc()
92
+
93
+ # ์ •์ƒ ์ข…๋ฃŒ
94
+ import sys
95
+ sys.exit(0)
96
+
Analysis_code/5.optima/lgb_ctgan10000/LGB_ctgan10000_daegu.py ADDED
@@ -0,0 +1,317 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ import pandas as pd
2
+ import numpy as np
3
+ import joblib
4
+ import os
5
+ from warnings import filterwarnings
6
+ from sklearn.metrics import confusion_matrix
7
+ from lightgbm import LGBMClassifier
8
+ from hyperopt import fmin, tpe, Trials, hp
9
+
10
+ filterwarnings('ignore')
11
+
12
+ # ์ƒ์ˆ˜ ์ •์˜
13
+ RANDOM_STATE = 42
14
+ N_ESTIMATORS = 4000
15
+ EARLY_STOPPING_ROUNDS = 400
16
+ MAX_EVALS = 100
17
+ DEVICE = 'gpu'
18
+ OBJECTIVE = 'multiclassova'
19
+
20
+ # Fold ์„ค์ •: (train_years, val_year)
21
+ FOLD_CONFIGS = [
22
+ ([2018, 2019], 2020), # Fold 1
23
+ ([2018, 2020], 2019), # Fold 2
24
+ ([2019, 2020], 2018), # Fold 3
25
+ ]
26
+
27
+ def calculate_csi(y_true, y_pred):
28
+ """CSI(Critical Success Index) ์ ์ˆ˜๋ฅผ ๊ณ„์‚ฐํ•ฉ๋‹ˆ๋‹ค.
29
+
30
+ Args:
31
+ y_true: ์‹ค์ œ ๋ ˆ์ด๋ธ”
32
+ y_pred: ์˜ˆ์ธก ๋ ˆ์ด๋ธ”
33
+
34
+ Returns:
35
+ CSI ์ ์ˆ˜ (0~1 ์‚ฌ์ด์˜ ๊ฐ’)
36
+ """
37
+ cm = confusion_matrix(y_true, y_pred)
38
+
39
+ # ํ˜ผ๋™ ํ–‰๋ ฌ์—์„œ H(Hit), F(False alarm), M(Miss) ์ถ”์ถœ
40
+ H = cm[0, 0] + cm[1, 1]
41
+ F = cm[1, 0] + cm[2, 0] + cm[0, 1] + cm[2, 1]
42
+ M = cm[0, 2] + cm[1, 2]
43
+
44
+ # CSI ๊ณ„์‚ฐ
45
+ csi = H / (H + F + M + 1e-10)
46
+ return csi
47
+
48
+
49
+ def csi_metric(y_true, pred_prob):
50
+ """LightGBM์šฉ CSI ๋ฉ”ํŠธ๋ฆญ ํ•จ์ˆ˜.
51
+
52
+ Args:
53
+ y_true: ์‹ค์ œ ๋ ˆ์ด๋ธ”
54
+ pred_prob: ์˜ˆ์ธก ํ™•๋ฅ  (shape: [n_samples, n_classes])
55
+
56
+ Returns:
57
+ ('CSI', score, higher_better) ํŠœํ”Œ
58
+ """
59
+ y_pred_binary = np.argmax(pred_prob, axis=1)
60
+ score = calculate_csi(y_true, y_pred_binary)
61
+ return 'CSI', score, True
62
+
63
+ def add_derived_features(df: pd.DataFrame) -> pd.DataFrame:
64
+ """
65
+ ์ œ๊ฑฐํ–ˆ๋˜ ํŒŒ์ƒ ๋ณ€์ˆ˜๋“ค์„ ๋ณต๊ตฌ
66
+
67
+ Args:
68
+ df: ๋ฐ์ดํ„ฐํ”„๋ ˆ์ž„
69
+
70
+ Returns:
71
+ ํŒŒ์ƒ ๋ณ€์ˆ˜๊ฐ€ ์ถ”๊ฐ€๋œ ๋ฐ์ดํ„ฐํ”„๋ ˆ์ž„
72
+ """
73
+ df = df.copy()
74
+ df['hour_sin'] = np.sin(2 * np.pi * df['hour'] / 24)
75
+ df['hour_cos'] = np.cos(2 * np.pi * df['hour'] / 24)
76
+ df['month_sin'] = np.sin(2 * np.pi * df['month'] / 12)
77
+ df['month_cos'] = np.cos(2 * np.pi * df['month'] / 12)
78
+ df['ground_temp - temp_C'] = df['groundtemp'] - df['temp_C']
79
+ return df
80
+
81
+ def preprocessing(df):
82
+ """๋ฐ์ดํ„ฐ ์ „์ฒ˜๋ฆฌ ํ•จ์ˆ˜.
83
+
84
+ Args:
85
+ df: ์›๋ณธ ๋ฐ์ดํ„ฐํ”„๋ ˆ์ž„
86
+
87
+ Returns:
88
+ ์ „์ฒ˜๋ฆฌ๋œ ๋ฐ์ดํ„ฐํ”„๋ ˆ์ž„
89
+ """
90
+ df = df[df.columns].copy()
91
+ df['year'] = df['year'].astype('int')
92
+ df['month'] = df['month'].astype('int')
93
+ df['hour'] = df['hour'].astype('int')
94
+ df = add_derived_features(df).copy()
95
+ df['multi_class'] = df['multi_class'].astype('int')
96
+ df.loc[df['wind_dir']=='์ •์˜จ', 'wind_dir'] = "0"
97
+ df['wind_dir'] = df['wind_dir'].astype('int')
98
+ df = df[['temp_C', 'precip_mm', 'wind_speed', 'wind_dir', 'hm',
99
+ 'vap_pressure', 'dewpoint_C', 'loc_pressure', 'sea_pressure',
100
+ 'solarRad', 'snow_cm', 'cloudcover', 'lm_cloudcover', 'low_cloudbase',
101
+ 'groundtemp', 'O3', 'NO2', 'PM10', 'PM25', 'year',
102
+ 'month', 'hour', 'ground_temp - temp_C', 'hour_sin', 'hour_cos',
103
+ 'month_sin', 'month_cos','multi_class']].copy()
104
+ return df
105
+
106
+
107
+ def split_data(df_sampled, df_original, train_years, val_year):
108
+ """๋ฐ์ดํ„ฐ๋ฅผ ํ•™์Šต์šฉ๊ณผ ๊ฒ€์ฆ์šฉ์œผ๋กœ ๋ถ„ํ• ํ•ฉ๋‹ˆ๋‹ค.
109
+
110
+ Args:
111
+ df_sampled: ์ƒ˜ํ”Œ๋ง๋œ ๋ฐ์ดํ„ฐํ”„๋ ˆ์ž„
112
+ df_original: ์›๋ณธ ๋ฐ์ดํ„ฐํ”„๋ ˆ์ž„
113
+ train_years: ํ•™์Šต์— ์‚ฌ์šฉํ•  ์—ฐ๋„ ๋ฆฌ์ŠคํŠธ
114
+ val_year: ๊ฒ€์ฆ์— ์‚ฌ์šฉํ•  ์—ฐ๋„
115
+
116
+ Returns:
117
+ (X_train, X_val, y_train, y_val) ํŠœํ”Œ
118
+ """
119
+ # ํ•™์Šต ๋ฐ์ดํ„ฐ: ์ƒ˜ํ”Œ๋ง๋œ ๋ฐ์ดํ„ฐ์—์„œ train_years์— ํ•ด๋‹นํ•˜๋Š” ๋ฐ์ดํ„ฐ
120
+ train_mask = df_sampled['year'].isin(train_years)
121
+ X_train = df_sampled.loc[train_mask, df_sampled.columns != 'multi_class'].copy()
122
+ y_train = df_sampled.loc[train_mask, 'multi_class']
123
+
124
+ # ๊ฒ€์ฆ ๋ฐ์ดํ„ฐ: ์›๋ณธ ๋ฐ์ดํ„ฐ์—์„œ val_year์— ํ•ด๋‹นํ•˜๋Š” ๋ฐ์ดํ„ฐ
125
+ val_mask = df_original['year'] == val_year
126
+ X_val = df_original.loc[val_mask, df_original.columns != 'multi_class'].copy()
127
+ y_val = df_original.loc[val_mask, 'multi_class']
128
+
129
+ # 'year' ์ปฌ๋Ÿผ ์ œ๊ฑฐ
130
+ X_train = X_train.drop(columns=['year'])
131
+ X_val = X_val.drop(columns=['year'])
132
+
133
+ return X_train, X_val, y_train, y_val
134
+
135
+
136
+ def create_lgb_model(search_space=None, best_params=None):
137
+ """LightGBM ๋ชจ๋ธ์„ ์ƒ์„ฑํ•ฉ๋‹ˆ๋‹ค.
138
+
139
+ Args:
140
+ search_space: ํ•˜์ดํผํŒŒ๋ผ๋ฏธํ„ฐ ๊ฒ€์ƒ‰ ๊ณต๊ฐ„ (objective_func์—์„œ ์‚ฌ์šฉ)
141
+ best_params: ์ตœ์ ํ™”๋œ ํ•˜์ดํผํŒŒ๋ผ๋ฏธํ„ฐ (์ตœ์ข… ๋ชจ๋ธ ํ•™์Šต์—์„œ ์‚ฌ์šฉ)
142
+
143
+ Returns:
144
+ LGBMClassifier ์ธ์Šคํ„ด์Šค
145
+ """
146
+ base_params = {
147
+ 'n_estimators': N_ESTIMATORS,
148
+ 'device': DEVICE,
149
+ 'objective': OBJECTIVE,
150
+ 'random_state': RANDOM_STATE,
151
+ 'early_stopping_rounds': EARLY_STOPPING_ROUNDS,
152
+ 'verbose': -1,
153
+ }
154
+
155
+ if search_space is not None:
156
+ # ํ•˜์ดํผํŒŒ๋ผ๋ฏธํ„ฐ ์ตœ์ ํ™” ์ค‘
157
+ params = {
158
+ **base_params,
159
+ 'learning_rate': search_space['learning_rate'],
160
+ 'max_depth': int(search_space['max_depth']),
161
+ 'num_leaves': int(search_space['num_leaves']),
162
+ 'min_child_weight': int(search_space['min_child_weight']),
163
+ 'subsample': search_space['subsample'],
164
+ 'colsample_bytree': search_space['colsample_bytree'],
165
+ 'reg_alpha': search_space['reg_alpha'],
166
+ 'reg_lambda': search_space['reg_lambda'],
167
+ }
168
+ elif best_params is not None:
169
+ # ์ตœ์ ํ™”๋œ ํŒŒ๋ผ๋ฏธํ„ฐ๋กœ ์ตœ์ข… ๋ชจ๋ธ ์ƒ์„ฑ
170
+ params = {
171
+ **base_params,
172
+ 'learning_rate': best_params['learning_rate'],
173
+ 'max_depth': int(best_params['max_depth']),
174
+ 'num_leaves': int(best_params['num_leaves']),
175
+ 'min_child_weight': int(best_params['min_child_weight']),
176
+ 'subsample': best_params['subsample'],
177
+ 'colsample_bytree': best_params['colsample_bytree'],
178
+ 'reg_alpha': best_params['reg_alpha'],
179
+ 'reg_lambda': best_params['reg_lambda'],
180
+ }
181
+ else:
182
+ params = base_params
183
+
184
+ return LGBMClassifier(**params)
185
+
186
+ # ๋ฐ์ดํ„ฐ ๋กœ๋”ฉ
187
+ print("๋ฐ์ดํ„ฐ ๋กœ๋”ฉ ์ค‘...")
188
+ # ํŒŒ์ผ ์œ„์น˜ ๊ธฐ๋ฐ˜์œผ๋กœ ๋ฐ์ดํ„ฐ ๋””๋ ‰ํ† ๋ฆฌ ๊ฒฝ๋กœ ์„ค์ •
189
+ current_file_dir = os.path.dirname(os.path.abspath(__file__))
190
+ data_base_dir = os.path.abspath(os.path.join(current_file_dir, '../../../data'))
191
+ df_daegu = pd.read_csv(os.path.join(data_base_dir, "data_for_modeling/daegu_train.csv"))
192
+ df_ctgan_daegu_1 = pd.read_csv(os.path.join(data_base_dir, "data_oversampled/ctgan10000/ctgan10000_1_daegu.csv"))
193
+ df_ctgan_daegu_2 = pd.read_csv(os.path.join(data_base_dir, "data_oversampled/ctgan10000/ctgan10000_2_daegu.csv"))
194
+ df_ctgan_daegu_3 = pd.read_csv(os.path.join(data_base_dir, "data_oversampled/ctgan10000/ctgan10000_3_daegu.csv"))
195
+
196
+ # ๋ฐ์ดํ„ฐ ์ „์ฒ˜๋ฆฌ
197
+ print("๋ฐ์ดํ„ฐ ์ „์ฒ˜๋ฆฌ ์ค‘...")
198
+ df_ctgan_daegu_1 = preprocessing(df_ctgan_daegu_1)
199
+ df_ctgan_daegu_2 = preprocessing(df_ctgan_daegu_2)
200
+ df_ctgan_daegu_3 = preprocessing(df_ctgan_daegu_3)
201
+ df_daegu = preprocessing(df_daegu)
202
+
203
+ # CTGAN ๋ฐ์ดํ„ฐ ๋ฆฌ์ŠคํŠธ (fold ์ˆœ์„œ์™€ ์ผ์น˜)
204
+ df_ctgan_list = [df_ctgan_daegu_1, df_ctgan_daegu_2, df_ctgan_daegu_3]
205
+
206
+ # ํ•˜์ดํผํŒŒ๋ผ๋ฏธํ„ฐ ๊ฒ€์ƒ‰ ๊ณต๊ฐ„ ์ •์˜
207
+ lgb_search_space = {
208
+ 'learning_rate': hp.loguniform('learning_rate', np.log(0.01), np.log(0.2)),
209
+ 'max_depth': hp.quniform('max_depth', 3, 15, 1),
210
+ 'num_leaves': hp.quniform('num_leaves', 20, 150, 1), # 2^max_depth ๋ณด๋‹ค๋Š” ์ž‘๊ฒŒ
211
+ 'min_child_weight': hp.quniform('min_child_weight', 1, 20, 1),
212
+ 'subsample': hp.uniform('subsample', 0.6, 1.0),
213
+ 'colsample_bytree': hp.uniform('colsample_bytree', 0.6, 1.0),
214
+ 'reg_alpha': hp.uniform('reg_alpha', 0.0, 1.0),
215
+ 'reg_lambda': hp.uniform('reg_lambda', 0.0, 1.0)
216
+ }
217
+
218
+
219
+ def objective_func(search_space):
220
+ """ํ•˜์ดํผํŒŒ๋ผ๋ฏธํ„ฐ ์ตœ์ ํ™”๋ฅผ ์œ„ํ•œ ๋ชฉ์  ํ•จ์ˆ˜.
221
+
222
+ Args:
223
+ search_space: ํ•˜์ดํผํŒŒ๋ผ๋ฏธํ„ฐ ๊ฒ€์ƒ‰ ๊ณต๊ฐ„
224
+
225
+ Returns:
226
+ ํ‰๊ท  CSI ์ ์ˆ˜์˜ ์Œ์ˆ˜๊ฐ’ (hyperopt๋Š” ์ตœ์†Œํ™”๋ฅผ ์ˆ˜ํ–‰ํ•˜๋ฏ€๋กœ)
227
+ """
228
+ lgb_model = create_lgb_model(search_space=search_space)
229
+ csi_scores = []
230
+
231
+ # ๊ฐ fold์— ๋Œ€ํ•ด ๊ต์ฐจ ๊ฒ€์ฆ ์ˆ˜ํ–‰
232
+ for df_ctgan, (train_years, val_year) in zip(df_ctgan_list, FOLD_CONFIGS):
233
+ X_train, X_val, y_train, y_val = split_data(
234
+ df_ctgan, df_daegu, train_years, val_year
235
+ )
236
+
237
+ lgb_model.fit(
238
+ X_train, y_train,
239
+ eval_set=[(X_val, y_val)],
240
+ eval_metric=csi_metric
241
+ )
242
+
243
+ csi = calculate_csi(y_val, lgb_model.predict(X_val))
244
+ csi_scores.append(csi)
245
+
246
+ # ํ‰๊ท  CSI์˜ ์Œ์ˆ˜๊ฐ’ ๋ฐ˜ํ™˜ (hyperopt๋Š” ์ตœ์†Œํ™”๋ฅผ ์ˆ˜ํ–‰)
247
+ return -1 * round(np.mean(csi_scores), 4)
248
+
249
+
250
+ # ํ•˜์ดํผํŒŒ๋ผ๋ฏธํ„ฐ ์ตœ์ ํ™”
251
+ print("ํ•˜์ดํผํŒŒ๋ผ๋ฏธํ„ฐ ์ตœ์ ํ™” ์‹œ์ž‘...")
252
+ trials = Trials()
253
+ lgb_best = fmin(
254
+ fn=objective_func,
255
+ space=lgb_search_space,
256
+ algo=tpe.suggest,
257
+ max_evals=MAX_EVALS,
258
+ trials=trials
259
+ )
260
+
261
+ # ์ตœ์ ํ™” ๊ฒฐ๊ณผ ๋ถ„์„ ๋ฐ ์ถœ๋ ฅ
262
+ print(f"\n์ตœ์ ํ™” ์™„๋ฃŒ. ์ตœ์  ํŒŒ๋ผ๋ฏธํ„ฐ: {lgb_best}")
263
+
264
+ # Best loss (CSI ์ ์ˆ˜์˜ ์Œ์ˆ˜๊ฐ’์ด๋ฏ€๋กœ, ์‹ค์ œ CSI๋Š” -loss)
265
+ best_loss = trials.best_trial['result']['loss']
266
+ best_csi = -best_loss
267
+ print(f"์ตœ์  CSI ์ ์ˆ˜: {best_csi:.4f} (loss: {best_loss:.4f})")
268
+
269
+ # ๋ชจ๋“  trial์˜ loss ๊ฐ’ ์ถ”์ถœ
270
+ losses = [trial['result']['loss'] for trial in trials.trials if trial['result']['status'] == 'ok']
271
+ csi_scores = [-loss for loss in losses]
272
+
273
+ print(f"\n์ตœ์ ํ™” ๊ณผ์ • ์š”์•ฝ:")
274
+ print(f" - ์ด ์‹œ๋„ ํšŸ์ˆ˜: {len(trials.trials)}")
275
+ print(f" - ์„ฑ๊ณตํ•œ ์‹œ๋„: {len(losses)}")
276
+ print(f" - ์ตœ์ดˆ CSI: {csi_scores[0]:.4f}")
277
+ print(f" - ์ตœ์ข… CSI: {csi_scores[-1]:.4f}")
278
+ print(f" - ์ตœ๊ณ  CSI: {max(csi_scores):.4f}")
279
+ print(f" - ์ตœ์ € CSI: {min(csi_scores):.4f}")
280
+ print(f" - ํ‰๊ท  CSI: {np.mean(csi_scores):.4f}")
281
+
282
+ # Trials ๊ฐ์ฒด ์ €์žฅ
283
+ import os
284
+ base_dir = os.path.dirname(os.path.dirname(current_file_dir)) # 5.optima ๋””๋ ‰ํ† ๋ฆฌ
285
+ os.makedirs(os.path.join(base_dir, "optimization_history"), exist_ok=True)
286
+ trials_path = os.path.join(base_dir, "optimization_history/lgb_ctgan10000_daegu_trials.pkl")
287
+ joblib.dump(trials, trials_path)
288
+ print(f"\n์ตœ์ ํ™” Trials ๊ฐ์ฒด๊ฐ€ {trials_path}์— ์ €์žฅ๋˜์—ˆ์Šต๋‹ˆ๋‹ค.")
289
+
290
+ # ์ตœ์ ํ™”๋œ ํ•˜์ดํผํŒŒ๋ผ๋ฏธํ„ฐ๋กœ ์ตœ์ข… ๋ชจ๋ธ ํ•™์Šต
291
+ print("์ตœ์ข… ๋ชจ๋ธ ํ•™์Šต ์‹œ์ž‘...")
292
+ models = []
293
+
294
+ for fold_idx, (df_ctgan, (train_years, val_year)) in enumerate(
295
+ zip(df_ctgan_list, FOLD_CONFIGS), start=1
296
+ ):
297
+ print(f"Fold {fold_idx} ํ•™์Šต ์ค‘... (ํ•™์Šต ์—ฐ๋„: {train_years}, ๊ฒ€์ฆ ์—ฐ๋„: {val_year})")
298
+
299
+ X_train, X_val, y_train, y_val = split_data(
300
+ df_ctgan, df_daegu, train_years, val_year
301
+ )
302
+
303
+ lgb_model = create_lgb_model(best_params=lgb_best)
304
+ lgb_model.fit(X_train, y_train, eval_set=[(X_val, y_val)])
305
+
306
+ # ๊ฒ€์ฆ ์„ฑ๋Šฅ ์ถœ๋ ฅ
307
+ val_csi = calculate_csi(y_val, lgb_model.predict(X_val))
308
+ print(f"Fold {fold_idx} ๊ฒ€์ฆ CSI: {val_csi:.4f}")
309
+
310
+ models.append(lgb_model)
311
+
312
+ # ๋ชจ๋ธ ์ €์žฅ
313
+ print("๋ชจ๋ธ ์ €์žฅ ์ค‘...")
314
+ model_save_path = os.path.join(base_dir, "save_model/lgb_optima/lgb_ctgan10000_daegu.pkl")
315
+ joblib.dump(models, model_save_path)
316
+ print(f"๋ชจ๋ธ์ด {model_save_path}์— ์ €์žฅ๋˜์—ˆ์Šต๋‹ˆ๋‹ค.")
317
+
Analysis_code/5.optima/lgb_ctgan10000/LGB_ctgan10000_daejeon.py ADDED
@@ -0,0 +1,317 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ import pandas as pd
2
+ import numpy as np
3
+ import joblib
4
+ import os
5
+ from warnings import filterwarnings
6
+ from sklearn.metrics import confusion_matrix
7
+ from lightgbm import LGBMClassifier
8
+ from hyperopt import fmin, tpe, Trials, hp
9
+
10
+ filterwarnings('ignore')
11
+
12
+ # ์ƒ์ˆ˜ ์ •์˜
13
+ RANDOM_STATE = 42
14
+ N_ESTIMATORS = 4000
15
+ EARLY_STOPPING_ROUNDS = 400
16
+ MAX_EVALS = 100
17
+ DEVICE = 'gpu'
18
+ OBJECTIVE = 'multiclassova'
19
+
20
+ # Fold ์„ค์ •: (train_years, val_year)
21
+ FOLD_CONFIGS = [
22
+ ([2018, 2019], 2020), # Fold 1
23
+ ([2018, 2020], 2019), # Fold 2
24
+ ([2019, 2020], 2018), # Fold 3
25
+ ]
26
+
27
+ def calculate_csi(y_true, y_pred):
28
+ """CSI(Critical Success Index) ์ ์ˆ˜๋ฅผ ๊ณ„์‚ฐํ•ฉ๋‹ˆ๋‹ค.
29
+
30
+ Args:
31
+ y_true: ์‹ค์ œ ๋ ˆ์ด๋ธ”
32
+ y_pred: ์˜ˆ์ธก ๋ ˆ์ด๋ธ”
33
+
34
+ Returns:
35
+ CSI ์ ์ˆ˜ (0~1 ์‚ฌ์ด์˜ ๊ฐ’)
36
+ """
37
+ cm = confusion_matrix(y_true, y_pred)
38
+
39
+ # ํ˜ผ๋™ ํ–‰๋ ฌ์—์„œ H(Hit), F(False alarm), M(Miss) ์ถ”์ถœ
40
+ H = cm[0, 0] + cm[1, 1]
41
+ F = cm[1, 0] + cm[2, 0] + cm[0, 1] + cm[2, 1]
42
+ M = cm[0, 2] + cm[1, 2]
43
+
44
+ # CSI ๊ณ„์‚ฐ
45
+ csi = H / (H + F + M + 1e-10)
46
+ return csi
47
+
48
+
49
+ def csi_metric(y_true, pred_prob):
50
+ """LightGBM์šฉ CSI ๋ฉ”ํŠธ๋ฆญ ํ•จ์ˆ˜.
51
+
52
+ Args:
53
+ y_true: ์‹ค์ œ ๋ ˆ์ด๋ธ”
54
+ pred_prob: ์˜ˆ์ธก ํ™•๋ฅ  (shape: [n_samples, n_classes])
55
+
56
+ Returns:
57
+ ('CSI', score, higher_better) ํŠœํ”Œ
58
+ """
59
+ y_pred_binary = np.argmax(pred_prob, axis=1)
60
+ score = calculate_csi(y_true, y_pred_binary)
61
+ return 'CSI', score, True
62
+
63
+ def add_derived_features(df: pd.DataFrame) -> pd.DataFrame:
64
+ """
65
+ ์ œ๊ฑฐํ–ˆ๋˜ ํŒŒ์ƒ ๋ณ€์ˆ˜๋“ค์„ ๋ณต๊ตฌ
66
+
67
+ Args:
68
+ df: ๋ฐ์ดํ„ฐํ”„๋ ˆ์ž„
69
+
70
+ Returns:
71
+ ํŒŒ์ƒ ๋ณ€์ˆ˜๊ฐ€ ์ถ”๊ฐ€๋œ ๋ฐ์ดํ„ฐํ”„๋ ˆ์ž„
72
+ """
73
+ df = df.copy()
74
+ df['hour_sin'] = np.sin(2 * np.pi * df['hour'] / 24)
75
+ df['hour_cos'] = np.cos(2 * np.pi * df['hour'] / 24)
76
+ df['month_sin'] = np.sin(2 * np.pi * df['month'] / 12)
77
+ df['month_cos'] = np.cos(2 * np.pi * df['month'] / 12)
78
+ df['ground_temp - temp_C'] = df['groundtemp'] - df['temp_C']
79
+ return df
80
+
81
+ def preprocessing(df):
82
+ """๋ฐ์ดํ„ฐ ์ „์ฒ˜๋ฆฌ ํ•จ์ˆ˜.
83
+
84
+ Args:
85
+ df: ์›๋ณธ ๋ฐ์ดํ„ฐํ”„๋ ˆ์ž„
86
+
87
+ Returns:
88
+ ์ „์ฒ˜๋ฆฌ๋œ ๋ฐ์ดํ„ฐํ”„๋ ˆ์ž„
89
+ """
90
+ df = df[df.columns].copy()
91
+ df['year'] = df['year'].astype('int')
92
+ df['month'] = df['month'].astype('int')
93
+ df['hour'] = df['hour'].astype('int')
94
+ df = add_derived_features(df).copy()
95
+ df['multi_class'] = df['multi_class'].astype('int')
96
+ df.loc[df['wind_dir']=='์ •์˜จ', 'wind_dir'] = "0"
97
+ df['wind_dir'] = df['wind_dir'].astype('int')
98
+ df = df[['temp_C', 'precip_mm', 'wind_speed', 'wind_dir', 'hm',
99
+ 'vap_pressure', 'dewpoint_C', 'loc_pressure', 'sea_pressure',
100
+ 'solarRad', 'snow_cm', 'cloudcover', 'lm_cloudcover', 'low_cloudbase',
101
+ 'groundtemp', 'O3', 'NO2', 'PM10', 'PM25', 'year',
102
+ 'month', 'hour', 'ground_temp - temp_C', 'hour_sin', 'hour_cos',
103
+ 'month_sin', 'month_cos','multi_class']].copy()
104
+ return df
105
+
106
+
107
+ def split_data(df_sampled, df_original, train_years, val_year):
108
+ """๋ฐ์ดํ„ฐ๋ฅผ ํ•™์Šต์šฉ๊ณผ ๊ฒ€์ฆ์šฉ์œผ๋กœ ๋ถ„ํ• ํ•ฉ๋‹ˆ๋‹ค.
109
+
110
+ Args:
111
+ df_sampled: ์ƒ˜ํ”Œ๋ง๋œ ๋ฐ์ดํ„ฐํ”„๋ ˆ์ž„
112
+ df_original: ์›๋ณธ ๋ฐ์ดํ„ฐํ”„๋ ˆ์ž„
113
+ train_years: ํ•™์Šต์— ์‚ฌ์šฉํ•  ์—ฐ๋„ ๋ฆฌ์ŠคํŠธ
114
+ val_year: ๊ฒ€์ฆ์— ์‚ฌ์šฉํ•  ์—ฐ๋„
115
+
116
+ Returns:
117
+ (X_train, X_val, y_train, y_val) ํŠœํ”Œ
118
+ """
119
+ # ํ•™์Šต ๋ฐ์ดํ„ฐ: ์ƒ˜ํ”Œ๋ง๋œ ๋ฐ์ดํ„ฐ์—์„œ train_years์— ํ•ด๋‹นํ•˜๋Š” ๋ฐ์ดํ„ฐ
120
+ train_mask = df_sampled['year'].isin(train_years)
121
+ X_train = df_sampled.loc[train_mask, df_sampled.columns != 'multi_class'].copy()
122
+ y_train = df_sampled.loc[train_mask, 'multi_class']
123
+
124
+ # ๊ฒ€์ฆ ๋ฐ์ดํ„ฐ: ์›๋ณธ ๋ฐ์ดํ„ฐ์—์„œ val_year์— ํ•ด๋‹นํ•˜๋Š” ๋ฐ์ดํ„ฐ
125
+ val_mask = df_original['year'] == val_year
126
+ X_val = df_original.loc[val_mask, df_original.columns != 'multi_class'].copy()
127
+ y_val = df_original.loc[val_mask, 'multi_class']
128
+
129
+ # 'year' ์ปฌ๋Ÿผ ์ œ๊ฑฐ
130
+ X_train = X_train.drop(columns=['year'])
131
+ X_val = X_val.drop(columns=['year'])
132
+
133
+ return X_train, X_val, y_train, y_val
134
+
135
+
136
+ def create_lgb_model(search_space=None, best_params=None):
137
+ """LightGBM ๋ชจ๋ธ์„ ์ƒ์„ฑํ•ฉ๋‹ˆ๋‹ค.
138
+
139
+ Args:
140
+ search_space: ํ•˜์ดํผํŒŒ๋ผ๋ฏธํ„ฐ ๊ฒ€์ƒ‰ ๊ณต๊ฐ„ (objective_func์—์„œ ์‚ฌ์šฉ)
141
+ best_params: ์ตœ์ ํ™”๋œ ํ•˜์ดํผํŒŒ๋ผ๋ฏธํ„ฐ (์ตœ์ข… ๋ชจ๋ธ ํ•™์Šต์—์„œ ์‚ฌ์šฉ)
142
+
143
+ Returns:
144
+ LGBMClassifier ์ธ์Šคํ„ด์Šค
145
+ """
146
+ base_params = {
147
+ 'n_estimators': N_ESTIMATORS,
148
+ 'device': DEVICE,
149
+ 'objective': OBJECTIVE,
150
+ 'random_state': RANDOM_STATE,
151
+ 'early_stopping_rounds': EARLY_STOPPING_ROUNDS,
152
+ 'verbose': -1,
153
+ }
154
+
155
+ if search_space is not None:
156
+ # ํ•˜์ดํผํŒŒ๋ผ๋ฏธํ„ฐ ์ตœ์ ํ™” ์ค‘
157
+ params = {
158
+ **base_params,
159
+ 'learning_rate': search_space['learning_rate'],
160
+ 'max_depth': int(search_space['max_depth']),
161
+ 'num_leaves': int(search_space['num_leaves']),
162
+ 'min_child_weight': int(search_space['min_child_weight']),
163
+ 'subsample': search_space['subsample'],
164
+ 'colsample_bytree': search_space['colsample_bytree'],
165
+ 'reg_alpha': search_space['reg_alpha'],
166
+ 'reg_lambda': search_space['reg_lambda'],
167
+ }
168
+ elif best_params is not None:
169
+ # ์ตœ์ ํ™”๋œ ํŒŒ๋ผ๋ฏธํ„ฐ๋กœ ์ตœ์ข… ๋ชจ๋ธ ์ƒ์„ฑ
170
+ params = {
171
+ **base_params,
172
+ 'learning_rate': best_params['learning_rate'],
173
+ 'max_depth': int(best_params['max_depth']),
174
+ 'num_leaves': int(best_params['num_leaves']),
175
+ 'min_child_weight': int(best_params['min_child_weight']),
176
+ 'subsample': best_params['subsample'],
177
+ 'colsample_bytree': best_params['colsample_bytree'],
178
+ 'reg_alpha': best_params['reg_alpha'],
179
+ 'reg_lambda': best_params['reg_lambda'],
180
+ }
181
+ else:
182
+ params = base_params
183
+
184
+ return LGBMClassifier(**params)
185
+
186
+ # ๋ฐ์ดํ„ฐ ๋กœ๋”ฉ
187
+ print("๋ฐ์ดํ„ฐ ๋กœ๋”ฉ ์ค‘...")
188
+ # ํŒŒ์ผ ์œ„์น˜ ๊ธฐ๋ฐ˜์œผ๋กœ ๋ฐ์ดํ„ฐ ๋””๋ ‰ํ† ๋ฆฌ ๊ฒฝ๋กœ ์„ค์ •
189
+ current_file_dir = os.path.dirname(os.path.abspath(__file__))
190
+ data_base_dir = os.path.abspath(os.path.join(current_file_dir, '../../../data'))
191
+ df_daejeon = pd.read_csv(os.path.join(data_base_dir, "data_for_modeling/daejeon_train.csv"))
192
+ df_ctgan_daejeon_1 = pd.read_csv(os.path.join(data_base_dir, "data_oversampled/ctgan10000/ctgan10000_1_daejeon.csv"))
193
+ df_ctgan_daejeon_2 = pd.read_csv(os.path.join(data_base_dir, "data_oversampled/ctgan10000/ctgan10000_2_daejeon.csv"))
194
+ df_ctgan_daejeon_3 = pd.read_csv(os.path.join(data_base_dir, "data_oversampled/ctgan10000/ctgan10000_3_daejeon.csv"))
195
+
196
+ # ๋ฐ์ดํ„ฐ ์ „์ฒ˜๋ฆฌ
197
+ print("๋ฐ์ดํ„ฐ ์ „์ฒ˜๋ฆฌ ์ค‘...")
198
+ df_ctgan_daejeon_1 = preprocessing(df_ctgan_daejeon_1)
199
+ df_ctgan_daejeon_2 = preprocessing(df_ctgan_daejeon_2)
200
+ df_ctgan_daejeon_3 = preprocessing(df_ctgan_daejeon_3)
201
+ df_daejeon = preprocessing(df_daejeon)
202
+
203
+ # CTGAN ๋ฐ์ดํ„ฐ ๋ฆฌ์ŠคํŠธ (fold ์ˆœ์„œ์™€ ์ผ์น˜)
204
+ df_ctgan_list = [df_ctgan_daejeon_1, df_ctgan_daejeon_2, df_ctgan_daejeon_3]
205
+
206
+ # ํ•˜์ดํผํŒŒ๋ผ๋ฏธํ„ฐ ๊ฒ€์ƒ‰ ๊ณต๊ฐ„ ์ •์˜
207
+ lgb_search_space = {
208
+ 'learning_rate': hp.loguniform('learning_rate', np.log(0.01), np.log(0.2)),
209
+ 'max_depth': hp.quniform('max_depth', 3, 15, 1),
210
+ 'num_leaves': hp.quniform('num_leaves', 20, 150, 1), # 2^max_depth ๋ณด๋‹ค๋Š” ์ž‘๊ฒŒ
211
+ 'min_child_weight': hp.quniform('min_child_weight', 1, 20, 1),
212
+ 'subsample': hp.uniform('subsample', 0.6, 1.0),
213
+ 'colsample_bytree': hp.uniform('colsample_bytree', 0.6, 1.0),
214
+ 'reg_alpha': hp.uniform('reg_alpha', 0.0, 1.0),
215
+ 'reg_lambda': hp.uniform('reg_lambda', 0.0, 1.0)
216
+ }
217
+
218
+
219
+ def objective_func(search_space):
220
+ """ํ•˜์ดํผํŒŒ๋ผ๋ฏธํ„ฐ ์ตœ์ ํ™”๋ฅผ ์œ„ํ•œ ๋ชฉ์  ํ•จ์ˆ˜.
221
+
222
+ Args:
223
+ search_space: ํ•˜์ดํผํŒŒ๋ผ๋ฏธํ„ฐ ๊ฒ€์ƒ‰ ๊ณต๊ฐ„
224
+
225
+ Returns:
226
+ ํ‰๊ท  CSI ์ ์ˆ˜์˜ ์Œ์ˆ˜๊ฐ’ (hyperopt๋Š” ์ตœ์†Œํ™”๋ฅผ ์ˆ˜ํ–‰ํ•˜๋ฏ€๋กœ)
227
+ """
228
+ lgb_model = create_lgb_model(search_space=search_space)
229
+ csi_scores = []
230
+
231
+ # ๊ฐ fold์— ๋Œ€ํ•ด ๊ต์ฐจ ๊ฒ€์ฆ ์ˆ˜ํ–‰
232
+ for df_ctgan, (train_years, val_year) in zip(df_ctgan_list, FOLD_CONFIGS):
233
+ X_train, X_val, y_train, y_val = split_data(
234
+ df_ctgan, df_daejeon, train_years, val_year
235
+ )
236
+
237
+ lgb_model.fit(
238
+ X_train, y_train,
239
+ eval_set=[(X_val, y_val)],
240
+ eval_metric=csi_metric
241
+ )
242
+
243
+ csi = calculate_csi(y_val, lgb_model.predict(X_val))
244
+ csi_scores.append(csi)
245
+
246
+ # ํ‰๊ท  CSI์˜ ์Œ์ˆ˜๊ฐ’ ๋ฐ˜ํ™˜ (hyperopt๋Š” ์ตœ์†Œํ™”๋ฅผ ์ˆ˜ํ–‰)
247
+ return -1 * round(np.mean(csi_scores), 4)
248
+
249
+
250
+ # ํ•˜์ดํผํŒŒ๋ผ๋ฏธํ„ฐ ์ตœ์ ํ™”
251
+ print("ํ•˜์ดํผํŒŒ๋ผ๋ฏธํ„ฐ ์ตœ์ ํ™” ์‹œ์ž‘...")
252
+ trials = Trials()
253
+ lgb_best = fmin(
254
+ fn=objective_func,
255
+ space=lgb_search_space,
256
+ algo=tpe.suggest,
257
+ max_evals=MAX_EVALS,
258
+ trials=trials
259
+ )
260
+
261
+ # ์ตœ์ ํ™” ๊ฒฐ๊ณผ ๋ถ„์„ ๋ฐ ์ถœ๋ ฅ
262
+ print(f"\n์ตœ์ ํ™” ์™„๋ฃŒ. ์ตœ์  ํŒŒ๋ผ๋ฏธํ„ฐ: {lgb_best}")
263
+
264
+ # Best loss (CSI ์ ์ˆ˜์˜ ์Œ์ˆ˜๊ฐ’์ด๋ฏ€๋กœ, ์‹ค์ œ CSI๋Š” -loss)
265
+ best_loss = trials.best_trial['result']['loss']
266
+ best_csi = -best_loss
267
+ print(f"์ตœ์  CSI ์ ์ˆ˜: {best_csi:.4f} (loss: {best_loss:.4f})")
268
+
269
+ # ๋ชจ๋“  trial์˜ loss ๊ฐ’ ์ถ”์ถœ
270
+ losses = [trial['result']['loss'] for trial in trials.trials if trial['result']['status'] == 'ok']
271
+ csi_scores = [-loss for loss in losses]
272
+
273
+ print(f"\n์ตœ์ ํ™” ๊ณผ์ • ์š”์•ฝ:")
274
+ print(f" - ์ด ์‹œ๋„ ํšŸ์ˆ˜: {len(trials.trials)}")
275
+ print(f" - ์„ฑ๊ณตํ•œ ์‹œ๋„: {len(losses)}")
276
+ print(f" - ์ตœ์ดˆ CSI: {csi_scores[0]:.4f}")
277
+ print(f" - ์ตœ์ข… CSI: {csi_scores[-1]:.4f}")
278
+ print(f" - ์ตœ๊ณ  CSI: {max(csi_scores):.4f}")
279
+ print(f" - ์ตœ์ € CSI: {min(csi_scores):.4f}")
280
+ print(f" - ํ‰๊ท  CSI: {np.mean(csi_scores):.4f}")
281
+
282
+ # Trials ๊ฐ์ฒด ์ €์žฅ
283
+ import os
284
+ base_dir = os.path.dirname(os.path.dirname(current_file_dir)) # 5.optima ๏ฟฝ๏ฟฝ๏ฟฝ๋ ‰ํ† ๋ฆฌ
285
+ os.makedirs(os.path.join(base_dir, "optimization_history"), exist_ok=True)
286
+ trials_path = os.path.join(base_dir, "optimization_history/lgb_ctgan10000_daejeon_trials.pkl")
287
+ joblib.dump(trials, trials_path)
288
+ print(f"\n์ตœ์ ํ™” Trials ๊ฐ์ฒด๊ฐ€ {trials_path}์— ์ €์žฅ๋˜์—ˆ์Šต๋‹ˆ๋‹ค.")
289
+
290
+ # ์ตœ์ ํ™”๋œ ํ•˜์ดํผํŒŒ๋ผ๋ฏธํ„ฐ๋กœ ์ตœ์ข… ๋ชจ๋ธ ํ•™์Šต
291
+ print("์ตœ์ข… ๋ชจ๋ธ ํ•™์Šต ์‹œ์ž‘...")
292
+ models = []
293
+
294
+ for fold_idx, (df_ctgan, (train_years, val_year)) in enumerate(
295
+ zip(df_ctgan_list, FOLD_CONFIGS), start=1
296
+ ):
297
+ print(f"Fold {fold_idx} ํ•™์Šต ์ค‘... (ํ•™์Šต ์—ฐ๋„: {train_years}, ๊ฒ€์ฆ ์—ฐ๋„: {val_year})")
298
+
299
+ X_train, X_val, y_train, y_val = split_data(
300
+ df_ctgan, df_daejeon, train_years, val_year
301
+ )
302
+
303
+ lgb_model = create_lgb_model(best_params=lgb_best)
304
+ lgb_model.fit(X_train, y_train, eval_set=[(X_val, y_val)])
305
+
306
+ # ๊ฒ€์ฆ ์„ฑ๋Šฅ ์ถœ๋ ฅ
307
+ val_csi = calculate_csi(y_val, lgb_model.predict(X_val))
308
+ print(f"Fold {fold_idx} ๊ฒ€์ฆ CSI: {val_csi:.4f}")
309
+
310
+ models.append(lgb_model)
311
+
312
+ # ๋ชจ๋ธ ์ €์žฅ
313
+ print("๋ชจ๋ธ ์ €์žฅ ์ค‘...")
314
+ model_save_path = os.path.join(base_dir, "save_model/lgb_optima/lgb_ctgan10000_daejeon.pkl")
315
+ joblib.dump(models, model_save_path)
316
+ print(f"๋ชจ๋ธ์ด {model_save_path}์— ์ €์žฅ๋˜์—ˆ์Šต๋‹ˆ๋‹ค.")
317
+
Analysis_code/5.optima/lgb_ctgan10000/LGB_ctgan10000_gwangju.py ADDED
@@ -0,0 +1,317 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ import pandas as pd
2
+ import numpy as np
3
+ import joblib
4
+ import os
5
+ from warnings import filterwarnings
6
+ from sklearn.metrics import confusion_matrix
7
+ from lightgbm import LGBMClassifier
8
+ from hyperopt import fmin, tpe, Trials, hp
9
+
10
+ filterwarnings('ignore')
11
+
12
+ # ์ƒ์ˆ˜ ์ •์˜
13
+ RANDOM_STATE = 42
14
+ N_ESTIMATORS = 4000
15
+ EARLY_STOPPING_ROUNDS = 400
16
+ MAX_EVALS = 100
17
+ DEVICE = 'gpu'
18
+ OBJECTIVE = 'multiclassova'
19
+
20
+ # Fold ์„ค์ •: (train_years, val_year)
21
+ FOLD_CONFIGS = [
22
+ ([2018, 2019], 2020), # Fold 1
23
+ ([2018, 2020], 2019), # Fold 2
24
+ ([2019, 2020], 2018), # Fold 3
25
+ ]
26
+
27
+ def calculate_csi(y_true, y_pred):
28
+ """CSI(Critical Success Index) ์ ์ˆ˜๋ฅผ ๊ณ„์‚ฐํ•ฉ๋‹ˆ๋‹ค.
29
+
30
+ Args:
31
+ y_true: ์‹ค์ œ ๋ ˆ์ด๋ธ”
32
+ y_pred: ์˜ˆ์ธก ๋ ˆ์ด๋ธ”
33
+
34
+ Returns:
35
+ CSI ์ ์ˆ˜ (0~1 ์‚ฌ์ด์˜ ๊ฐ’)
36
+ """
37
+ cm = confusion_matrix(y_true, y_pred)
38
+
39
+ # ํ˜ผ๋™ ํ–‰๋ ฌ์—์„œ H(Hit), F(False alarm), M(Miss) ์ถ”์ถœ
40
+ H = cm[0, 0] + cm[1, 1]
41
+ F = cm[1, 0] + cm[2, 0] + cm[0, 1] + cm[2, 1]
42
+ M = cm[0, 2] + cm[1, 2]
43
+
44
+ # CSI ๊ณ„์‚ฐ
45
+ csi = H / (H + F + M + 1e-10)
46
+ return csi
47
+
48
+
49
+ def csi_metric(y_true, pred_prob):
50
+ """LightGBM์šฉ CSI ๋ฉ”ํŠธ๋ฆญ ํ•จ์ˆ˜.
51
+
52
+ Args:
53
+ y_true: ์‹ค์ œ ๋ ˆ์ด๋ธ”
54
+ pred_prob: ์˜ˆ์ธก ํ™•๋ฅ  (shape: [n_samples, n_classes])
55
+
56
+ Returns:
57
+ ('CSI', score, higher_better) ํŠœํ”Œ
58
+ """
59
+ y_pred_binary = np.argmax(pred_prob, axis=1)
60
+ score = calculate_csi(y_true, y_pred_binary)
61
+ return 'CSI', score, True
62
+
63
+ def add_derived_features(df: pd.DataFrame) -> pd.DataFrame:
64
+ """
65
+ ์ œ๊ฑฐํ–ˆ๋˜ ํŒŒ์ƒ ๋ณ€์ˆ˜๋“ค์„ ๋ณต๊ตฌ
66
+
67
+ Args:
68
+ df: ๋ฐ์ดํ„ฐํ”„๋ ˆ์ž„
69
+
70
+ Returns:
71
+ ํŒŒ์ƒ ๋ณ€์ˆ˜๊ฐ€ ์ถ”๊ฐ€๋œ ๋ฐ์ดํ„ฐํ”„๋ ˆ์ž„
72
+ """
73
+ df = df.copy()
74
+ df['hour_sin'] = np.sin(2 * np.pi * df['hour'] / 24)
75
+ df['hour_cos'] = np.cos(2 * np.pi * df['hour'] / 24)
76
+ df['month_sin'] = np.sin(2 * np.pi * df['month'] / 12)
77
+ df['month_cos'] = np.cos(2 * np.pi * df['month'] / 12)
78
+ df['ground_temp - temp_C'] = df['groundtemp'] - df['temp_C']
79
+ return df
80
+
81
+ def preprocessing(df):
82
+ """๋ฐ์ดํ„ฐ ์ „์ฒ˜๋ฆฌ ํ•จ์ˆ˜.
83
+
84
+ Args:
85
+ df: ์›๋ณธ ๋ฐ์ดํ„ฐํ”„๋ ˆ์ž„
86
+
87
+ Returns:
88
+ ์ „์ฒ˜๋ฆฌ๋œ ๋ฐ์ดํ„ฐํ”„๋ ˆ์ž„
89
+ """
90
+ df = df[df.columns].copy()
91
+ df['year'] = df['year'].astype('int')
92
+ df['month'] = df['month'].astype('int')
93
+ df['hour'] = df['hour'].astype('int')
94
+ df = add_derived_features(df).copy()
95
+ df['multi_class'] = df['multi_class'].astype('int')
96
+ df.loc[df['wind_dir']=='์ •์˜จ', 'wind_dir'] = "0"
97
+ df['wind_dir'] = df['wind_dir'].astype('int')
98
+ df = df[['temp_C', 'precip_mm', 'wind_speed', 'wind_dir', 'hm',
99
+ 'vap_pressure', 'dewpoint_C', 'loc_pressure', 'sea_pressure',
100
+ 'solarRad', 'snow_cm', 'cloudcover', 'lm_cloudcover', 'low_cloudbase',
101
+ 'groundtemp', 'O3', 'NO2', 'PM10', 'PM25', 'year',
102
+ 'month', 'hour', 'ground_temp - temp_C', 'hour_sin', 'hour_cos',
103
+ 'month_sin', 'month_cos','multi_class']].copy()
104
+ return df
105
+
106
+
107
+ def split_data(df_sampled, df_original, train_years, val_year):
108
+ """๋ฐ์ดํ„ฐ๋ฅผ ํ•™์Šต์šฉ๊ณผ ๊ฒ€์ฆ์šฉ์œผ๋กœ ๋ถ„ํ• ํ•ฉ๋‹ˆ๋‹ค.
109
+
110
+ Args:
111
+ df_sampled: ์ƒ˜ํ”Œ๋ง๋œ ๋ฐ์ดํ„ฐํ”„๋ ˆ์ž„
112
+ df_original: ์›๋ณธ ๋ฐ์ดํ„ฐํ”„๋ ˆ์ž„
113
+ train_years: ํ•™์Šต์— ์‚ฌ์šฉํ•  ์—ฐ๋„ ๋ฆฌ์ŠคํŠธ
114
+ val_year: ๊ฒ€์ฆ์— ์‚ฌ์šฉํ•  ์—ฐ๋„
115
+
116
+ Returns:
117
+ (X_train, X_val, y_train, y_val) ํŠœํ”Œ
118
+ """
119
+ # ํ•™์Šต ๋ฐ์ดํ„ฐ: ์ƒ˜ํ”Œ๋ง๋œ ๋ฐ์ดํ„ฐ์—์„œ train_years์— ํ•ด๋‹นํ•˜๋Š” ๋ฐ์ดํ„ฐ
120
+ train_mask = df_sampled['year'].isin(train_years)
121
+ X_train = df_sampled.loc[train_mask, df_sampled.columns != 'multi_class'].copy()
122
+ y_train = df_sampled.loc[train_mask, 'multi_class']
123
+
124
+ # ๊ฒ€์ฆ ๋ฐ์ดํ„ฐ: ์›๋ณธ ๋ฐ์ดํ„ฐ์—์„œ val_year์— ํ•ด๋‹นํ•˜๋Š” ๋ฐ์ดํ„ฐ
125
+ val_mask = df_original['year'] == val_year
126
+ X_val = df_original.loc[val_mask, df_original.columns != 'multi_class'].copy()
127
+ y_val = df_original.loc[val_mask, 'multi_class']
128
+
129
+ # 'year' ์ปฌ๋Ÿผ ์ œ๊ฑฐ
130
+ X_train = X_train.drop(columns=['year'])
131
+ X_val = X_val.drop(columns=['year'])
132
+
133
+ return X_train, X_val, y_train, y_val
134
+
135
+
136
+ def create_lgb_model(search_space=None, best_params=None):
137
+ """LightGBM ๋ชจ๋ธ์„ ์ƒ์„ฑํ•ฉ๋‹ˆ๋‹ค.
138
+
139
+ Args:
140
+ search_space: ํ•˜์ดํผํŒŒ๋ผ๋ฏธํ„ฐ ๊ฒ€์ƒ‰ ๊ณต๊ฐ„ (objective_func์—์„œ ์‚ฌ์šฉ)
141
+ best_params: ์ตœ์ ํ™”๋œ ํ•˜์ดํผํŒŒ๋ผ๋ฏธํ„ฐ (์ตœ์ข… ๋ชจ๋ธ ํ•™์Šต์—์„œ ์‚ฌ์šฉ)
142
+
143
+ Returns:
144
+ LGBMClassifier ์ธ์Šคํ„ด์Šค
145
+ """
146
+ base_params = {
147
+ 'n_estimators': N_ESTIMATORS,
148
+ 'device': DEVICE,
149
+ 'objective': OBJECTIVE,
150
+ 'random_state': RANDOM_STATE,
151
+ 'early_stopping_rounds': EARLY_STOPPING_ROUNDS,
152
+ 'verbose': -1,
153
+ }
154
+
155
+ if search_space is not None:
156
+ # ํ•˜์ดํผํŒŒ๋ผ๋ฏธํ„ฐ ์ตœ์ ํ™” ์ค‘
157
+ params = {
158
+ **base_params,
159
+ 'learning_rate': search_space['learning_rate'],
160
+ 'max_depth': int(search_space['max_depth']),
161
+ 'num_leaves': int(search_space['num_leaves']),
162
+ 'min_child_weight': int(search_space['min_child_weight']),
163
+ 'subsample': search_space['subsample'],
164
+ 'colsample_bytree': search_space['colsample_bytree'],
165
+ 'reg_alpha': search_space['reg_alpha'],
166
+ 'reg_lambda': search_space['reg_lambda'],
167
+ }
168
+ elif best_params is not None:
169
+ # ์ตœ์ ํ™”๋œ ํŒŒ๋ผ๋ฏธํ„ฐ๋กœ ์ตœ์ข… ๋ชจ๋ธ ์ƒ์„ฑ
170
+ params = {
171
+ **base_params,
172
+ 'learning_rate': best_params['learning_rate'],
173
+ 'max_depth': int(best_params['max_depth']),
174
+ 'num_leaves': int(best_params['num_leaves']),
175
+ 'min_child_weight': int(best_params['min_child_weight']),
176
+ 'subsample': best_params['subsample'],
177
+ 'colsample_bytree': best_params['colsample_bytree'],
178
+ 'reg_alpha': best_params['reg_alpha'],
179
+ 'reg_lambda': best_params['reg_lambda'],
180
+ }
181
+ else:
182
+ params = base_params
183
+
184
+ return LGBMClassifier(**params)
185
+
186
+ # ๋ฐ์ดํ„ฐ ๋กœ๋”ฉ
187
+ print("๋ฐ์ดํ„ฐ ๋กœ๋”ฉ ์ค‘...")
188
+ # ํŒŒ์ผ ์œ„์น˜ ๊ธฐ๋ฐ˜์œผ๋กœ ๋ฐ์ดํ„ฐ ๋””๋ ‰ํ† ๋ฆฌ ๊ฒฝ๋กœ ์„ค์ •
189
+ current_file_dir = os.path.dirname(os.path.abspath(__file__))
190
+ data_base_dir = os.path.abspath(os.path.join(current_file_dir, '../../../data'))
191
+ df_gwangju = pd.read_csv(os.path.join(data_base_dir, "data_for_modeling/gwangju_train.csv"))
192
+ df_ctgan_gwangju_1 = pd.read_csv(os.path.join(data_base_dir, "data_oversampled/ctgan10000/ctgan10000_1_gwangju.csv"))
193
+ df_ctgan_gwangju_2 = pd.read_csv(os.path.join(data_base_dir, "data_oversampled/ctgan10000/ctgan10000_2_gwangju.csv"))
194
+ df_ctgan_gwangju_3 = pd.read_csv(os.path.join(data_base_dir, "data_oversampled/ctgan10000/ctgan10000_3_gwangju.csv"))
195
+
196
+ # ๋ฐ์ดํ„ฐ ์ „์ฒ˜๋ฆฌ
197
+ print("๋ฐ์ดํ„ฐ ์ „์ฒ˜๋ฆฌ ์ค‘...")
198
+ df_ctgan_gwangju_1 = preprocessing(df_ctgan_gwangju_1)
199
+ df_ctgan_gwangju_2 = preprocessing(df_ctgan_gwangju_2)
200
+ df_ctgan_gwangju_3 = preprocessing(df_ctgan_gwangju_3)
201
+ df_gwangju = preprocessing(df_gwangju)
202
+
203
+ # CTGAN ๋ฐ์ดํ„ฐ ๋ฆฌ์ŠคํŠธ (fold ์ˆœ์„œ์™€ ์ผ์น˜)
204
+ df_ctgan_list = [df_ctgan_gwangju_1, df_ctgan_gwangju_2, df_ctgan_gwangju_3]
205
+
206
+ # ํ•˜์ดํผํŒŒ๋ผ๋ฏธํ„ฐ ๊ฒ€์ƒ‰ ๊ณต๊ฐ„ ์ •์˜
207
+ lgb_search_space = {
208
+ 'learning_rate': hp.loguniform('learning_rate', np.log(0.01), np.log(0.2)),
209
+ 'max_depth': hp.quniform('max_depth', 3, 15, 1),
210
+ 'num_leaves': hp.quniform('num_leaves', 20, 150, 1), # 2^max_depth ๋ณด๋‹ค๋Š” ์ž‘๊ฒŒ
211
+ 'min_child_weight': hp.quniform('min_child_weight', 1, 20, 1),
212
+ 'subsample': hp.uniform('subsample', 0.6, 1.0),
213
+ 'colsample_bytree': hp.uniform('colsample_bytree', 0.6, 1.0),
214
+ 'reg_alpha': hp.uniform('reg_alpha', 0.0, 1.0),
215
+ 'reg_lambda': hp.uniform('reg_lambda', 0.0, 1.0)
216
+ }
217
+
218
+
219
+ def objective_func(search_space):
220
+ """ํ•˜์ดํผํŒŒ๋ผ๋ฏธํ„ฐ ์ตœ์ ํ™”๋ฅผ ์œ„ํ•œ ๋ชฉ์  ํ•จ์ˆ˜.
221
+
222
+ Args:
223
+ search_space: ํ•˜์ดํผํŒŒ๋ผ๋ฏธํ„ฐ ๊ฒ€์ƒ‰ ๊ณต๊ฐ„
224
+
225
+ Returns:
226
+ ํ‰๊ท  CSI ์ ์ˆ˜์˜ ์Œ์ˆ˜๊ฐ’ (hyperopt๋Š” ์ตœ์†Œํ™”๋ฅผ ์ˆ˜ํ–‰ํ•˜๋ฏ€๋กœ)
227
+ """
228
+ lgb_model = create_lgb_model(search_space=search_space)
229
+ csi_scores = []
230
+
231
+ # ๊ฐ fold์— ๋Œ€ํ•ด ๊ต์ฐจ ๊ฒ€์ฆ ์ˆ˜ํ–‰
232
+ for df_ctgan, (train_years, val_year) in zip(df_ctgan_list, FOLD_CONFIGS):
233
+ X_train, X_val, y_train, y_val = split_data(
234
+ df_ctgan, df_gwangju, train_years, val_year
235
+ )
236
+
237
+ lgb_model.fit(
238
+ X_train, y_train,
239
+ eval_set=[(X_val, y_val)],
240
+ eval_metric=csi_metric
241
+ )
242
+
243
+ csi = calculate_csi(y_val, lgb_model.predict(X_val))
244
+ csi_scores.append(csi)
245
+
246
+ # ํ‰๊ท  CSI์˜ ์Œ์ˆ˜๊ฐ’ ๋ฐ˜ํ™˜ (hyperopt๋Š” ์ตœ์†Œํ™”๋ฅผ ์ˆ˜ํ–‰)
247
+ return -1 * round(np.mean(csi_scores), 4)
248
+
249
+
250
+ # ํ•˜์ดํผํŒŒ๋ผ๋ฏธํ„ฐ ์ตœ์ ํ™”
251
+ print("ํ•˜์ดํผํŒŒ๋ผ๋ฏธํ„ฐ ์ตœ์ ํ™” ์‹œ์ž‘...")
252
+ trials = Trials()
253
+ lgb_best = fmin(
254
+ fn=objective_func,
255
+ space=lgb_search_space,
256
+ algo=tpe.suggest,
257
+ max_evals=MAX_EVALS,
258
+ trials=trials
259
+ )
260
+
261
+ # ์ตœ์ ํ™” ๊ฒฐ๊ณผ ๋ถ„์„ ๋ฐ ์ถœ๋ ฅ
262
+ print(f"\n์ตœ์ ํ™” ์™„๋ฃŒ. ์ตœ์  ํŒŒ๋ผ๋ฏธํ„ฐ: {lgb_best}")
263
+
264
+ # Best loss (CSI ์ ์ˆ˜์˜ ์Œ์ˆ˜๊ฐ’์ด๋ฏ€๋กœ, ์‹ค์ œ CSI๋Š” -loss)
265
+ best_loss = trials.best_trial['result']['loss']
266
+ best_csi = -best_loss
267
+ print(f"์ตœ์  CSI ์ ์ˆ˜: {best_csi:.4f} (loss: {best_loss:.4f})")
268
+
269
+ # ๋ชจ๋“  trial์˜ loss ๊ฐ’ ์ถ”์ถœ
270
+ losses = [trial['result']['loss'] for trial in trials.trials if trial['result']['status'] == 'ok']
271
+ csi_scores = [-loss for loss in losses]
272
+
273
+ print(f"\n์ตœ์ ํ™” ๊ณผ์ • ์š”์•ฝ:")
274
+ print(f" - ์ด ์‹œ๋„ ํšŸ์ˆ˜: {len(trials.trials)}")
275
+ print(f" - ์„ฑ๊ณตํ•œ ์‹œ๋„: {len(losses)}")
276
+ print(f" - ์ตœ์ดˆ CSI: {csi_scores[0]:.4f}")
277
+ print(f" - ์ตœ์ข… CSI: {csi_scores[-1]:.4f}")
278
+ print(f" - ์ตœ๊ณ  CSI: {max(csi_scores):.4f}")
279
+ print(f" - ์ตœ์ € CSI: {min(csi_scores):.4f}")
280
+ print(f" - ํ‰๊ท  CSI: {np.mean(csi_scores):.4f}")
281
+
282
+ # Trials ๊ฐ์ฒด ์ €์žฅ
283
+ import os
284
+ base_dir = os.path.dirname(os.path.dirname(current_file_dir)) # 5.optima ๏ฟฝ๏ฟฝ๏ฟฝ๋ ‰ํ† ๋ฆฌ
285
+ os.makedirs(os.path.join(base_dir, "optimization_history"), exist_ok=True)
286
+ trials_path = os.path.join(base_dir, "optimization_history/lgb_ctgan10000_gwangju_trials.pkl")
287
+ joblib.dump(trials, trials_path)
288
+ print(f"\n์ตœ์ ํ™” Trials ๊ฐ์ฒด๊ฐ€ {trials_path}์— ์ €์žฅ๋˜์—ˆ์Šต๋‹ˆ๋‹ค.")
289
+
290
+ # ์ตœ์ ํ™”๋œ ํ•˜์ดํผํŒŒ๋ผ๋ฏธํ„ฐ๋กœ ์ตœ์ข… ๋ชจ๋ธ ํ•™์Šต
291
+ print("์ตœ์ข… ๋ชจ๋ธ ํ•™์Šต ์‹œ์ž‘...")
292
+ models = []
293
+
294
+ for fold_idx, (df_ctgan, (train_years, val_year)) in enumerate(
295
+ zip(df_ctgan_list, FOLD_CONFIGS), start=1
296
+ ):
297
+ print(f"Fold {fold_idx} ํ•™์Šต ์ค‘... (ํ•™์Šต ์—ฐ๋„: {train_years}, ๊ฒ€์ฆ ์—ฐ๋„: {val_year})")
298
+
299
+ X_train, X_val, y_train, y_val = split_data(
300
+ df_ctgan, df_gwangju, train_years, val_year
301
+ )
302
+
303
+ lgb_model = create_lgb_model(best_params=lgb_best)
304
+ lgb_model.fit(X_train, y_train, eval_set=[(X_val, y_val)])
305
+
306
+ # ๊ฒ€์ฆ ์„ฑ๋Šฅ ์ถœ๋ ฅ
307
+ val_csi = calculate_csi(y_val, lgb_model.predict(X_val))
308
+ print(f"Fold {fold_idx} ๊ฒ€์ฆ CSI: {val_csi:.4f}")
309
+
310
+ models.append(lgb_model)
311
+
312
+ # ๋ชจ๋ธ ์ €์žฅ
313
+ print("๋ชจ๋ธ ์ €์žฅ ์ค‘...")
314
+ model_save_path = os.path.join(base_dir, "save_model/lgb_optima/lgb_ctgan10000_gwangju.pkl")
315
+ joblib.dump(models, model_save_path)
316
+ print(f"๋ชจ๋ธ์ด {model_save_path}์— ์ €์žฅ๋˜์—ˆ์Šต๋‹ˆ๋‹ค.")
317
+
Analysis_code/5.optima/lgb_ctgan10000/LGB_ctgan10000_incheon.py ADDED
@@ -0,0 +1,317 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ import pandas as pd
2
+ import numpy as np
3
+ import joblib
4
+ import os
5
+ from warnings import filterwarnings
6
+ from sklearn.metrics import confusion_matrix
7
+ from lightgbm import LGBMClassifier
8
+ from hyperopt import fmin, tpe, Trials, hp
9
+
10
+ filterwarnings('ignore')
11
+
12
+ # ์ƒ์ˆ˜ ์ •์˜
13
+ RANDOM_STATE = 42
14
+ N_ESTIMATORS = 4000
15
+ EARLY_STOPPING_ROUNDS = 400
16
+ MAX_EVALS = 100
17
+ DEVICE = 'gpu'
18
+ OBJECTIVE = 'multiclassova'
19
+
20
+ # Fold ์„ค์ •: (train_years, val_year)
21
+ FOLD_CONFIGS = [
22
+ ([2018, 2019], 2020), # Fold 1
23
+ ([2018, 2020], 2019), # Fold 2
24
+ ([2019, 2020], 2018), # Fold 3
25
+ ]
26
+
27
+ def calculate_csi(y_true, y_pred):
28
+ """CSI(Critical Success Index) ์ ์ˆ˜๋ฅผ ๊ณ„์‚ฐํ•ฉ๋‹ˆ๋‹ค.
29
+
30
+ Args:
31
+ y_true: ์‹ค์ œ ๋ ˆ์ด๋ธ”
32
+ y_pred: ์˜ˆ์ธก ๋ ˆ์ด๋ธ”
33
+
34
+ Returns:
35
+ CSI ์ ์ˆ˜ (0~1 ์‚ฌ์ด์˜ ๊ฐ’)
36
+ """
37
+ cm = confusion_matrix(y_true, y_pred)
38
+
39
+ # ํ˜ผ๋™ ํ–‰๋ ฌ์—์„œ H(Hit), F(False alarm), M(Miss) ์ถ”์ถœ
40
+ H = cm[0, 0] + cm[1, 1]
41
+ F = cm[1, 0] + cm[2, 0] + cm[0, 1] + cm[2, 1]
42
+ M = cm[0, 2] + cm[1, 2]
43
+
44
+ # CSI ๊ณ„์‚ฐ
45
+ csi = H / (H + F + M + 1e-10)
46
+ return csi
47
+
48
+
49
+ def csi_metric(y_true, pred_prob):
50
+ """LightGBM์šฉ CSI ๋ฉ”ํŠธ๋ฆญ ํ•จ์ˆ˜.
51
+
52
+ Args:
53
+ y_true: ์‹ค์ œ ๋ ˆ์ด๋ธ”
54
+ pred_prob: ์˜ˆ์ธก ํ™•๋ฅ  (shape: [n_samples, n_classes])
55
+
56
+ Returns:
57
+ ('CSI', score, higher_better) ํŠœํ”Œ
58
+ """
59
+ y_pred_binary = np.argmax(pred_prob, axis=1)
60
+ score = calculate_csi(y_true, y_pred_binary)
61
+ return 'CSI', score, True
62
+
63
+ def add_derived_features(df: pd.DataFrame) -> pd.DataFrame:
64
+ """
65
+ ์ œ๊ฑฐํ–ˆ๋˜ ํŒŒ์ƒ ๋ณ€์ˆ˜๋“ค์„ ๋ณต๊ตฌ
66
+
67
+ Args:
68
+ df: ๋ฐ์ดํ„ฐํ”„๋ ˆ์ž„
69
+
70
+ Returns:
71
+ ํŒŒ์ƒ ๋ณ€์ˆ˜๊ฐ€ ์ถ”๊ฐ€๋œ ๋ฐ์ดํ„ฐํ”„๋ ˆ์ž„
72
+ """
73
+ df = df.copy()
74
+ df['hour_sin'] = np.sin(2 * np.pi * df['hour'] / 24)
75
+ df['hour_cos'] = np.cos(2 * np.pi * df['hour'] / 24)
76
+ df['month_sin'] = np.sin(2 * np.pi * df['month'] / 12)
77
+ df['month_cos'] = np.cos(2 * np.pi * df['month'] / 12)
78
+ df['ground_temp - temp_C'] = df['groundtemp'] - df['temp_C']
79
+ return df
80
+
81
+ def preprocessing(df):
82
+ """๋ฐ์ดํ„ฐ ์ „์ฒ˜๋ฆฌ ํ•จ์ˆ˜.
83
+
84
+ Args:
85
+ df: ์›๋ณธ ๋ฐ์ดํ„ฐํ”„๋ ˆ์ž„
86
+
87
+ Returns:
88
+ ์ „์ฒ˜๋ฆฌ๋œ ๋ฐ์ดํ„ฐํ”„๋ ˆ์ž„
89
+ """
90
+ df = df[df.columns].copy()
91
+ df['year'] = df['year'].astype('int')
92
+ df['month'] = df['month'].astype('int')
93
+ df['hour'] = df['hour'].astype('int')
94
+ df = add_derived_features(df).copy()
95
+ df['multi_class'] = df['multi_class'].astype('int')
96
+ df.loc[df['wind_dir']=='์ •์˜จ', 'wind_dir'] = "0"
97
+ df['wind_dir'] = df['wind_dir'].astype('int')
98
+ df = df[['temp_C', 'precip_mm', 'wind_speed', 'wind_dir', 'hm',
99
+ 'vap_pressure', 'dewpoint_C', 'loc_pressure', 'sea_pressure',
100
+ 'solarRad', 'snow_cm', 'cloudcover', 'lm_cloudcover', 'low_cloudbase',
101
+ 'groundtemp', 'O3', 'NO2', 'PM10', 'PM25', 'year',
102
+ 'month', 'hour', 'ground_temp - temp_C', 'hour_sin', 'hour_cos',
103
+ 'month_sin', 'month_cos','multi_class']].copy()
104
+ return df
105
+
106
+
107
+ def split_data(df_sampled, df_original, train_years, val_year):
108
+ """๋ฐ์ดํ„ฐ๋ฅผ ํ•™์Šต์šฉ๊ณผ ๊ฒ€์ฆ์šฉ์œผ๋กœ ๋ถ„ํ• ํ•ฉ๋‹ˆ๋‹ค.
109
+
110
+ Args:
111
+ df_sampled: ์ƒ˜ํ”Œ๋ง๋œ ๋ฐ์ดํ„ฐํ”„๋ ˆ์ž„
112
+ df_original: ์›๋ณธ ๋ฐ์ดํ„ฐํ”„๋ ˆ์ž„
113
+ train_years: ํ•™์Šต์— ์‚ฌ์šฉํ•  ์—ฐ๋„ ๋ฆฌ์ŠคํŠธ
114
+ val_year: ๊ฒ€์ฆ์— ์‚ฌ์šฉํ•  ์—ฐ๋„
115
+
116
+ Returns:
117
+ (X_train, X_val, y_train, y_val) ํŠœํ”Œ
118
+ """
119
+ # ํ•™์Šต ๋ฐ์ดํ„ฐ: ์ƒ˜ํ”Œ๋ง๋œ ๋ฐ์ดํ„ฐ์—์„œ train_years์— ํ•ด๋‹นํ•˜๋Š” ๋ฐ์ดํ„ฐ
120
+ train_mask = df_sampled['year'].isin(train_years)
121
+ X_train = df_sampled.loc[train_mask, df_sampled.columns != 'multi_class'].copy()
122
+ y_train = df_sampled.loc[train_mask, 'multi_class']
123
+
124
+ # ๊ฒ€์ฆ ๋ฐ์ดํ„ฐ: ์›๋ณธ ๋ฐ์ดํ„ฐ์—์„œ val_year์— ํ•ด๋‹นํ•˜๋Š” ๋ฐ์ดํ„ฐ
125
+ val_mask = df_original['year'] == val_year
126
+ X_val = df_original.loc[val_mask, df_original.columns != 'multi_class'].copy()
127
+ y_val = df_original.loc[val_mask, 'multi_class']
128
+
129
+ # 'year' ์ปฌ๋Ÿผ ์ œ๊ฑฐ
130
+ X_train = X_train.drop(columns=['year'])
131
+ X_val = X_val.drop(columns=['year'])
132
+
133
+ return X_train, X_val, y_train, y_val
134
+
135
+
136
+ def create_lgb_model(search_space=None, best_params=None):
137
+ """LightGBM ๋ชจ๋ธ์„ ์ƒ์„ฑํ•ฉ๋‹ˆ๋‹ค.
138
+
139
+ Args:
140
+ search_space: ํ•˜์ดํผํŒŒ๋ผ๋ฏธํ„ฐ ๊ฒ€์ƒ‰ ๊ณต๊ฐ„ (objective_func์—์„œ ์‚ฌ์šฉ)
141
+ best_params: ์ตœ์ ํ™”๋œ ํ•˜์ดํผํŒŒ๋ผ๋ฏธํ„ฐ (์ตœ์ข… ๋ชจ๋ธ ํ•™์Šต์—์„œ ์‚ฌ์šฉ)
142
+
143
+ Returns:
144
+ LGBMClassifier ์ธ์Šคํ„ด์Šค
145
+ """
146
+ base_params = {
147
+ 'n_estimators': N_ESTIMATORS,
148
+ 'device': DEVICE,
149
+ 'objective': OBJECTIVE,
150
+ 'random_state': RANDOM_STATE,
151
+ 'early_stopping_rounds': EARLY_STOPPING_ROUNDS,
152
+ 'verbose': -1,
153
+ }
154
+
155
+ if search_space is not None:
156
+ # ํ•˜์ดํผํŒŒ๋ผ๋ฏธํ„ฐ ์ตœ์ ํ™” ์ค‘
157
+ params = {
158
+ **base_params,
159
+ 'learning_rate': search_space['learning_rate'],
160
+ 'max_depth': int(search_space['max_depth']),
161
+ 'num_leaves': int(search_space['num_leaves']),
162
+ 'min_child_weight': int(search_space['min_child_weight']),
163
+ 'subsample': search_space['subsample'],
164
+ 'colsample_bytree': search_space['colsample_bytree'],
165
+ 'reg_alpha': search_space['reg_alpha'],
166
+ 'reg_lambda': search_space['reg_lambda'],
167
+ }
168
+ elif best_params is not None:
169
+ # ์ตœ์ ํ™”๋œ ํŒŒ๋ผ๋ฏธํ„ฐ๋กœ ์ตœ์ข… ๋ชจ๋ธ ์ƒ์„ฑ
170
+ params = {
171
+ **base_params,
172
+ 'learning_rate': best_params['learning_rate'],
173
+ 'max_depth': int(best_params['max_depth']),
174
+ 'num_leaves': int(best_params['num_leaves']),
175
+ 'min_child_weight': int(best_params['min_child_weight']),
176
+ 'subsample': best_params['subsample'],
177
+ 'colsample_bytree': best_params['colsample_bytree'],
178
+ 'reg_alpha': best_params['reg_alpha'],
179
+ 'reg_lambda': best_params['reg_lambda'],
180
+ }
181
+ else:
182
+ params = base_params
183
+
184
+ return LGBMClassifier(**params)
185
+
186
+ # ๋ฐ์ดํ„ฐ ๋กœ๋”ฉ
187
+ print("๋ฐ์ดํ„ฐ ๋กœ๋”ฉ ์ค‘...")
188
+ # ํŒŒ์ผ ์œ„์น˜ ๊ธฐ๋ฐ˜์œผ๋กœ ๋ฐ์ดํ„ฐ ๋””๋ ‰ํ† ๋ฆฌ ๊ฒฝ๋กœ ์„ค์ •
189
+ current_file_dir = os.path.dirname(os.path.abspath(__file__))
190
+ data_base_dir = os.path.abspath(os.path.join(current_file_dir, '../../../data'))
191
+ df_incheon = pd.read_csv(os.path.join(data_base_dir, "data_for_modeling/incheon_train.csv"))
192
+ df_ctgan_incheon_1 = pd.read_csv(os.path.join(data_base_dir, "data_oversampled/ctgan10000/ctgan10000_1_incheon.csv"))
193
+ df_ctgan_incheon_2 = pd.read_csv(os.path.join(data_base_dir, "data_oversampled/ctgan10000/ctgan10000_2_incheon.csv"))
194
+ df_ctgan_incheon_3 = pd.read_csv(os.path.join(data_base_dir, "data_oversampled/ctgan10000/ctgan10000_3_incheon.csv"))
195
+
196
+ # ๋ฐ์ดํ„ฐ ์ „์ฒ˜๋ฆฌ
197
+ print("๋ฐ์ดํ„ฐ ์ „์ฒ˜๋ฆฌ ์ค‘...")
198
+ df_ctgan_incheon_1 = preprocessing(df_ctgan_incheon_1)
199
+ df_ctgan_incheon_2 = preprocessing(df_ctgan_incheon_2)
200
+ df_ctgan_incheon_3 = preprocessing(df_ctgan_incheon_3)
201
+ df_incheon = preprocessing(df_incheon)
202
+
203
+ # CTGAN ๋ฐ์ดํ„ฐ ๋ฆฌ์ŠคํŠธ (fold ์ˆœ์„œ์™€ ์ผ์น˜)
204
+ df_ctgan_list = [df_ctgan_incheon_1, df_ctgan_incheon_2, df_ctgan_incheon_3]
205
+
206
+ # ํ•˜์ดํผํŒŒ๋ผ๋ฏธํ„ฐ ๊ฒ€์ƒ‰ ๊ณต๊ฐ„ ์ •์˜
207
+ lgb_search_space = {
208
+ 'learning_rate': hp.loguniform('learning_rate', np.log(0.01), np.log(0.2)),
209
+ 'max_depth': hp.quniform('max_depth', 3, 15, 1),
210
+ 'num_leaves': hp.quniform('num_leaves', 20, 150, 1), # 2^max_depth ๋ณด๋‹ค๋Š” ์ž‘๊ฒŒ
211
+ 'min_child_weight': hp.quniform('min_child_weight', 1, 20, 1),
212
+ 'subsample': hp.uniform('subsample', 0.6, 1.0),
213
+ 'colsample_bytree': hp.uniform('colsample_bytree', 0.6, 1.0),
214
+ 'reg_alpha': hp.uniform('reg_alpha', 0.0, 1.0),
215
+ 'reg_lambda': hp.uniform('reg_lambda', 0.0, 1.0)
216
+ }
217
+
218
+
219
+ def objective_func(search_space):
220
+ """ํ•˜์ดํผํŒŒ๋ผ๋ฏธํ„ฐ ์ตœ์ ํ™”๋ฅผ ์œ„ํ•œ ๋ชฉ์  ํ•จ์ˆ˜.
221
+
222
+ Args:
223
+ search_space: ํ•˜์ดํผํŒŒ๋ผ๋ฏธํ„ฐ ๊ฒ€์ƒ‰ ๊ณต๊ฐ„
224
+
225
+ Returns:
226
+ ํ‰๊ท  CSI ์ ์ˆ˜์˜ ์Œ์ˆ˜๊ฐ’ (hyperopt๋Š” ์ตœ์†Œํ™”๋ฅผ ์ˆ˜ํ–‰ํ•˜๋ฏ€๋กœ)
227
+ """
228
+ lgb_model = create_lgb_model(search_space=search_space)
229
+ csi_scores = []
230
+
231
+ # ๊ฐ fold์— ๋Œ€ํ•ด ๊ต์ฐจ ๊ฒ€์ฆ ์ˆ˜ํ–‰
232
+ for df_ctgan, (train_years, val_year) in zip(df_ctgan_list, FOLD_CONFIGS):
233
+ X_train, X_val, y_train, y_val = split_data(
234
+ df_ctgan, df_incheon, train_years, val_year
235
+ )
236
+
237
+ lgb_model.fit(
238
+ X_train, y_train,
239
+ eval_set=[(X_val, y_val)],
240
+ eval_metric=csi_metric
241
+ )
242
+
243
+ csi = calculate_csi(y_val, lgb_model.predict(X_val))
244
+ csi_scores.append(csi)
245
+
246
+ # ํ‰๊ท  CSI์˜ ์Œ์ˆ˜๊ฐ’ ๋ฐ˜ํ™˜ (hyperopt๋Š” ์ตœ์†Œํ™”๋ฅผ ์ˆ˜ํ–‰)
247
+ return -1 * round(np.mean(csi_scores), 4)
248
+
249
+
250
+ # ํ•˜์ดํผํŒŒ๋ผ๋ฏธํ„ฐ ์ตœ์ ํ™”
251
+ print("ํ•˜์ดํผํŒŒ๋ผ๋ฏธํ„ฐ ์ตœ์ ํ™” ์‹œ์ž‘...")
252
+ trials = Trials()
253
+ lgb_best = fmin(
254
+ fn=objective_func,
255
+ space=lgb_search_space,
256
+ algo=tpe.suggest,
257
+ max_evals=MAX_EVALS,
258
+ trials=trials
259
+ )
260
+
261
+ # ์ตœ์ ํ™” ๊ฒฐ๊ณผ ๋ถ„์„ ๋ฐ ์ถœ๋ ฅ
262
+ print(f"\n์ตœ์ ํ™” ์™„๋ฃŒ. ์ตœ์  ํŒŒ๋ผ๋ฏธํ„ฐ: {lgb_best}")
263
+
264
+ # Best loss (CSI ์ ์ˆ˜์˜ ์Œ์ˆ˜๊ฐ’์ด๋ฏ€๋กœ, ์‹ค์ œ CSI๋Š” -loss)
265
+ best_loss = trials.best_trial['result']['loss']
266
+ best_csi = -best_loss
267
+ print(f"์ตœ์  CSI ์ ์ˆ˜: {best_csi:.4f} (loss: {best_loss:.4f})")
268
+
269
+ # ๋ชจ๋“  trial์˜ loss ๊ฐ’ ์ถ”์ถœ
270
+ losses = [trial['result']['loss'] for trial in trials.trials if trial['result']['status'] == 'ok']
271
+ csi_scores = [-loss for loss in losses]
272
+
273
+ print(f"\n์ตœ์ ํ™” ๊ณผ์ • ์š”์•ฝ:")
274
+ print(f" - ์ด ์‹œ๋„ ํšŸ์ˆ˜: {len(trials.trials)}")
275
+ print(f" - ์„ฑ๊ณตํ•œ ์‹œ๋„: {len(losses)}")
276
+ print(f" - ์ตœ์ดˆ CSI: {csi_scores[0]:.4f}")
277
+ print(f" - ์ตœ์ข… CSI: {csi_scores[-1]:.4f}")
278
+ print(f" - ์ตœ๊ณ  CSI: {max(csi_scores):.4f}")
279
+ print(f" - ์ตœ์ € CSI: {min(csi_scores):.4f}")
280
+ print(f" - ํ‰๊ท  CSI: {np.mean(csi_scores):.4f}")
281
+
282
+ # Trials ๊ฐ์ฒด ์ €์žฅ
283
+ import os
284
+ base_dir = os.path.dirname(os.path.dirname(current_file_dir)) # 5.optima ๏ฟฝ๏ฟฝ๏ฟฝ๋ ‰ํ† ๋ฆฌ
285
+ os.makedirs(os.path.join(base_dir, "optimization_history"), exist_ok=True)
286
+ trials_path = os.path.join(base_dir, "optimization_history/lgb_ctgan10000_incheon_trials.pkl")
287
+ joblib.dump(trials, trials_path)
288
+ print(f"\n์ตœ์ ํ™” Trials ๊ฐ์ฒด๊ฐ€ {trials_path}์— ์ €์žฅ๋˜์—ˆ์Šต๋‹ˆ๋‹ค.")
289
+
290
+ # ์ตœ์ ํ™”๋œ ํ•˜์ดํผํŒŒ๋ผ๋ฏธํ„ฐ๋กœ ์ตœ์ข… ๋ชจ๋ธ ํ•™์Šต
291
+ print("์ตœ์ข… ๋ชจ๋ธ ํ•™์Šต ์‹œ์ž‘...")
292
+ models = []
293
+
294
+ for fold_idx, (df_ctgan, (train_years, val_year)) in enumerate(
295
+ zip(df_ctgan_list, FOLD_CONFIGS), start=1
296
+ ):
297
+ print(f"Fold {fold_idx} ํ•™์Šต ์ค‘... (ํ•™์Šต ์—ฐ๋„: {train_years}, ๊ฒ€์ฆ ์—ฐ๋„: {val_year})")
298
+
299
+ X_train, X_val, y_train, y_val = split_data(
300
+ df_ctgan, df_incheon, train_years, val_year
301
+ )
302
+
303
+ lgb_model = create_lgb_model(best_params=lgb_best)
304
+ lgb_model.fit(X_train, y_train, eval_set=[(X_val, y_val)])
305
+
306
+ # ๊ฒ€์ฆ ์„ฑ๋Šฅ ์ถœ๋ ฅ
307
+ val_csi = calculate_csi(y_val, lgb_model.predict(X_val))
308
+ print(f"Fold {fold_idx} ๊ฒ€์ฆ CSI: {val_csi:.4f}")
309
+
310
+ models.append(lgb_model)
311
+
312
+ # ๋ชจ๋ธ ์ €์žฅ
313
+ print("๋ชจ๋ธ ์ €์žฅ ์ค‘...")
314
+ model_save_path = os.path.join(base_dir, "save_model/lgb_optima/lgb_ctgan10000_incheon.pkl")
315
+ joblib.dump(models, model_save_path)
316
+ print(f"๋ชจ๋ธ์ด {model_save_path}์— ์ €์žฅ๋˜์—ˆ์Šต๋‹ˆ๋‹ค.")
317
+
Analysis_code/5.optima/lgb_ctgan10000/LGB_ctgan10000_seoul.py ADDED
@@ -0,0 +1,317 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ import pandas as pd
2
+ import numpy as np
3
+ import joblib
4
+ import os
5
+ from warnings import filterwarnings
6
+ from sklearn.metrics import confusion_matrix
7
+ from lightgbm import LGBMClassifier
8
+ from hyperopt import fmin, tpe, Trials, hp
9
+
10
+ filterwarnings('ignore')
11
+
12
+ # ์ƒ์ˆ˜ ์ •์˜
13
+ RANDOM_STATE = 42
14
+ N_ESTIMATORS = 4000
15
+ EARLY_STOPPING_ROUNDS = 400
16
+ MAX_EVALS = 100
17
+ DEVICE = 'gpu'
18
+ OBJECTIVE = 'multiclassova'
19
+
20
+ # Fold ์„ค์ •: (train_years, val_year)
21
+ FOLD_CONFIGS = [
22
+ ([2018, 2019], 2020), # Fold 1
23
+ ([2018, 2020], 2019), # Fold 2
24
+ ([2019, 2020], 2018), # Fold 3
25
+ ]
26
+
27
+ def calculate_csi(y_true, y_pred):
28
+ """CSI(Critical Success Index) ์ ์ˆ˜๋ฅผ ๊ณ„์‚ฐํ•ฉ๋‹ˆ๋‹ค.
29
+
30
+ Args:
31
+ y_true: ์‹ค์ œ ๋ ˆ์ด๋ธ”
32
+ y_pred: ์˜ˆ์ธก ๋ ˆ์ด๋ธ”
33
+
34
+ Returns:
35
+ CSI ์ ์ˆ˜ (0~1 ์‚ฌ์ด์˜ ๊ฐ’)
36
+ """
37
+ cm = confusion_matrix(y_true, y_pred)
38
+
39
+ # ํ˜ผ๋™ ํ–‰๋ ฌ์—์„œ H(Hit), F(False alarm), M(Miss) ์ถ”์ถœ
40
+ H = cm[0, 0] + cm[1, 1]
41
+ F = cm[1, 0] + cm[2, 0] + cm[0, 1] + cm[2, 1]
42
+ M = cm[0, 2] + cm[1, 2]
43
+
44
+ # CSI ๊ณ„์‚ฐ
45
+ csi = H / (H + F + M + 1e-10)
46
+ return csi
47
+
48
+
49
+ def csi_metric(y_true, pred_prob):
50
+ """LightGBM์šฉ CSI ๋ฉ”ํŠธ๋ฆญ ํ•จ์ˆ˜.
51
+
52
+ Args:
53
+ y_true: ์‹ค์ œ ๋ ˆ์ด๋ธ”
54
+ pred_prob: ์˜ˆ์ธก ํ™•๋ฅ  (shape: [n_samples, n_classes])
55
+
56
+ Returns:
57
+ ('CSI', score, higher_better) ํŠœํ”Œ
58
+ """
59
+ y_pred_binary = np.argmax(pred_prob, axis=1)
60
+ score = calculate_csi(y_true, y_pred_binary)
61
+ return 'CSI', score, True
62
+
63
+ def add_derived_features(df: pd.DataFrame) -> pd.DataFrame:
64
+ """
65
+ ์ œ๊ฑฐํ–ˆ๋˜ ํŒŒ์ƒ ๋ณ€์ˆ˜๋“ค์„ ๋ณต๊ตฌ
66
+
67
+ Args:
68
+ df: ๋ฐ์ดํ„ฐํ”„๋ ˆ์ž„
69
+
70
+ Returns:
71
+ ํŒŒ์ƒ ๋ณ€์ˆ˜๊ฐ€ ์ถ”๊ฐ€๋œ ๋ฐ์ดํ„ฐํ”„๋ ˆ์ž„
72
+ """
73
+ df = df.copy()
74
+ df['hour_sin'] = np.sin(2 * np.pi * df['hour'] / 24)
75
+ df['hour_cos'] = np.cos(2 * np.pi * df['hour'] / 24)
76
+ df['month_sin'] = np.sin(2 * np.pi * df['month'] / 12)
77
+ df['month_cos'] = np.cos(2 * np.pi * df['month'] / 12)
78
+ df['ground_temp - temp_C'] = df['groundtemp'] - df['temp_C']
79
+ return df
80
+
81
+ def preprocessing(df):
82
+ """๋ฐ์ดํ„ฐ ์ „์ฒ˜๋ฆฌ ํ•จ์ˆ˜.
83
+
84
+ Args:
85
+ df: ์›๋ณธ ๋ฐ์ดํ„ฐํ”„๋ ˆ์ž„
86
+
87
+ Returns:
88
+ ์ „์ฒ˜๋ฆฌ๋œ ๋ฐ์ดํ„ฐํ”„๋ ˆ์ž„
89
+ """
90
+ df = df[df.columns].copy()
91
+ df['year'] = df['year'].astype('int')
92
+ df['month'] = df['month'].astype('int')
93
+ df['hour'] = df['hour'].astype('int')
94
+ df = add_derived_features(df).copy()
95
+ df['multi_class'] = df['multi_class'].astype('int')
96
+ df.loc[df['wind_dir']=='์ •์˜จ', 'wind_dir'] = "0"
97
+ df['wind_dir'] = df['wind_dir'].astype('int')
98
+ df = df[['temp_C', 'precip_mm', 'wind_speed', 'wind_dir', 'hm',
99
+ 'vap_pressure', 'dewpoint_C', 'loc_pressure', 'sea_pressure',
100
+ 'solarRad', 'snow_cm', 'cloudcover', 'lm_cloudcover', 'low_cloudbase',
101
+ 'groundtemp', 'O3', 'NO2', 'PM10', 'PM25', 'year',
102
+ 'month', 'hour', 'ground_temp - temp_C', 'hour_sin', 'hour_cos',
103
+ 'month_sin', 'month_cos','multi_class']].copy()
104
+ return df
105
+
106
+
107
+ def split_data(df_sampled, df_original, train_years, val_year):
108
+ """๋ฐ์ดํ„ฐ๋ฅผ ํ•™์Šต์šฉ๊ณผ ๊ฒ€์ฆ์šฉ์œผ๋กœ ๋ถ„ํ• ํ•ฉ๋‹ˆ๋‹ค.
109
+
110
+ Args:
111
+ df_sampled: ์ƒ˜ํ”Œ๋ง๋œ ๋ฐ์ดํ„ฐํ”„๋ ˆ์ž„
112
+ df_original: ์›๋ณธ ๋ฐ์ดํ„ฐํ”„๋ ˆ์ž„
113
+ train_years: ํ•™์Šต์— ์‚ฌ์šฉํ•  ์—ฐ๋„ ๋ฆฌ์ŠคํŠธ
114
+ val_year: ๊ฒ€์ฆ์— ์‚ฌ์šฉํ•  ์—ฐ๋„
115
+
116
+ Returns:
117
+ (X_train, X_val, y_train, y_val) ํŠœํ”Œ
118
+ """
119
+ # ํ•™์Šต ๋ฐ์ดํ„ฐ: ์ƒ˜ํ”Œ๋ง๋œ ๋ฐ์ดํ„ฐ์—์„œ train_years์— ํ•ด๋‹นํ•˜๋Š” ๋ฐ์ดํ„ฐ
120
+ train_mask = df_sampled['year'].isin(train_years)
121
+ X_train = df_sampled.loc[train_mask, df_sampled.columns != 'multi_class'].copy()
122
+ y_train = df_sampled.loc[train_mask, 'multi_class']
123
+
124
+ # ๊ฒ€์ฆ ๋ฐ์ดํ„ฐ: ์›๋ณธ ๋ฐ์ดํ„ฐ์—์„œ val_year์— ํ•ด๋‹นํ•˜๋Š” ๋ฐ์ดํ„ฐ
125
+ val_mask = df_original['year'] == val_year
126
+ X_val = df_original.loc[val_mask, df_original.columns != 'multi_class'].copy()
127
+ y_val = df_original.loc[val_mask, 'multi_class']
128
+
129
+ # 'year' ์ปฌ๋Ÿผ ์ œ๊ฑฐ
130
+ X_train = X_train.drop(columns=['year'])
131
+ X_val = X_val.drop(columns=['year'])
132
+
133
+ return X_train, X_val, y_train, y_val
134
+
135
+
136
+ def create_lgb_model(search_space=None, best_params=None):
137
+ """LightGBM ๋ชจ๋ธ์„ ์ƒ์„ฑํ•ฉ๋‹ˆ๋‹ค.
138
+
139
+ Args:
140
+ search_space: ํ•˜์ดํผํŒŒ๋ผ๋ฏธํ„ฐ ๊ฒ€์ƒ‰ ๊ณต๊ฐ„ (objective_func์—์„œ ์‚ฌ์šฉ)
141
+ best_params: ์ตœ์ ํ™”๋œ ํ•˜์ดํผํŒŒ๋ผ๋ฏธํ„ฐ (์ตœ์ข… ๋ชจ๋ธ ํ•™์Šต์—์„œ ์‚ฌ์šฉ)
142
+
143
+ Returns:
144
+ LGBMClassifier ์ธ์Šคํ„ด์Šค
145
+ """
146
+ base_params = {
147
+ 'n_estimators': N_ESTIMATORS,
148
+ 'device': DEVICE,
149
+ 'objective': OBJECTIVE,
150
+ 'random_state': RANDOM_STATE,
151
+ 'early_stopping_rounds': EARLY_STOPPING_ROUNDS,
152
+ 'verbose': -1,
153
+ }
154
+
155
+ if search_space is not None:
156
+ # ํ•˜์ดํผํŒŒ๋ผ๋ฏธํ„ฐ ์ตœ์ ํ™” ์ค‘
157
+ params = {
158
+ **base_params,
159
+ 'learning_rate': search_space['learning_rate'],
160
+ 'max_depth': int(search_space['max_depth']),
161
+ 'num_leaves': int(search_space['num_leaves']),
162
+ 'min_child_weight': int(search_space['min_child_weight']),
163
+ 'subsample': search_space['subsample'],
164
+ 'colsample_bytree': search_space['colsample_bytree'],
165
+ 'reg_alpha': search_space['reg_alpha'],
166
+ 'reg_lambda': search_space['reg_lambda'],
167
+ }
168
+ elif best_params is not None:
169
+ # ์ตœ์ ํ™”๋œ ํŒŒ๋ผ๋ฏธํ„ฐ๋กœ ์ตœ์ข… ๋ชจ๋ธ ์ƒ์„ฑ
170
+ params = {
171
+ **base_params,
172
+ 'learning_rate': best_params['learning_rate'],
173
+ 'max_depth': int(best_params['max_depth']),
174
+ 'num_leaves': int(best_params['num_leaves']),
175
+ 'min_child_weight': int(best_params['min_child_weight']),
176
+ 'subsample': best_params['subsample'],
177
+ 'colsample_bytree': best_params['colsample_bytree'],
178
+ 'reg_alpha': best_params['reg_alpha'],
179
+ 'reg_lambda': best_params['reg_lambda'],
180
+ }
181
+ else:
182
+ params = base_params
183
+
184
+ return LGBMClassifier(**params)
185
+
186
+ # ๋ฐ์ดํ„ฐ ๋กœ๋”ฉ
187
+ print("๋ฐ์ดํ„ฐ ๋กœ๋”ฉ ์ค‘...")
188
+ # ํŒŒ์ผ ์œ„์น˜ ๊ธฐ๋ฐ˜์œผ๋กœ ๋ฐ์ดํ„ฐ ๋””๋ ‰ํ† ๋ฆฌ ๊ฒฝ๋กœ ์„ค์ •
189
+ current_file_dir = os.path.dirname(os.path.abspath(__file__))
190
+ data_base_dir = os.path.abspath(os.path.join(current_file_dir, '../../../data'))
191
+ df_seoul = pd.read_csv(os.path.join(data_base_dir, "data_for_modeling/seoul_train.csv"))
192
+ df_ctgan_seoul_1 = pd.read_csv(os.path.join(data_base_dir, "data_oversampled/ctgan10000/ctgan10000_1_seoul.csv"))
193
+ df_ctgan_seoul_2 = pd.read_csv(os.path.join(data_base_dir, "data_oversampled/ctgan10000/ctgan10000_2_seoul.csv"))
194
+ df_ctgan_seoul_3 = pd.read_csv(os.path.join(data_base_dir, "data_oversampled/ctgan10000/ctgan10000_3_seoul.csv"))
195
+
196
+ # ๋ฐ์ดํ„ฐ ์ „์ฒ˜๋ฆฌ
197
+ print("๋ฐ์ดํ„ฐ ์ „์ฒ˜๋ฆฌ ์ค‘...")
198
+ df_ctgan_seoul_1 = preprocessing(df_ctgan_seoul_1)
199
+ df_ctgan_seoul_2 = preprocessing(df_ctgan_seoul_2)
200
+ df_ctgan_seoul_3 = preprocessing(df_ctgan_seoul_3)
201
+ df_seoul = preprocessing(df_seoul)
202
+
203
+ # CTGAN ๋ฐ์ดํ„ฐ ๋ฆฌ์ŠคํŠธ (fold ์ˆœ์„œ์™€ ์ผ์น˜)
204
+ df_ctgan_list = [df_ctgan_seoul_1, df_ctgan_seoul_2, df_ctgan_seoul_3]
205
+
206
+ # ํ•˜์ดํผํŒŒ๋ผ๋ฏธํ„ฐ ๊ฒ€์ƒ‰ ๊ณต๊ฐ„ ์ •์˜
207
+ lgb_search_space = {
208
+ 'learning_rate': hp.loguniform('learning_rate', np.log(0.01), np.log(0.2)),
209
+ 'max_depth': hp.quniform('max_depth', 3, 15, 1),
210
+ 'num_leaves': hp.quniform('num_leaves', 20, 150, 1), # 2^max_depth ๋ณด๋‹ค๋Š” ์ž‘๊ฒŒ
211
+ 'min_child_weight': hp.quniform('min_child_weight', 1, 20, 1),
212
+ 'subsample': hp.uniform('subsample', 0.6, 1.0),
213
+ 'colsample_bytree': hp.uniform('colsample_bytree', 0.6, 1.0),
214
+ 'reg_alpha': hp.uniform('reg_alpha', 0.0, 1.0),
215
+ 'reg_lambda': hp.uniform('reg_lambda', 0.0, 1.0)
216
+ }
217
+
218
+
219
+ def objective_func(search_space):
220
+ """ํ•˜์ดํผํŒŒ๋ผ๋ฏธํ„ฐ ์ตœ์ ํ™”๋ฅผ ์œ„ํ•œ ๋ชฉ์  ํ•จ์ˆ˜.
221
+
222
+ Args:
223
+ search_space: ํ•˜์ดํผํŒŒ๋ผ๋ฏธํ„ฐ ๊ฒ€์ƒ‰ ๊ณต๊ฐ„
224
+
225
+ Returns:
226
+ ํ‰๊ท  CSI ์ ์ˆ˜์˜ ์Œ์ˆ˜๊ฐ’ (hyperopt๋Š” ์ตœ์†Œํ™”๋ฅผ ์ˆ˜ํ–‰ํ•˜๋ฏ€๋กœ)
227
+ """
228
+ lgb_model = create_lgb_model(search_space=search_space)
229
+ csi_scores = []
230
+
231
+ # ๊ฐ fold์— ๋Œ€ํ•ด ๊ต์ฐจ ๊ฒ€์ฆ ์ˆ˜ํ–‰
232
+ for df_ctgan, (train_years, val_year) in zip(df_ctgan_list, FOLD_CONFIGS):
233
+ X_train, X_val, y_train, y_val = split_data(
234
+ df_ctgan, df_seoul, train_years, val_year
235
+ )
236
+
237
+ lgb_model.fit(
238
+ X_train, y_train,
239
+ eval_set=[(X_val, y_val)],
240
+ eval_metric=csi_metric
241
+ )
242
+
243
+ csi = calculate_csi(y_val, lgb_model.predict(X_val))
244
+ csi_scores.append(csi)
245
+
246
+ # ํ‰๊ท  CSI์˜ ์Œ์ˆ˜๊ฐ’ ๋ฐ˜ํ™˜ (hyperopt๋Š” ์ตœ์†Œํ™”๋ฅผ ์ˆ˜ํ–‰)
247
+ return -1 * round(np.mean(csi_scores), 4)
248
+
249
+
250
+ # ํ•˜์ดํผํŒŒ๋ผ๋ฏธํ„ฐ ์ตœ์ ํ™”
251
+ print("ํ•˜์ดํผํŒŒ๋ผ๋ฏธํ„ฐ ์ตœ์ ํ™” ์‹œ์ž‘...")
252
+ trials = Trials()
253
+ lgb_best = fmin(
254
+ fn=objective_func,
255
+ space=lgb_search_space,
256
+ algo=tpe.suggest,
257
+ max_evals=MAX_EVALS,
258
+ trials=trials
259
+ )
260
+
261
+ # ์ตœ์ ํ™” ๊ฒฐ๊ณผ ๋ถ„์„ ๋ฐ ์ถœ๋ ฅ
262
+ print(f"\n์ตœ์ ํ™” ์™„๋ฃŒ. ์ตœ์  ํŒŒ๋ผ๋ฏธํ„ฐ: {lgb_best}")
263
+
264
+ # Best loss (CSI ์ ์ˆ˜์˜ ์Œ์ˆ˜๊ฐ’์ด๋ฏ€๋กœ, ์‹ค์ œ CSI๋Š” -loss)
265
+ best_loss = trials.best_trial['result']['loss']
266
+ best_csi = -best_loss
267
+ print(f"์ตœ์  CSI ์ ์ˆ˜: {best_csi:.4f} (loss: {best_loss:.4f})")
268
+
269
+ # ๋ชจ๋“  trial์˜ loss ๊ฐ’ ์ถ”์ถœ
270
+ losses = [trial['result']['loss'] for trial in trials.trials if trial['result']['status'] == 'ok']
271
+ csi_scores = [-loss for loss in losses]
272
+
273
+ print(f"\n์ตœ์ ํ™” ๊ณผ์ • ์š”์•ฝ:")
274
+ print(f" - ์ด ์‹œ๋„ ํšŸ์ˆ˜: {len(trials.trials)}")
275
+ print(f" - ์„ฑ๊ณตํ•œ ์‹œ๋„: {len(losses)}")
276
+ print(f" - ์ตœ์ดˆ CSI: {csi_scores[0]:.4f}")
277
+ print(f" - ์ตœ์ข… CSI: {csi_scores[-1]:.4f}")
278
+ print(f" - ์ตœ๊ณ  CSI: {max(csi_scores):.4f}")
279
+ print(f" - ์ตœ์ € CSI: {min(csi_scores):.4f}")
280
+ print(f" - ํ‰๊ท  CSI: {np.mean(csi_scores):.4f}")
281
+
282
+ # Trials ๊ฐ์ฒด ์ €์žฅ
283
+ import os
284
+ base_dir = os.path.dirname(os.path.dirname(current_file_dir)) # 5.optima ๋””๋ ‰ํ† ๋ฆฌ
285
+ os.makedirs(os.path.join(base_dir, "optimization_history"), exist_ok=True)
286
+ trials_path = os.path.join(base_dir, "optimization_history/lgb_ctgan10000_seoul_trials.pkl")
287
+ joblib.dump(trials, trials_path)
288
+ print(f"\n์ตœ์ ํ™” Trials ๊ฐ์ฒด๊ฐ€ {trials_path}์— ์ €์žฅ๋˜์—ˆ์Šต๋‹ˆ๋‹ค.")
289
+
290
+ # ์ตœ์ ํ™”๋œ ํ•˜์ดํผํŒŒ๋ผ๋ฏธํ„ฐ๋กœ ์ตœ์ข… ๋ชจ๋ธ ํ•™์Šต
291
+ print("์ตœ์ข… ๋ชจ๋ธ ํ•™์Šต ์‹œ์ž‘...")
292
+ models = []
293
+
294
+ for fold_idx, (df_ctgan, (train_years, val_year)) in enumerate(
295
+ zip(df_ctgan_list, FOLD_CONFIGS), start=1
296
+ ):
297
+ print(f"Fold {fold_idx} ํ•™์Šต ์ค‘... (ํ•™์Šต ์—ฐ๋„: {train_years}, ๊ฒ€์ฆ ์—ฐ๋„: {val_year})")
298
+
299
+ X_train, X_val, y_train, y_val = split_data(
300
+ df_ctgan, df_seoul, train_years, val_year
301
+ )
302
+
303
+ lgb_model = create_lgb_model(best_params=lgb_best)
304
+ lgb_model.fit(X_train, y_train, eval_set=[(X_val, y_val)])
305
+
306
+ # ๊ฒ€์ฆ ์„ฑ๋Šฅ ์ถœ๋ ฅ
307
+ val_csi = calculate_csi(y_val, lgb_model.predict(X_val))
308
+ print(f"Fold {fold_idx} ๊ฒ€์ฆ CSI: {val_csi:.4f}")
309
+
310
+ models.append(lgb_model)
311
+
312
+ # ๋ชจ๋ธ ์ €์žฅ
313
+ print("๋ชจ๋ธ ์ €์žฅ ์ค‘...")
314
+ model_save_path = os.path.join(base_dir, "save_model/lgb_optima/lgb_ctgan10000_seoul.pkl")
315
+ joblib.dump(models, model_save_path)
316
+ print(f"๋ชจ๋ธ์ด {model_save_path}์— ์ €์žฅ๋˜์—ˆ์Šต๋‹ˆ๋‹ค.")
317
+
Analysis_code/5.optima/resnet_like_ctgan10000/resnet_like_ctgan10000_daegu.py ADDED
@@ -0,0 +1,97 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ import optuna
2
+ import numpy as np
3
+ import random
4
+ import pandas as pd
5
+ import joblib
6
+ import os
7
+ import torch
8
+ from utils import *
9
+ # Python ๋ฐ Numpy ์‹œ๋“œ ๊ณ ์ •
10
+ seed = 42
11
+ random.seed(seed)
12
+ np.random.seed(seed)
13
+
14
+
15
+ # 1. Study ์ƒ์„ฑ ์‹œ 'maximize'๋กœ ์„ค์ •
16
+ study = optuna.create_study(
17
+ direction="maximize", # CSI ์ ์ˆ˜๊ฐ€ ๋†’์„์ˆ˜๋ก ์ข‹์œผ๋ฏ€๋กœ maximize
18
+ pruner=optuna.pruners.MedianPruner(n_warmup_steps=10) # ์ดˆ๋ฐ˜ 10์—ํญ์€ ์ง€์ผœ๋ณด๊ณ  ์ดํ›„ ๊ฐ€์ง€์น˜๊ธฐ
19
+ )
20
+ # Trial ์™„๋ฃŒ ์‹œ ์ƒ์„ธ ์ •๋ณด ์ถœ๋ ฅํ•˜๋Š” callback ํ•จ์ˆ˜
21
+ def print_trial_callback(study, trial):
22
+ """๊ฐ trial ์™„๋ฃŒ ์‹œ best value๋ฅผ ํฌํ•จํ•œ ์ƒ์„ธ ์ •๋ณด ์ถœ๋ ฅ"""
23
+ print(f"\n{'='*80}")
24
+ print(f"Trial {trial.number} ์™„๋ฃŒ")
25
+ print(f" Value (CSI): {trial.value:.6f}" if trial.value is not None else f" Value: {trial.value}")
26
+ print(f" Parameters: {trial.params}")
27
+ print(f" Best Value (CSI): {study.best_value:.6f}" if study.best_value is not None else f" Best Value: {study.best_value}")
28
+ print(f" Best Trial: {study.best_trial.number}")
29
+ print(f" Best Parameters: {study.best_params}")
30
+ print(f"{'='*80}\n")
31
+
32
+
33
+
34
+ # 2. ์ตœ์ ํ™” ์‹คํ–‰
35
+ study.optimize(
36
+ lambda trial: objective(trial, model_choose="resnet_like", region="daegu", data_sample='ctgan10000'),
37
+ n_trials=100
38
+ ,
39
+ callbacks=[print_trial_callback]
40
+ )
41
+
42
+ # 3. ๊ฒฐ๊ณผ ํ™•์ธ ๋ฐ ์š”์•ฝ
43
+ print(f"\n์ตœ์ ํ™” ์™„๋ฃŒ.")
44
+ print(f"Best CSI Score: {study.best_value:.4f}")
45
+ print(f"Best Hyperparameters: {study.best_params}")
46
+
47
+ try:
48
+ # ๋ชจ๋“  trial์˜ CSI ์ ์ˆ˜ ์ถ”์ถœ
49
+ csi_scores = [trial.value for trial in study.trials if trial.value is not None]
50
+
51
+ if len(csi_scores) > 0:
52
+ print(f"\n์ตœ์ ํ™” ๊ณผ์ • ์š”์•ฝ:")
53
+ print(f" - ์ด ์‹œ๋„ ํšŸ์ˆ˜: {len(study.trials)}")
54
+ print(f" - ์„ฑ๊ณตํ•œ ์‹œ๋„: {len(csi_scores)}")
55
+ print(f" - ์ตœ์ดˆ CSI: {csi_scores[0]:.4f}")
56
+ print(f" - ์ตœ์ข… CSI: {csi_scores[-1]:.4f}")
57
+ print(f" - ์ตœ๊ณ  CSI: {max(csi_scores):.4f}")
58
+ print(f" - ์ตœ์ € CSI: {min(csi_scores):.4f}")
59
+ print(f" - ํ‰๊ท  CSI: {np.mean(csi_scores):.4f}")
60
+
61
+ # Study ๊ฐ์ฒด ์ €์žฅ
62
+ # ํŒŒ์ผ ์œ„์น˜ ๊ธฐ๋ฐ˜์œผ๋กœ base ๋””๋ ‰ํ† ๋ฆฌ ๊ฒฝ๋กœ ์„ค์ •
63
+ current_file_dir = os.path.dirname(os.path.abspath(__file__))
64
+ base_dir = os.path.dirname(os.path.dirname(current_file_dir)) # 5.optima ๋””๋ ‰ํ† ๋ฆฌ
65
+ os.makedirs(os.path.join(base_dir, "optimization_history"), exist_ok=True)
66
+ study_path = os.path.join(base_dir, "optimization_history/resnet_like_ctgan10000_daegu_trials.pkl")
67
+ joblib.dump(study, study_path)
68
+ print(f"\n์ตœ์ ํ™” Study ๊ฐ์ฒด๊ฐ€ {study_path}์— ์ €์žฅ๋˜์—ˆ์Šต๋‹ˆ๋‹ค.")
69
+
70
+ # ์ตœ์ ํ™”๋œ ํ•˜์ดํผํŒŒ๋ผ๋ฏธํ„ฐ๋กœ ์ตœ์ข… ๋ชจ๋ธ ํ•™์Šต ๋ฐ ์ €์žฅ
71
+ print("\n" + "="*50)
72
+ print("์ตœ์ ํ™”๋œ ํ•˜์ดํผํŒŒ๋ผ๋ฏธํ„ฐ๋กœ ์ตœ์ข… ๋ชจ๋ธ ํ•™์Šต ์‹œ์ž‘")
73
+ print("="*50)
74
+
75
+ best_params = study.best_params
76
+ model_path = train_final_model(
77
+ best_params=best_params,
78
+ model_choose="resnet_like",
79
+ region="daegu",
80
+ data_sample='ctgan10000',
81
+ target='multi',
82
+ n_folds=3,
83
+ random_state=seed
84
+ )
85
+
86
+ print(f"\n์ตœ์ข… ๋ชจ๋ธ ํ•™์Šต ๋ฐ ์ €์žฅ ์™„๋ฃŒ!")
87
+ print(f"์ €์žฅ๋œ ๋ชจ๋ธ ๊ฒฝ๋กœ: {model_path}")
88
+
89
+ except Exception as e:
90
+ print(f"\nโš ๏ธ ์ตœ์ ํ™” ๊ฒฐ๊ณผ ๋ถ„์„ ์ค‘ ์˜ค๋ฅ˜ ๋ฐœ์ƒ: {e}")
91
+ import traceback
92
+ traceback.print_exc()
93
+
94
+ # ์ •์ƒ ์ข…๋ฃŒ
95
+ import sys
96
+ sys.exit(0)
97
+
Analysis_code/5.optima/resnet_like_ctgan10000/resnet_like_ctgan10000_daejeon.py ADDED
@@ -0,0 +1,97 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ import optuna
2
+ import numpy as np
3
+ import random
4
+ import pandas as pd
5
+ import joblib
6
+ import os
7
+ import torch
8
+ from utils import *
9
+ # Python ๋ฐ Numpy ์‹œ๋“œ ๊ณ ์ •
10
+ seed = 42
11
+ random.seed(seed)
12
+ np.random.seed(seed)
13
+
14
+
15
+ # 1. Study ์ƒ์„ฑ ์‹œ 'maximize'๋กœ ์„ค์ •
16
+ study = optuna.create_study(
17
+ direction="maximize", # CSI ์ ์ˆ˜๊ฐ€ ๋†’์„์ˆ˜๋ก ์ข‹์œผ๋ฏ€๋กœ maximize
18
+ pruner=optuna.pruners.MedianPruner(n_warmup_steps=10) # ์ดˆ๋ฐ˜ 10์—ํญ์€ ์ง€์ผœ๋ณด๊ณ  ์ดํ›„ ๊ฐ€์ง€์น˜๊ธฐ
19
+ )
20
+ # Trial ์™„๋ฃŒ ์‹œ ์ƒ์„ธ ์ •๋ณด ์ถœ๋ ฅํ•˜๋Š” callback ํ•จ์ˆ˜
21
+ def print_trial_callback(study, trial):
22
+ """๊ฐ trial ์™„๋ฃŒ ์‹œ best value๋ฅผ ํฌํ•จํ•œ ์ƒ์„ธ ์ •๋ณด ์ถœ๋ ฅ"""
23
+ print(f"\n{'='*80}")
24
+ print(f"Trial {trial.number} ์™„๋ฃŒ")
25
+ print(f" Value (CSI): {trial.value:.6f}" if trial.value is not None else f" Value: {trial.value}")
26
+ print(f" Parameters: {trial.params}")
27
+ print(f" Best Value (CSI): {study.best_value:.6f}" if study.best_value is not None else f" Best Value: {study.best_value}")
28
+ print(f" Best Trial: {study.best_trial.number}")
29
+ print(f" Best Parameters: {study.best_params}")
30
+ print(f"{'='*80}\n")
31
+
32
+
33
+
34
+ # 2. ์ตœ์ ํ™” ์‹คํ–‰
35
+ study.optimize(
36
+ lambda trial: objective(trial, model_choose="resnet_like", region="daejeon", data_sample='ctgan10000'),
37
+ n_trials=100
38
+ ,
39
+ callbacks=[print_trial_callback]
40
+ )
41
+
42
+ # 3. ๊ฒฐ๊ณผ ํ™•์ธ ๋ฐ ์š”์•ฝ
43
+ print(f"\n์ตœ์ ํ™” ์™„๋ฃŒ.")
44
+ print(f"Best CSI Score: {study.best_value:.4f}")
45
+ print(f"Best Hyperparameters: {study.best_params}")
46
+
47
+ try:
48
+ # ๋ชจ๋“  trial์˜ CSI ์ ์ˆ˜ ์ถ”์ถœ
49
+ csi_scores = [trial.value for trial in study.trials if trial.value is not None]
50
+
51
+ if len(csi_scores) > 0:
52
+ print(f"\n์ตœ์ ํ™” ๊ณผ์ • ์š”์•ฝ:")
53
+ print(f" - ์ด ์‹œ๋„ ํšŸ์ˆ˜: {len(study.trials)}")
54
+ print(f" - ์„ฑ๊ณตํ•œ ์‹œ๋„: {len(csi_scores)}")
55
+ print(f" - ์ตœ์ดˆ CSI: {csi_scores[0]:.4f}")
56
+ print(f" - ์ตœ์ข… CSI: {csi_scores[-1]:.4f}")
57
+ print(f" - ์ตœ๊ณ  CSI: {max(csi_scores):.4f}")
58
+ print(f" - ์ตœ์ € CSI: {min(csi_scores):.4f}")
59
+ print(f" - ํ‰๊ท  CSI: {np.mean(csi_scores):.4f}")
60
+
61
+ # Study ๊ฐ์ฒด ์ €์žฅ
62
+ # ํŒŒ์ผ ์œ„์น˜ ๊ธฐ๋ฐ˜์œผ๋กœ base ๋””๋ ‰ํ† ๋ฆฌ ๊ฒฝ๋กœ ์„ค์ •
63
+ current_file_dir = os.path.dirname(os.path.abspath(__file__))
64
+ base_dir = os.path.dirname(os.path.dirname(current_file_dir)) # 5.optima ๋””๋ ‰ํ† ๋ฆฌ
65
+ os.makedirs(os.path.join(base_dir, "optimization_history"), exist_ok=True)
66
+ study_path = os.path.join(base_dir, "optimization_history/resnet_like_ctgan10000_daejeon_trials.pkl")
67
+ joblib.dump(study, study_path)
68
+ print(f"\n์ตœ์ ํ™” Study ๊ฐ์ฒด๊ฐ€ {study_path}์— ์ €์žฅ๋˜์—ˆ์Šต๋‹ˆ๋‹ค.")
69
+
70
+ # ์ตœ์ ํ™”๋œ ํ•˜์ดํผํŒŒ๋ผ๋ฏธํ„ฐ๋กœ ์ตœ์ข… ๋ชจ๋ธ ํ•™์Šต ๋ฐ ์ €์žฅ
71
+ print("\n" + "="*50)
72
+ print("์ตœ์ ํ™”๋œ ํ•˜์ดํผํŒŒ๋ผ๋ฏธํ„ฐ๋กœ ์ตœ์ข… ๋ชจ๋ธ ํ•™์Šต ์‹œ์ž‘")
73
+ print("="*50)
74
+
75
+ best_params = study.best_params
76
+ model_path = train_final_model(
77
+ best_params=best_params,
78
+ model_choose="resnet_like",
79
+ region="daejeon",
80
+ data_sample='ctgan10000',
81
+ target='multi',
82
+ n_folds=3,
83
+ random_state=seed
84
+ )
85
+
86
+ print(f"\n์ตœ์ข… ๋ชจ๋ธ ํ•™์Šต ๋ฐ ์ €์žฅ ์™„๋ฃŒ!")
87
+ print(f"์ €์žฅ๋œ ๋ชจ๋ธ ๊ฒฝ๋กœ: {model_path}")
88
+
89
+ except Exception as e:
90
+ print(f"\nโš ๏ธ ์ตœ์ ํ™” ๊ฒฐ๊ณผ ๋ถ„์„ ์ค‘ ์˜ค๋ฅ˜ ๋ฐœ์ƒ: {e}")
91
+ import traceback
92
+ traceback.print_exc()
93
+
94
+ # ์ •์ƒ ์ข…๋ฃŒ
95
+ import sys
96
+ sys.exit(0)
97
+
Analysis_code/5.optima/resnet_like_ctgan10000/resnet_like_ctgan10000_gwangju.py ADDED
@@ -0,0 +1,97 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ import optuna
2
+ import numpy as np
3
+ import random
4
+ import pandas as pd
5
+ import joblib
6
+ import os
7
+ import torch
8
+ from utils import *
9
+ # Python ๋ฐ Numpy ์‹œ๋“œ ๊ณ ์ •
10
+ seed = 42
11
+ random.seed(seed)
12
+ np.random.seed(seed)
13
+
14
+
15
+ # 1. Study ์ƒ์„ฑ ์‹œ 'maximize'๋กœ ์„ค์ •
16
+ study = optuna.create_study(
17
+ direction="maximize", # CSI ์ ์ˆ˜๊ฐ€ ๋†’์„์ˆ˜๋ก ์ข‹์œผ๋ฏ€๋กœ maximize
18
+ pruner=optuna.pruners.MedianPruner(n_warmup_steps=10) # ์ดˆ๋ฐ˜ 10์—ํญ์€ ์ง€์ผœ๋ณด๊ณ  ์ดํ›„ ๊ฐ€์ง€์น˜๊ธฐ
19
+ )
20
+ # Trial ์™„๋ฃŒ ์‹œ ์ƒ์„ธ ์ •๋ณด ์ถœ๋ ฅํ•˜๋Š” callback ํ•จ์ˆ˜
21
+ def print_trial_callback(study, trial):
22
+ """๊ฐ trial ์™„๋ฃŒ ์‹œ best value๋ฅผ ํฌํ•จํ•œ ์ƒ์„ธ ์ •๋ณด ์ถœ๋ ฅ"""
23
+ print(f"\n{'='*80}")
24
+ print(f"Trial {trial.number} ์™„๋ฃŒ")
25
+ print(f" Value (CSI): {trial.value:.6f}" if trial.value is not None else f" Value: {trial.value}")
26
+ print(f" Parameters: {trial.params}")
27
+ print(f" Best Value (CSI): {study.best_value:.6f}" if study.best_value is not None else f" Best Value: {study.best_value}")
28
+ print(f" Best Trial: {study.best_trial.number}")
29
+ print(f" Best Parameters: {study.best_params}")
30
+ print(f"{'='*80}\n")
31
+
32
+
33
+
34
+ # 2. ์ตœ์ ํ™” ์‹คํ–‰
35
+ study.optimize(
36
+ lambda trial: objective(trial, model_choose="resnet_like", region="gwangju", data_sample='ctgan10000'),
37
+ n_trials=100
38
+ ,
39
+ callbacks=[print_trial_callback]
40
+ )
41
+
42
+ # 3. ๊ฒฐ๊ณผ ํ™•์ธ ๋ฐ ์š”์•ฝ
43
+ print(f"\n์ตœ์ ํ™” ์™„๋ฃŒ.")
44
+ print(f"Best CSI Score: {study.best_value:.4f}")
45
+ print(f"Best Hyperparameters: {study.best_params}")
46
+
47
+ try:
48
+ # ๋ชจ๋“  trial์˜ CSI ์ ์ˆ˜ ์ถ”์ถœ
49
+ csi_scores = [trial.value for trial in study.trials if trial.value is not None]
50
+
51
+ if len(csi_scores) > 0:
52
+ print(f"\n์ตœ์ ํ™” ๊ณผ์ • ์š”์•ฝ:")
53
+ print(f" - ์ด ์‹œ๋„ ํšŸ์ˆ˜: {len(study.trials)}")
54
+ print(f" - ์„ฑ๊ณตํ•œ ์‹œ๋„: {len(csi_scores)}")
55
+ print(f" - ์ตœ์ดˆ CSI: {csi_scores[0]:.4f}")
56
+ print(f" - ์ตœ์ข… CSI: {csi_scores[-1]:.4f}")
57
+ print(f" - ์ตœ๊ณ  CSI: {max(csi_scores):.4f}")
58
+ print(f" - ์ตœ์ € CSI: {min(csi_scores):.4f}")
59
+ print(f" - ํ‰๊ท  CSI: {np.mean(csi_scores):.4f}")
60
+
61
+ # Study ๊ฐ์ฒด ์ €์žฅ
62
+ # ํŒŒ์ผ ์œ„์น˜ ๊ธฐ๋ฐ˜์œผ๋กœ base ๋””๋ ‰ํ† ๋ฆฌ ๊ฒฝ๋กœ ์„ค์ •
63
+ current_file_dir = os.path.dirname(os.path.abspath(__file__))
64
+ base_dir = os.path.dirname(os.path.dirname(current_file_dir)) # 5.optima ๋””๋ ‰ํ† ๋ฆฌ
65
+ os.makedirs(os.path.join(base_dir, "optimization_history"), exist_ok=True)
66
+ study_path = os.path.join(base_dir, "optimization_history/resnet_like_ctgan10000_gwangju_trials.pkl")
67
+ joblib.dump(study, study_path)
68
+ print(f"\n์ตœ์ ํ™” Study ๊ฐ์ฒด๊ฐ€ {study_path}์— ์ €์žฅ๋˜์—ˆ์Šต๋‹ˆ๋‹ค.")
69
+
70
+ # ์ตœ์ ํ™”๋œ ํ•˜์ดํผํŒŒ๋ผ๋ฏธํ„ฐ๋กœ ์ตœ์ข… ๋ชจ๋ธ ํ•™์Šต ๋ฐ ์ €์žฅ
71
+ print("\n" + "="*50)
72
+ print("์ตœ์ ํ™”๋œ ํ•˜์ดํผํŒŒ๋ผ๋ฏธํ„ฐ๋กœ ์ตœ์ข… ๋ชจ๋ธ ํ•™์Šต ์‹œ์ž‘")
73
+ print("="*50)
74
+
75
+ best_params = study.best_params
76
+ model_path = train_final_model(
77
+ best_params=best_params,
78
+ model_choose="resnet_like",
79
+ region="gwangju",
80
+ data_sample='ctgan10000',
81
+ target='multi',
82
+ n_folds=3,
83
+ random_state=seed
84
+ )
85
+
86
+ print(f"\n์ตœ์ข… ๋ชจ๋ธ ํ•™์Šต ๋ฐ ์ €์žฅ ์™„๋ฃŒ!")
87
+ print(f"์ €์žฅ๋œ ๋ชจ๋ธ ๊ฒฝ๋กœ: {model_path}")
88
+
89
+ except Exception as e:
90
+ print(f"\nโš ๏ธ ์ตœ์ ํ™” ๊ฒฐ๊ณผ ๋ถ„์„ ์ค‘ ์˜ค๋ฅ˜ ๋ฐœ์ƒ: {e}")
91
+ import traceback
92
+ traceback.print_exc()
93
+
94
+ # ์ •์ƒ ์ข…๋ฃŒ
95
+ import sys
96
+ sys.exit(0)
97
+
Analysis_code/5.optima/resnet_like_ctgan10000/resnet_like_ctgan10000_incheon.py ADDED
@@ -0,0 +1,97 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ import optuna
2
+ import numpy as np
3
+ import random
4
+ import pandas as pd
5
+ import joblib
6
+ import os
7
+ import torch
8
+ from utils import *
9
+ # Python ๋ฐ Numpy ์‹œ๋“œ ๊ณ ์ •
10
+ seed = 42
11
+ random.seed(seed)
12
+ np.random.seed(seed)
13
+
14
+
15
+ # 1. Study ์ƒ์„ฑ ์‹œ 'maximize'๋กœ ์„ค์ •
16
+ study = optuna.create_study(
17
+ direction="maximize", # CSI ์ ์ˆ˜๊ฐ€ ๋†’์„์ˆ˜๋ก ์ข‹์œผ๋ฏ€๋กœ maximize
18
+ pruner=optuna.pruners.MedianPruner(n_warmup_steps=10) # ์ดˆ๋ฐ˜ 10์—ํญ์€ ์ง€์ผœ๋ณด๊ณ  ์ดํ›„ ๊ฐ€์ง€์น˜๊ธฐ
19
+ )
20
+ # Trial ์™„๋ฃŒ ์‹œ ์ƒ์„ธ ์ •๋ณด ์ถœ๋ ฅํ•˜๋Š” callback ํ•จ์ˆ˜
21
+ def print_trial_callback(study, trial):
22
+ """๊ฐ trial ์™„๋ฃŒ ์‹œ best value๋ฅผ ํฌํ•จํ•œ ์ƒ์„ธ ์ •๋ณด ์ถœ๋ ฅ"""
23
+ print(f"\n{'='*80}")
24
+ print(f"Trial {trial.number} ์™„๋ฃŒ")
25
+ print(f" Value (CSI): {trial.value:.6f}" if trial.value is not None else f" Value: {trial.value}")
26
+ print(f" Parameters: {trial.params}")
27
+ print(f" Best Value (CSI): {study.best_value:.6f}" if study.best_value is not None else f" Best Value: {study.best_value}")
28
+ print(f" Best Trial: {study.best_trial.number}")
29
+ print(f" Best Parameters: {study.best_params}")
30
+ print(f"{'='*80}\n")
31
+
32
+
33
+
34
+ # 2. ์ตœ์ ํ™” ์‹คํ–‰
35
+ study.optimize(
36
+ lambda trial: objective(trial, model_choose="resnet_like", region="incheon", data_sample='ctgan10000'),
37
+ n_trials=100
38
+ ,
39
+ callbacks=[print_trial_callback]
40
+ )
41
+
42
+ # 3. ๊ฒฐ๊ณผ ํ™•์ธ ๋ฐ ์š”์•ฝ
43
+ print(f"\n์ตœ์ ํ™” ์™„๋ฃŒ.")
44
+ print(f"Best CSI Score: {study.best_value:.4f}")
45
+ print(f"Best Hyperparameters: {study.best_params}")
46
+
47
+ try:
48
+ # ๋ชจ๋“  trial์˜ CSI ์ ์ˆ˜ ์ถ”์ถœ
49
+ csi_scores = [trial.value for trial in study.trials if trial.value is not None]
50
+
51
+ if len(csi_scores) > 0:
52
+ print(f"\n์ตœ์ ํ™” ๊ณผ์ • ์š”์•ฝ:")
53
+ print(f" - ์ด ์‹œ๋„ ํšŸ์ˆ˜: {len(study.trials)}")
54
+ print(f" - ์„ฑ๊ณตํ•œ ์‹œ๋„: {len(csi_scores)}")
55
+ print(f" - ์ตœ์ดˆ CSI: {csi_scores[0]:.4f}")
56
+ print(f" - ์ตœ์ข… CSI: {csi_scores[-1]:.4f}")
57
+ print(f" - ์ตœ๊ณ  CSI: {max(csi_scores):.4f}")
58
+ print(f" - ์ตœ์ € CSI: {min(csi_scores):.4f}")
59
+ print(f" - ํ‰๊ท  CSI: {np.mean(csi_scores):.4f}")
60
+
61
+ # Study ๊ฐ์ฒด ์ €์žฅ
62
+ # ํŒŒ์ผ ์œ„์น˜ ๊ธฐ๋ฐ˜์œผ๋กœ base ๋””๋ ‰ํ† ๋ฆฌ ๊ฒฝ๋กœ ์„ค์ •
63
+ current_file_dir = os.path.dirname(os.path.abspath(__file__))
64
+ base_dir = os.path.dirname(os.path.dirname(current_file_dir)) # 5.optima ๋””๋ ‰ํ† ๋ฆฌ
65
+ os.makedirs(os.path.join(base_dir, "optimization_history"), exist_ok=True)
66
+ study_path = os.path.join(base_dir, "optimization_history/resnet_like_ctgan10000_incheon_trials.pkl")
67
+ joblib.dump(study, study_path)
68
+ print(f"\n์ตœ์ ํ™” Study ๊ฐ์ฒด๊ฐ€ {study_path}์— ์ €์žฅ๋˜์—ˆ์Šต๋‹ˆ๋‹ค.")
69
+
70
+ # ์ตœ์ ํ™”๋œ ํ•˜์ดํผํŒŒ๋ผ๋ฏธํ„ฐ๋กœ ์ตœ์ข… ๋ชจ๋ธ ํ•™์Šต ๋ฐ ์ €์žฅ
71
+ print("\n" + "="*50)
72
+ print("์ตœ์ ํ™”๋œ ํ•˜์ดํผํŒŒ๋ผ๋ฏธํ„ฐ๋กœ ์ตœ์ข… ๋ชจ๋ธ ํ•™์Šต ์‹œ์ž‘")
73
+ print("="*50)
74
+
75
+ best_params = study.best_params
76
+ model_path = train_final_model(
77
+ best_params=best_params,
78
+ model_choose="resnet_like",
79
+ region="incheon",
80
+ data_sample='ctgan10000',
81
+ target='multi',
82
+ n_folds=3,
83
+ random_state=seed
84
+ )
85
+
86
+ print(f"\n์ตœ์ข… ๋ชจ๋ธ ํ•™์Šต ๋ฐ ์ €์žฅ ์™„๋ฃŒ!")
87
+ print(f"์ €์žฅ๋œ ๋ชจ๋ธ ๊ฒฝ๋กœ: {model_path}")
88
+
89
+ except Exception as e:
90
+ print(f"\nโš ๏ธ ์ตœ์ ํ™” ๊ฒฐ๊ณผ ๋ถ„์„ ์ค‘ ์˜ค๋ฅ˜ ๋ฐœ์ƒ: {e}")
91
+ import traceback
92
+ traceback.print_exc()
93
+
94
+ # ์ •์ƒ ์ข…๋ฃŒ
95
+ import sys
96
+ sys.exit(0)
97
+
Analysis_code/5.optima/resnet_like_ctgan10000/resnet_like_ctgan10000_seoul.py ADDED
@@ -0,0 +1,97 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ import optuna
2
+ import numpy as np
3
+ import random
4
+ import pandas as pd
5
+ import joblib
6
+ import os
7
+ import torch
8
+ from utils import *
9
+ # Python ๋ฐ Numpy ์‹œ๋“œ ๊ณ ์ •
10
+ seed = 42
11
+ random.seed(seed)
12
+ np.random.seed(seed)
13
+
14
+
15
+ # 1. Study ์ƒ์„ฑ ์‹œ 'maximize'๋กœ ์„ค์ •
16
+ study = optuna.create_study(
17
+ direction="maximize", # CSI ์ ์ˆ˜๊ฐ€ ๋†’์„์ˆ˜๋ก ์ข‹์œผ๋ฏ€๋กœ maximize
18
+ pruner=optuna.pruners.MedianPruner(n_warmup_steps=10) # ์ดˆ๋ฐ˜ 10์—ํญ์€ ์ง€์ผœ๋ณด๊ณ  ์ดํ›„ ๊ฐ€์ง€์น˜๊ธฐ
19
+ )
20
+ # Trial ์™„๋ฃŒ ์‹œ ์ƒ์„ธ ์ •๋ณด ์ถœ๋ ฅํ•˜๋Š” callback ํ•จ์ˆ˜
21
+ def print_trial_callback(study, trial):
22
+ """๊ฐ trial ์™„๋ฃŒ ์‹œ best value๋ฅผ ํฌํ•จํ•œ ์ƒ์„ธ ์ •๋ณด ์ถœ๋ ฅ"""
23
+ print(f"\n{'='*80}")
24
+ print(f"Trial {trial.number} ์™„๋ฃŒ")
25
+ print(f" Value (CSI): {trial.value:.6f}" if trial.value is not None else f" Value: {trial.value}")
26
+ print(f" Parameters: {trial.params}")
27
+ print(f" Best Value (CSI): {study.best_value:.6f}" if study.best_value is not None else f" Best Value: {study.best_value}")
28
+ print(f" Best Trial: {study.best_trial.number}")
29
+ print(f" Best Parameters: {study.best_params}")
30
+ print(f"{'='*80}\n")
31
+
32
+
33
+
34
+ # 2. ์ตœ์ ํ™” ์‹คํ–‰
35
+ study.optimize(
36
+ lambda trial: objective(trial, model_choose="resnet_like", region="seoul", data_sample='ctgan10000'),
37
+ n_trials=100
38
+ ,
39
+ callbacks=[print_trial_callback]
40
+ )
41
+
42
+ # 3. ๊ฒฐ๊ณผ ํ™•์ธ ๋ฐ ์š”์•ฝ
43
+ print(f"\n์ตœ์ ํ™” ์™„๋ฃŒ.")
44
+ print(f"Best CSI Score: {study.best_value:.4f}")
45
+ print(f"Best Hyperparameters: {study.best_params}")
46
+
47
+ try:
48
+ # ๋ชจ๋“  trial์˜ CSI ์ ์ˆ˜ ์ถ”์ถœ
49
+ csi_scores = [trial.value for trial in study.trials if trial.value is not None]
50
+
51
+ if len(csi_scores) > 0:
52
+ print(f"\n์ตœ์ ํ™” ๊ณผ์ • ์š”์•ฝ:")
53
+ print(f" - ์ด ์‹œ๋„ ํšŸ์ˆ˜: {len(study.trials)}")
54
+ print(f" - ์„ฑ๊ณตํ•œ ์‹œ๋„: {len(csi_scores)}")
55
+ print(f" - ์ตœ์ดˆ CSI: {csi_scores[0]:.4f}")
56
+ print(f" - ์ตœ์ข… CSI: {csi_scores[-1]:.4f}")
57
+ print(f" - ์ตœ๊ณ  CSI: {max(csi_scores):.4f}")
58
+ print(f" - ์ตœ์ € CSI: {min(csi_scores):.4f}")
59
+ print(f" - ํ‰๊ท  CSI: {np.mean(csi_scores):.4f}")
60
+
61
+ # Study ๊ฐ์ฒด ์ €์žฅ
62
+ # ํŒŒ์ผ ์œ„์น˜ ๊ธฐ๋ฐ˜์œผ๋กœ base ๋””๋ ‰ํ† ๋ฆฌ ๊ฒฝ๋กœ ์„ค์ •
63
+ current_file_dir = os.path.dirname(os.path.abspath(__file__))
64
+ base_dir = os.path.dirname(os.path.dirname(current_file_dir)) # 5.optima ๋””๋ ‰ํ† ๋ฆฌ
65
+ os.makedirs(os.path.join(base_dir, "optimization_history"), exist_ok=True)
66
+ study_path = os.path.join(base_dir, "optimization_history/resnet_like_ctgan10000_seoul_trials.pkl")
67
+ joblib.dump(study, study_path)
68
+ print(f"\n์ตœ์ ํ™” Study ๊ฐ์ฒด๊ฐ€ {study_path}์— ์ €์žฅ๋˜์—ˆ์Šต๋‹ˆ๋‹ค.")
69
+
70
+ # ์ตœ์ ํ™”๋œ ํ•˜์ดํผํŒŒ๋ผ๋ฏธํ„ฐ๋กœ ์ตœ์ข… ๋ชจ๋ธ ํ•™์Šต ๋ฐ ์ €์žฅ
71
+ print("\n" + "="*50)
72
+ print("์ตœ์ ํ™”๋œ ํ•˜์ดํผํŒŒ๋ผ๋ฏธํ„ฐ๋กœ ์ตœ์ข… ๋ชจ๋ธ ํ•™์Šต ์‹œ์ž‘")
73
+ print("="*50)
74
+
75
+ best_params = study.best_params
76
+ model_path = train_final_model(
77
+ best_params=best_params,
78
+ model_choose="resnet_like",
79
+ region="seoul",
80
+ data_sample='ctgan10000',
81
+ target='multi',
82
+ n_folds=3,
83
+ random_state=seed
84
+ )
85
+
86
+ print(f"\n์ตœ์ข… ๋ชจ๋ธ ํ•™์Šต ๋ฐ ์ €์žฅ ์™„๋ฃŒ!")
87
+ print(f"์ €์žฅ๋œ ๋ชจ๋ธ ๊ฒฝ๋กœ: {model_path}")
88
+
89
+ except Exception as e:
90
+ print(f"\nโš ๏ธ ์ตœ์ ํ™” ๊ฒฐ๊ณผ ๋ถ„์„ ์ค‘ ์˜ค๋ฅ˜ ๋ฐœ์ƒ: {e}")
91
+ import traceback
92
+ traceback.print_exc()
93
+
94
+ # ์ •์ƒ ์ข…๋ฃŒ
95
+ import sys
96
+ sys.exit(0)
97
+
Analysis_code/5.optima/run_bash/deepgbm/deepgbm_ctgan10000 DELETED
The diff for this file is too large to render. See raw diff
 
Analysis_code/5.optima/run_bash/deepgbm/deepgbm_ctgan10000.log ADDED
The diff for this file is too large to render. See raw diff
 
Analysis_code/5.optima/run_bash/deepgbm/run_deepgbm_ctgan10000.sh CHANGED
@@ -15,6 +15,11 @@ echo ""
15
  # ์‹คํ–‰ํ•  ํŒŒ์ผ ๋ชฉ๋ก
16
  FILES=(
17
  "deepgbm_ctgan10000_busan.py"
 
 
 
 
 
18
  )
19
 
20
  # ์—๋Ÿฌ ๋ฐœ์ƒ ์‹œ ์ค‘๋‹จ ์—ฌ๋ถ€ (set -e๋ฅผ ์‚ฌ์šฉํ•˜๋ฉด ์—๋Ÿฌ ๋ฐœ์ƒ ์‹œ ์ฆ‰์‹œ ์ค‘๋‹จ)
 
15
  # ์‹คํ–‰ํ•  ํŒŒ์ผ ๋ชฉ๋ก
16
  FILES=(
17
  "deepgbm_ctgan10000_busan.py"
18
+ "deepgbm_ctgan10000_daegu.py"
19
+ "deepgbm_ctgan10000_daejeon.py"
20
+ "deepgbm_ctgan10000_gwangju.py"
21
+ "deepgbm_ctgan10000_incheon.py"
22
+ "deepgbm_ctgan10000_seoul.py"
23
  )
24
 
25
  # ์—๋Ÿฌ ๋ฐœ์ƒ ์‹œ ์ค‘๋‹จ ์—ฌ๋ถ€ (set -e๋ฅผ ์‚ฌ์šฉํ•˜๋ฉด ์—๋Ÿฌ ๋ฐœ์ƒ ์‹œ ์ฆ‰์‹œ ์ค‘๋‹จ)
Analysis_code/5.optima/run_bash/ft_transformer/ft_transformer_ctgan10000 DELETED
The diff for this file is too large to render. See raw diff
 
Analysis_code/5.optima/run_bash/ft_transformer/ft_transformer_ctgan10000.log ADDED
The diff for this file is too large to render. See raw diff
 
Analysis_code/5.optima/run_bash/ft_transformer/run_ft_transformer_ctgan10000.sh CHANGED
@@ -15,6 +15,11 @@ echo ""
15
  # ์‹คํ–‰ํ•  ํŒŒ์ผ ๋ชฉ๋ก
16
  FILES=(
17
  "ft_transformer_ctgan10000_busan.py"
 
 
 
 
 
18
  )
19
 
20
  # ์—๋Ÿฌ ๋ฐœ์ƒ ์‹œ ์ค‘๋‹จ ์—ฌ๋ถ€ (set -e๋ฅผ ์‚ฌ์šฉํ•˜๋ฉด ์—๋Ÿฌ ๋ฐœ์ƒ ์‹œ ์ฆ‰์‹œ ์ค‘๋‹จ)
 
15
  # ์‹คํ–‰ํ•  ํŒŒ์ผ ๋ชฉ๋ก
16
  FILES=(
17
  "ft_transformer_ctgan10000_busan.py"
18
+ "ft_transformer_ctgan10000_daegu.py"
19
+ "ft_transformer_ctgan10000_daejeon.py"
20
+ "ft_transformer_ctgan10000_gwangju.py"
21
+ "ft_transformer_ctgan10000_incheon.py"
22
+ "ft_transformer_ctgan10000_seoul.py"
23
  )
24
 
25
  # ์—๋Ÿฌ ๋ฐœ์ƒ ์‹œ ์ค‘๋‹จ ์—ฌ๋ถ€ (set -e๋ฅผ ์‚ฌ์šฉํ•˜๋ฉด ์—๋Ÿฌ ๋ฐœ์ƒ ์‹œ ์ฆ‰์‹œ ์ค‘๋‹จ)
Analysis_code/5.optima/run_bash/lgb/lgb_ctgan10000.log CHANGED
@@ -1,156 +1,219 @@
1
- nohup: ignoring input
2
- /bin/bash: /opt/conda/lib/libtinfo.so.6: no version information available (required by /bin/bash)
3
- ==========================================
4
- LGB CTGAN10000 ํŒŒ์ผ ์‹คํ–‰ ์‹œ์ž‘
5
- ์‹œ์ž‘ ์‹œ๊ฐ„: 2025-12-26 14:02:40
6
- GPU: 1๋ฒˆ (CUDA_VISIBLE_DEVICES=1)
7
- ==========================================
8
-
9
- ----------------------------------------
10
- ์‹คํ–‰ ์ค‘: lgb_ctgan10000/LGB_ctgan10000_busan.py
11
- ์‹œ์ž‘ ์‹œ๊ฐ„: 2025-12-26 14:02:40
12
- ----------------------------------------
13
- ๋ฐ์ดํ„ฐ ๋กœ๋”ฉ ์ค‘...
14
- ๋ฐ์ดํ„ฐ ์ „์ฒ˜๋ฆฌ ์ค‘...
15
- ํ•˜์ดํผํŒŒ๋ผ๋ฏธํ„ฐ ์ตœ์ ํ™” ์‹œ์ž‘...
16
-
17
- 0%| | 0/100 [00:00<?, ?trial/s, best loss=?]
18
- 1%| | 1/100 [00:17<29:00, 17.58s/trial, best loss: -0.4607]
19
- 2%|โ– | 2/100 [00:36<30:05, 18.43s/trial, best loss: -0.4607]
20
- 3%|โ–Ž | 3/100 [01:18<47:04, 29.12s/trial, best loss: -0.4607]
21
- 4%|โ– | 4/100 [01:56<52:20, 32.72s/trial, best loss: -0.4725]
22
- 5%|โ–Œ | 5/100 [02:33<54:17, 34.29s/trial, best loss: -0.4738]
23
- 6%|โ–Œ | 6/100 [03:41<1:11:47, 45.82s/trial, best loss: -0.4738]
24
- 7%|โ–‹ | 7/100 [04:05<59:46, 38.56s/trial, best loss: -0.4742]
25
- 8%|โ–Š | 8/100 [04:23<49:11, 32.08s/trial, best loss: -0.4742]
26
- 9%|โ–‰ | 9/100 [04:47<44:38, 29.43s/trial, best loss: -0.4742]
27
- 10%|โ–ˆ | 10/100 [05:03<37:59, 25.33s/trial, best loss: -0.4742]
28
- 11%|โ–ˆ | 11/100 [05:43<44:23, 29.93s/trial, best loss: -0.4742]
29
- 12%|โ–ˆโ– | 12/100 [06:06<40:31, 27.63s/trial, best loss: -0.4742]
30
- 13%|โ–ˆโ–Ž | 13/100 [06:29<38:06, 26.28s/trial, best loss: -0.4742]
31
- 14%|โ–ˆโ– | 14/100 [07:01<40:12, 28.06s/trial, best loss: -0.4742]
32
- 15%|โ–ˆโ–Œ | 15/100 [07:22<36:37, 25.86s/trial, best loss: -0.4742]
33
- 16%|โ–ˆโ–Œ | 16/100 [07:43<34:21, 24.54s/trial, best loss: -0.4742]
34
- 17%|โ–ˆโ–‹ | 17/100 [08:12<35:43, 25.83s/trial, best loss: -0.4742]
35
- 18%|โ–ˆโ–Š | 18/100 [08:49<39:51, 29.17s/trial, best loss: -0.4742]
36
- 19%|โ–ˆโ–‰ | 19/100 [09:24<41:40, 30.88s/trial, best loss: -0.4785]
37
- 20%|โ–ˆโ–ˆ | 20/100 [09:45<37:10, 27.88s/trial, best loss: -0.4785]
38
- 21%|โ–ˆโ–ˆ | 21/100 [10:11<36:01, 27.37s/trial, best loss: -0.4785]
39
- 22%|โ–ˆโ–ˆโ– | 22/100 [10:34<33:49, 26.02s/trial, best loss: -0.4819]
40
- 23%|โ–ˆโ–ˆโ–Ž | 23/100 [10:57<32:18, 25.17s/trial, best loss: -0.4819]
41
- 24%|โ–ˆโ–ˆโ– | 24/100 [11:34<36:16, 28.64s/trial, best loss: -0.4822]
42
- 25%|โ–ˆโ–ˆโ–Œ | 25/100 [11:57<33:52, 27.10s/trial, best loss: -0.486]
43
- 26%|โ–ˆโ–ˆโ–Œ | 26/100 [12:24<33:21, 27.05s/trial, best loss: -0.486]
44
- 27%|โ–ˆโ–ˆโ–‹ | 27/100 [12:56<34:44, 28.55s/trial, best loss: -0.486]
45
- 28%|โ–ˆโ–ˆโ–Š | 28/100 [13:16<30:54, 25.76s/trial, best loss: -0.486]
46
- 29%|โ–ˆโ–ˆโ–‰ | 29/100 [13:48<32:49, 27.74s/trial, best loss: -0.486]
47
- 30%|โ–ˆโ–ˆโ–ˆ | 30/100 [14:21<34:06, 29.24s/trial, best loss: -0.486]
48
- 31%|โ–ˆโ–ˆโ–ˆ | 31/100 [14:59<36:48, 32.01s/trial, best loss: -0.486]
49
- 32%|โ–ˆโ–ˆโ–ˆโ– | 32/100 [15:17<31:20, 27.66s/trial, best loss: -0.486]
50
- 33%|โ–ˆโ–ˆโ–ˆโ–Ž | 33/100 [15:41<29:43, 26.62s/trial, best loss: -0.486]
51
- 34%|โ–ˆโ–ˆโ–ˆโ– | 34/100 [16:22<33:56, 30.86s/trial, best loss: -0.486]
52
- 35%|โ–ˆโ–ˆโ–ˆโ–Œ | 35/100 [16:40<29:20, 27.08s/trial, best loss: -0.486]
53
- 36%|โ–ˆโ–ˆโ–ˆโ–Œ | 36/100 [16:57<25:33, 23.97s/trial, best loss: -0.486]
54
- 37%|โ–ˆโ–ˆโ–ˆโ–‹ | 37/100 [17:22<25:39, 24.44s/trial, best loss: -0.486]
55
- 38%|โ–ˆโ–ˆโ–ˆโ–Š | 38/100 [18:01<29:35, 28.64s/trial, best loss: -0.486]
56
- 39%|โ–ˆโ–ˆโ–ˆโ–‰ | 39/100 [18:17<25:31, 25.11s/trial, best loss: -0.486]
57
- 40%|โ–ˆโ–ˆโ–ˆโ–ˆ | 40/100 [18:42<24:52, 24.88s/trial, best loss: -0.486]
58
- 41%|โ–ˆโ–ˆโ–ˆโ–ˆ | 41/100 [19:01<22:44, 23.13s/trial, best loss: -0.486]
59
- 42%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 42/100 [19:25<22:48, 23.60s/trial, best loss: -0.486]
60
- 43%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 43/100 [20:06<27:17, 28.73s/trial, best loss: -0.486]
61
- 44%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 44/100 [20:35<26:57, 28.88s/trial, best loss: -0.486]
62
- 45%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 45/100 [21:03<26:12, 28.60s/trial, best loss: -0.486]
63
- 46%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 46/100 [21:22<22:59, 25.54s/trial, best loss: -0.486]
64
- 47%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 47/100 [21:47<22:34, 25.56s/trial, best loss: -0.486]
65
- 48%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 48/100 [22:08<20:50, 24.04s/trial, best loss: -0.486]
66
- 49%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 49/100 [23:09<29:53, 35.18s/trial, best loss: -0.486]
67
- 50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 50/100 [23:34<26:42, 32.05s/trial, best loss: -0.486]
68
- 51%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 51/100 [23:53<23:03, 28.24s/trial, best loss: -0.486]
69
- 52%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 52/100 [24:27<24:01, 30.03s/trial, best loss: -0.486]
70
- 53%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 53/100 [24:56<23:19, 29.77s/trial, best loss: -0.486]
71
- 54%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 54/100 [25:21<21:40, 28.28s/trial, best loss: -0.486]
72
- 55%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 55/100 [25:43<19:46, 26.36s/trial, best loss: -0.486]
73
- 56%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 56/100 [26:16<20:46, 28.33s/trial, best loss: -0.486]
74
- 57%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 57/100 [26:36<18:23, 25.67s/trial, best loss: -0.486]
75
- 58%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 58/100 [27:07<19:06, 27.30s/trial, best loss: -0.486]
76
- 59%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 59/100 [27:45<20:57, 30.66s/trial, best loss: -0.486]
77
- 60%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 60/100 [28:13<19:56, 29.90s/trial, best loss: -0.486]
78
- 61%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 61/100 [28:49<20:38, 31.75s/trial, best loss: -0.486]
79
- 62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 62/100 [29:25<20:45, 32.78s/trial, best loss: -0.486]
80
- 63%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 63/100 [29:42<17:21, 28.16s/trial, best loss: -0.486]
81
- 64%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 64/100 [30:01<15:15, 25.44s/trial, best loss: -0.486]
82
- 65%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 65/100 [30:27<15:00, 25.73s/trial, best loss: -0.486]
83
- 66%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 66/100 [31:03<16:16, 28.71s/trial, best loss: -0.486]
84
- 67%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 67/100 [31:40<17:08, 31.18s/trial, best loss: -0.486]
85
- 68%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 68/100 [32:18<17:45, 33.31s/trial, best loss: -0.486]
86
- 69%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 69/100 [32:52<17:16, 33.45s/trial, best loss: -0.486]
87
- 70%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 70/100 [33:30<17:26, 34.89s/trial, best loss: -0.486]
88
- 71%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 71/100 [34:01<16:12, 33.53s/trial, best loss: -0.486]
89
- 72%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 72/100 [34:27<14:40, 31.46s/trial, best loss: -0.486]
90
- 73%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 73/100 [34:58<14:01, 31.18s/trial, best loss: -0.486]
91
- 74%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 74/100 [35:38<14:37, 33.77s/trial, best loss: -0.486]
92
- 75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 75/100 [36:00<12:41, 30.44s/trial, best loss: -0.486]
93
- 76%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 76/100 [36:31<12:11, 30.48s/trial, best loss: -0.486]
94
- 77%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 77/100 [36:52<10:32, 27.52s/trial, best loss: -0.486]
95
- 78%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 78/100 [37:18<10:01, 27.35s/trial, best loss: -0.486]
96
- 79%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 79/100 [37:46<09:35, 27.40s/trial, best loss: -0.486]
97
- 80%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 80/100 [38:13<09:07, 27.38s/trial, best loss: -0.486]
98
- 81%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 81/100 [38:37<08:19, 26.29s/trial, best loss: -0.486]
99
- 82%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 82/100 [39:00<07:36, 25.38s/trial, best loss: -0.486]
100
- 83%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 83/100 [39:23<06:55, 24.45s/trial, best loss: -0.486]
101
- 84%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 84/100 [39:46<06:24, 24.03s/trial, best loss: -0.486]
102
- 85%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 85/100 [40:07<05:46, 23.12s/trial, best loss: -0.486]
103
- 86%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 86/100 [40:36<05:51, 25.10s/trial, best loss: -0.486]
104
- 87%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 87/100 [41:03<05:32, 25.55s/trial, best loss: -0.486]
105
- 88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 88/100 [41:26<04:57, 24.77s/trial, best loss: -0.486]
106
- 89%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 89/100 [41:49<04:25, 24.13s/trial, best loss: -0.486]
107
- 90%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 90/100 [42:15<04:08, 24.81s/trial, best loss: -0.486]
108
- 91%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 91/100 [42:34<03:28, 23.19s/trial, best loss: -0.486]
109
- 92%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 92/100 [42:56<03:01, 22.66s/trial, best loss: -0.486]
110
- 93%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž| 93/100 [43:21<02:43, 23.39s/trial, best loss: -0.486]
111
- 94%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 94/100 [43:47<02:25, 24.18s/trial, best loss: -0.486]
112
- 95%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ| 95/100 [44:21<02:15, 27.10s/trial, best loss: -0.486]
113
- 96%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ| 96/100 [44:44<01:43, 25.89s/trial, best loss: -0.486]
114
- 97%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹| 97/100 [45:06<01:14, 24.90s/trial, best loss: -0.486]
115
- 98%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š| 98/100 [45:37<00:52, 26.46s/trial, best loss: -0.486]
116
- 99%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰| 99/100 [46:04<00:26, 26.65s/trial, best loss: -0.488]
117
- 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 100/100 [46:24<00:00, 24.62s/trial, best loss: -0.488]
118
- 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 100/100 [46:24<00:00, 27.84s/trial, best loss: -0.488]
119
-
120
- ์ตœ์ ํ™” ์™„๋ฃŒ. ์ตœ์  ํŒŒ๋ผ๋ฏธํ„ฐ: {'colsample_bytree': 0.7801064403987199, 'learning_rate': 0.04039992222321611, 'max_depth': 13.0, 'min_child_weight': 8.0, 'num_leaves': 119.0, 'reg_alpha': 0.6320948905725006, 'reg_lambda': 0.018408747449243035, 'subsample': 0.8868375113319782}
121
- ์ตœ์  CSI ์ ์ˆ˜: 0.4880 (loss: -0.4880)
122
-
123
- ์ตœ์ ํ™” ๊ณผ์ • ์š”์•ฝ:
124
- - ์ด ์‹œ๋„ ํšŸ์ˆ˜: 100
125
- - ์„ฑ๊ณตํ•œ ์‹œ๋„: 100
126
- - ์ตœ์ดˆ CSI: 0.4607
127
- - ์ตœ์ข… CSI: 0.4751
128
- - ์ตœ๊ณ  CSI: 0.4880
129
- - ์ตœ์ € CSI: 0.3744
130
- - ํ‰๊ท  CSI: 0.4699
131
-
132
- ์ตœ์ ํ™” Trials ๊ฐ์ฒด๊ฐ€ /workspace/visibility_prediction/Analysis_code/optimization_history/lgb_ctgan10000_busan_trials.pkl์— ์ €์žฅ๋˜์—ˆ์Šต๋‹ˆ๋‹ค.
133
- ์ตœ์ข… ๋ชจ๋ธ ํ•™์Šต ์‹œ์ž‘...
134
- Fold 1 ํ•™์Šต ์ค‘... (ํ•™์Šต ์—ฐ๋„: [2018, 2019], ๊ฒ€์ฆ ์—ฐ๋„: 2020)
135
- Fold 1 ๊ฒ€์ฆ CSI: 0.3920
136
- Fold 2 ํ•™์Šต ์ค‘... (ํ•™์Šต ์—ฐ๋„: [2018, 2020], ๊ฒ€์ฆ ์—ฐ๋„: 2019)
137
- Fold 2 ๊ฒ€์ฆ CSI: 0.5059
138
- Fold 3 ํ•™์Šต ์ค‘... (ํ•™์Šต ์—ฐ๋„: [2019, 2020], ๊ฒ€์ฆ ์—ฐ๋„: 2018)
139
- Fold 3 ๊ฒ€์ฆ CSI: 0.5052
140
- ๋ชจ๋ธ ์ €์žฅ ๏ฟฝ๏ฟฝ...
141
- ๋ชจ๋ธ์ด /workspace/visibility_prediction/Analysis_code/save_model/lgb_optima/lgb_ctgan10000_busan.pkl์— ์ €์žฅ๋˜์—ˆ์Šต๋‹ˆ๋‹ค.
142
-
143
- โœ“ ์™„๋ฃŒ: lgb_ctgan10000/LGB_ctgan10000_busan.py (์†Œ์š” ์‹œ๊ฐ„: 2798์ดˆ)
144
-
145
- โš ๏ธ ๊ฒฝ๊ณ : lgb_ctgan10000/LGB_ctgan10000_daegu.py ํŒŒ์ผ์„ ์ฐพ์„ ์ˆ˜ ์—†์Šต๋‹ˆ๋‹ค. ๊ฑด๋„ˆ๋œ๋‹ˆ๋‹ค.
146
- โš ๏ธ ๊ฒฝ๊ณ : lgb_ctgan10000/LGB_ctgan10000_daejeon.py ํŒŒ์ผ์„ ์ฐพ์„ ์ˆ˜ ์—†์Šต๋‹ˆ๋‹ค. ๊ฑด๋„ˆ๋œ๋‹ˆ๋‹ค.
147
- โš ๏ธ ๊ฒฝ๊ณ : lgb_ctgan10000/LGB_ctgan10000_gwangju.py ํŒŒ์ผ์„ ์ฐพ์„ ์ˆ˜ ์—†์Šต๋‹ˆ๋‹ค. ๊ฑด๋„ˆ๋œ๋‹ˆ๋‹ค.
148
- โš ๏ธ ๊ฒฝ๊ณ : lgb_ctgan10000/LGB_ctgan10000_incheon.py ํŒŒ์ผ์„ ์ฐพ์„ ์ˆ˜ ์—†์Šต๋‹ˆ๋‹ค. ๊ฑด๋„ˆ๋œ๋‹ˆ๋‹ค.
149
- โš ๏ธ ๊ฒฝ๊ณ : lgb_ctgan10000/LGB_ctgan10000_seoul.py ํŒŒ์ผ์„ ์ฐพ์„ ์ˆ˜ ์—†์Šต๋‹ˆ๋‹ค. ๊ฑด๋„ˆ๋œ๋‹ˆ๋‹ค.
150
- ==========================================
151
- LGB CTGAN10000 ํŒŒ์ผ ์‹คํ–‰ ์™„๋ฃŒ
152
- ์ข…๋ฃŒ ์‹œ๊ฐ„: 2025-12-26 14:49:18
153
- ์ด ์†Œ์š” ์‹œ๊ฐ„: 0์‹œ๊ฐ„ 46๋ถ„ 38์ดˆ
154
- ์„ฑ๊ณต: 1๊ฐœ
155
- ์‹คํŒจ: 5๊ฐœ
156
- ==========================================
157
  0%| | 0/100 [00:00<?, ?trial/s, best loss=?]
158
  1%| | 1/100 [01:04<1:47:14, 65.00s/trial, best loss: -0.4238]
159
  2%|โ– | 2/100 [01:54<1:31:25, 55.98s/trial, best loss: -0.4576]
160
  3%|โ–Ž | 3/100 [02:31<1:16:36, 47.39s/trial, best loss: -0.4733]
161
  4%|โ– | 4/100 [03:21<1:17:24, 48.38s/trial, best loss: -0.4758]
162
  5%|โ–Œ | 5/100 [04:00<1:10:52, 44.77s/trial, best loss: -0.4758]
163
  6%|โ–Œ | 6/100 [04:24<59:01, 37.68s/trial, best loss: -0.4758]
164
  7%|โ–‹ | 7/100 [04:54<54:54, 35.42s/trial, best loss: -0.4758]
165
  8%|โ–Š | 8/100 [05:41<59:49, 39.02s/trial, best loss: -0.4758]
166
  9%|โ–‰ | 9/100 [06:04<51:22, 33.87s/trial, best loss: -0.4758]
167
  10%|โ–ˆ | 10/100 [06:52<57:39, 38.44s/trial, best loss: -0.4758]
168
  11%|โ–ˆ | 11/100 [07:30<56:39, 38.20s/trial, best loss: -0.4835]
169
  12%|โ–ˆโ– | 12/100 [08:01<52:39, 35.90s/trial, best loss: -0.4835]
170
  13%|โ–ˆโ–Ž | 13/100 [08:23<46:16, 31.91s/trial, best loss: -0.4835]
171
  14%|โ–ˆโ– | 14/100 [08:46<41:36, 29.03s/trial, best loss: -0.4835]
172
  15%|โ–ˆโ–Œ | 15/100 [09:24<44:58, 31.74s/trial, best loss: -0.4835]
173
  16%|โ–ˆโ–Œ | 16/100 [10:12<51:30, 36.80s/trial, best loss: -0.4835]
174
  17%|โ–ˆโ–‹ | 17/100 [10:47<50:13, 36.30s/trial, best loss: -0.4835]
175
  18%|โ–ˆโ–Š | 18/100 [11:15<46:03, 33.70s/trial, best loss: -0.4835]
176
  19%|โ–ˆโ–‰ | 19/100 [11:52<46:41, 34.58s/trial, best loss: -0.4835]
177
  20%|โ–ˆโ–ˆ | 20/100 [12:13<40:56, 30.71s/trial, best loss: -0.4835]
178
  21%|โ–ˆโ–ˆ | 21/100 [12:44<40:26, 30.71s/trial, best loss: -0.4835]
179
  22%|โ–ˆโ–ˆโ– | 22/100 [13:14<39:43, 30.56s/trial, best loss: -0.4836]
180
  23%|โ–ˆโ–ˆโ–Ž | 23/100 [13:40<37:14, 29.02s/trial, best loss: -0.4836]
181
  24%|โ–ˆโ–ˆโ– | 24/100 [14:23<42:05, 33.24s/trial, best loss: -0.4836]
182
  25%|โ–ˆโ–ˆโ–Œ | 25/100 [14:53<40:20, 32.27s/trial, best loss: -0.4836]
183
  26%|โ–ˆโ–ˆโ–Œ | 26/100 [15:18<37:18, 30.25s/trial, best loss: -0.4836]
184
  27%|โ–ˆโ–ˆโ–‹ | 27/100 [15:47<36:22, 29.90s/trial, best loss: -0.4836]
185
  28%|โ–ˆโ–ˆโ–Š | 28/100 [16:40<44:02, 36.70s/trial, best loss: -0.4836]
186
  29%|โ–ˆโ–ˆโ–‰ | 29/100 [17:20<44:27, 37.57s/trial, best loss: -0.4836]
187
  30%|โ–ˆโ–ˆโ–ˆ | 30/100 [18:02<45:34, 39.06s/trial, best loss: -0.4836]
188
  31%|โ–ˆโ–ˆโ–ˆ | 31/100 [18:26<39:34, 34.42s/trial, best loss: -0.4836]
189
  32%|โ–ˆโ–ˆโ–ˆโ– | 32/100 [19:00<39:06, 34.51s/trial, best loss: -0.4836]
190
  33%|โ–ˆโ–ˆโ–ˆโ–Ž | 33/100 [19:37<39:24, 35.29s/trial, best loss: -0.4836]
191
  34%|โ–ˆโ–ˆโ–ˆโ– | 34/100 [20:20<41:17, 37.54s/trial, best loss: -0.4836]
192
  35%|โ–ˆโ–ˆโ–ˆโ–Œ | 35/100 [20:46<36:49, 33.99s/trial, best loss: -0.4836]
193
  36%|โ–ˆโ–ˆโ–ˆโ–Œ | 36/100 [21:42<43:21, 40.65s/trial, best loss: -0.4836]
194
  37%|โ–ˆโ–ˆโ–ˆโ–‹ | 37/100 [22:19<41:21, 39.38s/trial, best loss: -0.4836]
195
  38%|โ–ˆโ–ˆโ–ˆโ–Š | 38/100 [23:07<43:38, 42.23s/trial, best loss: -0.4836]
196
  39%|โ–ˆโ–ˆโ–ˆโ–‰ | 39/100 [23:30<36:47, 36.19s/trial, best loss: -0.4836]
197
  40%|โ–ˆโ–ˆโ–ˆโ–ˆ | 40/100 [24:00<34:29, 34.49s/trial, best loss: -0.4836]
198
  41%|โ–ˆโ–ˆโ–ˆโ–ˆ | 41/100 [24:30<32:32, 33.10s/trial, best loss: -0.4836]
199
  42%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 42/100 [24:56<29:53, 30.93s/trial, best loss: -0.4836]
200
  43%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 43/100 [25:27<29:21, 30.90s/trial, best loss: -0.4836]
201
  44%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 44/100 [25:50<26:44, 28.65s/trial, best loss: -0.4836]
202
  45%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 45/100 [26:40<32:11, 35.13s/trial, best loss: -0.4836]
203
  46%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 46/100 [27:16<31:53, 35.43s/trial, best loss: -0.4836]
204
  47%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 47/100 [27:57<32:41, 37.01s/trial, best loss: -0.4836]
205
  48%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 48/100 [28:48<35:47, 41.30s/trial, best loss: -0.4836]
206
  49%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 49/100 [29:27<34:26, 40.53s/trial, best loss: -0.4836]
207
  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 50/100 [29:54<30:25, 36.51s/trial, best loss: -0.4836]
208
  51%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 51/100 [30:53<35:10, 43.06s/trial, best loss: -0.4836]
209
  52%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 52/100 [31:20<30:35, 38.24s/trial, best loss: -0.4836]
210
  53%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 53/100 [31:53<28:54, 36.90s/trial, best loss: -0.4836]
211
  54%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 54/100 [33:09<37:07, 48.43s/trial, best loss: -0.4836]
212
  55%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 55/100 [33:34<31:10, 41.56s/trial, best loss: -0.4836]
213
  56%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 56/100 [33:56<26:01, 35.48s/trial, best loss: -0.4836]
214
  57%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 57/100 [34:25<24:02, 33.54s/trial, best loss: -0.4836]
215
  58%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 58/100 [35:00<23:51, 34.09s/trial, best loss: -0.4836]
216
  59%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 59/100 [35:53<27:15, 39.88s/trial, best loss: -0.4836]
217
  60%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 60/100 [36:31<26:10, 39.26s/trial, best loss: -0.4836]
218
  61%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 61/100 [36:57<22:56, 35.30s/trial, best loss: -0.4836]
219
  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 62/100 [37:32<22:11, 35.04s/trial, best loss: -0.4836]
220
  63%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 63/100 [37:57<19:47, 32.11s/trial, best loss: -0.4836]
221
  64%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 64/100 [38:23<18:11, 30.33s/trial, best loss: -0.4836]
222
  65%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 65/100 [39:08<20:11, 34.62s/trial, best loss: -0.4836]
223
  66%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 66/100 [39:40<19:14, 33.96s/trial, best loss: -0.4836]
224
  67%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 67/100 [40:11<18:06, 32.93s/trial, best loss: -0.4836]
225
  68%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 68/100 [40:36<16:23, 30.74s/trial, best loss: -0.4836]
226
  69%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 69/100 [41:04<15:20, 29.70s/trial, best loss: -0.4836]
227
  70%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 70/100 [41:31<14:34, 29.15s/trial, best loss: -0.4836]
228
  71%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 71/100 [41:55<13:17, 27.51s/trial, best loss: -0.4836]
229
  72%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 72/100 [42:36<14:45, 31.64s/trial, best loss: -0.4836]
230
  73%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 73/100 [43:06<13:58, 31.06s/trial, best loss: -0.4836]
231
  74%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 74/100 [43:34<12:59, 29.97s/trial, best loss: -0.4836]
232
  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 75/100 [44:05<12:43, 30.53s/trial, best loss: -0.4836]
233
  76%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 76/100 [44:46<13:24, 33.52s/trial, best loss: -0.4836]
234
  77%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 77/100 [45:22<13:09, 34.35s/trial, best loss: -0.4836]
235
  78%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 78/100 [45:53<12:11, 33.24s/trial, best loss: -0.4836]
236
  79%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 79/100 [46:20<10:58, 31.38s/trial, best loss: -0.4836]
237
  80%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 80/100 [46:45<09:51, 29.59s/trial, best loss: -0.4836]
238
  81%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 81/100 [47:20<09:53, 31.23s/trial, best loss: -0.4836]
239
  82%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 82/100 [47:51<09:19, 31.11s/trial, best loss: -0.4836]
240
  83%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 83/100 [48:23<08:55, 31.49s/trial, best loss: -0.4836]
241
  84%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 84/100 [49:06<09:14, 34.66s/trial, best loss: -0.4836]
242
  85%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 85/100 [49:31<07:59, 31.94s/trial, best loss: -0.4836]
243
  86%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 86/100 [50:18<08:28, 36.32s/trial, best loss: -0.4836]
244
  87%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 87/100 [51:01<08:20, 38.50s/trial, best loss: -0.4836]
245
  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 88/100 [52:08<09:24, 47.02s/trial, best loss: -0.4836]
246
  89%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 89/100 [52:57<08:43, 47.60s/trial, best loss: -0.4836]
247
  90%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 90/100 [53:37<07:31, 45.17s/trial, best loss: -0.4836]
248
  91%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 91/100 [54:28<07:04, 47.18s/trial, best loss: -0.4836]
249
  92%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 92/100 [55:14<06:13, 46.70s/trial, best loss: -0.4836]
250
  93%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž| 93/100 [56:21<06:08, 52.71s/trial, best loss: -0.4836]
251
  94%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 94/100 [57:02<04:55, 49.27s/trial, best loss: -0.4836]
252
  95%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ| 95/100 [57:39<03:48, 45.62s/trial, best loss: -0.4836]
253
  96%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ| 96/100 [58:33<03:12, 48.15s/trial, best loss: -0.4836]
254
  97%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹| 97/100 [59:14<02:17, 45.95s/trial, best loss: -0.4836]
255
  98%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š| 98/100 [59:54<01:28, 44.22s/trial, best loss: -0.4836]
256
  99%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰| 99/100 [1:00:48<00:47, 47.12s/trial, best loss: -0.4836]
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
257
  0%| | 0/100 [00:00<?, ?trial/s, best loss=?]
258
  1%| | 1/100 [00:18<31:06, 18.85s/trial, best loss: -0.3977]
259
  2%|โ– | 2/100 [00:59<52:04, 31.88s/trial, best loss: -0.4107]
260
  3%|โ–Ž | 3/100 [01:25<46:42, 28.89s/trial, best loss: -0.4107]
261
  4%|โ– | 4/100 [02:15<59:36, 37.25s/trial, best loss: -0.4107]
262
  5%|โ–Œ | 5/100 [02:48<56:54, 35.94s/trial, best loss: -0.4107]
263
  6%|โ–Œ | 6/100 [03:16<52:00, 33.20s/trial, best loss: -0.4107]
264
  7%|โ–‹ | 7/100 [04:01<57:30, 37.10s/trial, best loss: -0.4107]
265
  8%|โ–Š | 8/100 [04:43<58:56, 38.44s/trial, best loss: -0.4107]
266
  9%|โ–‰ | 9/100 [05:10<52:53, 34.88s/trial, best loss: -0.4107]
267
  10%|โ–ˆ | 10/100 [05:34<47:28, 31.65s/trial, best loss: -0.4107]
268
  11%|โ–ˆ | 11/100 [06:25<55:28, 37.39s/trial, best loss: -0.4107]
269
  12%|โ–ˆโ– | 12/100 [06:52<50:33, 34.47s/trial, best loss: -0.4107]
270
  13%|โ–ˆโ–Ž | 13/100 [07:15<44:44, 30.85s/trial, best loss: -0.4155]
271
  14%|โ–ˆโ– | 14/100 [07:47<44:52, 31.31s/trial, best loss: -0.4155]
272
  15%|โ–ˆโ–Œ | 15/100 [08:10<40:45, 28.77s/trial, best loss: -0.4161]
273
  16%|โ–ˆโ–Œ | 16/100 [08:33<37:35, 26.85s/trial, best loss: -0.4161]
274
  17%|โ–ˆโ–‹ | 17/100 [09:15<43:36, 31.53s/trial, best loss: -0.4161]
275
  18%|โ–ˆโ–Š | 18/100 [09:51<45:05, 32.99s/trial, best loss: -0.4161]
276
  19%|โ–ˆโ–‰ | 19/100 [10:14<40:11, 29.77s/trial, best loss: -0.4161]
277
  20%|โ–ˆโ–ˆ | 20/100 [11:04<48:02, 36.03s/trial, best loss: -0.4161]
278
  21%|โ–ˆโ–ˆ | 21/100 [11:25<41:14, 31.32s/trial, best loss: -0.4203]
279
  22%|โ–ˆโ–ˆโ– | 22/100 [11:51<38:51, 29.89s/trial, best loss: -0.4203]
280
  23%|โ–ˆโ–ˆโ–Ž | 23/100 [12:16<36:18, 28.29s/trial, best loss: -0.4203]
281
  24%|โ–ˆโ–ˆโ– | 24/100 [12:42<35:07, 27.72s/trial, best loss: -0.4203]
282
  25%|โ–ˆโ–ˆโ–Œ | 25/100 [13:04<32:21, 25.88s/trial, best loss: -0.4203]
283
  26%|โ–ˆโ–ˆโ–Œ | 26/100 [13:25<30:16, 24.54s/trial, best loss: -0.4203]
284
  27%|โ–ˆโ–ˆโ–‹ | 27/100 [13:46<28:42, 23.60s/trial, best loss: -0.4203]
285
  28%|โ–ˆโ–ˆโ–Š | 28/100 [14:08<27:40, 23.06s/trial, best loss: -0.4203]
286
  29%|โ–ˆโ–ˆโ–‰ | 29/100 [14:33<27:46, 23.47s/trial, best loss: -0.4203]
287
  30%|โ–ˆโ–ˆโ–ˆ | 30/100 [14:53<26:12, 22.46s/trial, best loss: -0.4207]
288
  31%|โ–ˆโ–ˆโ–ˆ | 31/100 [15:14<25:33, 22.22s/trial, best loss: -0.4254]
289
  32%|โ–ˆโ–ˆโ–ˆโ– | 32/100 [15:36<24:48, 21.90s/trial, best loss: -0.4254]
290
  33%|โ–ˆโ–ˆโ–ˆโ–Ž | 33/100 [15:57<24:20, 21.80s/trial, best loss: -0.4254]
291
  34%|โ–ˆโ–ˆโ–ˆโ– | 34/100 [16:19<23:58, 21.79s/trial, best loss: -0.4254]
292
  35%|โ–ˆโ–ˆโ–ˆโ–Œ | 35/100 [16:47<25:30, 23.55s/trial, best loss: -0.4254]
293
  36%|โ–ˆโ–ˆโ–ˆโ–Œ | 36/100 [17:12<25:35, 24.00s/trial, best loss: -0.4254]
294
  37%|โ–ˆโ–ˆโ–ˆโ–‹ | 37/100 [17:34<24:35, 23.42s/trial, best loss: -0.4254]
295
  38%|โ–ˆโ–ˆโ–ˆโ–Š | 38/100 [18:02<25:41, 24.86s/trial, best loss: -0.4254]
296
  39%|โ–ˆโ–ˆโ–ˆโ–‰ | 39/100 [18:24<24:19, 23.93s/trial, best loss: -0.4254]
297
  40%|โ–ˆโ–ˆโ–ˆโ–ˆ | 40/100 [18:50<24:31, 24.52s/trial, best loss: -0.4254]
298
  41%|โ–ˆโ–ˆโ–ˆโ–ˆ | 41/100 [19:17<25:04, 25.51s/trial, best loss: -0.4254]
299
  42%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 42/100 [19:50<26:51, 27.78s/trial, best loss: -0.4254]
300
  43%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 43/100 [20:16<25:36, 26.96s/trial, best loss: -0.4254]
301
  44%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 44/100 [20:49<27:04, 29.00s/trial, best loss: -0.4254]
302
  45%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 45/100 [21:07<23:36, 25.75s/trial, best loss: -0.4254]
303
  46%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 46/100 [21:26<21:14, 23.60s/trial, best loss: -0.4254]
304
  47%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 47/100 [21:49<20:41, 23.42s/trial, best loss: -0.4254]
305
  48%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 48/100 [22:09<19:27, 22.45s/trial, best loss: -0.4254]
306
  49%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 49/100 [23:08<28:18, 33.30s/trial, best loss: -0.4254]
307
  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 50/100 [23:33<25:45, 30.90s/trial, best loss: -0.4254]
308
  51%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 51/100 [23:54<22:51, 27.99s/trial, best loss: -0.4254]
309
  52%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 52/100 [24:46<28:08, 35.17s/trial, best loss: -0.4255]
310
  53%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 53/100 [25:19<26:54, 34.35s/trial, best loss: -0.4255]
311
  54%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 54/100 [26:00<27:54, 36.41s/trial, best loss: -0.4255]
312
  55%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 55/100 [26:52<30:51, 41.14s/trial, best loss: -0.4255]
313
  56%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 56/100 [27:21<27:32, 37.55s/trial, best loss: -0.4255]
314
  57%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 57/100 [27:54<25:48, 36.01s/trial, best loss: -0.4255]
315
  58%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 58/100 [28:38<27:00, 38.59s/trial, best loss: -0.4308]
316
  59%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 59/100 [29:22<27:21, 40.03s/trial, best loss: -0.4308]
317
  60%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 60/100 [29:55<25:16, 37.92s/trial, best loss: -0.4308]
318
  61%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 61/100 [30:42<26:27, 40.70s/trial, best loss: -0.4308]
319
  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 62/100 [31:22<25:35, 40.40s/trial, best loss: -0.4308]
320
  63%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 63/100 [32:08<26:04, 42.29s/trial, best loss: -0.4308]
321
  64%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 64/100 [32:58<26:41, 44.49s/trial, best loss: -0.4308]
322
  65%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 65/100 [33:35<24:39, 42.28s/trial, best loss: -0.4308]
323
  66%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 66/100 [34:26<25:30, 45.01s/trial, best loss: -0.4308]
324
  67%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 67/100 [35:12<24:52, 45.21s/trial, best loss: -0.4308]
325
  68%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 68/100 [36:03<25:03, 47.00s/trial, best loss: -0.4308]
326
  69%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 69/100 [36:49<24:05, 46.63s/trial, best loss: -0.4308]
327
  70%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 70/100 [37:31<22:40, 45.35s/trial, best loss: -0.4308]
328
  71%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 71/100 [38:07<20:28, 42.35s/trial, best loss: -0.4308]
329
  72%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 72/100 [38:45<19:12, 41.15s/trial, best loss: -0.4308]
330
  73%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 73/100 [39:21<17:45, 39.48s/trial, best loss: -0.4308]
331
  74%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 74/100 [39:55<16:22, 37.80s/trial, best loss: -0.4308]
332
  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 75/100 [40:30<15:26, 37.07s/trial, best loss: -0.4308]
333
  76%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 76/100 [41:12<15:22, 38.43s/trial, best loss: -0.4308]
334
  77%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 77/100 [41:43<13:55, 36.31s/trial, best loss: -0.4308]
335
  78%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 78/100 [42:09<12:10, 33.21s/trial, best loss: -0.4308]
336
  79%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 79/100 [42:37<11:02, 31.57s/trial, best loss: -0.4308]
337
  80%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 80/100 [43:10<10:44, 32.23s/trial, best loss: -0.4308]
338
  81%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 81/100 [43:46<10:28, 33.10s/trial, best loss: -0.4308]
339
  82%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 82/100 [44:40<11:49, 39.44s/trial, best loss: -0.4317]
340
  83%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 83/100 [45:16<10:55, 38.57s/trial, best loss: -0.4317]
341
  84%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 84/100 [46:07<11:13, 42.10s/trial, best loss: -0.4317]
342
  85%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 85/100 [47:05<11:43, 46.91s/trial, best loss: -0.4317]
343
  86%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 86/100 [47:54<11:05, 47.51s/trial, best loss: -0.4317]
344
  87%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 87/100 [48:33<09:44, 44.98s/trial, best loss: -0.4317]
345
  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 88/100 [48:57<07:46, 38.87s/trial, best loss: -0.4317]
346
  89%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 89/100 [49:25<06:31, 35.56s/trial, best loss: -0.4317]
347
  90%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 90/100 [50:23<07:01, 42.18s/trial, best loss: -0.4339]
348
  91%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 91/100 [51:11<06:35, 43.97s/trial, best loss: -0.4339]
349
  92%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 92/100 [52:08<06:21, 47.75s/trial, best loss: -0.4339]
350
  93%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž| 93/100 [52:49<05:21, 45.99s/trial, best loss: -0.4339]
351
  94%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 94/100 [53:41<04:45, 47.66s/trial, best loss: -0.4339]
352
  95%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ| 95/100 [54:27<03:56, 47.24s/trial, best loss: -0.4339]
353
  96%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ| 96/100 [55:20<03:14, 48.75s/trial, best loss: -0.4339]
354
  97%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹| 97/100 [55:47<02:06, 42.27s/trial, best loss: -0.4339]
355
  98%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š| 98/100 [56:52<01:38, 49.05s/trial, best loss: -0.4339]
356
  99%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰| 99/100 [57:25<00:44, 44.40s/trial, best loss: -0.4339]
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
357
  0%| | 0/100 [00:00<?, ?trial/s, best loss=?]
358
  1%| | 1/100 [00:28<47:17, 28.66s/trial, best loss: -0.4792]
359
  2%|โ– | 2/100 [01:38<1:25:59, 52.65s/trial, best loss: -0.4833]
360
  3%|โ–Ž | 3/100 [02:12<1:11:30, 44.23s/trial, best loss: -0.4833]
361
  4%|โ– | 4/100 [02:44<1:02:52, 39.29s/trial, best loss: -0.4833]
362
  5%|โ–Œ | 5/100 [03:08<53:32, 33.81s/trial, best loss: -0.4833]
363
  6%|โ–Œ | 6/100 [03:41<52:46, 33.68s/trial, best loss: -0.4833]
364
  7%|โ–‹ | 7/100 [04:23<56:25, 36.40s/trial, best loss: -0.4833]
365
  8%|โ–Š | 8/100 [05:32<1:11:34, 46.68s/trial, best loss: -0.4833]
366
  9%|โ–‰ | 9/100 [06:02<1:02:47, 41.41s/trial, best loss: -0.4864]
367
  10%|โ–ˆ | 10/100 [07:04<1:12:04, 48.05s/trial, best loss: -0.4864]
368
  11%|โ–ˆ | 11/100 [07:31<1:01:24, 41.40s/trial, best loss: -0.4864]
369
  12%|โ–ˆโ– | 12/100 [07:54<52:32, 35.82s/trial, best loss: -0.4864]
370
  13%|โ–ˆโ–Ž | 13/100 [09:06<1:07:45, 46.72s/trial, best loss: -0.4878]
371
  14%|โ–ˆโ– | 14/100 [09:35<59:23, 41.44s/trial, best loss: -0.4878]
372
  15%|โ–ˆโ–Œ | 15/100 [10:15<58:02, 40.98s/trial, best loss: -0.4878]
373
  16%|โ–ˆโ–Œ | 16/100 [10:42<51:40, 36.91s/trial, best loss: -0.4878]
374
  17%|โ–ˆโ–‹ | 17/100 [11:16<49:36, 35.86s/trial, best loss: -0.4878]
375
  18%|โ–ˆโ–Š | 18/100 [11:59<52:13, 38.21s/trial, best loss: -0.4878]
376
  19%|โ–ˆโ–‰ | 19/100 [12:54<58:10, 43.09s/trial, best loss: -0.4878]
377
  20%|โ–ˆโ–ˆ | 20/100 [13:18<50:04, 37.56s/trial, best loss: -0.4878]
378
  21%|โ–ˆโ–ˆ | 21/100 [14:05<53:03, 40.30s/trial, best loss: -0.4878]
379
  22%|โ–ˆโ–ˆโ– | 22/100 [14:40<50:06, 38.54s/trial, best loss: -0.4878]
380
  23%|โ–ˆโ–ˆโ–Ž | 23/100 [15:37<56:52, 44.32s/trial, best loss: -0.4878]
381
  24%|โ–ˆโ–ˆโ– | 24/100 [16:00<47:53, 37.81s/trial, best loss: -0.4878]
382
  25%|โ–ˆโ–ˆโ–Œ | 25/100 [17:12<1:00:06, 48.08s/trial, best loss: -0.4878]
383
  26%|โ–ˆโ–ˆโ–Œ | 26/100 [17:39<51:24, 41.69s/trial, best loss: -0.4878]
384
  27%|โ–ˆโ–ˆโ–‹ | 27/100 [18:33<55:09, 45.34s/trial, best loss: -0.4878]
385
  28%|โ–ˆโ–ˆโ–Š | 28/100 [19:15<53:28, 44.56s/trial, best loss: -0.4878]
386
  29%|โ–ˆโ–ˆโ–‰ | 29/100 [19:59<52:25, 44.30s/trial, best loss: -0.4878]
387
  30%|โ–ˆโ–ˆโ–ˆ | 30/100 [20:24<44:59, 38.56s/trial, best loss: -0.4878]
388
  31%|โ–ˆโ–ˆโ–ˆ | 31/100 [21:21<50:25, 43.84s/trial, best loss: -0.4878]
389
  32%|โ–ˆโ–ˆโ–ˆโ– | 32/100 [22:25<56:51, 50.17s/trial, best loss: -0.4878]
390
  33%|โ–ˆโ–ˆโ–ˆโ–Ž | 33/100 [22:54<48:42, 43.62s/trial, best loss: -0.4878]
391
  34%|โ–ˆโ–ˆโ–ˆโ– | 34/100 [23:21<42:43, 38.84s/trial, best loss: -0.4894]
392
  35%|โ–ˆโ–ˆโ–ˆโ–Œ | 35/100 [23:52<39:29, 36.46s/trial, best loss: -0.4894]
393
  36%|โ–ˆโ–ˆโ–ˆโ–Œ | 36/100 [24:14<34:09, 32.02s/trial, best loss: -0.4894]
394
  37%|โ–ˆโ–ˆโ–ˆโ–‹ | 37/100 [25:02<38:37, 36.79s/trial, best loss: -0.4894]
395
  38%|โ–ˆโ–ˆโ–ˆโ–Š | 38/100 [25:30<35:24, 34.27s/trial, best loss: -0.4894]
396
  39%|โ–ˆโ–ˆโ–ˆโ–‰ | 39/100 [26:02<34:10, 33.62s/trial, best loss: -0.4894]
397
  40%|โ–ˆโ–ˆโ–ˆโ–ˆ | 40/100 [26:31<31:57, 31.97s/trial, best loss: -0.4894]
398
  41%|โ–ˆโ–ˆโ–ˆโ–ˆ | 41/100 [27:05<32:16, 32.82s/trial, best loss: -0.4894]
399
  42%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 42/100 [27:45<33:44, 34.91s/trial, best loss: -0.4894]
400
  43%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 43/100 [28:17<32:15, 33.95s/trial, best loss: -0.4894]
401
  44%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 44/100 [28:50<31:28, 33.72s/trial, best loss: -0.4894]
402
  45%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 45/100 [29:24<30:56, 33.75s/trial, best loss: -0.4894]
403
  46%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 46/100 [30:01<31:23, 34.88s/trial, best loss: -0.4894]
404
  47%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 47/100 [30:38<31:23, 35.54s/trial, best loss: -0.4894]
405
  48%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 48/100 [31:05<28:20, 32.71s/trial, best loss: -0.4894]
406
  49%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 49/100 [31:46<30:03, 35.36s/trial, best loss: -0.4894]
407
  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 50/100 [32:24<30:08, 36.17s/trial, best loss: -0.4894]
408
  51%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 51/100 [33:17<33:40, 41.24s/trial, best loss: -0.4894]
409
  52%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 52/100 [33:40<28:34, 35.72s/trial, best loss: -0.4894]
410
  53%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 53/100 [34:57<37:33, 47.95s/trial, best loss: -0.4894]
411
  54%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 54/100 [35:22<31:33, 41.17s/trial, best loss: -0.4894]
412
  55%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 55/100 [36:12<32:59, 43.98s/trial, best loss: -0.4894]
413
  56%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 56/100 [36:39<28:21, 38.67s/trial, best loss: -0.4894]
414
  57%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 57/100 [37:38<32:05, 44.79s/trial, best loss: -0.4894]
415
  58%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 58/100 [38:18<30:26, 43.49s/trial, best loss: -0.4894]
416
  59%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 59/100 [38:46<26:35, 38.90s/trial, best loss: -0.4894]
417
  60%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 60/100 [39:14<23:41, 35.55s/trial, best loss: -0.4894]
418
  61%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 61/100 [40:09<26:51, 41.32s/trial, best loss: -0.4894]
419
  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 62/100 [40:48<25:48, 40.76s/trial, best loss: -0.4894]
420
  63%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 63/100 [41:20<23:25, 37.97s/trial, best loss: -0.4894]
421
  64%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 64/100 [41:54<22:03, 36.77s/trial, best loss: -0.4894]
422
  65%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 65/100 [42:27<20:53, 35.82s/trial, best loss: -0.4894]
423
  66%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 66/100 [43:12<21:46, 38.42s/trial, best loss: -0.4894]
424
  67%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 67/100 [43:46<20:25, 37.13s/trial, best loss: -0.4894]
425
  68%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 68/100 [44:18<19:00, 35.65s/trial, best loss: -0.4894]
426
  69%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 69/100 [44:52<18:09, 35.16s/trial, best loss: -0.4894]
427
  70%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 70/100 [45:42<19:50, 39.67s/trial, best loss: -0.4894]
428
  71%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 71/100 [46:24<19:24, 40.15s/trial, best loss: -0.4894]
429
  72%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 72/100 [46:52<17:05, 36.63s/trial, best loss: -0.4901]
430
  73%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 73/100 [47:36<17:26, 38.74s/trial, best loss: -0.4901]
431
  74%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 74/100 [48:08<15:56, 36.80s/trial, best loss: -0.4901]
432
  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 75/100 [48:34<14:00, 33.61s/trial, best loss: -0.4908]
433
  76%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 76/100 [49:02<12:44, 31.84s/trial, best loss: -0.4908]
434
  77%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 77/100 [49:28<11:29, 29.97s/trial, best loss: -0.4908]
435
  78%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 78/100 [49:52<10:22, 28.28s/trial, best loss: -0.4908]
436
  79%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 79/100 [50:21<10:01, 28.64s/trial, best loss: -0.4908]
437
  80%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 80/100 [50:46<09:11, 27.56s/trial, best loss: -0.4908]
438
  81%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 81/100 [51:16<08:53, 28.06s/trial, best loss: -0.4908]
439
  82%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 82/100 [51:46<08:36, 28.69s/trial, best loss: -0.4908]
440
  83%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 83/100 [52:15<08:10, 28.85s/trial, best loss: -0.4908]
441
  84%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 84/100 [52:46<07:51, 29.44s/trial, best loss: -0.4908]
442
  85%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 85/100 [53:12<07:08, 28.55s/trial, best loss: -0.4908]
443
  86%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 86/100 [53:43<06:48, 29.21s/trial, best loss: -0.4908]
444
  87%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 87/100 [54:08<06:03, 27.99s/trial, best loss: -0.4908]
445
  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 88/100 [54:32<05:20, 26.69s/trial, best loss: -0.4908]
446
  89%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 89/100 [54:56<04:45, 26.00s/trial, best loss: -0.4908]
447
  90%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 90/100 [55:31<04:45, 28.51s/trial, best loss: -0.4908]
448
  91%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 91/100 [56:00<04:20, 28.91s/trial, best loss: -0.4908]
449
  92%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 92/100 [56:37<04:09, 31.18s/trial, best loss: -0.4908]
450
  93%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž| 93/100 [57:05<03:31, 30.15s/trial, best loss: -0.4908]
451
  94%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 94/100 [57:26<02:44, 27.48s/trial, best loss: -0.4908]
452
  95%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ| 95/100 [57:53<02:16, 27.34s/trial, best loss: -0.4908]
453
  96%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ| 96/100 [58:28<01:58, 29.56s/trial, best loss: -0.4908]
454
  97%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹| 97/100 [58:53<01:24, 28.32s/trial, best loss: -0.4908]
455
  98%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š| 98/100 [59:16<00:53, 26.57s/trial, best loss: -0.4908]
456
  99%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰| 99/100 [59:58<00:31, 31.41s/trial, best loss: -0.4908]
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
457
  0%| | 0/100 [00:00<?, ?trial/s, best loss=?]
458
  1%| | 1/100 [01:02<1:42:38, 62.20s/trial, best loss: -0.4807]
459
  2%|โ– | 2/100 [01:49<1:27:01, 53.28s/trial, best loss: -0.4841]
460
  3%|โ–Ž | 3/100 [02:42<1:25:52, 53.12s/trial, best loss: -0.4848]
461
  4%|โ– | 4/100 [03:15<1:12:13, 45.14s/trial, best loss: -0.4916]
462
  5%|โ–Œ | 5/100 [04:13<1:19:05, 49.96s/trial, best loss: -0.4916]
463
  6%|โ–Œ | 6/100 [05:10<1:22:01, 52.35s/trial, best loss: -0.4916]
464
  7%|โ–‹ | 7/100 [05:34<1:06:33, 42.94s/trial, best loss: -0.4916]
465
  8%|โ–Š | 8/100 [06:55<1:24:29, 55.10s/trial, best loss: -0.4916]
466
  9%|โ–‰ | 9/100 [07:43<1:20:06, 52.82s/trial, best loss: -0.4916]
467
  10%|โ–ˆ | 10/100 [08:33<1:18:03, 52.04s/trial, best loss: -0.4916]
468
  11%|โ–ˆ | 11/100 [08:58<1:04:48, 43.69s/trial, best loss: -0.4916]
469
  12%|โ–ˆโ– | 12/100 [09:36<1:01:44, 42.09s/trial, best loss: -0.4916]
470
  13%|โ–ˆโ–Ž | 13/100 [11:00<1:19:31, 54.85s/trial, best loss: -0.4916]
471
  14%|โ–ˆโ– | 14/100 [12:01<1:21:08, 56.61s/trial, best loss: -0.4916]
472
  15%|โ–ˆโ–Œ | 15/100 [12:29<1:08:01, 48.02s/trial, best loss: -0.4916]
473
  16%|โ–ˆโ–Œ | 16/100 [13:15<1:06:13, 47.30s/trial, best loss: -0.4916]
474
  17%|โ–ˆโ–‹ | 17/100 [13:36<54:35, 39.46s/trial, best loss: -0.4916]
475
  18%|โ–ˆโ–Š | 18/100 [14:34<1:01:25, 44.94s/trial, best loss: -0.4916]
476
  19%|โ–ˆโ–‰ | 19/100 [15:04<54:45, 40.56s/trial, best loss: -0.4916]
477
  20%|โ–ˆโ–ˆ | 20/100 [16:14<1:05:52, 49.40s/trial, best loss: -0.4916]
478
  21%|โ–ˆโ–ˆ | 21/100 [16:54<1:01:24, 46.64s/trial, best loss: -0.4971]
479
  22%|โ–ˆโ–ˆโ– | 22/100 [17:30<56:16, 43.29s/trial, best loss: -0.4971]
480
  23%|โ–ˆโ–ˆโ–Ž | 23/100 [18:01<51:01, 39.77s/trial, best loss: -0.4971]
481
  24%|โ–ˆโ–ˆโ– | 24/100 [18:33<47:11, 37.25s/trial, best loss: -0.4971]
482
  25%|โ–ˆโ–ˆโ–Œ | 25/100 [19:12<47:11, 37.75s/trial, best loss: -0.4971]
483
  26%|โ–ˆโ–ˆโ–Œ | 26/100 [19:48<45:54, 37.22s/trial, best loss: -0.4971]
484
  27%|โ–ˆโ–ˆโ–‹ | 27/100 [20:30<47:14, 38.83s/trial, best loss: -0.4971]
485
  28%|โ–ˆโ–ˆโ–Š | 28/100 [21:01<43:51, 36.55s/trial, best loss: -0.4971]
486
  29%|โ–ˆโ–ˆโ–‰ | 29/100 [21:48<47:00, 39.73s/trial, best loss: -0.4971]
487
  30%|โ–ˆโ–ˆโ–ˆ | 30/100 [22:23<44:41, 38.30s/trial, best loss: -0.4971]
488
  31%|โ–ˆโ–ˆโ–ˆ | 31/100 [22:49<39:43, 34.54s/trial, best loss: -0.4971]
489
  32%|โ–ˆโ–ˆโ–ˆโ– | 32/100 [23:13<35:34, 31.39s/trial, best loss: -0.4971]
490
  33%|โ–ˆโ–ˆโ–ˆโ–Ž | 33/100 [23:34<31:37, 28.32s/trial, best loss: -0.4971]
491
  34%|โ–ˆโ–ˆโ–ˆโ– | 34/100 [24:14<35:00, 31.82s/trial, best loss: -0.4971]
492
  35%|โ–ˆโ–ˆโ–ˆโ–Œ | 35/100 [24:59<38:36, 35.64s/trial, best loss: -0.4971]
493
  36%|โ–ˆโ–ˆโ–ˆโ–Œ | 36/100 [25:35<38:10, 35.80s/trial, best loss: -0.4971]
494
  37%|โ–ˆโ–ˆโ–ˆโ–‹ | 37/100 [26:39<46:25, 44.22s/trial, best loss: -0.4971]
495
  38%|โ–ˆโ–ˆโ–ˆโ–Š | 38/100 [27:04<39:35, 38.31s/trial, best loss: -0.4971]
496
  39%|โ–ˆโ–ˆโ–ˆโ–‰ | 39/100 [27:38<37:49, 37.20s/trial, best loss: -0.4971]
497
  40%|โ–ˆโ–ˆโ–ˆโ–ˆ | 40/100 [28:10<35:45, 35.75s/trial, best loss: -0.4971]
498
  41%|โ–ˆโ–ˆโ–ˆโ–ˆ | 41/100 [28:34<31:29, 32.03s/trial, best loss: -0.4971]
499
  42%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 42/100 [29:01<29:39, 30.67s/trial, best loss: -0.4971]
500
  43%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 43/100 [29:33<29:29, 31.05s/trial, best loss: -0.4971]
501
  44%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 44/100 [30:15<32:02, 34.33s/trial, best loss: -0.4971]
502
  45%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 45/100 [30:46<30:33, 33.34s/trial, best loss: -0.4971]
503
  46%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 46/100 [31:18<29:33, 32.84s/trial, best loss: -0.4971]
504
  47%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 47/100 [31:55<30:00, 33.97s/trial, best loss: -0.4971]
505
  48%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 48/100 [32:40<32:31, 37.52s/trial, best loss: -0.4971]
506
  49%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 49/100 [33:06<28:58, 34.08s/trial, best loss: -0.4971]
507
  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 50/100 [33:29<25:34, 30.69s/trial, best loss: -0.4971]
508
  51%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 51/100 [33:54<23:39, 28.96s/trial, best loss: -0.4971]
509
  52%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 52/100 [34:21<22:42, 28.39s/trial, best loss: -0.4971]
510
  53%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 53/100 [34:57<23:53, 30.51s/trial, best loss: -0.4971]
511
  54%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 54/100 [35:35<25:16, 32.96s/trial, best loss: -0.4971]
512
  55%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 55/100 [36:07<24:24, 32.54s/trial, best loss: -0.4971]
513
  56%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 56/100 [37:12<31:05, 42.40s/trial, best loss: -0.4971]
514
  57%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 57/100 [37:49<29:04, 40.57s/trial, best loss: -0.4971]
515
  58%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 58/100 [38:23<27:06, 38.72s/trial, best loss: -0.4971]
516
  59%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 59/100 [38:56<25:20, 37.08s/trial, best loss: -0.4971]
517
  60%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 60/100 [39:30<24:08, 36.22s/trial, best loss: -0.4971]
518
  61%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 61/100 [40:38<29:41, 45.69s/trial, best loss: -0.4971]
519
  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 62/100 [41:09<26:05, 41.21s/trial, best loss: -0.4971]
520
  63%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 63/100 [41:45<24:28, 39.69s/trial, best loss: -0.4971]
521
  64%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 64/100 [42:17<22:26, 37.40s/trial, best loss: -0.4971]
522
  65%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 65/100 [42:46<20:20, 34.88s/trial, best loss: -0.4971]
523
  66%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 66/100 [43:19<19:23, 34.21s/trial, best loss: -0.4994]
524
  67%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 67/100 [43:52<18:36, 33.85s/trial, best loss: -0.4994]
525
  68%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 68/100 [44:26<18:10, 34.08s/trial, best loss: -0.4994]
526
  69%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 69/100 [45:15<19:46, 38.27s/trial, best loss: -0.4994]
527
  70%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 70/100 [45:56<19:36, 39.23s/trial, best loss: -0.4994]
528
  71%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 71/100 [46:41<19:51, 41.09s/trial, best loss: -0.4994]
529
  72%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 72/100 [47:26<19:44, 42.29s/trial, best loss: -0.4994]
530
  73%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 73/100 [48:36<22:40, 50.38s/trial, best loss: -0.4994]
531
  74%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 74/100 [49:12<20:01, 46.21s/trial, best loss: -0.4994]
532
  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 75/100 [49:58<19:11, 46.04s/trial, best loss: -0.4994]
533
  76%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 76/100 [50:36<17:24, 43.52s/trial, best loss: -0.4994]
534
  77%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 77/100 [51:07<15:19, 39.98s/trial, best loss: -0.4994]
535
  78%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 78/100 [52:08<16:54, 46.11s/trial, best loss: -0.4994]
536
  79%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 79/100 [52:46<15:22, 43.92s/trial, best loss: -0.4994]
537
  80%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 80/100 [53:27<14:18, 42.91s/trial, best loss: -0.4994]
538
  81%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 81/100 [53:59<12:33, 39.67s/trial, best loss: -0.4994]
539
  82%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 82/100 [54:47<12:39, 42.19s/trial, best loss: -0.4994]
540
  83%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 83/100 [55:36<12:30, 44.15s/trial, best loss: -0.4994]
541
  84%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 84/100 [56:13<11:10, 41.89s/trial, best loss: -0.4994]
542
  85%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 85/100 [56:50<10:09, 40.66s/trial, best loss: -0.4994]
543
  86%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 86/100 [57:41<10:11, 43.69s/trial, best loss: -0.4994]
544
  87%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 87/100 [58:47<10:54, 50.36s/trial, best loss: -0.4994]
545
  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 88/100 [59:26<09:22, 46.84s/trial, best loss: -0.4994]
546
  89%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 89/100 [1:00:02<08:02, 43.84s/trial, best loss: -0.4994]
547
  90%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 90/100 [1:00:31<06:33, 39.38s/trial, best loss: -0.4994]
548
  91%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 91/100 [1:01:09<05:48, 38.76s/trial, best loss: -0.4994]
549
  92%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 92/100 [1:01:45<05:04, 38.04s/trial, best loss: -0.4994]
550
  93%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž| 93/100 [1:02:39<04:59, 42.76s/trial, best loss: -0.4994]
551
  94%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 94/100 [1:03:06<03:48, 38.12s/trial, best loss: -0.4994]
552
  95%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ| 95/100 [1:03:39<03:02, 36.58s/trial, best loss: -0.4994]
553
  96%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ| 96/100 [1:04:16<02:26, 36.56s/trial, best loss: -0.4994]
554
  97%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹| 97/100 [1:04:51<01:48, 36.21s/trial, best loss: -0.4994]
555
  98%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š| 98/100 [1:05:15<01:05, 32.67s/trial, best loss: -0.4994]
556
  99%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰| 99/100 [1:05:43<00:31, 31.21s/trial, best loss: -0.4994]
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
557
  0%| | 0/100 [00:00<?, ?trial/s, best loss=?]
558
  1%| | 1/100 [00:54<1:30:09, 54.64s/trial, best loss: -0.5469]
559
  2%|โ– | 2/100 [01:19<1:00:47, 37.22s/trial, best loss: -0.5519]
560
  3%|โ–Ž | 3/100 [01:50<55:12, 34.15s/trial, best loss: -0.5519]
561
  4%|โ– | 4/100 [02:25<55:19, 34.57s/trial, best loss: -0.5519]
562
  5%|โ–Œ | 5/100 [03:31<1:12:51, 46.01s/trial, best loss: -0.5557]
563
  6%|โ–Œ | 6/100 [04:02<1:03:56, 40.81s/trial, best loss: -0.5557]
564
  7%|โ–‹ | 7/100 [04:30<56:42, 36.58s/trial, best loss: -0.5557]
565
  8%|โ–Š | 8/100 [05:14<59:48, 39.00s/trial, best loss: -0.5557]
566
  9%|โ–‰ | 9/100 [05:44<54:59, 36.26s/trial, best loss: -0.5557]
567
  10%|โ–ˆ | 10/100 [06:26<56:54, 37.94s/trial, best loss: -0.5557]
568
  11%|โ–ˆ | 11/100 [06:56<52:53, 35.66s/trial, best loss: -0.5557]
569
  12%|โ–ˆโ– | 12/100 [08:02<1:05:32, 44.69s/trial, best loss: -0.5557]
570
  13%|โ–ˆโ–Ž | 13/100 [08:46<1:04:34, 44.53s/trial, best loss: -0.5557]
571
  14%|โ–ˆโ– | 14/100 [09:35<1:05:36, 45.77s/trial, best loss: -0.5557]
572
  15%|โ–ˆโ–Œ | 15/100 [10:59<1:21:31, 57.55s/trial, best loss: -0.5557]
573
  16%|โ–ˆโ–Œ | 16/100 [11:22<1:05:53, 47.07s/trial, best loss: -0.5557]
574
  17%|โ–ˆโ–‹ | 17/100 [12:15<1:07:27, 48.77s/trial, best loss: -0.5557]
575
  18%|โ–ˆโ–Š | 18/100 [12:46<59:16, 43.37s/trial, best loss: -0.5557]
576
  19%|โ–ˆโ–‰ | 19/100 [13:18<54:13, 40.17s/trial, best loss: -0.5557]
577
  20%|โ–ˆโ–ˆ | 20/100 [13:43<47:31, 35.64s/trial, best loss: -0.5557]
578
  21%|โ–ˆโ–ˆ | 21/100 [14:13<44:40, 33.93s/trial, best loss: -0.5557]
579
  22%|โ–ˆโ–ˆโ– | 22/100 [15:23<58:03, 44.67s/trial, best loss: -0.5557]
580
  23%|โ–ˆโ–ˆโ–Ž | 23/100 [15:46<49:03, 38.23s/trial, best loss: -0.5557]
581
  24%|โ–ˆโ–ˆโ– | 24/100 [16:16<45:01, 35.55s/trial, best loss: -0.5557]
582
  25%|โ–ˆโ–ˆโ–Œ | 25/100 [16:48<43:17, 34.64s/trial, best loss: -0.5557]
583
  26%|โ–ˆโ–ˆโ–Œ | 26/100 [17:28<44:29, 36.07s/trial, best loss: -0.5557]
584
  27%|โ–ˆโ–ˆโ–‹ | 27/100 [17:55<40:51, 33.59s/trial, best loss: -0.5557]
585
  28%|โ–ˆโ–ˆโ–Š | 28/100 [18:25<39:01, 32.52s/trial, best loss: -0.556]
586
  29%|โ–ˆโ–ˆโ–‰ | 29/100 [19:42<54:10, 45.78s/trial, best loss: -0.556]
587
  30%|โ–ˆโ–ˆโ–ˆ | 30/100 [20:16<49:15, 42.23s/trial, best loss: -0.556]
588
  31%|โ–ˆโ–ˆโ–ˆ | 31/100 [20:49<45:25, 39.50s/trial, best loss: -0.556]
589
  32%|โ–ˆโ–ˆโ–ˆโ– | 32/100 [21:32<45:48, 40.41s/trial, best loss: -0.556]
590
  33%|โ–ˆโ–ˆโ–ˆโ–Ž | 33/100 [22:16<46:24, 41.57s/trial, best loss: -0.5567]
591
  34%|โ–ˆโ–ˆโ–ˆโ– | 34/100 [22:57<45:31, 41.39s/trial, best loss: -0.5567]
592
  35%|โ–ˆโ–ˆโ–ˆโ–Œ | 35/100 [23:40<45:17, 41.81s/trial, best loss: -0.5567]
593
  36%|โ–ˆโ–ˆโ–ˆโ–Œ | 36/100 [24:46<52:33, 49.28s/trial, best loss: -0.5567]
594
  37%|โ–ˆโ–ˆโ–ˆโ–‹ | 37/100 [25:24<48:09, 45.86s/trial, best loss: -0.558]
595
  38%|โ–ˆโ–ˆโ–ˆโ–Š | 38/100 [26:06<46:08, 44.65s/trial, best loss: -0.558]
596
  39%|โ–ˆโ–ˆโ–ˆโ–‰ | 39/100 [26:54<46:31, 45.76s/trial, best loss: -0.558]
597
  40%|โ–ˆโ–ˆโ–ˆโ–ˆ | 40/100 [27:40<45:35, 45.60s/trial, best loss: -0.558]
598
  41%|โ–ˆโ–ˆโ–ˆโ–ˆ | 41/100 [28:19<42:58, 43.71s/trial, best loss: -0.558]
599
  42%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 42/100 [29:14<45:34, 47.14s/trial, best loss: -0.558]
600
  43%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 43/100 [29:56<43:11, 45.47s/trial, best loss: -0.558]
601
  44%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 44/100 [30:58<47:01, 50.39s/trial, best loss: -0.558]
602
  45%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 45/100 [31:43<44:47, 48.86s/trial, best loss: -0.558]
603
  46%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 46/100 [32:39<46:01, 51.15s/trial, best loss: -0.558]
604
  47%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 47/100 [33:32<45:28, 51.48s/trial, best loss: -0.558]
605
  48%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 48/100 [34:10<41:20, 47.70s/trial, best loss: -0.558]
606
  49%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 49/100 [34:49<38:16, 45.04s/trial, best loss: -0.558]
607
  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 50/100 [35:28<35:54, 43.09s/trial, best loss: -0.558]
608
  51%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 51/100 [36:07<34:20, 42.06s/trial, best loss: -0.558]
609
  52%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 52/100 [36:43<32:09, 40.19s/trial, best loss: -0.558]
610
  53%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 53/100 [37:19<30:30, 38.94s/trial, best loss: -0.558]
611
  54%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 54/100 [37:47<27:17, 35.59s/trial, best loss: -0.558]
612
  55%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 55/100 [38:19<25:50, 34.45s/trial, best loss: -0.558]
613
  56%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 56/100 [39:05<27:44, 37.83s/trial, best loss: -0.558]
614
  57%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 57/100 [39:37<25:53, 36.12s/trial, best loss: -0.558]
615
  58%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 58/100 [40:15<25:40, 36.67s/trial, best loss: -0.558]
616
  59%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 59/100 [40:53<25:27, 37.25s/trial, best loss: -0.558]
617
  60%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 60/100 [41:39<26:29, 39.73s/trial, best loss: -0.558]
618
  61%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 61/100 [42:12<24:36, 37.85s/trial, best loss: -0.558]
619
  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 62/100 [42:45<22:55, 36.21s/trial, best loss: -0.558]
620
  63%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 63/100 [43:34<24:41, 40.05s/trial, best loss: -0.558]
621
  64%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 64/100 [43:56<20:46, 34.61s/trial, best loss: -0.558]
622
  65%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 65/100 [44:36<21:12, 36.36s/trial, best loss: -0.558]
623
  66%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 66/100 [45:08<19:49, 34.98s/trial, best loss: -0.558]
624
  67%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 67/100 [45:36<18:03, 32.83s/trial, best loss: -0.558]
625
  68%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 68/100 [46:02<16:32, 31.03s/trial, best loss: -0.558]
626
  69%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 69/100 [46:45<17:48, 34.45s/trial, best loss: -0.5588]
627
  70%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 70/100 [47:26<18:11, 36.38s/trial, best loss: -0.5588]
628
  71%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 71/100 [48:08<18:24, 38.10s/trial, best loss: -0.5588]
629
  72%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 72/100 [48:40<16:57, 36.33s/trial, best loss: -0.5588]
630
  73%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 73/100 [49:47<20:26, 45.41s/trial, best loss: -0.5588]
631
  74%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 74/100 [50:25<18:42, 43.17s/trial, best loss: -0.5588]
632
  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 75/100 [51:28<20:32, 49.28s/trial, best loss: -0.5588]
633
  76%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 76/100 [52:21<20:06, 50.28s/trial, best loss: -0.5588]
634
  77%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 77/100 [53:03<18:18, 47.74s/trial, best loss: -0.5588]
635
  78%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 78/100 [53:47<17:11, 46.87s/trial, best loss: -0.5588]
636
  79%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 79/100 [54:27<15:40, 44.78s/trial, best loss: -0.5588]
637
  80%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 80/100 [55:22<15:58, 47.90s/trial, best loss: -0.5588]
638
  81%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 81/100 [55:57<13:54, 43.91s/trial, best loss: -0.5588]
639
  82%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 82/100 [56:31<12:14, 40.78s/trial, best loss: -0.5588]
640
  83%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 83/100 [57:01<10:39, 37.63s/trial, best loss: -0.5588]
641
  84%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 84/100 [57:42<10:18, 38.68s/trial, best loss: -0.5588]
642
  85%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 85/100 [58:32<10:29, 41.95s/trial, best loss: -0.5588]
643
  86%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 86/100 [59:09<09:27, 40.52s/trial, best loss: -0.5588]
644
  87%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 87/100 [59:52<08:58, 41.40s/trial, best loss: -0.5588]
645
  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 88/100 [1:00:15<07:08, 35.74s/trial, best loss: -0.5588]
646
  89%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 89/100 [1:00:53<06:40, 36.37s/trial, best loss: -0.5588]
647
  90%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 90/100 [1:01:38<06:30, 39.04s/trial, best loss: -0.5588]
648
  91%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 91/100 [1:02:20<05:59, 39.93s/trial, best loss: -0.5588]
649
  92%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 92/100 [1:03:11<05:45, 43.19s/trial, best loss: -0.5592]
650
  93%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž| 93/100 [1:04:06<05:27, 46.72s/trial, best loss: -0.5592]
651
  94%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 94/100 [1:05:23<05:34, 55.81s/trial, best loss: -0.5592]
652
  95%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ| 95/100 [1:06:36<05:05, 61.13s/trial, best loss: -0.5592]
653
  96%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ| 96/100 [1:07:16<03:39, 54.80s/trial, best loss: -0.5592]
654
  97%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹| 97/100 [1:07:55<02:30, 50.12s/trial, best loss: -0.5592]
655
  98%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š| 98/100 [1:08:36<01:34, 47.21s/trial, best loss: -0.5592]
656
  99%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰| 99/100 [1:09:51<00:55, 55.54s/trial, best loss: -0.5592]
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
657
  0%| | 0/100 [00:00<?, ?trial/s, best loss=?]
658
  1%| | 1/100 [01:13<2:01:00, 73.34s/trial, best loss: -0.5479]
659
  2%|โ– | 2/100 [01:43<1:18:00, 47.76s/trial, best loss: -0.5552]
660
  3%|โ–Ž | 3/100 [02:04<57:22, 35.48s/trial, best loss: -0.558]
661
  4%|โ– | 4/100 [03:04<1:12:39, 45.41s/trial, best loss: -0.558]
662
  5%|โ–Œ | 5/100 [03:45<1:09:30, 43.90s/trial, best loss: -0.558]
663
  6%|โ–Œ | 6/100 [04:11<58:53, 37.59s/trial, best loss: -0.5639]
664
  7%|โ–‹ | 7/100 [04:54<1:01:02, 39.38s/trial, best loss: -0.5639]
665
  8%|โ–Š | 8/100 [05:50<1:08:46, 44.86s/trial, best loss: -0.5639]
666
  9%|โ–‰ | 9/100 [06:40<1:10:17, 46.34s/trial, best loss: -0.5639]
667
  10%|โ–ˆ | 10/100 [07:29<1:10:30, 47.01s/trial, best loss: -0.5639]
668
  11%|โ–ˆ | 11/100 [08:14<1:08:51, 46.42s/trial, best loss: -0.5639]
669
  12%|โ–ˆโ– | 12/100 [08:33<56:03, 38.22s/trial, best loss: -0.5639]
670
  13%|โ–ˆโ–Ž | 13/100 [08:57<49:03, 33.84s/trial, best loss: -0.5639]
671
  14%|โ–ˆโ– | 14/100 [09:20<43:45, 30.53s/trial, best loss: -0.5639]
672
  15%|โ–ˆโ–Œ | 15/100 [09:49<42:37, 30.09s/trial, best loss: -0.5639]
673
  16%|โ–ˆโ–Œ | 16/100 [11:05<1:01:44, 44.10s/trial, best loss: -0.5639]
674
  17%|โ–ˆโ–‹ | 17/100 [11:51<1:01:40, 44.58s/trial, best loss: -0.5639]
675
  18%|โ–ˆโ–Š | 18/100 [12:21<55:03, 40.28s/trial, best loss: -0.5639]
676
  19%|โ–ˆโ–‰ | 19/100 [12:46<47:51, 35.45s/trial, best loss: -0.5639]
677
  20%|โ–ˆโ–ˆ | 20/100 [13:30<50:43, 38.05s/trial, best loss: -0.5639]
678
  21%|โ–ˆโ–ˆ | 21/100 [13:54<44:35, 33.86s/trial, best loss: -0.5639]
679
  22%|โ–ˆโ–ˆโ– | 22/100 [14:21<41:16, 31.75s/trial, best loss: -0.5639]
680
  23%|โ–ˆโ–ˆโ–Ž | 23/100 [14:43<37:04, 28.89s/trial, best loss: -0.5639]
681
  24%|โ–ˆโ–ˆโ– | 24/100 [15:09<35:34, 28.08s/trial, best loss: -0.5639]
682
  25%|โ–ˆโ–ˆโ–Œ | 25/100 [15:31<32:49, 26.26s/trial, best loss: -0.5639]
683
  26%|โ–ˆโ–ˆโ–Œ | 26/100 [15:54<31:08, 25.25s/trial, best loss: -0.5639]
684
  27%|โ–ˆโ–ˆโ–‹ | 27/100 [16:19<30:45, 25.28s/trial, best loss: -0.5639]
685
  28%|โ–ˆโ–ˆโ–Š | 28/100 [16:46<30:58, 25.81s/trial, best loss: -0.5639]
686
  29%|โ–ˆโ–ˆโ–‰ | 29/100 [17:08<28:59, 24.51s/trial, best loss: -0.5639]
687
  30%|โ–ˆโ–ˆโ–ˆ | 30/100 [17:43<32:21, 27.74s/trial, best loss: -0.5639]
688
  31%|โ–ˆโ–ˆโ–ˆ | 31/100 [18:09<31:10, 27.11s/trial, best loss: -0.5639]
689
  32%|โ–ˆโ–ˆโ–ˆโ– | 32/100 [18:37<31:01, 27.38s/trial, best loss: -0.5639]
690
  33%|โ–ˆโ–ˆโ–ˆโ–Ž | 33/100 [19:01<29:22, 26.31s/trial, best loss: -0.5639]
691
  34%|โ–ˆโ–ˆโ–ˆโ– | 34/100 [19:30<30:00, 27.28s/trial, best loss: -0.5639]
692
  35%|โ–ˆโ–ˆโ–ˆโ–Œ | 35/100 [19:58<29:44, 27.46s/trial, best loss: -0.5639]
693
  36%|โ–ˆโ–ˆโ–ˆโ–Œ | 36/100 [20:22<28:19, 26.55s/trial, best loss: -0.5639]
694
  37%|โ–ˆโ–ˆโ–ˆโ–‹ | 37/100 [21:29<40:25, 38.50s/trial, best loss: -0.5639]
695
  38%|โ–ˆโ–ˆโ–ˆโ–Š | 38/100 [21:51<34:50, 33.72s/trial, best loss: -0.5639]
696
  39%|โ–ˆโ–ˆโ–ˆโ–‰ | 39/100 [22:17<31:58, 31.44s/trial, best loss: -0.5639]
697
  40%|โ–ˆโ–ˆโ–ˆโ–ˆ | 40/100 [22:41<28:57, 28.96s/trial, best loss: -0.5639]
698
  41%|โ–ˆโ–ˆโ–ˆโ–ˆ | 41/100 [23:15<30:07, 30.63s/trial, best loss: -0.5639]
699
  42%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 42/100 [23:39<27:46, 28.74s/trial, best loss: -0.5639]
700
  43%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 43/100 [24:00<25:01, 26.34s/trial, best loss: -0.5639]
701
  44%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 44/100 [24:27<24:44, 26.51s/trial, best loss: -0.5639]
702
  45%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 45/100 [25:06<27:45, 30.28s/trial, best loss: -0.5639]
703
  46%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 46/100 [26:00<33:30, 37.23s/trial, best loss: -0.5639]
704
  47%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 47/100 [26:37<32:59, 37.35s/trial, best loss: -0.5639]
705
  48%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 48/100 [27:20<33:53, 39.11s/trial, best loss: -0.5639]
706
  49%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 49/100 [28:20<38:25, 45.22s/trial, best loss: -0.5639]
707
  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 50/100 [28:53<34:36, 41.53s/trial, best loss: -0.5639]
708
  51%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 51/100 [29:31<32:57, 40.36s/trial, best loss: -0.5639]
709
  52%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 52/100 [30:14<32:59, 41.23s/trial, best loss: -0.5639]
710
  53%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 53/100 [30:47<30:18, 38.70s/trial, best loss: -0.5639]
711
  54%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 54/100 [31:18<28:03, 36.61s/trial, best loss: -0.5639]
712
  55%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 55/100 [31:49<26:11, 34.93s/trial, best loss: -0.5639]
713
  56%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 56/100 [32:46<30:26, 41.51s/trial, best loss: -0.5639]
714
  57%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 57/100 [33:33<30:59, 43.25s/trial, best loss: -0.5639]
715
  58%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 58/100 [34:05<27:50, 39.78s/trial, best loss: -0.5639]
716
  59%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 59/100 [34:53<28:45, 42.09s/trial, best loss: -0.5639]
717
  60%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 60/100 [35:17<24:35, 36.90s/trial, best loss: -0.5639]
718
  61%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 61/100 [35:44<22:03, 33.93s/trial, best loss: -0.5639]
719
  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 62/100 [36:08<19:31, 30.83s/trial, best loss: -0.5639]
720
  63%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 63/100 [36:36<18:26, 29.91s/trial, best loss: -0.5639]
721
  64%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 64/100 [36:56<16:16, 27.13s/trial, best loss: -0.5639]
722
  65%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 65/100 [37:22<15:30, 26.57s/trial, best loss: -0.5639]
723
  66%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 66/100 [37:54<16:05, 28.41s/trial, best loss: -0.5655]
724
  67%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 67/100 [38:28<16:32, 30.06s/trial, best loss: -0.5655]
725
  68%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 68/100 [39:05<17:07, 32.12s/trial, best loss: -0.5655]
726
  69%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 69/100 [39:35<16:15, 31.48s/trial, best loss: -0.5655]
727
  70%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 70/100 [40:17<17:17, 34.58s/trial, best loss: -0.5655]
728
  71%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 71/100 [40:41<15:13, 31.49s/trial, best loss: -0.5655]
729
  72%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 72/100 [41:26<16:34, 35.53s/trial, best loss: -0.5655]
730
  73%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 73/100 [41:53<14:51, 33.02s/trial, best loss: -0.5655]
731
  74%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 74/100 [42:31<14:57, 34.53s/trial, best loss: -0.5655]
732
  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 75/100 [43:02<13:50, 33.22s/trial, best loss: -0.5655]
733
  76%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 76/100 [43:46<14:37, 36.58s/trial, best loss: -0.5655]
734
  77%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 77/100 [44:15<13:06, 34.20s/trial, best loss: -0.5655]
735
  78%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 78/100 [44:47<12:22, 33.75s/trial, best loss: -0.5655]
736
  79%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 79/100 [45:17<11:20, 32.40s/trial, best loss: -0.5655]
737
  80%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 80/100 [45:48<10:41, 32.08s/trial, best loss: -0.5655]
738
  81%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 81/100 [46:27<10:47, 34.07s/trial, best loss: -0.5655]
739
  82%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 82/100 [47:05<10:36, 35.34s/trial, best loss: -0.5655]
740
  83%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 83/100 [47:37<09:44, 34.37s/trial, best loss: -0.5655]
741
  84%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 84/100 [48:20<09:50, 36.90s/trial, best loss: -0.5655]
742
  85%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 85/100 [48:51<08:46, 35.11s/trial, best loss: -0.5655]
743
  86%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 86/100 [49:25<08:06, 34.73s/trial, best loss: -0.5655]
744
  87%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 87/100 [49:56<07:16, 33.56s/trial, best loss: -0.5655]
745
  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 88/100 [50:33<06:56, 34.70s/trial, best loss: -0.566]
746
  89%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 89/100 [51:19<06:57, 37.99s/trial, best loss: -0.566]
747
  90%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 90/100 [51:54<06:10, 37.08s/trial, best loss: -0.566]
748
  91%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 91/100 [52:47<06:18, 42.10s/trial, best loss: -0.566]
749
  92%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 92/100 [53:24<05:23, 40.43s/trial, best loss: -0.5671]
750
  93%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž| 93/100 [54:01<04:36, 39.53s/trial, best loss: -0.5671]
751
  94%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 94/100 [54:56<04:24, 44.12s/trial, best loss: -0.5671]
752
  95%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ| 95/100 [55:34<03:31, 42.24s/trial, best loss: -0.5671]
753
  96%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ| 96/100 [56:12<02:43, 40.95s/trial, best loss: -0.5671]
754
  97%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹| 97/100 [56:56<02:05, 41.79s/trial, best loss: -0.5671]
755
  98%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š| 98/100 [57:43<01:26, 43.42s/trial, best loss: -0.5671]
756
  99%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰| 99/100 [58:35<00:45, 45.96s/trial, best loss: -0.5671]
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ nohup: ignoring input
2
+ /bin/bash: /opt/conda/lib/libtinfo.so.6: no version information available (required by /bin/bash)
3
+ ==========================================
4
+ LGB CTGAN10000 ํŒŒ์ผ ์‹คํ–‰ ์‹œ์ž‘
5
+ ์‹œ์ž‘ ์‹œ๊ฐ„: 2025-12-28 04:29:39
6
+ GPU: 1๋ฒˆ (CUDA_VISIBLE_DEVICES=1)
7
+ ==========================================
8
+
9
+ ----------------------------------------
10
+ ์‹คํ–‰ ์ค‘: lgb_ctgan10000/LGB_ctgan10000_busan.py
11
+ ์‹œ์ž‘ ์‹œ๊ฐ„: 2025-12-28 04:29:39
12
+ ----------------------------------------
13
+ ๋ฐ์ดํ„ฐ ๋กœ๋”ฉ ์ค‘...
14
+ ๋ฐ์ดํ„ฐ ์ „์ฒ˜๋ฆฌ ์ค‘...
15
+ ํ•˜์ดํผํŒŒ๋ผ๋ฏธํ„ฐ ์ตœ์ ํ™” ์‹œ์ž‘...
16
+
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
17
  0%| | 0/100 [00:00<?, ?trial/s, best loss=?]
18
  1%| | 1/100 [01:04<1:47:14, 65.00s/trial, best loss: -0.4238]
19
  2%|โ– | 2/100 [01:54<1:31:25, 55.98s/trial, best loss: -0.4576]
20
  3%|โ–Ž | 3/100 [02:31<1:16:36, 47.39s/trial, best loss: -0.4733]
21
  4%|โ– | 4/100 [03:21<1:17:24, 48.38s/trial, best loss: -0.4758]
22
  5%|โ–Œ | 5/100 [04:00<1:10:52, 44.77s/trial, best loss: -0.4758]
23
  6%|โ–Œ | 6/100 [04:24<59:01, 37.68s/trial, best loss: -0.4758]
24
  7%|โ–‹ | 7/100 [04:54<54:54, 35.42s/trial, best loss: -0.4758]
25
  8%|โ–Š | 8/100 [05:41<59:49, 39.02s/trial, best loss: -0.4758]
26
  9%|โ–‰ | 9/100 [06:04<51:22, 33.87s/trial, best loss: -0.4758]
27
  10%|โ–ˆ | 10/100 [06:52<57:39, 38.44s/trial, best loss: -0.4758]
28
  11%|โ–ˆ | 11/100 [07:30<56:39, 38.20s/trial, best loss: -0.4835]
29
  12%|โ–ˆโ– | 12/100 [08:01<52:39, 35.90s/trial, best loss: -0.4835]
30
  13%|โ–ˆโ–Ž | 13/100 [08:23<46:16, 31.91s/trial, best loss: -0.4835]
31
  14%|โ–ˆโ– | 14/100 [08:46<41:36, 29.03s/trial, best loss: -0.4835]
32
  15%|โ–ˆโ–Œ | 15/100 [09:24<44:58, 31.74s/trial, best loss: -0.4835]
33
  16%|โ–ˆโ–Œ | 16/100 [10:12<51:30, 36.80s/trial, best loss: -0.4835]
34
  17%|โ–ˆโ–‹ | 17/100 [10:47<50:13, 36.30s/trial, best loss: -0.4835]
35
  18%|โ–ˆโ–Š | 18/100 [11:15<46:03, 33.70s/trial, best loss: -0.4835]
36
  19%|โ–ˆโ–‰ | 19/100 [11:52<46:41, 34.58s/trial, best loss: -0.4835]
37
  20%|โ–ˆโ–ˆ | 20/100 [12:13<40:56, 30.71s/trial, best loss: -0.4835]
38
  21%|โ–ˆโ–ˆ | 21/100 [12:44<40:26, 30.71s/trial, best loss: -0.4835]
39
  22%|โ–ˆโ–ˆโ– | 22/100 [13:14<39:43, 30.56s/trial, best loss: -0.4836]
40
  23%|โ–ˆโ–ˆโ–Ž | 23/100 [13:40<37:14, 29.02s/trial, best loss: -0.4836]
41
  24%|โ–ˆโ–ˆโ– | 24/100 [14:23<42:05, 33.24s/trial, best loss: -0.4836]
42
  25%|โ–ˆโ–ˆโ–Œ | 25/100 [14:53<40:20, 32.27s/trial, best loss: -0.4836]
43
  26%|โ–ˆโ–ˆโ–Œ | 26/100 [15:18<37:18, 30.25s/trial, best loss: -0.4836]
44
  27%|โ–ˆโ–ˆโ–‹ | 27/100 [15:47<36:22, 29.90s/trial, best loss: -0.4836]
45
  28%|โ–ˆโ–ˆโ–Š | 28/100 [16:40<44:02, 36.70s/trial, best loss: -0.4836]
46
  29%|โ–ˆโ–ˆโ–‰ | 29/100 [17:20<44:27, 37.57s/trial, best loss: -0.4836]
47
  30%|โ–ˆโ–ˆโ–ˆ | 30/100 [18:02<45:34, 39.06s/trial, best loss: -0.4836]
48
  31%|โ–ˆโ–ˆโ–ˆ | 31/100 [18:26<39:34, 34.42s/trial, best loss: -0.4836]
49
  32%|โ–ˆโ–ˆโ–ˆโ– | 32/100 [19:00<39:06, 34.51s/trial, best loss: -0.4836]
50
  33%|โ–ˆโ–ˆโ–ˆโ–Ž | 33/100 [19:37<39:24, 35.29s/trial, best loss: -0.4836]
51
  34%|โ–ˆโ–ˆโ–ˆโ– | 34/100 [20:20<41:17, 37.54s/trial, best loss: -0.4836]
52
  35%|โ–ˆโ–ˆโ–ˆโ–Œ | 35/100 [20:46<36:49, 33.99s/trial, best loss: -0.4836]
53
  36%|โ–ˆโ–ˆโ–ˆโ–Œ | 36/100 [21:42<43:21, 40.65s/trial, best loss: -0.4836]
54
  37%|โ–ˆโ–ˆโ–ˆโ–‹ | 37/100 [22:19<41:21, 39.38s/trial, best loss: -0.4836]
55
  38%|โ–ˆโ–ˆโ–ˆโ–Š | 38/100 [23:07<43:38, 42.23s/trial, best loss: -0.4836]
56
  39%|โ–ˆโ–ˆโ–ˆโ–‰ | 39/100 [23:30<36:47, 36.19s/trial, best loss: -0.4836]
57
  40%|โ–ˆโ–ˆโ–ˆโ–ˆ | 40/100 [24:00<34:29, 34.49s/trial, best loss: -0.4836]
58
  41%|โ–ˆโ–ˆโ–ˆโ–ˆ | 41/100 [24:30<32:32, 33.10s/trial, best loss: -0.4836]
59
  42%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 42/100 [24:56<29:53, 30.93s/trial, best loss: -0.4836]
60
  43%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 43/100 [25:27<29:21, 30.90s/trial, best loss: -0.4836]
61
  44%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 44/100 [25:50<26:44, 28.65s/trial, best loss: -0.4836]
62
  45%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 45/100 [26:40<32:11, 35.13s/trial, best loss: -0.4836]
63
  46%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 46/100 [27:16<31:53, 35.43s/trial, best loss: -0.4836]
64
  47%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 47/100 [27:57<32:41, 37.01s/trial, best loss: -0.4836]
65
  48%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 48/100 [28:48<35:47, 41.30s/trial, best loss: -0.4836]
66
  49%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 49/100 [29:27<34:26, 40.53s/trial, best loss: -0.4836]
67
  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 50/100 [29:54<30:25, 36.51s/trial, best loss: -0.4836]
68
  51%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 51/100 [30:53<35:10, 43.06s/trial, best loss: -0.4836]
69
  52%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 52/100 [31:20<30:35, 38.24s/trial, best loss: -0.4836]
70
  53%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 53/100 [31:53<28:54, 36.90s/trial, best loss: -0.4836]
71
  54%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 54/100 [33:09<37:07, 48.43s/trial, best loss: -0.4836]
72
  55%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 55/100 [33:34<31:10, 41.56s/trial, best loss: -0.4836]
73
  56%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 56/100 [33:56<26:01, 35.48s/trial, best loss: -0.4836]
74
  57%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 57/100 [34:25<24:02, 33.54s/trial, best loss: -0.4836]
75
  58%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 58/100 [35:00<23:51, 34.09s/trial, best loss: -0.4836]
76
  59%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 59/100 [35:53<27:15, 39.88s/trial, best loss: -0.4836]
77
  60%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 60/100 [36:31<26:10, 39.26s/trial, best loss: -0.4836]
78
  61%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 61/100 [36:57<22:56, 35.30s/trial, best loss: -0.4836]
79
  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 62/100 [37:32<22:11, 35.04s/trial, best loss: -0.4836]
80
  63%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 63/100 [37:57<19:47, 32.11s/trial, best loss: -0.4836]
81
  64%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 64/100 [38:23<18:11, 30.33s/trial, best loss: -0.4836]
82
  65%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 65/100 [39:08<20:11, 34.62s/trial, best loss: -0.4836]
83
  66%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 66/100 [39:40<19:14, 33.96s/trial, best loss: -0.4836]
84
  67%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 67/100 [40:11<18:06, 32.93s/trial, best loss: -0.4836]
85
  68%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 68/100 [40:36<16:23, 30.74s/trial, best loss: -0.4836]
86
  69%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 69/100 [41:04<15:20, 29.70s/trial, best loss: -0.4836]
87
  70%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 70/100 [41:31<14:34, 29.15s/trial, best loss: -0.4836]
88
  71%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 71/100 [41:55<13:17, 27.51s/trial, best loss: -0.4836]
89
  72%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 72/100 [42:36<14:45, 31.64s/trial, best loss: -0.4836]
90
  73%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 73/100 [43:06<13:58, 31.06s/trial, best loss: -0.4836]
91
  74%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 74/100 [43:34<12:59, 29.97s/trial, best loss: -0.4836]
92
  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 75/100 [44:05<12:43, 30.53s/trial, best loss: -0.4836]
93
  76%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 76/100 [44:46<13:24, 33.52s/trial, best loss: -0.4836]
94
  77%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 77/100 [45:22<13:09, 34.35s/trial, best loss: -0.4836]
95
  78%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 78/100 [45:53<12:11, 33.24s/trial, best loss: -0.4836]
96
  79%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 79/100 [46:20<10:58, 31.38s/trial, best loss: -0.4836]
97
  80%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 80/100 [46:45<09:51, 29.59s/trial, best loss: -0.4836]
98
  81%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 81/100 [47:20<09:53, 31.23s/trial, best loss: -0.4836]
99
  82%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 82/100 [47:51<09:19, 31.11s/trial, best loss: -0.4836]
100
  83%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 83/100 [48:23<08:55, 31.49s/trial, best loss: -0.4836]
101
  84%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 84/100 [49:06<09:14, 34.66s/trial, best loss: -0.4836]
102
  85%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 85/100 [49:31<07:59, 31.94s/trial, best loss: -0.4836]
103
  86%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 86/100 [50:18<08:28, 36.32s/trial, best loss: -0.4836]
104
  87%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 87/100 [51:01<08:20, 38.50s/trial, best loss: -0.4836]
105
  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 88/100 [52:08<09:24, 47.02s/trial, best loss: -0.4836]
106
  89%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 89/100 [52:57<08:43, 47.60s/trial, best loss: -0.4836]
107
  90%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 90/100 [53:37<07:31, 45.17s/trial, best loss: -0.4836]
108
  91%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 91/100 [54:28<07:04, 47.18s/trial, best loss: -0.4836]
109
  92%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 92/100 [55:14<06:13, 46.70s/trial, best loss: -0.4836]
110
  93%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž| 93/100 [56:21<06:08, 52.71s/trial, best loss: -0.4836]
111
  94%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 94/100 [57:02<04:55, 49.27s/trial, best loss: -0.4836]
112
  95%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ| 95/100 [57:39<03:48, 45.62s/trial, best loss: -0.4836]
113
  96%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ| 96/100 [58:33<03:12, 48.15s/trial, best loss: -0.4836]
114
  97%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹| 97/100 [59:14<02:17, 45.95s/trial, best loss: -0.4836]
115
  98%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š| 98/100 [59:54<01:28, 44.22s/trial, best loss: -0.4836]
116
  99%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰| 99/100 [1:00:48<00:47, 47.12s/trial, best loss: -0.4836]
117
+
118
+ ์ตœ์ ํ™” ์™„๋ฃŒ. ์ตœ์  ํŒŒ๋ผ๋ฏธํ„ฐ: {'colsample_bytree': 0.7243835590014314, 'learning_rate': 0.052472053724070156, 'max_depth': 15.0, 'min_child_weight': 9.0, 'num_leaves': 120.0, 'reg_alpha': 0.566895668532905, 'reg_lambda': 0.9659771198744264, 'subsample': 0.8425484904296862}
119
+ ์ตœ์  CSI ์ ์ˆ˜: 0.4836 (loss: -0.4836)
120
+
121
+ ์ตœ์ ํ™” ๊ณผ์ • ์š”์•ฝ:
122
+ - ์ด ์‹œ๋„ ํšŸ์ˆ˜: 100
123
+ - ์„ฑ๊ณตํ•œ ์‹œ๋„: 100
124
+ - ์ตœ์ดˆ CSI: 0.4238
125
+ - ์ตœ์ข… CSI: 0.4676
126
+ - ์ตœ๊ณ  CSI: 0.4836
127
+ - ์ตœ์ € CSI: 0.4200
128
+ - ํ‰๊ท  CSI: 0.4700
129
+
130
+ ์ตœ์ ํ™” Trials ๊ฐ์ฒด๊ฐ€ /workspace/visibility_prediction/Analysis_code/optimization_history/lgb_ctgan10000_busan_trials.pkl์— ์ €์žฅ๋˜์—ˆ์Šต๋‹ˆ๋‹ค.
131
+ ์ตœ์ข… ๋ชจ๋ธ ํ•™์Šต ์‹œ์ž‘...
132
+ Fold 1 ํ•™์Šต ์ค‘... (ํ•™์Šต ์—ฐ๋„: [2018, 2019], ๊ฒ€์ฆ ์—ฐ๋„: 2020)
133
+ Fold 1 ๊ฒ€์ฆ CSI: 0.3905
134
+ Fold 2 ํ•™์Šต ์ค‘... (ํ•™์Šต ์—ฐ๋„: [2018, 2020], ๊ฒ€์ฆ ์—ฐ๋„: 2019)
135
+ Fold 2 ๊ฒ€์ฆ CSI: 0.5044
136
+ Fold 3 ํ•™์Šต ์ค‘... (ํ•™์Šต ์—ฐ๋„: [2019, 2020], ๊ฒ€์ฆ ์—ฐ๋„: 2018)
137
+ Fold 3 ๊ฒ€์ฆ CSI: 0.4985
138
+ ๋ชจ๋ธ ์ €์žฅ ์ค‘...
139
+ ๋ชจ๋ธ์ด /workspace/visibility_prediction/Analysis_code/save_model/lgb_optima/lgb_ctgan10000_busan.pkl์— ์ €์žฅ๋˜์—ˆ์Šต๋‹ˆ๋‹ค.
140
+
141
+ โœ“ ์™„๋ฃŒ: lgb_ctgan10000/LGB_ctgan10000_busan.py (์†Œ์š” ์‹œ๊ฐ„: 3720์ดˆ)
142
+
143
+ ----------------------------------------
144
+ ์‹คํ–‰ ์ค‘: lgb_ctgan10000/LGB_ctgan10000_daegu.py
145
+ ์‹œ์ž‘ ์‹œ๊ฐ„: 2025-12-28 05:31:39
146
+ ----------------------------------------
147
+ ๋ฐ์ดํ„ฐ ๋กœ๋”ฉ ์ค‘...
148
+ ๋ฐ์ดํ„ฐ ์ „์ฒ˜๋ฆฌ ์ค‘...
149
+ ํ•˜์ดํผํŒŒ๋ผ๋ฏธํ„ฐ ์ตœ์ ํ™” ์‹œ์ž‘...
150
+
151
  0%| | 0/100 [00:00<?, ?trial/s, best loss=?]
152
  1%| | 1/100 [00:18<31:06, 18.85s/trial, best loss: -0.3977]
153
  2%|โ– | 2/100 [00:59<52:04, 31.88s/trial, best loss: -0.4107]
154
  3%|โ–Ž | 3/100 [01:25<46:42, 28.89s/trial, best loss: -0.4107]
155
  4%|โ– | 4/100 [02:15<59:36, 37.25s/trial, best loss: -0.4107]
156
  5%|โ–Œ | 5/100 [02:48<56:54, 35.94s/trial, best loss: -0.4107]
157
  6%|โ–Œ | 6/100 [03:16<52:00, 33.20s/trial, best loss: -0.4107]
158
  7%|โ–‹ | 7/100 [04:01<57:30, 37.10s/trial, best loss: -0.4107]
159
  8%|โ–Š | 8/100 [04:43<58:56, 38.44s/trial, best loss: -0.4107]
160
  9%|โ–‰ | 9/100 [05:10<52:53, 34.88s/trial, best loss: -0.4107]
161
  10%|โ–ˆ | 10/100 [05:34<47:28, 31.65s/trial, best loss: -0.4107]
162
  11%|โ–ˆ | 11/100 [06:25<55:28, 37.39s/trial, best loss: -0.4107]
163
  12%|โ–ˆโ– | 12/100 [06:52<50:33, 34.47s/trial, best loss: -0.4107]
164
  13%|โ–ˆโ–Ž | 13/100 [07:15<44:44, 30.85s/trial, best loss: -0.4155]
165
  14%|โ–ˆโ– | 14/100 [07:47<44:52, 31.31s/trial, best loss: -0.4155]
166
  15%|โ–ˆโ–Œ | 15/100 [08:10<40:45, 28.77s/trial, best loss: -0.4161]
167
  16%|โ–ˆโ–Œ | 16/100 [08:33<37:35, 26.85s/trial, best loss: -0.4161]
168
  17%|โ–ˆโ–‹ | 17/100 [09:15<43:36, 31.53s/trial, best loss: -0.4161]
169
  18%|โ–ˆโ–Š | 18/100 [09:51<45:05, 32.99s/trial, best loss: -0.4161]
170
  19%|โ–ˆโ–‰ | 19/100 [10:14<40:11, 29.77s/trial, best loss: -0.4161]
171
  20%|โ–ˆโ–ˆ | 20/100 [11:04<48:02, 36.03s/trial, best loss: -0.4161]
172
  21%|โ–ˆโ–ˆ | 21/100 [11:25<41:14, 31.32s/trial, best loss: -0.4203]
173
  22%|โ–ˆโ–ˆโ– | 22/100 [11:51<38:51, 29.89s/trial, best loss: -0.4203]
174
  23%|โ–ˆโ–ˆโ–Ž | 23/100 [12:16<36:18, 28.29s/trial, best loss: -0.4203]
175
  24%|โ–ˆโ–ˆโ– | 24/100 [12:42<35:07, 27.72s/trial, best loss: -0.4203]
176
  25%|โ–ˆโ–ˆโ–Œ | 25/100 [13:04<32:21, 25.88s/trial, best loss: -0.4203]
177
  26%|โ–ˆโ–ˆโ–Œ | 26/100 [13:25<30:16, 24.54s/trial, best loss: -0.4203]
178
  27%|โ–ˆโ–ˆโ–‹ | 27/100 [13:46<28:42, 23.60s/trial, best loss: -0.4203]
179
  28%|โ–ˆโ–ˆโ–Š | 28/100 [14:08<27:40, 23.06s/trial, best loss: -0.4203]
180
  29%|โ–ˆโ–ˆโ–‰ | 29/100 [14:33<27:46, 23.47s/trial, best loss: -0.4203]
181
  30%|โ–ˆโ–ˆโ–ˆ | 30/100 [14:53<26:12, 22.46s/trial, best loss: -0.4207]
182
  31%|โ–ˆโ–ˆโ–ˆ | 31/100 [15:14<25:33, 22.22s/trial, best loss: -0.4254]
183
  32%|โ–ˆโ–ˆโ–ˆโ– | 32/100 [15:36<24:48, 21.90s/trial, best loss: -0.4254]
184
  33%|โ–ˆโ–ˆโ–ˆโ–Ž | 33/100 [15:57<24:20, 21.80s/trial, best loss: -0.4254]
185
  34%|โ–ˆโ–ˆโ–ˆโ– | 34/100 [16:19<23:58, 21.79s/trial, best loss: -0.4254]
186
  35%|โ–ˆโ–ˆโ–ˆโ–Œ | 35/100 [16:47<25:30, 23.55s/trial, best loss: -0.4254]
187
  36%|โ–ˆโ–ˆโ–ˆโ–Œ | 36/100 [17:12<25:35, 24.00s/trial, best loss: -0.4254]
188
  37%|โ–ˆโ–ˆโ–ˆโ–‹ | 37/100 [17:34<24:35, 23.42s/trial, best loss: -0.4254]
189
  38%|โ–ˆโ–ˆโ–ˆโ–Š | 38/100 [18:02<25:41, 24.86s/trial, best loss: -0.4254]
190
  39%|โ–ˆโ–ˆโ–ˆโ–‰ | 39/100 [18:24<24:19, 23.93s/trial, best loss: -0.4254]
191
  40%|โ–ˆโ–ˆโ–ˆโ–ˆ | 40/100 [18:50<24:31, 24.52s/trial, best loss: -0.4254]
192
  41%|โ–ˆโ–ˆโ–ˆโ–ˆ | 41/100 [19:17<25:04, 25.51s/trial, best loss: -0.4254]
193
  42%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 42/100 [19:50<26:51, 27.78s/trial, best loss: -0.4254]
194
  43%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 43/100 [20:16<25:36, 26.96s/trial, best loss: -0.4254]
195
  44%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 44/100 [20:49<27:04, 29.00s/trial, best loss: -0.4254]
196
  45%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 45/100 [21:07<23:36, 25.75s/trial, best loss: -0.4254]
197
  46%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 46/100 [21:26<21:14, 23.60s/trial, best loss: -0.4254]
198
  47%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 47/100 [21:49<20:41, 23.42s/trial, best loss: -0.4254]
199
  48%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 48/100 [22:09<19:27, 22.45s/trial, best loss: -0.4254]
200
  49%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 49/100 [23:08<28:18, 33.30s/trial, best loss: -0.4254]
201
  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 50/100 [23:33<25:45, 30.90s/trial, best loss: -0.4254]
202
  51%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 51/100 [23:54<22:51, 27.99s/trial, best loss: -0.4254]
203
  52%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 52/100 [24:46<28:08, 35.17s/trial, best loss: -0.4255]
204
  53%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 53/100 [25:19<26:54, 34.35s/trial, best loss: -0.4255]
205
  54%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 54/100 [26:00<27:54, 36.41s/trial, best loss: -0.4255]
206
  55%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 55/100 [26:52<30:51, 41.14s/trial, best loss: -0.4255]
207
  56%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 56/100 [27:21<27:32, 37.55s/trial, best loss: -0.4255]
208
  57%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 57/100 [27:54<25:48, 36.01s/trial, best loss: -0.4255]
209
  58%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 58/100 [28:38<27:00, 38.59s/trial, best loss: -0.4308]
210
  59%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 59/100 [29:22<27:21, 40.03s/trial, best loss: -0.4308]
211
  60%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 60/100 [29:55<25:16, 37.92s/trial, best loss: -0.4308]
212
  61%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 61/100 [30:42<26:27, 40.70s/trial, best loss: -0.4308]
213
  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 62/100 [31:22<25:35, 40.40s/trial, best loss: -0.4308]
214
  63%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 63/100 [32:08<26:04, 42.29s/trial, best loss: -0.4308]
215
  64%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 64/100 [32:58<26:41, 44.49s/trial, best loss: -0.4308]
216
  65%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 65/100 [33:35<24:39, 42.28s/trial, best loss: -0.4308]
217
  66%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 66/100 [34:26<25:30, 45.01s/trial, best loss: -0.4308]
218
  67%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 67/100 [35:12<24:52, 45.21s/trial, best loss: -0.4308]
219
  68%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 68/100 [36:03<25:03, 47.00s/trial, best loss: -0.4308]
220
  69%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 69/100 [36:49<24:05, 46.63s/trial, best loss: -0.4308]
221
  70%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 70/100 [37:31<22:40, 45.35s/trial, best loss: -0.4308]
222
  71%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 71/100 [38:07<20:28, 42.35s/trial, best loss: -0.4308]
223
  72%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 72/100 [38:45<19:12, 41.15s/trial, best loss: -0.4308]
224
  73%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 73/100 [39:21<17:45, 39.48s/trial, best loss: -0.4308]
225
  74%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 74/100 [39:55<16:22, 37.80s/trial, best loss: -0.4308]
226
  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 75/100 [40:30<15:26, 37.07s/trial, best loss: -0.4308]
227
  76%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 76/100 [41:12<15:22, 38.43s/trial, best loss: -0.4308]
228
  77%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 77/100 [41:43<13:55, 36.31s/trial, best loss: -0.4308]
229
  78%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 78/100 [42:09<12:10, 33.21s/trial, best loss: -0.4308]
230
  79%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 79/100 [42:37<11:02, 31.57s/trial, best loss: -0.4308]
231
  80%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 80/100 [43:10<10:44, 32.23s/trial, best loss: -0.4308]
232
  81%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 81/100 [43:46<10:28, 33.10s/trial, best loss: -0.4308]
233
  82%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 82/100 [44:40<11:49, 39.44s/trial, best loss: -0.4317]
234
  83%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 83/100 [45:16<10:55, 38.57s/trial, best loss: -0.4317]
235
  84%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 84/100 [46:07<11:13, 42.10s/trial, best loss: -0.4317]
236
  85%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 85/100 [47:05<11:43, 46.91s/trial, best loss: -0.4317]
237
  86%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 86/100 [47:54<11:05, 47.51s/trial, best loss: -0.4317]
238
  87%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 87/100 [48:33<09:44, 44.98s/trial, best loss: -0.4317]
239
  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 88/100 [48:57<07:46, 38.87s/trial, best loss: -0.4317]
240
  89%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 89/100 [49:25<06:31, 35.56s/trial, best loss: -0.4317]
241
  90%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 90/100 [50:23<07:01, 42.18s/trial, best loss: -0.4339]
242
  91%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 91/100 [51:11<06:35, 43.97s/trial, best loss: -0.4339]
243
  92%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 92/100 [52:08<06:21, 47.75s/trial, best loss: -0.4339]
244
  93%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž| 93/100 [52:49<05:21, 45.99s/trial, best loss: -0.4339]
245
  94%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 94/100 [53:41<04:45, 47.66s/trial, best loss: -0.4339]
246
  95%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ| 95/100 [54:27<03:56, 47.24s/trial, best loss: -0.4339]
247
  96%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ| 96/100 [55:20<03:14, 48.75s/trial, best loss: -0.4339]
248
  97%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹| 97/100 [55:47<02:06, 42.27s/trial, best loss: -0.4339]
249
  98%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š| 98/100 [56:52<01:38, 49.05s/trial, best loss: -0.4339]
250
  99%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰| 99/100 [57:25<00:44, 44.40s/trial, best loss: -0.4339]
251
+
252
+ ์ตœ์ ํ™” ์™„๋ฃŒ. ์ตœ์  ํŒŒ๋ผ๋ฏธํ„ฐ: {'colsample_bytree': 0.885595994008888, 'learning_rate': 0.010106842270671093, 'max_depth': 14.0, 'min_child_weight': 1.0, 'num_leaves': 122.0, 'reg_alpha': 0.12648188723964116, 'reg_lambda': 0.873682924904797, 'subsample': 0.7806598236159817}
253
+ ์ตœ์  CSI ์ ์ˆ˜: 0.4339 (loss: -0.4339)
254
+
255
+ ์ตœ์ ํ™” ๊ณผ์ • ์š”์•ฝ:
256
+ - ์ด ์‹œ๋„ ํšŸ์ˆ˜: 100
257
+ - ์„ฑ๊ณตํ•œ ์‹œ๋„: 100
258
+ - ์ตœ์ดˆ CSI: 0.3977
259
+ - ์ตœ์ข… CSI: 0.3974
260
+ - ์ตœ๊ณ  CSI: 0.4339
261
+ - ์ตœ์ € CSI: 0.3802
262
+ - ํ‰๊ท  CSI: 0.4106
263
+
264
+ ์ตœ์ ํ™” Trials ๊ฐ์ฒด๊ฐ€ /workspace/visibility_prediction/Analysis_code/optimization_history/lgb_ctgan10000_daegu_trials.pkl์— ์ €์žฅ๋˜์—ˆ์Šต๋‹ˆ๋‹ค.
265
+ ์ตœ์ข… ๋ชจ๋ธ ํ•™์Šต ์‹œ์ž‘...
266
+ Fold 1 ํ•™์Šต ์ค‘... (ํ•™์Šต ์—ฐ๋„: [2018, 2019], ๊ฒ€์ฆ ์—ฐ๋„: 2020)
267
+ Fold 1 ๊ฒ€์ฆ CSI: 0.4293
268
+ Fold 2 ํ•™์Šต ์ค‘... (ํ•™์Šต ์—ฐ๋„: [2018, 2020], ๊ฒ€์ฆ ์—ฐ๋„: 2019)
269
+ Fold 2 ๊ฒ€์ฆ CSI: 0.4656
270
+ Fold 3 ํ•™์Šต ์ค‘... (ํ•™์Šต ์—ฐ๋„: [2019, 2020], ๊ฒ€์ฆ ์—ฐ๋„: 2018)
271
+ Fold 3 ๊ฒ€์ฆ CSI: 0.3270
272
+ ๋ชจ๋ธ ์ €์žฅ ์ค‘...
273
+ ๋ชจ๋ธ์ด /workspace/visibility_prediction/Analysis_code/save_model/lgb_optima/lgb_ctgan10000_daegu.pkl์— ์ €์žฅ๋˜์—ˆ์Šต๋‹ˆ๋‹ค.
274
+
275
+ โœ“ ์™„๋ฃŒ: lgb_ctgan10000/LGB_ctgan10000_daegu.py (์†Œ์š” ์‹œ๊ฐ„: 3538์ดˆ)
276
+
277
+ ----------------------------------------
278
+ ์‹คํ–‰ ์ค‘: lgb_ctgan10000/LGB_ctgan10000_daejeon.py
279
+ ์‹œ์ž‘ ์‹œ๊ฐ„: 2025-12-28 06:30:37
280
+ ----------------------------------------
281
+ ๋ฐ์ดํ„ฐ ๋กœ๋”ฉ ์ค‘...
282
+ ๋ฐ์ดํ„ฐ ์ „์ฒ˜๋ฆฌ ์ค‘...
283
+ ํ•˜์ดํผํŒŒ๋ผ๋ฏธํ„ฐ ์ตœ์ ํ™” ์‹œ์ž‘...
284
+
285
  0%| | 0/100 [00:00<?, ?trial/s, best loss=?]
286
  1%| | 1/100 [00:28<47:17, 28.66s/trial, best loss: -0.4792]
287
  2%|โ– | 2/100 [01:38<1:25:59, 52.65s/trial, best loss: -0.4833]
288
  3%|โ–Ž | 3/100 [02:12<1:11:30, 44.23s/trial, best loss: -0.4833]
289
  4%|โ– | 4/100 [02:44<1:02:52, 39.29s/trial, best loss: -0.4833]
290
  5%|โ–Œ | 5/100 [03:08<53:32, 33.81s/trial, best loss: -0.4833]
291
  6%|โ–Œ | 6/100 [03:41<52:46, 33.68s/trial, best loss: -0.4833]
292
  7%|โ–‹ | 7/100 [04:23<56:25, 36.40s/trial, best loss: -0.4833]
293
  8%|โ–Š | 8/100 [05:32<1:11:34, 46.68s/trial, best loss: -0.4833]
294
  9%|โ–‰ | 9/100 [06:02<1:02:47, 41.41s/trial, best loss: -0.4864]
295
  10%|โ–ˆ | 10/100 [07:04<1:12:04, 48.05s/trial, best loss: -0.4864]
296
  11%|โ–ˆ | 11/100 [07:31<1:01:24, 41.40s/trial, best loss: -0.4864]
297
  12%|โ–ˆโ– | 12/100 [07:54<52:32, 35.82s/trial, best loss: -0.4864]
298
  13%|โ–ˆโ–Ž | 13/100 [09:06<1:07:45, 46.72s/trial, best loss: -0.4878]
299
  14%|โ–ˆโ– | 14/100 [09:35<59:23, 41.44s/trial, best loss: -0.4878]
300
  15%|โ–ˆโ–Œ | 15/100 [10:15<58:02, 40.98s/trial, best loss: -0.4878]
301
  16%|โ–ˆโ–Œ | 16/100 [10:42<51:40, 36.91s/trial, best loss: -0.4878]
302
  17%|โ–ˆโ–‹ | 17/100 [11:16<49:36, 35.86s/trial, best loss: -0.4878]
303
  18%|โ–ˆโ–Š | 18/100 [11:59<52:13, 38.21s/trial, best loss: -0.4878]
304
  19%|โ–ˆโ–‰ | 19/100 [12:54<58:10, 43.09s/trial, best loss: -0.4878]
305
  20%|โ–ˆโ–ˆ | 20/100 [13:18<50:04, 37.56s/trial, best loss: -0.4878]
306
  21%|โ–ˆโ–ˆ | 21/100 [14:05<53:03, 40.30s/trial, best loss: -0.4878]
307
  22%|โ–ˆโ–ˆโ– | 22/100 [14:40<50:06, 38.54s/trial, best loss: -0.4878]
308
  23%|โ–ˆโ–ˆโ–Ž | 23/100 [15:37<56:52, 44.32s/trial, best loss: -0.4878]
309
  24%|โ–ˆโ–ˆโ– | 24/100 [16:00<47:53, 37.81s/trial, best loss: -0.4878]
310
  25%|โ–ˆโ–ˆโ–Œ | 25/100 [17:12<1:00:06, 48.08s/trial, best loss: -0.4878]
311
  26%|โ–ˆโ–ˆโ–Œ | 26/100 [17:39<51:24, 41.69s/trial, best loss: -0.4878]
312
  27%|โ–ˆโ–ˆโ–‹ | 27/100 [18:33<55:09, 45.34s/trial, best loss: -0.4878]
313
  28%|โ–ˆโ–ˆโ–Š | 28/100 [19:15<53:28, 44.56s/trial, best loss: -0.4878]
314
  29%|โ–ˆโ–ˆโ–‰ | 29/100 [19:59<52:25, 44.30s/trial, best loss: -0.4878]
315
  30%|โ–ˆโ–ˆโ–ˆ | 30/100 [20:24<44:59, 38.56s/trial, best loss: -0.4878]
316
  31%|โ–ˆโ–ˆโ–ˆ | 31/100 [21:21<50:25, 43.84s/trial, best loss: -0.4878]
317
  32%|โ–ˆโ–ˆโ–ˆโ– | 32/100 [22:25<56:51, 50.17s/trial, best loss: -0.4878]
318
  33%|โ–ˆโ–ˆโ–ˆโ–Ž | 33/100 [22:54<48:42, 43.62s/trial, best loss: -0.4878]
319
  34%|โ–ˆโ–ˆโ–ˆโ– | 34/100 [23:21<42:43, 38.84s/trial, best loss: -0.4894]
320
  35%|โ–ˆโ–ˆโ–ˆโ–Œ | 35/100 [23:52<39:29, 36.46s/trial, best loss: -0.4894]
321
  36%|โ–ˆโ–ˆโ–ˆโ–Œ | 36/100 [24:14<34:09, 32.02s/trial, best loss: -0.4894]
322
  37%|โ–ˆโ–ˆโ–ˆโ–‹ | 37/100 [25:02<38:37, 36.79s/trial, best loss: -0.4894]
323
  38%|โ–ˆโ–ˆโ–ˆโ–Š | 38/100 [25:30<35:24, 34.27s/trial, best loss: -0.4894]
324
  39%|โ–ˆโ–ˆโ–ˆโ–‰ | 39/100 [26:02<34:10, 33.62s/trial, best loss: -0.4894]
325
  40%|โ–ˆโ–ˆโ–ˆโ–ˆ | 40/100 [26:31<31:57, 31.97s/trial, best loss: -0.4894]
326
  41%|โ–ˆโ–ˆโ–ˆโ–ˆ | 41/100 [27:05<32:16, 32.82s/trial, best loss: -0.4894]
327
  42%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 42/100 [27:45<33:44, 34.91s/trial, best loss: -0.4894]
328
  43%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 43/100 [28:17<32:15, 33.95s/trial, best loss: -0.4894]
329
  44%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 44/100 [28:50<31:28, 33.72s/trial, best loss: -0.4894]
330
  45%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 45/100 [29:24<30:56, 33.75s/trial, best loss: -0.4894]
331
  46%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 46/100 [30:01<31:23, 34.88s/trial, best loss: -0.4894]
332
  47%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 47/100 [30:38<31:23, 35.54s/trial, best loss: -0.4894]
333
  48%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 48/100 [31:05<28:20, 32.71s/trial, best loss: -0.4894]
334
  49%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 49/100 [31:46<30:03, 35.36s/trial, best loss: -0.4894]
335
  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 50/100 [32:24<30:08, 36.17s/trial, best loss: -0.4894]
336
  51%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 51/100 [33:17<33:40, 41.24s/trial, best loss: -0.4894]
337
  52%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 52/100 [33:40<28:34, 35.72s/trial, best loss: -0.4894]
338
  53%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 53/100 [34:57<37:33, 47.95s/trial, best loss: -0.4894]
339
  54%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 54/100 [35:22<31:33, 41.17s/trial, best loss: -0.4894]
340
  55%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 55/100 [36:12<32:59, 43.98s/trial, best loss: -0.4894]
341
  56%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 56/100 [36:39<28:21, 38.67s/trial, best loss: -0.4894]
342
  57%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 57/100 [37:38<32:05, 44.79s/trial, best loss: -0.4894]
343
  58%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 58/100 [38:18<30:26, 43.49s/trial, best loss: -0.4894]
344
  59%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 59/100 [38:46<26:35, 38.90s/trial, best loss: -0.4894]
345
  60%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 60/100 [39:14<23:41, 35.55s/trial, best loss: -0.4894]
346
  61%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 61/100 [40:09<26:51, 41.32s/trial, best loss: -0.4894]
347
  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 62/100 [40:48<25:48, 40.76s/trial, best loss: -0.4894]
348
  63%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 63/100 [41:20<23:25, 37.97s/trial, best loss: -0.4894]
349
  64%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 64/100 [41:54<22:03, 36.77s/trial, best loss: -0.4894]
350
  65%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 65/100 [42:27<20:53, 35.82s/trial, best loss: -0.4894]
351
  66%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 66/100 [43:12<21:46, 38.42s/trial, best loss: -0.4894]
352
  67%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 67/100 [43:46<20:25, 37.13s/trial, best loss: -0.4894]
353
  68%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 68/100 [44:18<19:00, 35.65s/trial, best loss: -0.4894]
354
  69%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 69/100 [44:52<18:09, 35.16s/trial, best loss: -0.4894]
355
  70%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 70/100 [45:42<19:50, 39.67s/trial, best loss: -0.4894]
356
  71%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 71/100 [46:24<19:24, 40.15s/trial, best loss: -0.4894]
357
  72%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 72/100 [46:52<17:05, 36.63s/trial, best loss: -0.4901]
358
  73%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 73/100 [47:36<17:26, 38.74s/trial, best loss: -0.4901]
359
  74%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 74/100 [48:08<15:56, 36.80s/trial, best loss: -0.4901]
360
  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 75/100 [48:34<14:00, 33.61s/trial, best loss: -0.4908]
361
  76%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 76/100 [49:02<12:44, 31.84s/trial, best loss: -0.4908]
362
  77%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 77/100 [49:28<11:29, 29.97s/trial, best loss: -0.4908]
363
  78%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 78/100 [49:52<10:22, 28.28s/trial, best loss: -0.4908]
364
  79%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 79/100 [50:21<10:01, 28.64s/trial, best loss: -0.4908]
365
  80%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 80/100 [50:46<09:11, 27.56s/trial, best loss: -0.4908]
366
  81%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 81/100 [51:16<08:53, 28.06s/trial, best loss: -0.4908]
367
  82%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 82/100 [51:46<08:36, 28.69s/trial, best loss: -0.4908]
368
  83%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 83/100 [52:15<08:10, 28.85s/trial, best loss: -0.4908]
369
  84%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 84/100 [52:46<07:51, 29.44s/trial, best loss: -0.4908]
370
  85%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 85/100 [53:12<07:08, 28.55s/trial, best loss: -0.4908]
371
  86%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 86/100 [53:43<06:48, 29.21s/trial, best loss: -0.4908]
372
  87%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 87/100 [54:08<06:03, 27.99s/trial, best loss: -0.4908]
373
  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 88/100 [54:32<05:20, 26.69s/trial, best loss: -0.4908]
374
  89%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 89/100 [54:56<04:45, 26.00s/trial, best loss: -0.4908]
375
  90%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 90/100 [55:31<04:45, 28.51s/trial, best loss: -0.4908]
376
  91%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 91/100 [56:00<04:20, 28.91s/trial, best loss: -0.4908]
377
  92%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 92/100 [56:37<04:09, 31.18s/trial, best loss: -0.4908]
378
  93%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž| 93/100 [57:05<03:31, 30.15s/trial, best loss: -0.4908]
379
  94%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 94/100 [57:26<02:44, 27.48s/trial, best loss: -0.4908]
380
  95%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ| 95/100 [57:53<02:16, 27.34s/trial, best loss: -0.4908]
381
  96%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ| 96/100 [58:28<01:58, 29.56s/trial, best loss: -0.4908]
382
  97%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹| 97/100 [58:53<01:24, 28.32s/trial, best loss: -0.4908]
383
  98%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š| 98/100 [59:16<00:53, 26.57s/trial, best loss: -0.4908]
384
  99%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰| 99/100 [59:58<00:31, 31.41s/trial, best loss: -0.4908]
385
+
386
+ ์ตœ์ ํ™” ์™„๋ฃŒ. ์ตœ์  ํŒŒ๋ผ๋ฏธํ„ฐ: {'colsample_bytree': 0.7077604272501928, 'learning_rate': 0.10351387699107398, 'max_depth': 6.0, 'min_child_weight': 4.0, 'num_leaves': 51.0, 'reg_alpha': 0.06973941883143871, 'reg_lambda': 0.8477821589656351, 'subsample': 0.8664583588640111}
387
+ ์ตœ์  CSI ์ ์ˆ˜: 0.4908 (loss: -0.4908)
388
+
389
+ ์ตœ์ ํ™” ๊ณผ์ • ์š”์•ฝ:
390
+ - ์ด ์‹œ๋„ ํšŸ์ˆ˜: 100
391
+ - ์„ฑ๊ณตํ•œ ์‹œ๋„: 100
392
+ - ์ตœ์ดˆ CSI: 0.4792
393
+ - ์ตœ์ข… CSI: 0.4809
394
+ - ์ตœ๊ณ  CSI: 0.4908
395
+ - ์ตœ์ € CSI: 0.4682
396
+ - ํ‰๊ท  CSI: 0.4815
397
+
398
+ ์ตœ์ ํ™” Trials ๊ฐ์ฒด๊ฐ€ /workspace/visibility_prediction/Analysis_code/optimization_history/lgb_ctgan10000_daejeon_trials.pkl์— ์ €์žฅ๋˜์—ˆ์Šต๋‹ˆ๋‹ค.
399
+ ์ตœ์ข… ๋ชจ๋ธ ํ•™์Šต ์‹œ์ž‘...
400
+ Fold 1 ํ•™์Šต ์ค‘... (ํ•™์Šต ์—ฐ๋„: [2018, 2019], ๊ฒ€์ฆ ์—ฐ๋„: 2020)
401
+ Fold 1 ๊ฒ€์ฆ CSI: 0.4324
402
+ Fold 2 ํ•™์Šต ์ค‘... (ํ•™์Šต ์—ฐ๋„: [2018, 2020], ๊ฒ€์ฆ ์—ฐ๋„: 2019)
403
+ Fold 2 ๊ฒ€์ฆ CSI: 0.4714
404
+ Fold 3 ํ•™์Šต ์ค‘... (ํ•™์Šต ์—ฐ๋„: [2019, 2020], ๊ฒ€์ฆ ์—ฐ๋„: 2018)
405
+ Fold 3 ๊ฒ€์ฆ CSI: 0.5557
406
+ ๋ชจ๋ธ ์ €์žฅ ์ค‘...
407
+ ๋ชจ๋ธ์ด /workspace/visibility_prediction/Analysis_code/save_model/lgb_optima/lgb_ctgan10000_daejeon.pkl์— ์ €์žฅ๋˜์—ˆ์Šต๋‹ˆ๋‹ค.
408
+
409
+ โœ“ ์™„๋ฃŒ: lgb_ctgan10000/LGB_ctgan10000_daejeon.py (์†Œ์š” ์‹œ๊ฐ„: 3642์ดˆ)
410
+
411
+ ----------------------------------------
412
+ ์‹คํ–‰ ์ค‘: lgb_ctgan10000/LGB_ctgan10000_gwangju.py
413
+ ์‹œ์ž‘ ์‹œ๊ฐ„: 2025-12-28 07:31:19
414
+ ----------------------------------------
415
+ ๋ฐ์ดํ„ฐ ๋กœ๋”ฉ ์ค‘...
416
+ ๋ฐ์ดํ„ฐ ์ „์ฒ˜๋ฆฌ ์ค‘...
417
+ ํ•˜์ดํผํŒŒ๋ผ๋ฏธํ„ฐ ์ตœ์ ํ™” ์‹œ์ž‘...
418
+
419
  0%| | 0/100 [00:00<?, ?trial/s, best loss=?]
420
  1%| | 1/100 [01:02<1:42:38, 62.20s/trial, best loss: -0.4807]
421
  2%|โ– | 2/100 [01:49<1:27:01, 53.28s/trial, best loss: -0.4841]
422
  3%|โ–Ž | 3/100 [02:42<1:25:52, 53.12s/trial, best loss: -0.4848]
423
  4%|โ– | 4/100 [03:15<1:12:13, 45.14s/trial, best loss: -0.4916]
424
  5%|โ–Œ | 5/100 [04:13<1:19:05, 49.96s/trial, best loss: -0.4916]
425
  6%|โ–Œ | 6/100 [05:10<1:22:01, 52.35s/trial, best loss: -0.4916]
426
  7%|โ–‹ | 7/100 [05:34<1:06:33, 42.94s/trial, best loss: -0.4916]
427
  8%|โ–Š | 8/100 [06:55<1:24:29, 55.10s/trial, best loss: -0.4916]
428
  9%|โ–‰ | 9/100 [07:43<1:20:06, 52.82s/trial, best loss: -0.4916]
429
  10%|โ–ˆ | 10/100 [08:33<1:18:03, 52.04s/trial, best loss: -0.4916]
430
  11%|โ–ˆ | 11/100 [08:58<1:04:48, 43.69s/trial, best loss: -0.4916]
431
  12%|โ–ˆโ– | 12/100 [09:36<1:01:44, 42.09s/trial, best loss: -0.4916]
432
  13%|โ–ˆโ–Ž | 13/100 [11:00<1:19:31, 54.85s/trial, best loss: -0.4916]
433
  14%|โ–ˆโ– | 14/100 [12:01<1:21:08, 56.61s/trial, best loss: -0.4916]
434
  15%|โ–ˆโ–Œ | 15/100 [12:29<1:08:01, 48.02s/trial, best loss: -0.4916]
435
  16%|โ–ˆโ–Œ | 16/100 [13:15<1:06:13, 47.30s/trial, best loss: -0.4916]
436
  17%|โ–ˆโ–‹ | 17/100 [13:36<54:35, 39.46s/trial, best loss: -0.4916]
437
  18%|โ–ˆโ–Š | 18/100 [14:34<1:01:25, 44.94s/trial, best loss: -0.4916]
438
  19%|โ–ˆโ–‰ | 19/100 [15:04<54:45, 40.56s/trial, best loss: -0.4916]
439
  20%|โ–ˆโ–ˆ | 20/100 [16:14<1:05:52, 49.40s/trial, best loss: -0.4916]
440
  21%|โ–ˆโ–ˆ | 21/100 [16:54<1:01:24, 46.64s/trial, best loss: -0.4971]
441
  22%|โ–ˆโ–ˆโ– | 22/100 [17:30<56:16, 43.29s/trial, best loss: -0.4971]
442
  23%|โ–ˆโ–ˆโ–Ž | 23/100 [18:01<51:01, 39.77s/trial, best loss: -0.4971]
443
  24%|โ–ˆโ–ˆโ– | 24/100 [18:33<47:11, 37.25s/trial, best loss: -0.4971]
444
  25%|โ–ˆโ–ˆโ–Œ | 25/100 [19:12<47:11, 37.75s/trial, best loss: -0.4971]
445
  26%|โ–ˆโ–ˆโ–Œ | 26/100 [19:48<45:54, 37.22s/trial, best loss: -0.4971]
446
  27%|โ–ˆโ–ˆโ–‹ | 27/100 [20:30<47:14, 38.83s/trial, best loss: -0.4971]
447
  28%|โ–ˆโ–ˆโ–Š | 28/100 [21:01<43:51, 36.55s/trial, best loss: -0.4971]
448
  29%|โ–ˆโ–ˆโ–‰ | 29/100 [21:48<47:00, 39.73s/trial, best loss: -0.4971]
449
  30%|โ–ˆโ–ˆโ–ˆ | 30/100 [22:23<44:41, 38.30s/trial, best loss: -0.4971]
450
  31%|โ–ˆโ–ˆโ–ˆ | 31/100 [22:49<39:43, 34.54s/trial, best loss: -0.4971]
451
  32%|โ–ˆโ–ˆโ–ˆโ– | 32/100 [23:13<35:34, 31.39s/trial, best loss: -0.4971]
452
  33%|โ–ˆโ–ˆโ–ˆโ–Ž | 33/100 [23:34<31:37, 28.32s/trial, best loss: -0.4971]
453
  34%|โ–ˆโ–ˆโ–ˆโ– | 34/100 [24:14<35:00, 31.82s/trial, best loss: -0.4971]
454
  35%|โ–ˆโ–ˆโ–ˆโ–Œ | 35/100 [24:59<38:36, 35.64s/trial, best loss: -0.4971]
455
  36%|โ–ˆโ–ˆโ–ˆโ–Œ | 36/100 [25:35<38:10, 35.80s/trial, best loss: -0.4971]
456
  37%|โ–ˆโ–ˆโ–ˆโ–‹ | 37/100 [26:39<46:25, 44.22s/trial, best loss: -0.4971]
457
  38%|โ–ˆโ–ˆโ–ˆโ–Š | 38/100 [27:04<39:35, 38.31s/trial, best loss: -0.4971]
458
  39%|โ–ˆโ–ˆโ–ˆโ–‰ | 39/100 [27:38<37:49, 37.20s/trial, best loss: -0.4971]
459
  40%|โ–ˆโ–ˆโ–ˆโ–ˆ | 40/100 [28:10<35:45, 35.75s/trial, best loss: -0.4971]
460
  41%|โ–ˆโ–ˆโ–ˆโ–ˆ | 41/100 [28:34<31:29, 32.03s/trial, best loss: -0.4971]
461
  42%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 42/100 [29:01<29:39, 30.67s/trial, best loss: -0.4971]
462
  43%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 43/100 [29:33<29:29, 31.05s/trial, best loss: -0.4971]
463
  44%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 44/100 [30:15<32:02, 34.33s/trial, best loss: -0.4971]
464
  45%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 45/100 [30:46<30:33, 33.34s/trial, best loss: -0.4971]
465
  46%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 46/100 [31:18<29:33, 32.84s/trial, best loss: -0.4971]
466
  47%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 47/100 [31:55<30:00, 33.97s/trial, best loss: -0.4971]
467
  48%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 48/100 [32:40<32:31, 37.52s/trial, best loss: -0.4971]
468
  49%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 49/100 [33:06<28:58, 34.08s/trial, best loss: -0.4971]
469
  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 50/100 [33:29<25:34, 30.69s/trial, best loss: -0.4971]
470
  51%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 51/100 [33:54<23:39, 28.96s/trial, best loss: -0.4971]
471
  52%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 52/100 [34:21<22:42, 28.39s/trial, best loss: -0.4971]
472
  53%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 53/100 [34:57<23:53, 30.51s/trial, best loss: -0.4971]
473
  54%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 54/100 [35:35<25:16, 32.96s/trial, best loss: -0.4971]
474
  55%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 55/100 [36:07<24:24, 32.54s/trial, best loss: -0.4971]
475
  56%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 56/100 [37:12<31:05, 42.40s/trial, best loss: -0.4971]
476
  57%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 57/100 [37:49<29:04, 40.57s/trial, best loss: -0.4971]
477
  58%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 58/100 [38:23<27:06, 38.72s/trial, best loss: -0.4971]
478
  59%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 59/100 [38:56<25:20, 37.08s/trial, best loss: -0.4971]
479
  60%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 60/100 [39:30<24:08, 36.22s/trial, best loss: -0.4971]
480
  61%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 61/100 [40:38<29:41, 45.69s/trial, best loss: -0.4971]
481
  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 62/100 [41:09<26:05, 41.21s/trial, best loss: -0.4971]
482
  63%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 63/100 [41:45<24:28, 39.69s/trial, best loss: -0.4971]
483
  64%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 64/100 [42:17<22:26, 37.40s/trial, best loss: -0.4971]
484
  65%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 65/100 [42:46<20:20, 34.88s/trial, best loss: -0.4971]
485
  66%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 66/100 [43:19<19:23, 34.21s/trial, best loss: -0.4994]
486
  67%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 67/100 [43:52<18:36, 33.85s/trial, best loss: -0.4994]
487
  68%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 68/100 [44:26<18:10, 34.08s/trial, best loss: -0.4994]
488
  69%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 69/100 [45:15<19:46, 38.27s/trial, best loss: -0.4994]
489
  70%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 70/100 [45:56<19:36, 39.23s/trial, best loss: -0.4994]
490
  71%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 71/100 [46:41<19:51, 41.09s/trial, best loss: -0.4994]
491
  72%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 72/100 [47:26<19:44, 42.29s/trial, best loss: -0.4994]
492
  73%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 73/100 [48:36<22:40, 50.38s/trial, best loss: -0.4994]
493
  74%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 74/100 [49:12<20:01, 46.21s/trial, best loss: -0.4994]
494
  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 75/100 [49:58<19:11, 46.04s/trial, best loss: -0.4994]
495
  76%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 76/100 [50:36<17:24, 43.52s/trial, best loss: -0.4994]
496
  77%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 77/100 [51:07<15:19, 39.98s/trial, best loss: -0.4994]
497
  78%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 78/100 [52:08<16:54, 46.11s/trial, best loss: -0.4994]
498
  79%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 79/100 [52:46<15:22, 43.92s/trial, best loss: -0.4994]
499
  80%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 80/100 [53:27<14:18, 42.91s/trial, best loss: -0.4994]
500
  81%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 81/100 [53:59<12:33, 39.67s/trial, best loss: -0.4994]
501
  82%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 82/100 [54:47<12:39, 42.19s/trial, best loss: -0.4994]
502
  83%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 83/100 [55:36<12:30, 44.15s/trial, best loss: -0.4994]
503
  84%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 84/100 [56:13<11:10, 41.89s/trial, best loss: -0.4994]
504
  85%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 85/100 [56:50<10:09, 40.66s/trial, best loss: -0.4994]
505
  86%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 86/100 [57:41<10:11, 43.69s/trial, best loss: -0.4994]
506
  87%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 87/100 [58:47<10:54, 50.36s/trial, best loss: -0.4994]
507
  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 88/100 [59:26<09:22, 46.84s/trial, best loss: -0.4994]
508
  89%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 89/100 [1:00:02<08:02, 43.84s/trial, best loss: -0.4994]
509
  90%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 90/100 [1:00:31<06:33, 39.38s/trial, best loss: -0.4994]
510
  91%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 91/100 [1:01:09<05:48, 38.76s/trial, best loss: -0.4994]
511
  92%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 92/100 [1:01:45<05:04, 38.04s/trial, best loss: -0.4994]
512
  93%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž| 93/100 [1:02:39<04:59, 42.76s/trial, best loss: -0.4994]
513
  94%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 94/100 [1:03:06<03:48, 38.12s/trial, best loss: -0.4994]
514
  95%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ| 95/100 [1:03:39<03:02, 36.58s/trial, best loss: -0.4994]
515
  96%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ| 96/100 [1:04:16<02:26, 36.56s/trial, best loss: -0.4994]
516
  97%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹| 97/100 [1:04:51<01:48, 36.21s/trial, best loss: -0.4994]
517
  98%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š| 98/100 [1:05:15<01:05, 32.67s/trial, best loss: -0.4994]
518
  99%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰| 99/100 [1:05:43<00:31, 31.21s/trial, best loss: -0.4994]
519
+
520
+ ์ตœ์ ํ™” ์™„๋ฃŒ. ์ตœ์  ํŒŒ๋ผ๋ฏธํ„ฐ: {'colsample_bytree': 0.9974290644555891, 'learning_rate': 0.03488079849604818, 'max_depth': 15.0, 'min_child_weight': 13.0, 'num_leaves': 47.0, 'reg_alpha': 0.22968749134640387, 'reg_lambda': 0.42745540115072206, 'subsample': 0.9875948361694687}
521
+ ์ตœ์  CSI ์ ์ˆ˜: 0.4994 (loss: -0.4994)
522
+
523
+ ์ตœ์ ํ™” ๊ณผ์ • ์š”์•ฝ:
524
+ - ์ด ์‹œ๋„ ํšŸ์ˆ˜: 100
525
+ - ์„ฑ๊ณตํ•œ ์‹œ๋„: 100
526
+ - ์ตœ์ดˆ CSI: 0.4807
527
+ - ์ตœ์ข… CSI: 0.4865
528
+ - ์ตœ๊ณ  CSI: 0.4994
529
+ - ์ตœ์ € CSI: 0.4678
530
+ - ํ‰๊ท  CSI: 0.4866
531
+
532
+ ์ตœ์ ํ™” Trials ๊ฐ์ฒด๊ฐ€ /workspace/visibility_prediction/Analysis_code/optimization_history/lgb_ctgan10000_gwangju_trials.pkl์— ์ €์žฅ๋˜์—ˆ์Šต๋‹ˆ๋‹ค.
533
+ ์ตœ์ข… ๋ชจ๋ธ ํ•™์Šต ์‹œ์ž‘...
534
+ Fold 1 ํ•™์Šต ์ค‘... (ํ•™์Šต ์—ฐ๋„: [2018, 2019], ๊ฒ€์ฆ ์—ฐ๋„: 2020)
535
+ Fold 1 ๊ฒ€์ฆ CSI: 0.4045
536
+ Fold 2 ํ•™์Šต ์ค‘... (ํ•™์Šต ์—ฐ๋„: [2018, 2020], ๊ฒ€์ฆ ์—ฐ๋„: 2019)
537
+ Fold 2 ๊ฒ€์ฆ CSI: 0.5536
538
+ Fold 3 ํ•™์Šต ์ค‘... (ํ•™์Šต ์—ฐ๋„: [2019, 2020], ๏ฟฝ๏ฟฝ๏ฟฝ์ฆ ์—ฐ๋„: 2018)
539
+ Fold 3 ๊ฒ€์ฆ CSI: 0.5277
540
+ ๋ชจ๋ธ ์ €์žฅ ์ค‘...
541
+ ๋ชจ๋ธ์ด /workspace/visibility_prediction/Analysis_code/save_model/lgb_optima/lgb_ctgan10000_gwangju.pkl์— ์ €์žฅ๋˜์—ˆ์Šต๋‹ˆ๋‹ค.
542
+
543
+ โœ“ ์™„๋ฃŒ: lgb_ctgan10000/LGB_ctgan10000_gwangju.py (์†Œ์š” ์‹œ๊ฐ„: 4001์ดˆ)
544
+
545
+ ----------------------------------------
546
+ ์‹คํ–‰ ์ค‘: lgb_ctgan10000/LGB_ctgan10000_incheon.py
547
+ ์‹œ์ž‘ ์‹œ๊ฐ„: 2025-12-28 08:38:00
548
+ ----------------------------------------
549
+ ๋ฐ์ดํ„ฐ ๋กœ๋”ฉ ์ค‘...
550
+ ๋ฐ์ดํ„ฐ ์ „์ฒ˜๋ฆฌ ์ค‘...
551
+ ํ•˜์ดํผํŒŒ๋ผ๋ฏธํ„ฐ ์ตœ์ ํ™” ์‹œ์ž‘...
552
+
553
  0%| | 0/100 [00:00<?, ?trial/s, best loss=?]
554
  1%| | 1/100 [00:54<1:30:09, 54.64s/trial, best loss: -0.5469]
555
  2%|โ– | 2/100 [01:19<1:00:47, 37.22s/trial, best loss: -0.5519]
556
  3%|โ–Ž | 3/100 [01:50<55:12, 34.15s/trial, best loss: -0.5519]
557
  4%|โ– | 4/100 [02:25<55:19, 34.57s/trial, best loss: -0.5519]
558
  5%|โ–Œ | 5/100 [03:31<1:12:51, 46.01s/trial, best loss: -0.5557]
559
  6%|โ–Œ | 6/100 [04:02<1:03:56, 40.81s/trial, best loss: -0.5557]
560
  7%|โ–‹ | 7/100 [04:30<56:42, 36.58s/trial, best loss: -0.5557]
561
  8%|โ–Š | 8/100 [05:14<59:48, 39.00s/trial, best loss: -0.5557]
562
  9%|โ–‰ | 9/100 [05:44<54:59, 36.26s/trial, best loss: -0.5557]
563
  10%|โ–ˆ | 10/100 [06:26<56:54, 37.94s/trial, best loss: -0.5557]
564
  11%|โ–ˆ | 11/100 [06:56<52:53, 35.66s/trial, best loss: -0.5557]
565
  12%|โ–ˆโ– | 12/100 [08:02<1:05:32, 44.69s/trial, best loss: -0.5557]
566
  13%|โ–ˆโ–Ž | 13/100 [08:46<1:04:34, 44.53s/trial, best loss: -0.5557]
567
  14%|โ–ˆโ– | 14/100 [09:35<1:05:36, 45.77s/trial, best loss: -0.5557]
568
  15%|โ–ˆโ–Œ | 15/100 [10:59<1:21:31, 57.55s/trial, best loss: -0.5557]
569
  16%|โ–ˆโ–Œ | 16/100 [11:22<1:05:53, 47.07s/trial, best loss: -0.5557]
570
  17%|โ–ˆโ–‹ | 17/100 [12:15<1:07:27, 48.77s/trial, best loss: -0.5557]
571
  18%|โ–ˆโ–Š | 18/100 [12:46<59:16, 43.37s/trial, best loss: -0.5557]
572
  19%|โ–ˆโ–‰ | 19/100 [13:18<54:13, 40.17s/trial, best loss: -0.5557]
573
  20%|โ–ˆโ–ˆ | 20/100 [13:43<47:31, 35.64s/trial, best loss: -0.5557]
574
  21%|โ–ˆโ–ˆ | 21/100 [14:13<44:40, 33.93s/trial, best loss: -0.5557]
575
  22%|โ–ˆโ–ˆโ– | 22/100 [15:23<58:03, 44.67s/trial, best loss: -0.5557]
576
  23%|โ–ˆโ–ˆโ–Ž | 23/100 [15:46<49:03, 38.23s/trial, best loss: -0.5557]
577
  24%|โ–ˆโ–ˆโ– | 24/100 [16:16<45:01, 35.55s/trial, best loss: -0.5557]
578
  25%|โ–ˆโ–ˆโ–Œ | 25/100 [16:48<43:17, 34.64s/trial, best loss: -0.5557]
579
  26%|โ–ˆโ–ˆโ–Œ | 26/100 [17:28<44:29, 36.07s/trial, best loss: -0.5557]
580
  27%|โ–ˆโ–ˆโ–‹ | 27/100 [17:55<40:51, 33.59s/trial, best loss: -0.5557]
581
  28%|โ–ˆโ–ˆโ–Š | 28/100 [18:25<39:01, 32.52s/trial, best loss: -0.556]
582
  29%|โ–ˆโ–ˆโ–‰ | 29/100 [19:42<54:10, 45.78s/trial, best loss: -0.556]
583
  30%|โ–ˆโ–ˆโ–ˆ | 30/100 [20:16<49:15, 42.23s/trial, best loss: -0.556]
584
  31%|โ–ˆโ–ˆโ–ˆ | 31/100 [20:49<45:25, 39.50s/trial, best loss: -0.556]
585
  32%|โ–ˆโ–ˆโ–ˆโ– | 32/100 [21:32<45:48, 40.41s/trial, best loss: -0.556]
586
  33%|โ–ˆโ–ˆโ–ˆโ–Ž | 33/100 [22:16<46:24, 41.57s/trial, best loss: -0.5567]
587
  34%|โ–ˆโ–ˆโ–ˆโ– | 34/100 [22:57<45:31, 41.39s/trial, best loss: -0.5567]
588
  35%|โ–ˆโ–ˆโ–ˆโ–Œ | 35/100 [23:40<45:17, 41.81s/trial, best loss: -0.5567]
589
  36%|โ–ˆโ–ˆโ–ˆโ–Œ | 36/100 [24:46<52:33, 49.28s/trial, best loss: -0.5567]
590
  37%|โ–ˆโ–ˆโ–ˆโ–‹ | 37/100 [25:24<48:09, 45.86s/trial, best loss: -0.558]
591
  38%|โ–ˆโ–ˆโ–ˆโ–Š | 38/100 [26:06<46:08, 44.65s/trial, best loss: -0.558]
592
  39%|โ–ˆโ–ˆโ–ˆโ–‰ | 39/100 [26:54<46:31, 45.76s/trial, best loss: -0.558]
593
  40%|โ–ˆโ–ˆโ–ˆโ–ˆ | 40/100 [27:40<45:35, 45.60s/trial, best loss: -0.558]
594
  41%|โ–ˆโ–ˆโ–ˆโ–ˆ | 41/100 [28:19<42:58, 43.71s/trial, best loss: -0.558]
595
  42%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 42/100 [29:14<45:34, 47.14s/trial, best loss: -0.558]
596
  43%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 43/100 [29:56<43:11, 45.47s/trial, best loss: -0.558]
597
  44%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 44/100 [30:58<47:01, 50.39s/trial, best loss: -0.558]
598
  45%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 45/100 [31:43<44:47, 48.86s/trial, best loss: -0.558]
599
  46%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 46/100 [32:39<46:01, 51.15s/trial, best loss: -0.558]
600
  47%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 47/100 [33:32<45:28, 51.48s/trial, best loss: -0.558]
601
  48%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 48/100 [34:10<41:20, 47.70s/trial, best loss: -0.558]
602
  49%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 49/100 [34:49<38:16, 45.04s/trial, best loss: -0.558]
603
  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 50/100 [35:28<35:54, 43.09s/trial, best loss: -0.558]
604
  51%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 51/100 [36:07<34:20, 42.06s/trial, best loss: -0.558]
605
  52%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 52/100 [36:43<32:09, 40.19s/trial, best loss: -0.558]
606
  53%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 53/100 [37:19<30:30, 38.94s/trial, best loss: -0.558]
607
  54%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 54/100 [37:47<27:17, 35.59s/trial, best loss: -0.558]
608
  55%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 55/100 [38:19<25:50, 34.45s/trial, best loss: -0.558]
609
  56%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 56/100 [39:05<27:44, 37.83s/trial, best loss: -0.558]
610
  57%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 57/100 [39:37<25:53, 36.12s/trial, best loss: -0.558]
611
  58%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 58/100 [40:15<25:40, 36.67s/trial, best loss: -0.558]
612
  59%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 59/100 [40:53<25:27, 37.25s/trial, best loss: -0.558]
613
  60%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 60/100 [41:39<26:29, 39.73s/trial, best loss: -0.558]
614
  61%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 61/100 [42:12<24:36, 37.85s/trial, best loss: -0.558]
615
  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 62/100 [42:45<22:55, 36.21s/trial, best loss: -0.558]
616
  63%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 63/100 [43:34<24:41, 40.05s/trial, best loss: -0.558]
617
  64%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 64/100 [43:56<20:46, 34.61s/trial, best loss: -0.558]
618
  65%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 65/100 [44:36<21:12, 36.36s/trial, best loss: -0.558]
619
  66%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 66/100 [45:08<19:49, 34.98s/trial, best loss: -0.558]
620
  67%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 67/100 [45:36<18:03, 32.83s/trial, best loss: -0.558]
621
  68%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 68/100 [46:02<16:32, 31.03s/trial, best loss: -0.558]
622
  69%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 69/100 [46:45<17:48, 34.45s/trial, best loss: -0.5588]
623
  70%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 70/100 [47:26<18:11, 36.38s/trial, best loss: -0.5588]
624
  71%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 71/100 [48:08<18:24, 38.10s/trial, best loss: -0.5588]
625
  72%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 72/100 [48:40<16:57, 36.33s/trial, best loss: -0.5588]
626
  73%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 73/100 [49:47<20:26, 45.41s/trial, best loss: -0.5588]
627
  74%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 74/100 [50:25<18:42, 43.17s/trial, best loss: -0.5588]
628
  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 75/100 [51:28<20:32, 49.28s/trial, best loss: -0.5588]
629
  76%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 76/100 [52:21<20:06, 50.28s/trial, best loss: -0.5588]
630
  77%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 77/100 [53:03<18:18, 47.74s/trial, best loss: -0.5588]
631
  78%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 78/100 [53:47<17:11, 46.87s/trial, best loss: -0.5588]
632
  79%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 79/100 [54:27<15:40, 44.78s/trial, best loss: -0.5588]
633
  80%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 80/100 [55:22<15:58, 47.90s/trial, best loss: -0.5588]
634
  81%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 81/100 [55:57<13:54, 43.91s/trial, best loss: -0.5588]
635
  82%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 82/100 [56:31<12:14, 40.78s/trial, best loss: -0.5588]
636
  83%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 83/100 [57:01<10:39, 37.63s/trial, best loss: -0.5588]
637
  84%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 84/100 [57:42<10:18, 38.68s/trial, best loss: -0.5588]
638
  85%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 85/100 [58:32<10:29, 41.95s/trial, best loss: -0.5588]
639
  86%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 86/100 [59:09<09:27, 40.52s/trial, best loss: -0.5588]
640
  87%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 87/100 [59:52<08:58, 41.40s/trial, best loss: -0.5588]
641
  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 88/100 [1:00:15<07:08, 35.74s/trial, best loss: -0.5588]
642
  89%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 89/100 [1:00:53<06:40, 36.37s/trial, best loss: -0.5588]
643
  90%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 90/100 [1:01:38<06:30, 39.04s/trial, best loss: -0.5588]
644
  91%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 91/100 [1:02:20<05:59, 39.93s/trial, best loss: -0.5588]
645
  92%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 92/100 [1:03:11<05:45, 43.19s/trial, best loss: -0.5592]
646
  93%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž| 93/100 [1:04:06<05:27, 46.72s/trial, best loss: -0.5592]
647
  94%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 94/100 [1:05:23<05:34, 55.81s/trial, best loss: -0.5592]
648
  95%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ| 95/100 [1:06:36<05:05, 61.13s/trial, best loss: -0.5592]
649
  96%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ| 96/100 [1:07:16<03:39, 54.80s/trial, best loss: -0.5592]
650
  97%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹| 97/100 [1:07:55<02:30, 50.12s/trial, best loss: -0.5592]
651
  98%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š| 98/100 [1:08:36<01:34, 47.21s/trial, best loss: -0.5592]
652
  99%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰| 99/100 [1:09:51<00:55, 55.54s/trial, best loss: -0.5592]
653
+
654
+ ์ตœ์ ํ™” ์™„๋ฃŒ. ์ตœ์  ํŒŒ๋ผ๋ฏธํ„ฐ: {'colsample_bytree': 0.7615743363801121, 'learning_rate': 0.032013705340192794, 'max_depth': 12.0, 'min_child_weight': 4.0, 'num_leaves': 135.0, 'reg_alpha': 0.07355917150019742, 'reg_lambda': 0.7693270890686972, 'subsample': 0.8491133431153928}
655
+ ์ตœ์  CSI ์ ์ˆ˜: 0.5592 (loss: -0.5592)
656
+
657
+ ์ตœ์ ํ™” ๊ณผ์ • ์š”์•ฝ:
658
+ - ์ด ์‹œ๋„ ํšŸ์ˆ˜: 100
659
+ - ์„ฑ๊ณตํ•œ ์‹œ๋„: 100
660
+ - ์ตœ์ดˆ CSI: 0.5469
661
+ - ์ตœ์ข… CSI: 0.5567
662
+ - ์ตœ๊ณ  CSI: 0.5592
663
+ - ์ตœ์ € CSI: 0.5428
664
+ - ํ‰๊ท  CSI: 0.5520
665
+
666
+ ์ตœ์ ํ™” Trials ๊ฐ์ฒด๊ฐ€ /workspace/visibility_prediction/Analysis_code/optimization_history/lgb_ctgan10000_incheon_trials.pkl์— ์ €์žฅ๋˜์—ˆ์Šต๋‹ˆ๋‹ค.
667
+ ์ตœ์ข… ๋ชจ๋ธ ํ•™์Šต ์‹œ์ž‘...
668
+ Fold 1 ํ•™์Šต ์ค‘... (ํ•™์Šต ์—ฐ๋„: [2018, 2019], ๊ฒ€์ฆ ์—ฐ๋„: 2020)
669
+ Fold 1 ๊ฒ€์ฆ CSI: 0.4967
670
+ Fold 2 ํ•™์Šต ์ค‘... (ํ•™์Šต ์—ฐ๋„: [2018, 2020], ๊ฒ€์ฆ ์—ฐ๋„: 2019)
671
+ Fold 2 ๊ฒ€์ฆ CSI: 0.6068
672
+ Fold 3 ํ•™์Šต ์ค‘... (ํ•™์Šต ์—ฐ๋„: [2019, 2020], ๊ฒ€์ฆ ์—ฐ๋„: 2018)
673
+ Fold 3 ๊ฒ€์ฆ CSI: 0.5748
674
+ ๋ชจ๋ธ ์ €์žฅ ์ค‘...
675
+ ๋ชจ๋ธ์ด /workspace/visibility_prediction/Analysis_code/save_model/lgb_optima/lgb_ctgan10000_incheon.pkl์— ์ €์žฅ๋˜์—ˆ์Šต๋‹ˆ๋‹ค.
676
+
677
+ โœ“ ์™„๋ฃŒ: lgb_ctgan10000/LGB_ctgan10000_incheon.py (์†Œ์š” ์‹œ๊ฐ„: 4299์ดˆ)
678
+
679
+ ----------------------------------------
680
+ ์‹คํ–‰ ์ค‘: lgb_ctgan10000/LGB_ctgan10000_seoul.py
681
+ ์‹œ์ž‘ ์‹œ๊ฐ„: 2025-12-28 09:49:39
682
+ ----------------------------------------
683
+ ๋ฐ์ดํ„ฐ ๋กœ๋”ฉ ์ค‘...
684
+ ๋ฐ์ดํ„ฐ ์ „์ฒ˜๋ฆฌ ์ค‘...
685
+ ํ•˜์ดํผํŒŒ๋ผ๋ฏธํ„ฐ ์ตœ์ ํ™” ์‹œ์ž‘...
686
+
687
  0%| | 0/100 [00:00<?, ?trial/s, best loss=?]
688
  1%| | 1/100 [01:13<2:01:00, 73.34s/trial, best loss: -0.5479]
689
  2%|โ– | 2/100 [01:43<1:18:00, 47.76s/trial, best loss: -0.5552]
690
  3%|โ–Ž | 3/100 [02:04<57:22, 35.48s/trial, best loss: -0.558]
691
  4%|โ– | 4/100 [03:04<1:12:39, 45.41s/trial, best loss: -0.558]
692
  5%|โ–Œ | 5/100 [03:45<1:09:30, 43.90s/trial, best loss: -0.558]
693
  6%|โ–Œ | 6/100 [04:11<58:53, 37.59s/trial, best loss: -0.5639]
694
  7%|โ–‹ | 7/100 [04:54<1:01:02, 39.38s/trial, best loss: -0.5639]
695
  8%|โ–Š | 8/100 [05:50<1:08:46, 44.86s/trial, best loss: -0.5639]
696
  9%|โ–‰ | 9/100 [06:40<1:10:17, 46.34s/trial, best loss: -0.5639]
697
  10%|โ–ˆ | 10/100 [07:29<1:10:30, 47.01s/trial, best loss: -0.5639]
698
  11%|โ–ˆ | 11/100 [08:14<1:08:51, 46.42s/trial, best loss: -0.5639]
699
  12%|โ–ˆโ– | 12/100 [08:33<56:03, 38.22s/trial, best loss: -0.5639]
700
  13%|โ–ˆโ–Ž | 13/100 [08:57<49:03, 33.84s/trial, best loss: -0.5639]
701
  14%|โ–ˆโ– | 14/100 [09:20<43:45, 30.53s/trial, best loss: -0.5639]
702
  15%|โ–ˆโ–Œ | 15/100 [09:49<42:37, 30.09s/trial, best loss: -0.5639]
703
  16%|โ–ˆโ–Œ | 16/100 [11:05<1:01:44, 44.10s/trial, best loss: -0.5639]
704
  17%|โ–ˆโ–‹ | 17/100 [11:51<1:01:40, 44.58s/trial, best loss: -0.5639]
705
  18%|โ–ˆโ–Š | 18/100 [12:21<55:03, 40.28s/trial, best loss: -0.5639]
706
  19%|โ–ˆโ–‰ | 19/100 [12:46<47:51, 35.45s/trial, best loss: -0.5639]
707
  20%|โ–ˆโ–ˆ | 20/100 [13:30<50:43, 38.05s/trial, best loss: -0.5639]
708
  21%|โ–ˆโ–ˆ | 21/100 [13:54<44:35, 33.86s/trial, best loss: -0.5639]
709
  22%|โ–ˆโ–ˆโ– | 22/100 [14:21<41:16, 31.75s/trial, best loss: -0.5639]
710
  23%|โ–ˆโ–ˆโ–Ž | 23/100 [14:43<37:04, 28.89s/trial, best loss: -0.5639]
711
  24%|โ–ˆโ–ˆโ– | 24/100 [15:09<35:34, 28.08s/trial, best loss: -0.5639]
712
  25%|โ–ˆโ–ˆโ–Œ | 25/100 [15:31<32:49, 26.26s/trial, best loss: -0.5639]
713
  26%|โ–ˆโ–ˆโ–Œ | 26/100 [15:54<31:08, 25.25s/trial, best loss: -0.5639]
714
  27%|โ–ˆโ–ˆโ–‹ | 27/100 [16:19<30:45, 25.28s/trial, best loss: -0.5639]
715
  28%|โ–ˆโ–ˆโ–Š | 28/100 [16:46<30:58, 25.81s/trial, best loss: -0.5639]
716
  29%|โ–ˆโ–ˆโ–‰ | 29/100 [17:08<28:59, 24.51s/trial, best loss: -0.5639]
717
  30%|โ–ˆโ–ˆโ–ˆ | 30/100 [17:43<32:21, 27.74s/trial, best loss: -0.5639]
718
  31%|โ–ˆโ–ˆโ–ˆ | 31/100 [18:09<31:10, 27.11s/trial, best loss: -0.5639]
719
  32%|โ–ˆโ–ˆโ–ˆโ– | 32/100 [18:37<31:01, 27.38s/trial, best loss: -0.5639]
720
  33%|โ–ˆโ–ˆโ–ˆโ–Ž | 33/100 [19:01<29:22, 26.31s/trial, best loss: -0.5639]
721
  34%|โ–ˆโ–ˆโ–ˆโ– | 34/100 [19:30<30:00, 27.28s/trial, best loss: -0.5639]
722
  35%|โ–ˆโ–ˆโ–ˆโ–Œ | 35/100 [19:58<29:44, 27.46s/trial, best loss: -0.5639]
723
  36%|โ–ˆโ–ˆโ–ˆโ–Œ | 36/100 [20:22<28:19, 26.55s/trial, best loss: -0.5639]
724
  37%|โ–ˆโ–ˆโ–ˆโ–‹ | 37/100 [21:29<40:25, 38.50s/trial, best loss: -0.5639]
725
  38%|โ–ˆโ–ˆโ–ˆโ–Š | 38/100 [21:51<34:50, 33.72s/trial, best loss: -0.5639]
726
  39%|โ–ˆโ–ˆโ–ˆโ–‰ | 39/100 [22:17<31:58, 31.44s/trial, best loss: -0.5639]
727
  40%|โ–ˆโ–ˆโ–ˆโ–ˆ | 40/100 [22:41<28:57, 28.96s/trial, best loss: -0.5639]
728
  41%|โ–ˆโ–ˆโ–ˆโ–ˆ | 41/100 [23:15<30:07, 30.63s/trial, best loss: -0.5639]
729
  42%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 42/100 [23:39<27:46, 28.74s/trial, best loss: -0.5639]
730
  43%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 43/100 [24:00<25:01, 26.34s/trial, best loss: -0.5639]
731
  44%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 44/100 [24:27<24:44, 26.51s/trial, best loss: -0.5639]
732
  45%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 45/100 [25:06<27:45, 30.28s/trial, best loss: -0.5639]
733
  46%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 46/100 [26:00<33:30, 37.23s/trial, best loss: -0.5639]
734
  47%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 47/100 [26:37<32:59, 37.35s/trial, best loss: -0.5639]
735
  48%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 48/100 [27:20<33:53, 39.11s/trial, best loss: -0.5639]
736
  49%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 49/100 [28:20<38:25, 45.22s/trial, best loss: -0.5639]
737
  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 50/100 [28:53<34:36, 41.53s/trial, best loss: -0.5639]
738
  51%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 51/100 [29:31<32:57, 40.36s/trial, best loss: -0.5639]
739
  52%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 52/100 [30:14<32:59, 41.23s/trial, best loss: -0.5639]
740
  53%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 53/100 [30:47<30:18, 38.70s/trial, best loss: -0.5639]
741
  54%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 54/100 [31:18<28:03, 36.61s/trial, best loss: -0.5639]
742
  55%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 55/100 [31:49<26:11, 34.93s/trial, best loss: -0.5639]
743
  56%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 56/100 [32:46<30:26, 41.51s/trial, best loss: -0.5639]
744
  57%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 57/100 [33:33<30:59, 43.25s/trial, best loss: -0.5639]
745
  58%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 58/100 [34:05<27:50, 39.78s/trial, best loss: -0.5639]
746
  59%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 59/100 [34:53<28:45, 42.09s/trial, best loss: -0.5639]
747
  60%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 60/100 [35:17<24:35, 36.90s/trial, best loss: -0.5639]
748
  61%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 61/100 [35:44<22:03, 33.93s/trial, best loss: -0.5639]
749
  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 62/100 [36:08<19:31, 30.83s/trial, best loss: -0.5639]
750
  63%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 63/100 [36:36<18:26, 29.91s/trial, best loss: -0.5639]
751
  64%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 64/100 [36:56<16:16, 27.13s/trial, best loss: -0.5639]
752
  65%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 65/100 [37:22<15:30, 26.57s/trial, best loss: -0.5639]
753
  66%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 66/100 [37:54<16:05, 28.41s/trial, best loss: -0.5655]
754
  67%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 67/100 [38:28<16:32, 30.06s/trial, best loss: -0.5655]
755
  68%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 68/100 [39:05<17:07, 32.12s/trial, best loss: -0.5655]
756
  69%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 69/100 [39:35<16:15, 31.48s/trial, best loss: -0.5655]
757
  70%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 70/100 [40:17<17:17, 34.58s/trial, best loss: -0.5655]
758
  71%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 71/100 [40:41<15:13, 31.49s/trial, best loss: -0.5655]
759
  72%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 72/100 [41:26<16:34, 35.53s/trial, best loss: -0.5655]
760
  73%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 73/100 [41:53<14:51, 33.02s/trial, best loss: -0.5655]
761
  74%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 74/100 [42:31<14:57, 34.53s/trial, best loss: -0.5655]
762
  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 75/100 [43:02<13:50, 33.22s/trial, best loss: -0.5655]
763
  76%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 76/100 [43:46<14:37, 36.58s/trial, best loss: -0.5655]
764
  77%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 77/100 [44:15<13:06, 34.20s/trial, best loss: -0.5655]
765
  78%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 78/100 [44:47<12:22, 33.75s/trial, best loss: -0.5655]
766
  79%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 79/100 [45:17<11:20, 32.40s/trial, best loss: -0.5655]
767
  80%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 80/100 [45:48<10:41, 32.08s/trial, best loss: -0.5655]
768
  81%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 81/100 [46:27<10:47, 34.07s/trial, best loss: -0.5655]
769
  82%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 82/100 [47:05<10:36, 35.34s/trial, best loss: -0.5655]
770
  83%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 83/100 [47:37<09:44, 34.37s/trial, best loss: -0.5655]
771
  84%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 84/100 [48:20<09:50, 36.90s/trial, best loss: -0.5655]
772
  85%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 85/100 [48:51<08:46, 35.11s/trial, best loss: -0.5655]
773
  86%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 86/100 [49:25<08:06, 34.73s/trial, best loss: -0.5655]
774
  87%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 87/100 [49:56<07:16, 33.56s/trial, best loss: -0.5655]
775
  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 88/100 [50:33<06:56, 34.70s/trial, best loss: -0.566]
776
  89%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 89/100 [51:19<06:57, 37.99s/trial, best loss: -0.566]
777
  90%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 90/100 [51:54<06:10, 37.08s/trial, best loss: -0.566]
778
  91%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 91/100 [52:47<06:18, 42.10s/trial, best loss: -0.566]
779
  92%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 92/100 [53:24<05:23, 40.43s/trial, best loss: -0.5671]
780
  93%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž| 93/100 [54:01<04:36, 39.53s/trial, best loss: -0.5671]
781
  94%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 94/100 [54:56<04:24, 44.12s/trial, best loss: -0.5671]
782
  95%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ| 95/100 [55:34<03:31, 42.24s/trial, best loss: -0.5671]
783
  96%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ| 96/100 [56:12<02:43, 40.95s/trial, best loss: -0.5671]
784
  97%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹| 97/100 [56:56<02:05, 41.79s/trial, best loss: -0.5671]
785
  98%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š| 98/100 [57:43<01:26, 43.42s/trial, best loss: -0.5671]
786
  99%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰| 99/100 [58:35<00:45, 45.96s/trial, best loss: -0.5671]
787
+
788
+ ์ตœ์ ํ™” ์™„๋ฃŒ. ์ตœ์  ํŒŒ๋ผ๋ฏธํ„ฐ: {'colsample_bytree': 0.661683034534645, 'learning_rate': 0.02117850018558707, 'max_depth': 15.0, 'min_child_weight': 16.0, 'num_leaves': 83.0, 'reg_alpha': 0.6438462886327296, 'reg_lambda': 0.8929153518940249, 'subsample': 0.9547922722157274}
789
+ ์ตœ์  CSI ์ ์ˆ˜: 0.5671 (loss: -0.5671)
790
+
791
+ ์ตœ์ ํ™” ๊ณผ์ • ์š”์•ฝ:
792
+ - ์ด ์‹œ๋„ ํšŸ์ˆ˜: 100
793
+ - ์„ฑ๊ณตํ•œ ์‹œ๋„: 100
794
+ - ์ตœ์ดˆ CSI: 0.5479
795
+ - ์ตœ์ข… CSI: 0.5505
796
+ - ์ตœ๊ณ  CSI: 0.5671
797
+ - ์ตœ์ € CSI: 0.5432
798
+ - ํ‰๊ท  CSI: 0.5579
799
+
800
+ ์ตœ์ ํ™” Trials ๊ฐ์ฒด๊ฐ€ /workspace/visibility_prediction/Analysis_code/optimization_history/lgb_ctgan10000_seoul_trials.pkl์— ์ €์žฅ๋˜์—ˆ์Šต๋‹ˆ๋‹ค.
801
+ ์ตœ์ข… ๋ชจ๋ธ ํ•™์Šต ์‹œ์ž‘...
802
+ Fold 1 ํ•™์Šต ์ค‘... (ํ•™์Šต ์—ฐ๋„: [2018, 2019], ๊ฒ€์ฆ ์—ฐ๋„: 2020)
803
+ Fold 1 ๊ฒ€์ฆ CSI: 0.4967
804
+ Fold 2 ํ•™์Šต ์ค‘... (ํ•™์Šต ์—ฐ๋„: [2018, 2020], ๊ฒ€์ฆ ์—ฐ๋„: 2019)
805
+ Fold 2 ๊ฒ€์ฆ CSI: 0.5994
806
+ Fold 3 ํ•™์Šต ์ค‘... (ํ•™์Šต ์—ฐ๋„: [2019, 2020], ๊ฒ€์ฆ ์—ฐ๋„: 2018)
807
+ Fold 3 ๊ฒ€์ฆ CSI: 0.5777
808
+ ๋ชจ๋ธ ์ €์žฅ ์ค‘...
809
+ ๋ชจ๋ธ์ด /workspace/visibility_prediction/Analysis_code/save_model/lgb_optima/lgb_ctgan10000_seoul.pkl์— ์ €์žฅ๋˜์—ˆ์Šต๋‹ˆ๋‹ค.
810
+
811
+ โœ“ ์™„๋ฃŒ: lgb_ctgan10000/LGB_ctgan10000_seoul.py (์†Œ์š” ์‹œ๊ฐ„: 3571์ดˆ)
812
+
813
+ ==========================================
814
+ LGB CTGAN10000 ํŒŒ์ผ ์‹คํ–‰ ์™„๋ฃŒ
815
+ ์ข…๋ฃŒ ์‹œ๊ฐ„: 2025-12-28 10:49:10
816
+ ์ด ์†Œ์š” ์‹œ๊ฐ„: 6์‹œ๊ฐ„ 19๋ถ„ 31์ดˆ
817
+ ์„ฑ๊ณต: 6๊ฐœ
818
+ ์‹คํŒจ: 0๊ฐœ
819
+ ==========================================
Analysis_code/5.optima/run_bash/lgb/run_lgb_ctgan10000.sh CHANGED
@@ -45,7 +45,7 @@ for file in "${FILES[@]}"; do
45
  FILE_START=$(date +%s)
46
 
47
  # Python ์Šคํฌ๋ฆฝํŠธ ์‹คํ–‰ (GPU 1๋ฒˆ ์„ค์ •)
48
- if CUDA_VISIBLE_DEVICES=0 python3 -u "$filepath"; then
49
  FILE_END=$(date +%s)
50
  FILE_DURATION=$((FILE_END - FILE_START))
51
  echo ""
 
45
  FILE_START=$(date +%s)
46
 
47
  # Python ์Šคํฌ๋ฆฝํŠธ ์‹คํ–‰ (GPU 1๋ฒˆ ์„ค์ •)
48
+ if CUDA_VISIBLE_DEVICES=1 python3 -u "$filepath"; then
49
  FILE_END=$(date +%s)
50
  FILE_DURATION=$((FILE_END - FILE_START))
51
  echo ""
Analysis_code/5.optima/run_bash/resnet_like/resnet_like_ctgan10000 DELETED
The diff for this file is too large to render. See raw diff
 
Analysis_code/5.optima/run_bash/resnet_like/resnet_like_ctgan10000.log ADDED
The diff for this file is too large to render. See raw diff
 
Analysis_code/5.optima/run_bash/resnet_like/run_resnet_like_ctgan10000.sh CHANGED
@@ -15,6 +15,11 @@ echo ""
15
  # ์‹คํ–‰ํ•  ํŒŒ์ผ ๋ชฉ๋ก
16
  FILES=(
17
  "resnet_like_ctgan10000_busan.py"
 
 
 
 
 
18
  )
19
 
20
  # ์—๋Ÿฌ ๋ฐœ์ƒ ์‹œ ์ค‘๋‹จ ์—ฌ๋ถ€ (set -e๋ฅผ ์‚ฌ์šฉํ•˜๋ฉด ์—๋Ÿฌ ๋ฐœ์ƒ ์‹œ ์ฆ‰์‹œ ์ค‘๋‹จ)
 
15
  # ์‹คํ–‰ํ•  ํŒŒ์ผ ๋ชฉ๋ก
16
  FILES=(
17
  "resnet_like_ctgan10000_busan.py"
18
+ "resnet_like_ctgan10000_daegu.py"
19
+ "resnet_like_ctgan10000_daejeon.py"
20
+ "resnet_like_ctgan10000_gwangju.py"
21
+ "resnet_like_ctgan10000_incheon.py"
22
+ "resnet_like_ctgan10000_seoul.py"
23
  )
24
 
25
  # ์—๋Ÿฌ ๋ฐœ์ƒ ์‹œ ์ค‘๋‹จ ์—ฌ๋ถ€ (set -e๋ฅผ ์‚ฌ์šฉํ•˜๋ฉด ์—๋Ÿฌ ๋ฐœ์ƒ ์‹œ ์ฆ‰์‹œ ์ค‘๋‹จ)
Analysis_code/5.optima/run_bash/xgb/xgb_ctgan10000.log CHANGED
@@ -1,156 +1,219 @@
1
- nohup: ignoring input
2
- /bin/bash: /opt/conda/lib/libtinfo.so.6: no version information available (required by /bin/bash)
3
- ==========================================
4
- XGB CTGAN10000 ํŒŒ์ผ ์‹คํ–‰ ์‹œ์ž‘
5
- ์‹œ์ž‘ ์‹œ๊ฐ„: 2025-12-23 19:08:25
6
- GPU: 0๋ฒˆ (CUDA_VISIBLE_DEVICES=0)
7
- ==========================================
8
-
9
- ----------------------------------------
10
- ์‹คํ–‰ ์ค‘: xgb_ctgan10000/XGB_ctgan10000_busan.py
11
- ์‹œ์ž‘ ์‹œ๊ฐ„: 2025-12-23 19:08:25
12
- ----------------------------------------
13
- ๋ฐ์ดํ„ฐ ๋กœ๋”ฉ ์ค‘...
14
- ๋ฐ์ดํ„ฐ ์ „์ฒ˜๋ฆฌ ์ค‘...
15
- ํ•˜์ดํผํŒŒ๋ผ๋ฏธํ„ฐ ์ตœ์ ํ™” ์‹œ์ž‘...
16
-
17
- 0%| | 0/100 [00:00<?, ?trial/s, best loss=?]
18
- 1%| | 1/100 [00:45<1:15:32, 45.78s/trial, best loss: -0.4742]
19
- 2%|โ– | 2/100 [01:39<1:22:40, 50.62s/trial, best loss: -0.4742]
20
- 3%|โ–Ž | 3/100 [02:20<1:14:17, 45.95s/trial, best loss: -0.4742]
21
- 4%|โ– | 4/100 [02:41<57:43, 36.08s/trial, best loss: -0.4742]
22
- 5%|โ–Œ | 5/100 [03:30<1:04:58, 41.04s/trial, best loss: -0.4756]
23
- 6%|โ–Œ | 6/100 [04:28<1:13:19, 46.80s/trial, best loss: -0.4756]
24
- 7%|โ–‹ | 7/100 [05:49<1:29:34, 57.79s/trial, best loss: -0.4756]
25
- 8%|โ–Š | 8/100 [07:20<1:45:00, 68.48s/trial, best loss: -0.4756]
26
- 9%|โ–‰ | 9/100 [08:20<1:39:34, 65.65s/trial, best loss: -0.4756]
27
- 10%|โ–ˆ | 10/100 [08:48<1:21:19, 54.22s/trial, best loss: -0.4756]
28
- 11%|โ–ˆ | 11/100 [09:59<1:27:52, 59.24s/trial, best loss: -0.4756]
29
- 12%|โ–ˆโ– | 12/100 [10:46<1:21:30, 55.58s/trial, best loss: -0.4756]
30
- 13%|โ–ˆโ–Ž | 13/100 [11:56<1:26:59, 60.00s/trial, best loss: -0.4756]
31
- 14%|โ–ˆโ– | 14/100 [13:27<1:39:05, 69.14s/trial, best loss: -0.4756]
32
- 15%|โ–ˆโ–Œ | 15/100 [13:55<1:20:42, 56.97s/trial, best loss: -0.4756]
33
- 16%|โ–ˆโ–Œ | 16/100 [14:28<1:09:36, 49.72s/trial, best loss: -0.4756]
34
- 17%|โ–ˆโ–‹ | 17/100 [15:44<1:19:28, 57.45s/trial, best loss: -0.4756]
35
- 18%|โ–ˆโ–Š | 18/100 [16:32<1:14:59, 54.87s/trial, best loss: -0.4756]
36
- 19%|โ–ˆโ–‰ | 19/100 [18:02<1:28:10, 65.32s/trial, best loss: -0.4756]
37
- 20%|โ–ˆโ–ˆ | 20/100 [18:39<1:15:40, 56.75s/trial, best loss: -0.4756]
38
- 21%|โ–ˆโ–ˆ | 21/100 [19:43<1:17:41, 59.01s/trial, best loss: -0.4756]
39
- 22%|โ–ˆโ–ˆโ– | 22/100 [20:26<1:10:23, 54.15s/trial, best loss: -0.4756]
40
- 23%|โ–ˆโ–ˆโ–Ž | 23/100 [21:19<1:09:13, 53.95s/trial, best loss: -0.4763]
41
- 24%|โ–ˆโ–ˆโ– | 24/100 [21:59<1:02:44, 49.53s/trial, best loss: -0.4795]
42
- 25%|โ–ˆโ–ˆโ–Œ | 25/100 [22:30<55:02, 44.04s/trial, best loss: -0.4795]
43
- 26%|โ–ˆโ–ˆโ–Œ | 26/100 [23:16<55:08, 44.71s/trial, best loss: -0.4795]
44
- 27%|โ–ˆโ–ˆโ–‹ | 27/100 [24:03<55:13, 45.39s/trial, best loss: -0.481]
45
- 28%|โ–ˆโ–ˆโ–Š | 28/100 [24:32<48:28, 40.39s/trial, best loss: -0.4816]
46
- 29%|โ–ˆโ–ˆโ–‰ | 29/100 [24:56<42:07, 35.60s/trial, best loss: -0.4816]
47
- 30%|โ–ˆโ–ˆโ–ˆ | 30/100 [25:23<38:21, 32.88s/trial, best loss: -0.4816]
48
- 31%|โ–ˆโ–ˆโ–ˆ | 31/100 [25:54<37:18, 32.45s/trial, best loss: -0.4838]
49
- 32%|โ–ˆโ–ˆโ–ˆโ– | 32/100 [26:22<35:07, 30.99s/trial, best loss: -0.4838]
50
- 33%|โ–ˆโ–ˆโ–ˆโ–Ž | 33/100 [26:53<34:38, 31.03s/trial, best loss: -0.4838]
51
- 34%|โ–ˆโ–ˆโ–ˆโ– | 34/100 [27:39<38:58, 35.44s/trial, best loss: -0.4838]
52
- 35%|โ–ˆโ–ˆโ–ˆโ–Œ | 35/100 [28:08<36:29, 33.69s/trial, best loss: -0.4838]
53
- 36%|โ–ˆโ–ˆโ–ˆโ–Œ | 36/100 [28:40<35:19, 33.11s/trial, best loss: -0.4838]
54
- 37%|โ–ˆโ–ˆโ–ˆโ–‹ | 37/100 [29:11<34:09, 32.54s/trial, best loss: -0.4838]
55
- 38%|โ–ˆโ–ˆโ–ˆโ–Š | 38/100 [29:49<35:16, 34.13s/trial, best loss: -0.4838]
56
- 39%|โ–ˆโ–ˆโ–ˆโ–‰ | 39/100 [30:34<37:59, 37.37s/trial, best loss: -0.4838]
57
- 40%|โ–ˆโ–ˆโ–ˆโ–ˆ | 40/100 [31:40<46:04, 46.07s/trial, best loss: -0.4838]
58
- 41%|โ–ˆโ–ˆโ–ˆโ–ˆ | 41/100 [32:06<39:16, 39.94s/trial, best loss: -0.4838]
59
- 42%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 42/100 [32:32<34:30, 35.71s/trial, best loss: -0.4838]
60
- 43%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 43/100 [32:54<30:06, 31.69s/trial, best loss: -0.4838]
61
- 44%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 44/100 [33:30<30:43, 32.92s/trial, best loss: -0.4838]
62
- 45%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 45/100 [34:00<29:21, 32.02s/trial, best loss: -0.4838]
63
- 46%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 46/100 [34:59<36:12, 40.24s/trial, best loss: -0.4838]
64
- 47%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 47/100 [35:42<36:16, 41.07s/trial, best loss: -0.4838]
65
- 48%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 48/100 [36:56<44:04, 50.86s/trial, best loss: -0.4838]
66
- 49%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 49/100 [37:20<36:16, 42.67s/trial, best loss: -0.4838]
67
- 50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 50/100 [38:41<45:07, 54.15s/trial, best loss: -0.4838]
68
- 51%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 51/100 [39:30<43:10, 52.86s/trial, best loss: -0.4838]
69
- 52%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 52/100 [40:23<42:13, 52.79s/trial, best loss: -0.4838]
70
- 53%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 53/100 [41:21<42:28, 54.23s/trial, best loss: -0.4838]
71
- 54%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 54/100 [41:56<37:14, 48.57s/trial, best loss: -0.4838]
72
- 55%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 55/100 [42:27<32:24, 43.21s/trial, best loss: -0.4838]
73
- 56%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 56/100 [43:06<30:53, 42.12s/trial, best loss: -0.4838]
74
- 57%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 57/100 [43:27<25:38, 35.79s/trial, best loss: -0.4838]
75
- 58%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 58/100 [44:15<27:28, 39.25s/trial, best loss: -0.4838]
76
- 59%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 59/100 [44:54<26:54, 39.38s/trial, best loss: -0.4838]
77
- 60%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 60/100 [45:39<27:23, 41.09s/trial, best loss: -0.4838]
78
- 61%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 61/100 [46:33<29:11, 44.90s/trial, best loss: -0.4838]
79
- 62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 62/100 [47:06<26:07, 41.26s/trial, best loss: -0.4838]
80
- 63%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 63/100 [47:27<21:38, 35.09s/trial, best loss: -0.4838]
81
- 64%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 64/100 [48:11<22:40, 37.78s/trial, best loss: -0.4838]
82
- 65%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 65/100 [48:42<20:49, 35.71s/trial, best loss: -0.4838]
83
- 66%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 66/100 [49:36<23:23, 41.27s/trial, best loss: -0.4838]
84
- 67%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 67/100 [50:34<25:32, 46.43s/trial, best loss: -0.4838]
85
- 68%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 68/100 [51:19<24:26, 45.84s/trial, best loss: -0.4838]
86
- 69%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 69/100 [52:09<24:18, 47.04s/trial, best loss: -0.4838]
87
- 70%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 70/100 [52:47<22:09, 44.33s/trial, best loss: -0.4838]
88
- 71%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 71/100 [53:47<23:49, 49.28s/trial, best loss: -0.4861]
89
- 72%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 72/100 [54:34<22:35, 48.41s/trial, best loss: -0.4861]
90
- 73%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 73/100 [55:40<24:12, 53.81s/trial, best loss: -0.4861]
91
- 74%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 74/100 [56:24<22:02, 50.87s/trial, best loss: -0.4861]
92
- 75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 75/100 [57:19<21:38, 51.93s/trial, best loss: -0.4861]
93
- 76%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 76/100 [58:34<23:31, 58.83s/trial, best loss: -0.4861]
94
- 77%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 77/100 [59:31<22:22, 58.39s/trial, best loss: -0.4861]
95
- 78%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 78/100 [1:00:32<21:41, 59.16s/trial, best loss: -0.4861]
96
- 79%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 79/100 [1:01:33<20:56, 59.84s/trial, best loss: -0.4861]
97
- 80%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 80/100 [1:02:32<19:49, 59.48s/trial, best loss: -0.4861]
98
- 81%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 81/100 [1:03:29<18:35, 58.69s/trial, best loss: -0.4861]
99
- 82%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 82/100 [1:04:16<16:33, 55.21s/trial, best loss: -0.4861]
100
- 83%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 83/100 [1:05:07<15:18, 54.04s/trial, best loss: -0.4861]
101
- 84%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 84/100 [1:05:42<12:53, 48.33s/trial, best loss: -0.4861]
102
- 85%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 85/100 [1:06:22<11:24, 45.63s/trial, best loss: -0.4861]
103
- 86%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 86/100 [1:07:23<11:43, 50.26s/trial, best loss: -0.4861]
104
- 87%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 87/100 [1:07:51<09:27, 43.68s/trial, best loss: -0.4861]
105
- 88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 88/100 [1:08:33<08:38, 43.22s/trial, best loss: -0.4861]
106
- 89%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 89/100 [1:09:12<07:42, 42.07s/trial, best loss: -0.4861]
107
- 90%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 90/100 [1:10:43<09:26, 56.65s/trial, best loss: -0.4861]
108
- 91%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 91/100 [1:11:46<08:46, 58.50s/trial, best loss: -0.4861]
109
- 92%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 92/100 [1:12:41<07:39, 57.41s/trial, best loss: -0.4861]
110
- 93%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž| 93/100 [1:13:12<05:47, 49.68s/trial, best loss: -0.4861]
111
- 94%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 94/100 [1:14:05<05:03, 50.65s/trial, best loss: -0.4861]
112
- 95%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ| 95/100 [1:15:05<04:26, 53.38s/trial, best loss: -0.4861]
113
- 96%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ| 96/100 [1:15:37<03:07, 46.98s/trial, best loss: -0.4861]
114
- 97%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹| 97/100 [1:16:26<02:22, 47.59s/trial, best loss: -0.4861]
115
- 98%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š| 98/100 [1:17:10<01:32, 46.49s/trial, best loss: -0.4861]
116
- 99%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰| 99/100 [1:17:41<00:41, 41.78s/trial, best loss: -0.4861]
117
- 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 100/100 [1:18:46<00:00, 48.69s/trial, best loss: -0.4861]
118
- 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 100/100 [1:18:46<00:00, 47.26s/trial, best loss: -0.4861]
119
-
120
- ์ตœ์ ํ™” ์™„๋ฃŒ. ์ตœ์  ํŒŒ๋ผ๋ฏธํ„ฐ: {'colsample_bytree': 0.791441621112874, 'gamma': 0.42439975661558715, 'learning_rate': 0.011136150784699721, 'max_depth': 12.0, 'min_child_weight': 12.0, 'reg_alpha': 0.5297190743505086, 'reg_lambda': 0.8682538180888419, 'subsample': 0.736720141444502}
121
- ์ตœ์  CSI ์ ์ˆ˜: 0.4861 (loss: -0.4861)
122
-
123
- ์ตœ์ ํ™” ๊ณผ์ • ์š”์•ฝ:
124
- - ์ด ์‹œ๋„ ํšŸ์ˆ˜: 100
125
- - ์„ฑ๊ณตํ•œ ์‹œ๋„: 100
126
- - ์ตœ์ดˆ CSI: 0.4742
127
- - ์ตœ์ข… CSI: 0.4829
128
- - ์ตœ๊ณ  CSI: 0.4861
129
- - ์ตœ์ € CSI: 0.4146
130
- - ํ‰๊ท  CSI: 0.4732
131
-
132
- ์ตœ์ ํ™” Trials ๊ฐ์ฒด๊ฐ€ ../optimization_history/xgb_ctgan10000_busan_trials.pkl์— ์ €์žฅ๋˜์—ˆ์Šต๋‹ˆ๋‹ค.
133
- ์ตœ์ข… ๋ชจ๋ธ ํ•™์Šต ์‹œ์ž‘...
134
- Fold 1 ํ•™์Šต ์ค‘... (ํ•™์Šต ์—ฐ๋„: [2018, 2019], ๊ฒ€์ฆ ์—ฐ๋„: 2020)
135
- Fold 1 ๊ฒ€์ฆ CSI: 0.4306
136
- Fold 2 ํ•™์Šต ์ค‘... (ํ•™์Šต ์—ฐ๋„: [2018, 2020], ๊ฒ€์ฆ ์—ฐ๋„: 2019)
137
- Fold 2 ๊ฒ€์ฆ CSI: 0.5131
138
- Fold 3 ํ•™์Šต ์ค‘... (ํ•™์Šต ์—ฐ๋„: [2019, 2020], ๊ฒ€์ฆ ์—ฐ๋„: 2018)
139
- Fold 3 ๊ฒ€์ฆ CSI: 0.5145
140
- ๋ชจ๋ธ ์ €์žฅ ์ค‘...
141
- ๋ชจ๋ธ์ด ../save_model/xgb_optima/xgb_ctgan10000_busan.pkl์— ์ €์žฅ๋˜์—ˆ์Šต๋‹ˆ๋‹ค.
142
-
143
- โœ“ ์™„๋ฃŒ: xgb_ctgan10000/XGB_ctgan10000_busan.py (์†Œ์š” ์‹œ๊ฐ„: 4785์ดˆ)
144
-
145
- โš ๏ธ ๊ฒฝ๊ณ : xgb_ctgan10000/XGB_ctgan10000_daegu.py ํŒŒ์ผ์„ ์ฐพ์„ ์ˆ˜ ์—†์Šต๋‹ˆ๋‹ค. ๊ฑด๋„ˆ๋œ๋‹ˆ๋‹ค.
146
- โš ๏ธ ๊ฒฝ๊ณ : xgb_ctgan10000/XGB_ctgan10000_daejeon.py ํŒŒ์ผ์„ ์ฐพ์„ ์ˆ˜ ์—†์Šต๋‹ˆ๋‹ค. ๊ฑด๋„ˆ๋œ๋‹ˆ๋‹ค.
147
- โš ๏ธ ๊ฒฝ๊ณ : xgb_ctgan10000/XGB_ctgan10000_gwangju.py ํŒŒ์ผ์„ ์ฐพ์„ ์ˆ˜ ์—†์Šต๋‹ˆ๋‹ค. ๊ฑด๋„ˆ๋œ๋‹ˆ๋‹ค.
148
- โš ๏ธ ๊ฒฝ๊ณ : xgb_ctgan10000/XGB_ctgan10000_incheon.py ํŒŒ์ผ์„ ์ฐพ์„ ์ˆ˜ ์—†์Šต๋‹ˆ๋‹ค. ๊ฑด๋„ˆ๋œ๋‹ˆ๋‹ค.
149
- โš ๏ธ ๊ฒฝ๊ณ : xgb_ctgan10000/XGB_ctgan10000_seoul.py ํŒŒ์ผ์„ ์ฐพ์„ ์ˆ˜ ์—†์Šต๋‹ˆ๋‹ค. ๊ฑด๋„ˆ๋œ๋‹ˆ๋‹ค.
150
- ==========================================
151
- XGB CTGAN10000 ํŒŒ์ผ ์‹คํ–‰ ์™„๋ฃŒ
152
- ์ข…๋ฃŒ ์‹œ๊ฐ„: 2025-12-23 20:28:10
153
- ์ด ์†Œ์š” ์‹œ๊ฐ„: 1์‹œ๊ฐ„ 19๋ถ„ 45์ดˆ
154
- ์„ฑ๊ณต: 1๊ฐœ
155
- ์‹คํŒจ: 5๊ฐœ
156
- ==========================================
157
  0%| | 0/100 [00:00<?, ?trial/s, best loss=?]
158
  1%| | 1/100 [01:00<1:39:06, 60.06s/trial, best loss: -0.4522]
159
  2%|โ– | 2/100 [01:27<1:06:28, 40.70s/trial, best loss: -0.4709]
160
  3%|โ–Ž | 3/100 [02:00<1:00:22, 37.35s/trial, best loss: -0.4806]
161
  4%|โ– | 4/100 [02:36<58:57, 36.85s/trial, best loss: -0.4806]
162
  5%|โ–Œ | 5/100 [02:59<50:07, 31.66s/trial, best loss: -0.4822]
163
  6%|โ–Œ | 6/100 [03:46<57:59, 37.02s/trial, best loss: -0.4822]
164
  7%|โ–‹ | 7/100 [04:12<51:49, 33.43s/trial, best loss: -0.4822]
165
  8%|โ–Š | 8/100 [04:40<48:45, 31.80s/trial, best loss: -0.4822]
166
  9%|โ–‰ | 9/100 [05:37<1:00:09, 39.66s/trial, best loss: -0.4822]
167
  10%|โ–ˆ | 10/100 [06:13<57:38, 38.43s/trial, best loss: -0.4822]
168
  11%|โ–ˆ | 11/100 [06:34<49:07, 33.12s/trial, best loss: -0.4822]
169
  12%|โ–ˆโ– | 12/100 [07:20<54:22, 37.07s/trial, best loss: -0.4822]
170
  13%|โ–ˆโ–Ž | 13/100 [08:01<55:35, 38.34s/trial, best loss: -0.4822]
171
  14%|โ–ˆโ– | 14/100 [08:34<52:25, 36.57s/trial, best loss: -0.4822]
172
  15%|โ–ˆโ–Œ | 15/100 [09:03<48:30, 34.24s/trial, best loss: -0.4822]
173
  16%|โ–ˆโ–Œ | 16/100 [09:29<44:45, 31.97s/trial, best loss: -0.4822]
174
  17%|โ–ˆโ–‹ | 17/100 [10:29<55:53, 40.40s/trial, best loss: -0.4822]
175
  18%|โ–ˆโ–Š | 18/100 [10:46<45:13, 33.10s/trial, best loss: -0.4822]
176
  19%|โ–ˆโ–‰ | 19/100 [11:11<41:26, 30.70s/trial, best loss: -0.4822]
177
  20%|โ–ˆโ–ˆ | 20/100 [11:37<39:10, 29.38s/trial, best loss: -0.4822]
178
  21%|โ–ˆโ–ˆ | 21/100 [12:17<42:42, 32.43s/trial, best loss: -0.4822]
179
  22%|โ–ˆโ–ˆโ– | 22/100 [13:23<55:18, 42.55s/trial, best loss: -0.4822]
180
  23%|โ–ˆโ–ˆโ–Ž | 23/100 [13:58<51:48, 40.37s/trial, best loss: -0.4822]
181
  24%|โ–ˆโ–ˆโ– | 24/100 [14:29<47:44, 37.69s/trial, best loss: -0.4822]
182
  25%|โ–ˆโ–ˆโ–Œ | 25/100 [16:19<1:14:11, 59.35s/trial, best loss: -0.4822]
183
  26%|โ–ˆโ–ˆโ–Œ | 26/100 [16:57<1:05:04, 52.76s/trial, best loss: -0.4822]
184
  27%|โ–ˆโ–ˆโ–‹ | 27/100 [17:39<1:00:28, 49.70s/trial, best loss: -0.4822]
185
  28%|โ–ˆโ–ˆโ–Š | 28/100 [18:11<53:04, 44.23s/trial, best loss: -0.4822]
186
  29%|โ–ˆโ–ˆโ–‰ | 29/100 [18:34<44:58, 38.01s/trial, best loss: -0.4822]
187
  30%|โ–ˆโ–ˆโ–ˆ | 30/100 [19:28<49:57, 42.82s/trial, best loss: -0.4822]
188
  31%|โ–ˆโ–ˆโ–ˆ | 31/100 [20:07<47:46, 41.54s/trial, best loss: -0.4822]
189
  32%|โ–ˆโ–ˆโ–ˆโ– | 32/100 [20:43<45:24, 40.07s/trial, best loss: -0.4822]
190
  33%|โ–ˆโ–ˆโ–ˆโ–Ž | 33/100 [21:19<43:07, 38.62s/trial, best loss: -0.4822]
191
  34%|โ–ˆโ–ˆโ–ˆโ– | 34/100 [21:48<39:24, 35.83s/trial, best loss: -0.4822]
192
  35%|โ–ˆโ–ˆโ–ˆโ–Œ | 35/100 [22:31<41:08, 37.98s/trial, best loss: -0.4822]
193
  36%|โ–ˆโ–ˆโ–ˆโ–Œ | 36/100 [23:04<39:03, 36.62s/trial, best loss: -0.4822]
194
  37%|โ–ˆโ–ˆโ–ˆโ–‹ | 37/100 [23:23<32:46, 31.22s/trial, best loss: -0.4822]
195
  38%|โ–ˆโ–ˆโ–ˆโ–Š | 38/100 [24:18<39:43, 38.44s/trial, best loss: -0.4822]
196
  39%|โ–ˆโ–ˆโ–ˆโ–‰ | 39/100 [24:56<38:44, 38.10s/trial, best loss: -0.4822]
197
  40%|โ–ˆโ–ˆโ–ˆโ–ˆ | 40/100 [25:22<34:34, 34.57s/trial, best loss: -0.4822]
198
  41%|โ–ˆโ–ˆโ–ˆโ–ˆ | 41/100 [26:22<41:38, 42.35s/trial, best loss: -0.4822]
199
  42%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 42/100 [26:55<38:01, 39.34s/trial, best loss: -0.4822]
200
  43%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 43/100 [27:18<32:39, 34.38s/trial, best loss: -0.4822]
201
  44%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 44/100 [27:47<30:33, 32.74s/trial, best loss: -0.4822]
202
  45%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 45/100 [28:19<29:49, 32.54s/trial, best loss: -0.4822]
203
  46%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 46/100 [28:45<27:34, 30.64s/trial, best loss: -0.4822]
204
  47%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 47/100 [29:14<26:38, 30.15s/trial, best loss: -0.4822]
205
  48%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 48/100 [29:46<26:33, 30.65s/trial, best loss: -0.4822]
206
  49%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 49/100 [30:25<28:21, 33.36s/trial, best loss: -0.4822]
207
  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 50/100 [31:31<35:53, 43.06s/trial, best loss: -0.4822]
208
  51%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 51/100 [31:58<31:21, 38.40s/trial, best loss: -0.4822]
209
  52%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 52/100 [32:28<28:27, 35.58s/trial, best loss: -0.4822]
210
  53%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 53/100 [33:11<29:43, 37.96s/trial, best loss: -0.4822]
211
  54%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 54/100 [33:55<30:23, 39.63s/trial, best loss: -0.4822]
212
  55%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 55/100 [34:24<27:21, 36.48s/trial, best loss: -0.4822]
213
  56%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 56/100 [34:51<24:49, 33.84s/trial, best loss: -0.4822]
214
  57%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 57/100 [35:28<24:50, 34.66s/trial, best loss: -0.4822]
215
  58%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 58/100 [36:06<25:02, 35.78s/trial, best loss: -0.4822]
216
  59%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 59/100 [36:42<24:24, 35.72s/trial, best loss: -0.4822]
217
  60%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 60/100 [37:06<21:31, 32.29s/trial, best loss: -0.4822]
218
  61%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 61/100 [37:32<19:40, 30.28s/trial, best loss: -0.4822]
219
  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 62/100 [38:46<27:34, 43.54s/trial, best loss: -0.4822]
220
  63%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 63/100 [39:13<23:43, 38.47s/trial, best loss: -0.4822]
221
  64%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 64/100 [39:56<23:52, 39.79s/trial, best loss: -0.4822]
222
  65%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 65/100 [40:47<25:10, 43.16s/trial, best loss: -0.4822]
223
  66%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 66/100 [41:09<20:56, 36.97s/trial, best loss: -0.4822]
224
  67%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 67/100 [41:44<19:56, 36.27s/trial, best loss: -0.4822]
225
  68%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 68/100 [42:13<18:06, 33.96s/trial, best loss: -0.4822]
226
  69%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 69/100 [42:38<16:17, 31.53s/trial, best loss: -0.4822]
227
  70%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 70/100 [43:17<16:46, 33.55s/trial, best loss: -0.4822]
228
  71%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 71/100 [44:05<18:23, 38.06s/trial, best loss: -0.4822]
229
  72%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 72/100 [44:36<16:42, 35.80s/trial, best loss: -0.4822]
230
  73%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 73/100 [44:57<14:11, 31.55s/trial, best loss: -0.4822]
231
  74%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 74/100 [45:29<13:43, 31.66s/trial, best loss: -0.4822]
232
  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 75/100 [45:50<11:52, 28.50s/trial, best loss: -0.4822]
233
  76%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 76/100 [46:19<11:22, 28.43s/trial, best loss: -0.4822]
234
  77%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 77/100 [46:44<10:32, 27.51s/trial, best loss: -0.4822]
235
  78%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 78/100 [47:10<09:56, 27.11s/trial, best loss: -0.4822]
236
  79%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 79/100 [47:56<11:27, 32.75s/trial, best loss: -0.4822]
237
  80%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 80/100 [48:24<10:24, 31.23s/trial, best loss: -0.4822]
238
  81%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 81/100 [48:43<08:45, 27.68s/trial, best loss: -0.4822]
239
  82%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 82/100 [49:12<08:25, 28.09s/trial, best loss: -0.4822]
240
  83%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 83/100 [49:39<07:49, 27.62s/trial, best loss: -0.4822]
241
  84%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 84/100 [50:07<07:24, 27.78s/trial, best loss: -0.4822]
242
  85%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 85/100 [50:55<08:25, 33.72s/trial, best loss: -0.4822]
243
  86%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 86/100 [51:11<06:38, 28.47s/trial, best loss: -0.4845]
244
  87%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 87/100 [51:30<05:33, 25.68s/trial, best loss: -0.4845]
245
  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 88/100 [52:03<05:34, 27.85s/trial, best loss: -0.4845]
246
  89%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 89/100 [52:36<05:23, 29.37s/trial, best loss: -0.4845]
247
  90%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 90/100 [53:00<04:38, 27.88s/trial, best loss: -0.4845]
248
  91%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 91/100 [53:23<03:56, 26.31s/trial, best loss: -0.4845]
249
  92%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 92/100 [54:16<04:34, 34.36s/trial, best loss: -0.4845]
250
  93%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž| 93/100 [54:44<03:47, 32.57s/trial, best loss: -0.4845]
251
  94%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 94/100 [55:04<02:52, 28.71s/trial, best loss: -0.4845]
252
  95%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ| 95/100 [55:47<02:45, 33.04s/trial, best loss: -0.4845]
253
  96%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ| 96/100 [56:11<02:01, 30.30s/trial, best loss: -0.4845]
254
  97%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹| 97/100 [56:42<01:31, 30.51s/trial, best loss: -0.4845]
255
  98%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š| 98/100 [57:01<00:53, 26.91s/trial, best loss: -0.4845]
256
  99%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰| 99/100 [57:30<00:27, 27.60s/trial, best loss: -0.4881]
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
257
  0%| | 0/100 [00:00<?, ?trial/s, best loss=?]
258
  1%| | 1/100 [00:44<1:13:09, 44.34s/trial, best loss: -0.4037]
259
  2%|โ– | 2/100 [01:13<58:05, 35.57s/trial, best loss: -0.4037]
260
  3%|โ–Ž | 3/100 [01:31<44:34, 27.57s/trial, best loss: -0.4037]
261
  4%|โ– | 4/100 [02:03<46:37, 29.14s/trial, best loss: -0.427]
262
  5%|โ–Œ | 5/100 [02:28<43:56, 27.75s/trial, best loss: -0.427]
263
  6%|โ–Œ | 6/100 [03:09<50:15, 32.08s/trial, best loss: -0.427]
264
  7%|โ–‹ | 7/100 [03:47<52:46, 34.05s/trial, best loss: -0.427]
265
  8%|โ–Š | 8/100 [04:35<59:09, 38.58s/trial, best loss: -0.427]
266
  9%|โ–‰ | 9/100 [05:06<55:05, 36.32s/trial, best loss: -0.427]
267
  10%|โ–ˆ | 10/100 [05:26<46:43, 31.15s/trial, best loss: -0.427]
268
  11%|โ–ˆ | 11/100 [05:59<47:10, 31.80s/trial, best loss: -0.427]
269
  12%|โ–ˆโ– | 12/100 [06:38<49:41, 33.88s/trial, best loss: -0.427]
270
  13%|โ–ˆโ–Ž | 13/100 [07:14<49:58, 34.47s/trial, best loss: -0.427]
271
  14%|โ–ˆโ– | 14/100 [07:46<48:22, 33.75s/trial, best loss: -0.427]
272
  15%|โ–ˆโ–Œ | 15/100 [08:53<1:02:15, 43.95s/trial, best loss: -0.427]
273
  16%|โ–ˆโ–Œ | 16/100 [09:27<57:04, 40.77s/trial, best loss: -0.427]
274
  17%|โ–ˆโ–‹ | 17/100 [09:54<50:35, 36.57s/trial, best loss: -0.427]
275
  18%|โ–ˆโ–Š | 18/100 [10:31<50:22, 36.86s/trial, best loss: -0.427]
276
  19%|โ–ˆโ–‰ | 19/100 [11:01<46:58, 34.80s/trial, best loss: -0.427]
277
  20%|โ–ˆโ–ˆ | 20/100 [11:33<45:04, 33.81s/trial, best loss: -0.4356]
278
  21%|โ–ˆโ–ˆ | 21/100 [11:58<41:05, 31.21s/trial, best loss: -0.4356]
279
  22%|โ–ˆโ–ˆโ– | 22/100 [12:28<40:14, 30.96s/trial, best loss: -0.4356]
280
  23%|โ–ˆโ–ˆโ–Ž | 23/100 [12:59<39:36, 30.86s/trial, best loss: -0.4356]
281
  24%|โ–ˆโ–ˆโ– | 24/100 [13:22<36:20, 28.69s/trial, best loss: -0.4356]
282
  25%|โ–ˆโ–ˆโ–Œ | 25/100 [13:43<32:45, 26.20s/trial, best loss: -0.4356]
283
  26%|โ–ˆโ–ˆโ–Œ | 26/100 [14:31<40:32, 32.87s/trial, best loss: -0.4356]
284
  27%|โ–ˆโ–ˆโ–‹ | 27/100 [15:03<39:37, 32.57s/trial, best loss: -0.4356]
285
  28%|โ–ˆโ–ˆโ–Š | 28/100 [15:44<42:03, 35.05s/trial, best loss: -0.4356]
286
  29%|โ–ˆโ–ˆโ–‰ | 29/100 [16:06<36:44, 31.04s/trial, best loss: -0.4356]
287
  30%|โ–ˆโ–ˆโ–ˆ | 30/100 [16:31<34:04, 29.21s/trial, best loss: -0.4356]
288
  31%|โ–ˆโ–ˆโ–ˆ | 31/100 [17:21<40:48, 35.48s/trial, best loss: -0.4356]
289
  32%|โ–ˆโ–ˆโ–ˆโ– | 32/100 [17:53<38:59, 34.40s/trial, best loss: -0.4356]
290
  33%|โ–ˆโ–ˆโ–ˆโ–Ž | 33/100 [18:25<37:36, 33.68s/trial, best loss: -0.4356]
291
  34%|โ–ˆโ–ˆโ–ˆโ– | 34/100 [19:02<38:21, 34.87s/trial, best loss: -0.4356]
292
  35%|โ–ˆโ–ˆโ–ˆโ–Œ | 35/100 [19:46<40:41, 37.56s/trial, best loss: -0.4356]
293
  36%|โ–ˆโ–ˆโ–ˆโ–Œ | 36/100 [20:19<38:39, 36.24s/trial, best loss: -0.4356]
294
  37%|โ–ˆโ–ˆโ–ˆโ–‹ | 37/100 [20:58<38:45, 36.92s/trial, best loss: -0.4356]
295
  38%|โ–ˆโ–ˆโ–ˆโ–Š | 38/100 [21:35<38:17, 37.06s/trial, best loss: -0.4356]
296
  39%|โ–ˆโ–ˆโ–ˆโ–‰ | 39/100 [22:13<37:55, 37.30s/trial, best loss: -0.4356]
297
  40%|โ–ˆโ–ˆโ–ˆโ–ˆ | 40/100 [22:50<37:13, 37.22s/trial, best loss: -0.4356]
298
  41%|โ–ˆโ–ˆโ–ˆโ–ˆ | 41/100 [23:24<35:32, 36.15s/trial, best loss: -0.4356]
299
  42%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 42/100 [24:04<36:02, 37.29s/trial, best loss: -0.4356]
300
  43%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 43/100 [24:49<37:45, 39.75s/trial, best loss: -0.4356]
301
  44%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 44/100 [25:16<33:24, 35.80s/trial, best loss: -0.4356]
302
  45%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 45/100 [26:10<37:56, 41.39s/trial, best loss: -0.4356]
303
  46%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 46/100 [26:50<36:48, 40.90s/trial, best loss: -0.4356]
304
  47%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 47/100 [27:14<31:46, 35.97s/trial, best loss: -0.4356]
305
  48%|โ–ˆโ–ˆโ–ˆ๏ฟฝ๏ฟฝ๏ฟฝโ–Š | 48/100 [27:47<30:19, 35.00s/trial, best loss: -0.4356]
306
  49%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 49/100 [28:32<32:12, 37.89s/trial, best loss: -0.4356]
307
  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 50/100 [29:28<36:14, 43.50s/trial, best loss: -0.4356]
308
  51%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 51/100 [30:21<37:40, 46.14s/trial, best loss: -0.4356]
309
  52%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 52/100 [31:09<37:22, 46.71s/trial, best loss: -0.4356]
310
  53%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 53/100 [32:18<41:53, 53.48s/trial, best loss: -0.4356]
311
  54%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 54/100 [32:59<38:09, 49.77s/trial, best loss: -0.4356]
312
  55%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 55/100 [33:27<32:22, 43.16s/trial, best loss: -0.4356]
313
  56%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 56/100 [33:57<28:47, 39.26s/trial, best loss: -0.4356]
314
  57%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 57/100 [34:23<25:14, 35.22s/trial, best loss: -0.4356]
315
  58%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 58/100 [34:48<22:39, 32.38s/trial, best loss: -0.4356]
316
  59%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 59/100 [35:24<22:48, 33.38s/trial, best loss: -0.4356]
317
  60%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 60/100 [36:06<23:54, 35.87s/trial, best loss: -0.4356]
318
  61%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 61/100 [36:30<20:57, 32.23s/trial, best loss: -0.4356]
319
  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 62/100 [37:49<29:19, 46.31s/trial, best loss: -0.4356]
320
  63%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 63/100 [38:30<27:42, 44.93s/trial, best loss: -0.4356]
321
  64%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 64/100 [39:13<26:27, 44.09s/trial, best loss: -0.4356]
322
  65%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 65/100 [40:08<27:38, 47.39s/trial, best loss: -0.4356]
323
  66%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 66/100 [40:29<22:22, 39.48s/trial, best loss: -0.4356]
324
  67%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 67/100 [40:47<18:14, 33.17s/trial, best loss: -0.4356]
325
  68%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 68/100 [41:12<16:25, 30.80s/trial, best loss: -0.4356]
326
  69%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 69/100 [41:34<14:30, 28.09s/trial, best loss: -0.4356]
327
  70%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 70/100 [41:55<12:53, 25.80s/trial, best loss: -0.4356]
328
  71%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 71/100 [42:33<14:15, 29.51s/trial, best loss: -0.4356]
329
  72%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 72/100 [43:08<14:35, 31.26s/trial, best loss: -0.4356]
330
  73%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 73/100 [43:38<13:51, 30.79s/trial, best loss: -0.4356]
331
  74%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 74/100 [44:06<12:57, 29.92s/trial, best loss: -0.4356]
332
  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 75/100 [44:40<13:04, 31.37s/trial, best loss: -0.4356]
333
  76%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 76/100 [45:08<12:05, 30.22s/trial, best loss: -0.4356]
334
  77%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 77/100 [45:38<11:33, 30.17s/trial, best loss: -0.4392]
335
  78%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 78/100 [46:12<11:27, 31.26s/trial, best loss: -0.4392]
336
  79%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 79/100 [46:52<11:55, 34.05s/trial, best loss: -0.4392]
337
  80%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 80/100 [47:46<13:18, 39.93s/trial, best loss: -0.4392]
338
  81%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 81/100 [48:28<12:49, 40.49s/trial, best loss: -0.4392]
339
  82%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 82/100 [49:20<13:11, 43.98s/trial, best loss: -0.4392]
340
  83%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 83/100 [49:44<10:44, 37.90s/trial, best loss: -0.4392]
341
  84%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 84/100 [50:14<09:32, 35.78s/trial, best loss: -0.4392]
342
  85%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 85/100 [50:59<09:38, 38.55s/trial, best loss: -0.4392]
343
  86%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 86/100 [51:33<08:39, 37.09s/trial, best loss: -0.4392]
344
  87%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 87/100 [51:53<06:53, 31.80s/trial, best loss: -0.4392]
345
  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 88/100 [52:14<05:45, 28.78s/trial, best loss: -0.4392]
346
  89%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 89/100 [52:47<05:28, 29.87s/trial, best loss: -0.4392]
347
  90%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 90/100 [53:16<04:56, 29.61s/trial, best loss: -0.4392]
348
  91%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 91/100 [53:43<04:21, 29.03s/trial, best loss: -0.4392]
349
  92%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 92/100 [54:14<03:54, 29.37s/trial, best loss: -0.4392]
350
  93%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž| 93/100 [54:35<03:08, 26.99s/trial, best loss: -0.4392]
351
  94%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 94/100 [54:59<02:36, 26.00s/trial, best loss: -0.4392]
352
  95%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ| 95/100 [55:37<02:28, 29.75s/trial, best loss: -0.4392]
353
  96%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ| 96/100 [55:55<01:45, 26.28s/trial, best loss: -0.4392]
354
  97%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹| 97/100 [56:31<01:27, 29.00s/trial, best loss: -0.4392]
355
  98%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š| 98/100 [56:54<00:54, 27.17s/trial, best loss: -0.4392]
356
  99%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰| 99/100 [57:34<00:31, 31.01s/trial, best loss: -0.4392]
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
357
  0%| | 0/100 [00:00<?, ?trial/s, best loss=?]
358
  1%| | 1/100 [00:37<1:02:28, 37.86s/trial, best loss: -0.4839]
359
  2%|โ– | 2/100 [01:13<59:40, 36.53s/trial, best loss: -0.4839]
360
  3%|โ–Ž | 3/100 [01:51<1:00:22, 37.34s/trial, best loss: -0.4865]
361
  4%|โ– | 4/100 [02:59<1:19:11, 49.49s/trial, best loss: -0.4865]
362
  5%|โ–Œ | 5/100 [04:05<1:27:35, 55.32s/trial, best loss: -0.4953]
363
  6%|โ–Œ | 6/100 [04:39<1:15:30, 48.19s/trial, best loss: -0.4953]
364
  7%|โ–‹ | 7/100 [05:08<1:04:51, 41.84s/trial, best loss: -0.4953]
365
  8%|โ–Š | 8/100 [05:51<1:04:45, 42.23s/trial, best loss: -0.4953]
366
  9%|โ–‰ | 9/100 [06:43<1:08:41, 45.30s/trial, best loss: -0.4953]
367
  10%|โ–ˆ | 10/100 [07:11<1:00:00, 40.00s/trial, best loss: -0.4953]
368
  11%|โ–ˆ | 11/100 [07:50<58:33, 39.47s/trial, best loss: -0.4953]
369
  12%|โ–ˆโ– | 12/100 [08:40<1:02:40, 42.74s/trial, best loss: -0.502]
370
  13%|โ–ˆโ–Ž | 13/100 [09:11<56:49, 39.19s/trial, best loss: -0.502]
371
  14%|โ–ˆโ– | 14/100 [10:06<1:03:07, 44.04s/trial, best loss: -0.502]
372
  15%|โ–ˆโ–Œ | 15/100 [10:59<1:06:00, 46.60s/trial, best loss: -0.502]
373
  16%|โ–ˆโ–Œ | 16/100 [11:49<1:06:55, 47.80s/trial, best loss: -0.502]
374
  17%|โ–ˆโ–‹ | 17/100 [13:07<1:18:45, 56.93s/trial, best loss: -0.502]
375
  18%|โ–ˆโ–Š | 18/100 [13:24<1:01:13, 44.79s/trial, best loss: -0.502]
376
  19%|โ–ˆโ–‰ | 19/100 [13:55<54:42, 40.53s/trial, best loss: -0.502]
377
  20%|โ–ˆโ–ˆ | 20/100 [14:36<54:26, 40.83s/trial, best loss: -0.502]
378
  21%|โ–ˆโ–ˆ | 21/100 [15:25<57:02, 43.32s/trial, best loss: -0.502]
379
  22%|โ–ˆโ–ˆโ– | 22/100 [15:51<49:20, 37.95s/trial, best loss: -0.502]
380
  23%|โ–ˆโ–ˆโ–Ž | 23/100 [16:26<47:50, 37.28s/trial, best loss: -0.502]
381
  24%|โ–ˆโ–ˆโ– | 24/100 [16:53<43:12, 34.11s/trial, best loss: -0.502]
382
  25%|โ–ˆโ–ˆโ–Œ | 25/100 [17:17<38:47, 31.04s/trial, best loss: -0.502]
383
  26%|โ–ˆโ–ˆโ–Œ | 26/100 [17:53<39:57, 32.41s/trial, best loss: -0.502]
384
  27%|โ–ˆโ–ˆโ–‹ | 27/100 [18:24<39:06, 32.14s/trial, best loss: -0.502]
385
  28%|โ–ˆโ–ˆโ–Š | 28/100 [19:03<40:56, 34.12s/trial, best loss: -0.502]
386
  29%|โ–ˆโ–ˆโ–‰ | 29/100 [19:45<43:05, 36.42s/trial, best loss: -0.5029]
387
  30%|โ–ˆโ–ˆโ–ˆ | 30/100 [20:21<42:37, 36.54s/trial, best loss: -0.5029]
388
  31%|โ–ˆโ–ˆโ–ˆ | 31/100 [20:55<40:57, 35.62s/trial, best loss: -0.5029]
389
  32%|โ–ˆโ–ˆโ–ˆโ– | 32/100 [21:32<40:42, 35.92s/trial, best loss: -0.5029]
390
  33%|โ–ˆโ–ˆโ–ˆโ–Ž | 33/100 [22:06<39:42, 35.55s/trial, best loss: -0.5029]
391
  34%|โ–ˆโ–ˆโ–ˆโ– | 34/100 [22:48<41:01, 37.30s/trial, best loss: -0.5029]
392
  35%|โ–ˆโ–ˆโ–ˆโ–Œ | 35/100 [23:25<40:19, 37.23s/trial, best loss: -0.5029]
393
  36%|โ–ˆโ–ˆโ–ˆโ–Œ | 36/100 [24:00<38:58, 36.54s/trial, best loss: -0.5029]
394
  37%|โ–ˆโ–ˆโ–ˆโ–‹ | 37/100 [24:24<34:28, 32.83s/trial, best loss: -0.5029]
395
  38%|โ–ˆโ–ˆโ–ˆโ–Š | 38/100 [24:57<34:06, 33.01s/trial, best loss: -0.5029]
396
  39%|โ–ˆโ–ˆโ–ˆโ–‰ | 39/100 [25:44<37:50, 37.22s/trial, best loss: -0.5029]
397
  40%|โ–ˆโ–ˆโ–ˆโ–ˆ | 40/100 [26:30<39:40, 39.68s/trial, best loss: -0.5029]
398
  41%|โ–ˆโ–ˆโ–ˆโ–ˆ | 41/100 [27:20<42:07, 42.84s/trial, best loss: -0.5029]
399
  42%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 42/100 [27:51<38:06, 39.41s/trial, best loss: -0.5029]
400
  43%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 43/100 [28:15<33:02, 34.79s/trial, best loss: -0.5029]
401
  44%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 44/100 [29:30<43:38, 46.75s/trial, best loss: -0.5029]
402
  45%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 45/100 [30:15<42:20, 46.19s/trial, best loss: -0.5029]
403
  46%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 46/100 [30:53<39:26, 43.82s/trial, best loss: -0.5029]
404
  47%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 47/100 [31:15<32:57, 37.32s/trial, best loss: -0.5029]
405
  48%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 48/100 [31:43<29:44, 34.32s/trial, best loss: -0.5029]
406
  49%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 49/100 [32:11<27:32, 32.40s/trial, best loss: -0.5029]
407
  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 50/100 [32:38<25:52, 31.05s/trial, best loss: -0.5029]
408
  51%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 51/100 [33:21<28:12, 34.55s/trial, best loss: -0.5029]
409
  52%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 52/100 [33:56<27:48, 34.77s/trial, best loss: -0.5029]
410
  53%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 53/100 [34:35<28:10, 35.98s/trial, best loss: -0.5029]
411
  54%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 54/100 [35:06<26:20, 34.36s/trial, best loss: -0.5029]
412
  55%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 55/100 [35:38<25:22, 33.84s/trial, best loss: -0.5029]
413
  56%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 56/100 [36:30<28:49, 39.30s/trial, best loss: -0.5029]
414
  57%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 57/100 [37:21<30:29, 42.55s/trial, best loss: -0.5029]
415
  58%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 58/100 [38:01<29:24, 42.00s/trial, best loss: -0.5029]
416
  59%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 59/100 [38:39<27:43, 40.57s/trial, best loss: -0.5029]
417
  60%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 60/100 [39:17<26:36, 39.92s/trial, best loss: -0.5029]
418
  61%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 61/100 [40:33<33:02, 50.83s/trial, best loss: -0.5029]
419
  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 62/100 [41:01<27:54, 44.05s/trial, best loss: -0.5029]
420
  63%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 63/100 [41:30<24:15, 39.33s/trial, best loss: -0.5029]
421
  64%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 64/100 [42:06<22:58, 38.29s/trial, best loss: -0.5029]
422
  65%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 65/100 [42:37<21:10, 36.30s/trial, best loss: -0.5029]
423
  66%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 66/100 [43:07<19:29, 34.39s/trial, best loss: -0.5029]
424
  67%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 67/100 [43:41<18:52, 34.31s/trial, best loss: -0.5029]
425
  68%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 68/100 [44:11<17:29, 32.80s/trial, best loss: -0.5029]
426
  69%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 69/100 [44:39<16:10, 31.32s/trial, best loss: -0.5029]
427
  70%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 70/100 [45:18<16:51, 33.72s/trial, best loss: -0.5029]
428
  71%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 71/100 [46:03<17:59, 37.22s/trial, best loss: -0.5029]
429
  72%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 72/100 [46:37<16:54, 36.22s/trial, best loss: -0.5029]
430
  73%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 73/100 [47:05<15:07, 33.61s/trial, best loss: -0.5029]
431
  74%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 74/100 [47:28<13:13, 30.51s/trial, best loss: -0.5029]
432
  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 75/100 [48:09<14:03, 33.75s/trial, best loss: -0.5029]
433
  76%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 76/100 [48:34<12:28, 31.19s/trial, best loss: -0.5029]
434
  77%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 77/100 [49:12<12:40, 33.05s/trial, best loss: -0.5029]
435
  78%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 78/100 [49:46<12:17, 33.50s/trial, best loss: -0.5029]
436
  79%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 79/100 [50:25<12:18, 35.15s/trial, best loss: -0.5029]
437
  80%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 80/100 [51:02<11:49, 35.46s/trial, best loss: -0.5029]
438
  81%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 81/100 [52:07<14:07, 44.61s/trial, best loss: -0.5029]
439
  82%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 82/100 [52:39<12:13, 40.76s/trial, best loss: -0.5029]
440
  83%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 83/100 [53:41<13:21, 47.14s/trial, best loss: -0.5029]
441
  84%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 84/100 [54:31<12:47, 47.94s/trial, best loss: -0.5029]
442
  85%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 85/100 [54:54<10:06, 40.42s/trial, best loss: -0.5029]
443
  86%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 86/100 [55:25<08:46, 37.60s/trial, best loss: -0.5029]
444
  87%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 87/100 [55:54<07:35, 35.01s/trial, best loss: -0.5029]
445
  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 88/100 [56:45<07:56, 39.74s/trial, best loss: -0.5029]
446
  89%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 89/100 [57:25<07:18, 39.87s/trial, best loss: -0.5029]
447
  90%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 90/100 [58:02<06:31, 39.12s/trial, best loss: -0.5029]
448
  91%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 91/100 [58:38<05:42, 38.08s/trial, best loss: -0.5029]
449
  92%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 92/100 [59:05<04:39, 34.90s/trial, best loss: -0.5029]
450
  93%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž| 93/100 [1:00:12<05:10, 44.39s/trial, best loss: -0.5029]
451
  94%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 94/100 [1:00:53<04:19, 43.29s/trial, best loss: -0.5029]
452
  95%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ| 95/100 [1:01:48<03:54, 46.95s/trial, best loss: -0.5029]
453
  96%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ| 96/100 [1:02:42<03:16, 49.08s/trial, best loss: -0.5029]
454
  97%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹| 97/100 [1:03:52<02:46, 55.36s/trial, best loss: -0.5029]
455
  98%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š| 98/100 [1:04:30<01:39, 49.96s/trial, best loss: -0.5029]
456
  99%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰| 99/100 [1:05:12<00:47, 47.59s/trial, best loss: -0.5029]
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
457
  0%| | 0/100 [00:00<?, ?trial/s, best loss=?]
458
  1%| | 1/100 [00:25<41:41, 25.27s/trial, best loss: -0.4941]
459
  2%|โ– | 2/100 [01:28<1:17:46, 47.61s/trial, best loss: -0.4941]
460
  3%|โ–Ž | 3/100 [02:09<1:11:52, 44.46s/trial, best loss: -0.4941]
461
  4%|โ– | 4/100 [03:21<1:28:25, 55.27s/trial, best loss: -0.4941]
462
  5%|โ–Œ | 5/100 [04:15<1:26:54, 54.89s/trial, best loss: -0.4941]
463
  6%|โ–Œ | 6/100 [04:47<1:14:05, 47.29s/trial, best loss: -0.4941]
464
  7%|โ–‹ | 7/100 [05:30<1:11:03, 45.85s/trial, best loss: -0.4941]
465
  8%|โ–Š | 8/100 [06:17<1:10:33, 46.01s/trial, best loss: -0.4941]
466
  9%|โ–‰ | 9/100 [06:38<58:16, 38.42s/trial, best loss: -0.4941]
467
  10%|โ–ˆ | 10/100 [07:21<59:33, 39.70s/trial, best loss: -0.4941]
468
  11%|โ–ˆ | 11/100 [08:11<1:03:31, 42.82s/trial, best loss: -0.4941]
469
  12%|โ–ˆโ– | 12/100 [08:40<56:37, 38.61s/trial, best loss: -0.4941]
470
  13%|โ–ˆโ–Ž | 13/100 [09:29<1:00:31, 41.74s/trial, best loss: -0.4941]
471
  14%|โ–ˆโ– | 14/100 [09:52<51:46, 36.12s/trial, best loss: -0.4941]
472
  15%|โ–ˆโ–Œ | 15/100 [10:31<52:22, 36.96s/trial, best loss: -0.4941]
473
  16%|โ–ˆโ–Œ | 16/100 [11:05<50:37, 36.16s/trial, best loss: -0.4941]
474
  17%|โ–ˆโ–‹ | 17/100 [12:46<1:16:56, 55.62s/trial, best loss: -0.4941]
475
  18%|โ–ˆโ–Š | 18/100 [13:14<1:04:51, 47.46s/trial, best loss: -0.4941]
476
  19%|โ–ˆโ–‰ | 19/100 [13:50<59:23, 44.00s/trial, best loss: -0.4941]
477
  20%|โ–ˆโ–ˆ | 20/100 [14:43<1:02:07, 46.59s/trial, best loss: -0.4941]
478
  21%|โ–ˆโ–ˆ | 21/100 [15:08<52:40, 40.00s/trial, best loss: -0.4941]
479
  22%|โ–ˆโ–ˆโ– | 22/100 [15:46<51:25, 39.56s/trial, best loss: -0.4941]
480
  23%|โ–ˆโ–ˆโ–Ž | 23/100 [16:16<47:05, 36.70s/trial, best loss: -0.4975]
481
  24%|โ–ˆโ–ˆโ– | 24/100 [16:56<47:48, 37.75s/trial, best loss: -0.4975]
482
  25%|โ–ˆโ–ˆโ–Œ | 25/100 [17:26<44:15, 35.41s/trial, best loss: -0.4975]
483
  26%|โ–ˆโ–ˆโ–Œ | 26/100 [17:53<40:27, 32.81s/trial, best loss: -0.4975]
484
  27%|โ–ˆโ–ˆโ–‹ | 27/100 [18:16<36:21, 29.89s/trial, best loss: -0.4975]
485
  28%|โ–ˆโ–ˆโ–Š | 28/100 [18:58<40:12, 33.50s/trial, best loss: -0.4975]
486
  29%|โ–ˆโ–ˆโ–‰ | 29/100 [19:58<48:53, 41.32s/trial, best loss: -0.4975]
487
  30%|โ–ˆโ–ˆโ–ˆ | 30/100 [20:29<44:54, 38.49s/trial, best loss: -0.4975]
488
  31%|โ–ˆโ–ˆโ–ˆ | 31/100 [21:09<44:27, 38.66s/trial, best loss: -0.4975]
489
  32%|โ–ˆโ–ˆโ–ˆโ– | 32/100 [21:48<44:08, 38.94s/trial, best loss: -0.4991]
490
  33%|โ–ˆโ–ˆโ–ˆโ–Ž | 33/100 [22:18<40:26, 36.21s/trial, best loss: -0.4991]
491
  34%|โ–ˆโ–ˆโ–ˆโ– | 34/100 [22:47<37:32, 34.13s/trial, best loss: -0.4991]
492
  35%|โ–ˆโ–ˆโ–ˆโ–Œ | 35/100 [23:14<34:32, 31.88s/trial, best loss: -0.4991]
493
  36%|โ–ˆโ–ˆโ–ˆโ–Œ | 36/100 [23:39<31:40, 29.70s/trial, best loss: -0.4991]
494
  37%|โ–ˆโ–ˆโ–ˆโ–‹ | 37/100 [24:20<34:47, 33.13s/trial, best loss: -0.4991]
495
  38%|โ–ˆโ–ˆโ–ˆโ–Š | 38/100 [24:54<34:35, 33.47s/trial, best loss: -0.4991]
496
  39%|โ–ˆโ–ˆโ–ˆโ–‰ | 39/100 [25:26<33:35, 33.05s/trial, best loss: -0.4991]
497
  40%|โ–ˆโ–ˆโ–ˆโ–ˆ | 40/100 [26:03<34:11, 34.19s/trial, best loss: -0.4991]
498
  41%|โ–ˆโ–ˆโ–ˆโ–ˆ | 41/100 [26:45<35:55, 36.54s/trial, best loss: -0.4991]
499
  42%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 42/100 [27:12<32:38, 33.76s/trial, best loss: -0.4991]
500
  43%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 43/100 [28:18<41:16, 43.45s/trial, best loss: -0.4991]
501
  44%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 44/100 [28:46<36:11, 38.77s/trial, best loss: -0.4991]
502
  45%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 45/100 [29:38<39:08, 42.71s/trial, best loss: -0.4991]
503
  46%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 46/100 [30:24<39:16, 43.64s/trial, best loss: -0.4991]
504
  47%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 47/100 [30:48<33:24, 37.83s/trial, best loss: -0.4991]
505
  48%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 48/100 [31:18<30:43, 35.45s/trial, best loss: -0.4991]
506
  49%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 49/100 [32:28<38:51, 45.71s/trial, best loss: -0.4991]
507
  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 50/100 [32:56<33:50, 40.60s/trial, best loss: -0.4991]
508
  51%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 51/100 [33:45<35:11, 43.09s/trial, best loss: -0.4991]
509
  52%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 52/100 [34:45<38:28, 48.10s/trial, best loss: -0.4991]
510
  53%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 53/100 [35:06<31:25, 40.11s/trial, best loss: -0.4991]
511
  54%|โ–ˆ๏ฟฝ๏ฟฝ๏ฟฝโ–ˆโ–ˆโ–ˆโ– | 54/100 [35:50<31:31, 41.13s/trial, best loss: -0.4991]
512
  55%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 55/100 [36:31<30:51, 41.15s/trial, best loss: -0.4991]
513
  56%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 56/100 [36:51<25:32, 34.83s/trial, best loss: -0.4991]
514
  57%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 57/100 [37:30<25:48, 36.00s/trial, best loss: -0.4991]
515
  58%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 58/100 [38:18<27:43, 39.60s/trial, best loss: -0.4991]
516
  59%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 59/100 [38:42<23:51, 34.91s/trial, best loss: -0.4991]
517
  60%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 60/100 [39:10<21:51, 32.80s/trial, best loss: -0.4991]
518
  61%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 61/100 [40:10<26:39, 41.02s/trial, best loss: -0.4991]
519
  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 62/100 [40:54<26:28, 41.80s/trial, best loss: -0.4991]
520
  63%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 63/100 [41:14<21:46, 35.32s/trial, best loss: -0.4991]
521
  64%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 64/100 [41:41<19:48, 33.02s/trial, best loss: -0.4991]
522
  65%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 65/100 [42:14<19:07, 32.80s/trial, best loss: -0.4991]
523
  66%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 66/100 [42:50<19:10, 33.83s/trial, best loss: -0.4991]
524
  67%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 67/100 [43:20<18:03, 32.84s/trial, best loss: -0.4991]
525
  68%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 68/100 [43:49<16:47, 31.49s/trial, best loss: -0.4991]
526
  69%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 69/100 [44:17<15:43, 30.42s/trial, best loss: -0.4991]
527
  70%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 70/100 [44:43<14:36, 29.21s/trial, best loss: -0.4991]
528
  71%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 71/100 [45:10<13:43, 28.40s/trial, best loss: -0.4991]
529
  72%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 72/100 [45:32<12:25, 26.64s/trial, best loss: -0.4991]
530
  73%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 73/100 [46:05<12:50, 28.55s/trial, best loss: -0.4991]
531
  74%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 74/100 [46:38<12:53, 29.74s/trial, best loss: -0.4991]
532
  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 75/100 [47:08<12:28, 29.93s/trial, best loss: -0.4991]
533
  76%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 76/100 [47:36<11:40, 29.19s/trial, best loss: -0.4999]
534
  77%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 77/100 [47:58<10:25, 27.18s/trial, best loss: -0.4999]
535
  78%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 78/100 [48:32<10:40, 29.13s/trial, best loss: -0.4999]
536
  79%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 79/100 [48:55<09:34, 27.34s/trial, best loss: -0.4999]
537
  80%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 80/100 [49:24<09:18, 27.92s/trial, best loss: -0.4999]
538
  81%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 81/100 [49:43<07:58, 25.18s/trial, best loss: -0.4999]
539
  82%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 82/100 [50:03<07:03, 23.55s/trial, best loss: -0.4999]
540
  83%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 83/100 [50:25<06:35, 23.24s/trial, best loss: -0.4999]
541
  84%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 84/100 [50:55<06:41, 25.11s/trial, best loss: -0.4999]
542
  85%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 85/100 [51:15<05:57, 23.82s/trial, best loss: -0.4999]
543
  86%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 86/100 [52:06<07:24, 31.75s/trial, best loss: -0.4999]
544
  87%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 87/100 [52:29<06:20, 29.29s/trial, best loss: -0.4999]
545
  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 88/100 [52:56<05:42, 28.56s/trial, best loss: -0.4999]
546
  89%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 89/100 [53:27<05:23, 29.39s/trial, best loss: -0.4999]
547
  90%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 90/100 [53:55<04:47, 28.75s/trial, best loss: -0.4999]
548
  91%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 91/100 [54:28<04:30, 30.04s/trial, best loss: -0.4999]
549
  92%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 92/100 [55:22<04:58, 37.30s/trial, best loss: -0.4999]
550
  93%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž| 93/100 [56:11<04:45, 40.74s/trial, best loss: -0.4999]
551
  94%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 94/100 [56:39<03:41, 36.98s/trial, best loss: -0.4999]
552
  95%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ| 95/100 [57:03<02:44, 32.98s/trial, best loss: -0.4999]
553
  96%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ| 96/100 [57:33<02:08, 32.24s/trial, best loss: -0.4999]
554
  97%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹| 97/100 [57:51<01:23, 27.84s/trial, best loss: -0.4999]
555
  98%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š| 98/100 [58:14<00:52, 26.39s/trial, best loss: -0.4999]
556
  99%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰| 99/100 [58:35<00:24, 24.80s/trial, best loss: -0.4999]
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
557
  0%| | 0/100 [00:00<?, ?trial/s, best loss=?]
558
  1%| | 1/100 [00:20<34:14, 20.76s/trial, best loss: -0.5632]
559
  2%|โ– | 2/100 [00:37<30:03, 18.41s/trial, best loss: -0.5632]
560
  3%|โ–Ž | 3/100 [01:03<35:30, 21.96s/trial, best loss: -0.5632]
561
  4%|โ– | 4/100 [01:29<37:51, 23.66s/trial, best loss: -0.5632]
562
  5%|โ–Œ | 5/100 [01:52<36:56, 23.33s/trial, best loss: -0.5632]
563
  6%|โ–Œ | 6/100 [02:47<53:33, 34.18s/trial, best loss: -0.5632]
564
  7%|โ–‹ | 7/100 [03:23<53:40, 34.62s/trial, best loss: -0.5633]
565
  8%|โ–Š | 8/100 [04:16<1:01:57, 40.41s/trial, best loss: -0.5633]
566
  9%|โ–‰ | 9/100 [04:34<50:47, 33.49s/trial, best loss: -0.5633]
567
  10%|โ–ˆ | 10/100 [05:16<54:10, 36.11s/trial, best loss: -0.5633]
568
  11%|โ–ˆ | 11/100 [05:43<49:17, 33.23s/trial, best loss: -0.5633]
569
  12%|โ–ˆโ– | 12/100 [06:37<57:55, 39.49s/trial, best loss: -0.5633]
570
  13%|โ–ˆโ–Ž | 13/100 [07:17<57:38, 39.75s/trial, best loss: -0.5633]
571
  14%|โ–ˆโ– | 14/100 [07:53<55:28, 38.71s/trial, best loss: -0.5633]
572
  15%|โ–ˆโ–Œ | 15/100 [08:29<53:39, 37.87s/trial, best loss: -0.5633]
573
  16%|โ–ˆโ–Œ | 16/100 [08:55<47:53, 34.21s/trial, best loss: -0.5633]
574
  17%|โ–ˆโ–‹ | 17/100 [09:19<42:58, 31.06s/trial, best loss: -0.5633]
575
  18%|โ–ˆโ–Š | 18/100 [10:25<56:45, 41.54s/trial, best loss: -0.5633]
576
  19%|โ–ˆโ–‰ | 19/100 [10:47<48:32, 35.95s/trial, best loss: -0.5633]
577
  20%|โ–ˆโ–ˆ | 20/100 [11:12<43:15, 32.45s/trial, best loss: -0.5633]
578
  21%|โ–ˆโ–ˆ | 21/100 [11:35<39:02, 29.65s/trial, best loss: -0.5633]
579
  22%|โ–ˆโ–ˆโ– | 22/100 [11:55<34:38, 26.64s/trial, best loss: -0.5633]
580
  23%|โ–ˆโ–ˆโ–Ž | 23/100 [12:16<32:13, 25.11s/trial, best loss: -0.5633]
581
  24%|โ–ˆโ–ˆโ– | 24/100 [12:47<33:55, 26.78s/trial, best loss: -0.5633]
582
  25%|โ–ˆโ–ˆโ–Œ | 25/100 [13:49<46:58, 37.58s/trial, best loss: -0.5633]
583
  26%|โ–ˆโ–ˆโ–Œ | 26/100 [14:16<42:20, 34.33s/trial, best loss: -0.5633]
584
  27%|โ–ˆโ–ˆโ–‹ | 27/100 [14:45<39:33, 32.51s/trial, best loss: -0.5633]
585
  28%|โ–ˆโ–ˆโ–Š | 28/100 [15:10<36:39, 30.55s/trial, best loss: -0.5633]
586
  29%|โ–ˆโ–ˆโ–‰ | 29/100 [15:42<36:29, 30.84s/trial, best loss: -0.5633]
587
  30%|โ–ˆโ–ˆโ–ˆ | 30/100 [16:04<32:59, 28.27s/trial, best loss: -0.5633]
588
  31%|โ–ˆโ–ˆโ–ˆ | 31/100 [16:38<34:23, 29.91s/trial, best loss: -0.5645]
589
  32%|โ–ˆโ–ˆโ–ˆโ– | 32/100 [17:22<38:46, 34.21s/trial, best loss: -0.5706]
590
  33%|โ–ˆโ–ˆโ–ˆโ–Ž | 33/100 [18:15<44:24, 39.76s/trial, best loss: -0.5706]
591
  34%|โ–ˆโ–ˆโ–ˆโ– | 34/100 [19:01<45:49, 41.65s/trial, best loss: -0.5706]
592
  35%|โ–ˆโ–ˆโ–ˆโ–Œ | 35/100 [19:35<42:44, 39.45s/trial, best loss: -0.5714]
593
  36%|โ–ˆโ–ˆโ–ˆโ–Œ | 36/100 [20:19<43:18, 40.60s/trial, best loss: -0.5714]
594
  37%|โ–ˆโ–ˆโ–ˆโ–‹ | 37/100 [20:54<40:58, 39.02s/trial, best loss: -0.5728]
595
  38%|โ–ˆโ–ˆโ–ˆโ–Š | 38/100 [21:20<36:23, 35.21s/trial, best loss: -0.5728]
596
  39%|โ–ˆโ–ˆโ–ˆโ–‰ | 39/100 [22:31<46:32, 45.77s/trial, best loss: -0.5728]
597
  40%|โ–ˆโ–ˆโ–ˆโ–ˆ | 40/100 [23:00<40:50, 40.84s/trial, best loss: -0.5728]
598
  41%|โ–ˆโ–ˆโ–ˆโ–ˆ | 41/100 [23:50<42:55, 43.65s/trial, best loss: -0.5728]
599
  42%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 42/100 [24:25<39:33, 40.92s/trial, best loss: -0.5728]
600
  43%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 43/100 [25:12<40:33, 42.68s/trial, best loss: -0.5728]
601
  44%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 44/100 [25:44<36:53, 39.53s/trial, best loss: -0.5728]
602
  45%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 45/100 [26:27<37:07, 40.50s/trial, best loss: -0.5728]
603
  46%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 46/100 [26:55<33:11, 36.89s/trial, best loss: -0.5728]
604
  47%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 47/100 [27:29<31:48, 36.00s/trial, best loss: -0.5752]
605
  48%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 48/100 [28:12<32:56, 38.02s/trial, best loss: -0.5752]
606
  49%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 49/100 [29:03<35:42, 42.00s/trial, best loss: -0.5752]
607
  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 50/100 [29:44<34:41, 41.64s/trial, best loss: -0.5752]
608
  51%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 51/100 [30:31<35:24, 43.36s/trial, best loss: -0.5752]
609
  52%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 52/100 [31:10<33:37, 42.03s/trial, best loss: -0.5752]
610
  53%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 53/100 [32:15<38:25, 49.04s/trial, best loss: -0.5752]
611
  54%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 54/100 [33:01<36:43, 47.91s/trial, best loss: -0.5752]
612
  55%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 55/100 [33:49<36:06, 48.15s/trial, best loss: -0.5752]
613
  56%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 56/100 [34:14<30:07, 41.07s/trial, best loss: -0.5752]
614
  57%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 57/100 [35:00<30:34, 42.67s/trial, best loss: -0.5752]
615
  58%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 58/100 [35:40<29:10, 41.68s/trial, best loss: -0.5752]
616
  59%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 59/100 [36:03<24:48, 36.30s/trial, best loss: -0.5752]
617
  60%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 60/100 [36:36<23:29, 35.23s/trial, best loss: -0.5752]
618
  61%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 61/100 [37:05<21:41, 33.38s/trial, best loss: -0.5752]
619
  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 62/100 [37:54<24:06, 38.07s/trial, best loss: -0.5752]
620
  63%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 63/100 [38:44<25:39, 41.62s/trial, best loss: -0.5752]
621
  64%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 64/100 [39:31<25:51, 43.10s/trial, best loss: -0.5752]
622
  65%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 65/100 [40:19<26:01, 44.62s/trial, best loss: -0.5752]
623
  66%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 66/100 [40:58<24:23, 43.04s/trial, best loss: -0.5752]
624
  67%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 67/100 [41:51<25:12, 45.84s/trial, best loss: -0.5752]
625
  68%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 68/100 [42:34<24:06, 45.19s/trial, best loss: -0.5752]
626
  69%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 69/100 [43:11<22:05, 42.75s/trial, best loss: -0.5752]
627
  70%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 70/100 [43:52<20:59, 41.99s/trial, best loss: -0.5752]
628
  71%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 71/100 [44:35<20:27, 42.32s/trial, best loss: -0.5752]
629
  72%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 72/100 [44:58<17:02, 36.50s/trial, best loss: -0.5752]
630
  73%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 73/100 [45:17<14:03, 31.24s/trial, best loss: -0.5752]
631
  74%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 74/100 [45:58<14:54, 34.42s/trial, best loss: -0.5752]
632
  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 75/100 [46:29<13:49, 33.19s/trial, best loss: -0.5752]
633
  76%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 76/100 [46:50<11:49, 29.56s/trial, best loss: -0.5752]
634
  77%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 77/100 [47:37<13:24, 34.96s/trial, best loss: -0.5752]
635
  78%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 78/100 [48:10<12:32, 34.23s/trial, best loss: -0.5752]
636
  79%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 79/100 [48:29<10:21, 29.59s/trial, best loss: -0.5752]
637
  80%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 80/100 [48:48<08:47, 26.39s/trial, best loss: -0.5752]
638
  81%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 81/100 [49:21<09:03, 28.62s/trial, best loss: -0.5752]
639
  82%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 82/100 [50:05<09:58, 33.23s/trial, best loss: -0.5752]
640
  83%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 83/100 [50:31<08:45, 30.90s/trial, best loss: -0.5752]
641
  84%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 84/100 [51:08<08:44, 32.80s/trial, best loss: -0.5752]
642
  85%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 85/100 [51:39<08:03, 32.23s/trial, best loss: -0.5752]
643
  86%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 86/100 [52:06<07:07, 30.56s/trial, best loss: -0.5752]
644
  87%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 87/100 [52:34<06:26, 29.76s/trial, best loss: -0.5752]
645
  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 88/100 [54:13<10:08, 50.68s/trial, best loss: -0.5752]
646
  89%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 89/100 [54:46<08:17, 45.21s/trial, best loss: -0.5752]
647
  90%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 90/100 [55:12<06:34, 39.45s/trial, best loss: -0.5752]
648
  91%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 91/100 [55:50<05:53, 39.23s/trial, best loss: -0.5752]
649
  92%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 92/100 [56:14<04:35, 34.50s/trial, best loss: -0.5752]
650
  93%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž| 93/100 [56:38<03:40, 31.57s/trial, best loss: -0.5752]
651
  94%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 94/100 [57:13<03:14, 32.49s/trial, best loss: -0.5752]
652
  95%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ| 95/100 [57:49<02:47, 33.54s/trial, best loss: -0.5752]
653
  96%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ| 96/100 [58:46<02:42, 40.69s/trial, best loss: -0.5752]
654
  97%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹| 97/100 [59:20<01:55, 38.56s/trial, best loss: -0.5752]
655
  98%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š| 98/100 [59:58<01:16, 38.38s/trial, best loss: -0.5752]
656
  99%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰| 99/100 [1:00:25<00:35, 35.02s/trial, best loss: -0.5752]
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
657
  0%| | 0/100 [00:00<?, ?trial/s, best loss=?]
658
  1%| | 1/100 [00:26<44:04, 26.71s/trial, best loss: -0.5553]
659
  2%|โ– | 2/100 [01:25<1:14:19, 45.50s/trial, best loss: -0.5578]
660
  3%|โ–Ž | 3/100 [01:43<53:05, 32.84s/trial, best loss: -0.5642]
661
  4%|โ– | 4/100 [02:23<57:11, 35.74s/trial, best loss: -0.5722]
662
  5%|โ–Œ | 5/100 [03:14<1:05:13, 41.19s/trial, best loss: -0.5722]
663
  6%|โ–Œ | 6/100 [03:53<1:03:36, 40.60s/trial, best loss: -0.5722]
664
  7%|โ–‹ | 7/100 [04:34<1:03:04, 40.69s/trial, best loss: -0.5722]
665
  8%|โ–Š | 8/100 [05:56<1:22:33, 53.85s/trial, best loss: -0.5722]
666
  9%|โ–‰ | 9/100 [06:33<1:13:50, 48.69s/trial, best loss: -0.5722]
667
  10%|โ–ˆ | 10/100 [07:35<1:19:14, 52.83s/trial, best loss: -0.5722]
668
  11%|โ–ˆ | 11/100 [08:04<1:07:21, 45.41s/trial, best loss: -0.5722]
669
  12%|โ–ˆโ– | 12/100 [08:37<1:01:12, 41.74s/trial, best loss: -0.5722]
670
  13%|โ–ˆโ–Ž | 13/100 [09:20<1:00:55, 42.02s/trial, best loss: -0.5722]
671
  14%|โ–ˆโ– | 14/100 [09:48<53:56, 37.64s/trial, best loss: -0.5722]
672
  15%|โ–ˆโ–Œ | 15/100 [10:32<56:09, 39.64s/trial, best loss: -0.5722]
673
  16%|โ–ˆโ–Œ | 16/100 [10:50<46:20, 33.10s/trial, best loss: -0.5722]
674
  17%|โ–ˆโ–‹ | 17/100 [12:02<1:02:10, 44.95s/trial, best loss: -0.5722]
675
  18%|โ–ˆโ–Š | 18/100 [12:32<55:19, 40.49s/trial, best loss: -0.5733]
676
  19%|โ–ˆโ–‰ | 19/100 [13:24<59:17, 43.91s/trial, best loss: -0.5733]
677
  20%|โ–ˆโ–ˆ | 20/100 [13:59<54:50, 41.13s/trial, best loss: -0.5733]
678
  21%|โ–ˆโ–ˆ | 21/100 [14:32<51:00, 38.74s/trial, best loss: -0.5746]
679
  22%|โ–ˆโ–ˆโ– | 22/100 [15:02<47:06, 36.24s/trial, best loss: -0.5746]
680
  23%|โ–ˆโ–ˆโ–Ž | 23/100 [15:27<42:08, 32.83s/trial, best loss: -0.5746]
681
  24%|โ–ˆโ–ˆโ– | 24/100 [16:08<44:35, 35.20s/trial, best loss: -0.5755]
682
  25%|โ–ˆโ–ˆโ–Œ | 25/100 [16:32<39:49, 31.86s/trial, best loss: -0.5755]
683
  26%|โ–ˆโ–ˆโ–Œ | 26/100 [17:09<41:12, 33.42s/trial, best loss: -0.5755]
684
  27%|โ–ˆโ–ˆโ–‹ | 27/100 [17:38<38:48, 31.90s/trial, best loss: -0.5755]
685
  28%|โ–ˆโ–ˆโ–Š | 28/100 [18:12<39:05, 32.58s/trial, best loss: -0.5755]
686
  29%|โ–ˆโ–ˆโ–‰ | 29/100 [18:37<35:55, 30.36s/trial, best loss: -0.5755]
687
  30%|โ–ˆโ–ˆโ–ˆ | 30/100 [19:01<33:14, 28.50s/trial, best loss: -0.5755]
688
  31%|โ–ˆโ–ˆโ–ˆ | 31/100 [19:44<37:34, 32.68s/trial, best loss: -0.5755]
689
  32%|โ–ˆโ–ˆโ–ˆโ– | 32/100 [20:22<39:02, 34.45s/trial, best loss: -0.5756]
690
  33%|โ–ˆโ–ˆโ–ˆโ–Ž | 33/100 [21:26<48:30, 43.44s/trial, best loss: -0.5756]
691
  34%|โ–ˆโ–ˆโ–ˆโ– | 34/100 [22:10<47:57, 43.60s/trial, best loss: -0.5756]
692
  35%|โ–ˆโ–ˆโ–ˆโ–Œ | 35/100 [22:53<46:44, 43.14s/trial, best loss: -0.5765]
693
  36%|โ–ˆโ–ˆโ–ˆโ–Œ | 36/100 [23:22<41:39, 39.06s/trial, best loss: -0.5765]
694
  37%|โ–ˆโ–ˆโ–ˆโ–‹ | 37/100 [23:59<40:26, 38.52s/trial, best loss: -0.5765]
695
  38%|โ–ˆโ–ˆโ–ˆโ–Š | 38/100 [24:33<38:21, 37.12s/trial, best loss: -0.5765]
696
  39%|โ–ˆโ–ˆโ–ˆโ–‰ | 39/100 [24:59<34:25, 33.87s/trial, best loss: -0.5765]
697
  40%|โ–ˆโ–ˆโ–ˆโ–ˆ | 40/100 [25:43<36:46, 36.77s/trial, best loss: -0.5765]
698
  41%|โ–ˆโ–ˆโ–ˆโ–ˆ | 41/100 [26:10<33:16, 33.83s/trial, best loss: -0.5765]
699
  42%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 42/100 [26:48<33:59, 35.16s/trial, best loss: -0.5795]
700
  43%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 43/100 [27:34<36:30, 38.44s/trial, best loss: -0.5795]
701
  44%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 44/100 [28:07<34:18, 36.75s/trial, best loss: -0.5795]
702
  45%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 45/100 [29:03<38:56, 42.49s/trial, best loss: -0.5795]
703
  46%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 46/100 [30:11<45:07, 50.14s/trial, best loss: -0.5795]
704
  47%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 47/100 [30:41<38:58, 44.12s/trial, best loss: -0.5795]
705
  48%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 48/100 [31:09<34:00, 39.25s/trial, best loss: -0.5795]
706
  49%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 49/100 [31:36<30:15, 35.60s/trial, best loss: -0.5795]
707
  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 50/100 [32:00<26:38, 31.96s/trial, best loss: -0.5795]
708
  51%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 51/100 [32:38<27:48, 34.04s/trial, best loss: -0.5795]
709
  52%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 52/100 [33:11<26:53, 33.62s/trial, best loss: -0.5795]
710
  53%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 53/100 [34:06<31:27, 40.15s/trial, best loss: -0.5795]
711
  54%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 54/100 [34:35<28:05, 36.63s/trial, best loss: -0.5795]
712
  55%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 55/100 [35:03<25:27, 33.96s/trial, best loss: -0.5795]
713
  56%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 56/100 [35:32<23:48, 32.47s/trial, best loss: -0.5795]
714
  57%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 57/100 [36:16<25:55, 36.18s/trial, best loss: -0.5795]
715
  58%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 58/100 [36:39<22:28, 32.12s/trial, best loss: -0.5795]
716
  59%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 59/100 [37:05<20:46, 30.41s/trial, best loss: -0.5795]
717
  60%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ๏ฟฝ๏ฟฝ | 60/100 [37:46<22:14, 33.37s/trial, best loss: -0.5795]
718
  61%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 61/100 [38:24<22:40, 34.89s/trial, best loss: -0.5795]
719
  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 62/100 [39:05<23:12, 36.64s/trial, best loss: -0.5795]
720
  63%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 63/100 [39:57<25:27, 41.29s/trial, best loss: -0.5795]
721
  64%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 64/100 [40:19<21:21, 35.59s/trial, best loss: -0.5795]
722
  65%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 65/100 [40:52<20:16, 34.76s/trial, best loss: -0.5795]
723
  66%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 66/100 [41:14<17:26, 30.79s/trial, best loss: -0.5795]
724
  67%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 67/100 [41:44<16:53, 30.70s/trial, best loss: -0.5795]
725
  68%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 68/100 [42:07<15:10, 28.45s/trial, best loss: -0.5795]
726
  69%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 69/100 [42:27<13:23, 25.92s/trial, best loss: -0.5795]
727
  70%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 70/100 [42:55<13:15, 26.52s/trial, best loss: -0.5797]
728
  71%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 71/100 [43:20<12:29, 25.85s/trial, best loss: -0.5824]
729
  72%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 72/100 [43:50<12:40, 27.17s/trial, best loss: -0.5824]
730
  73%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 73/100 [44:17<12:11, 27.08s/trial, best loss: -0.5824]
731
  74%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 74/100 [44:38<10:59, 25.37s/trial, best loss: -0.5824]
732
  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 75/100 [45:08<11:10, 26.80s/trial, best loss: -0.5824]
733
  76%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 76/100 [45:54<12:56, 32.36s/trial, best loss: -0.5824]
734
  77%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 77/100 [46:12<10:48, 28.20s/trial, best loss: -0.5824]
735
  78%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 78/100 [46:36<09:51, 26.88s/trial, best loss: -0.5824]
736
  79%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 79/100 [46:59<08:58, 25.63s/trial, best loss: -0.5824]
737
  80%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 80/100 [47:29<09:04, 27.20s/trial, best loss: -0.5824]
738
  81%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 81/100 [47:55<08:26, 26.67s/trial, best loss: -0.5824]
739
  82%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 82/100 [48:35<09:13, 30.73s/trial, best loss: -0.5824]
740
  83%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 83/100 [48:59<08:06, 28.60s/trial, best loss: -0.5824]
741
  84%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 84/100 [49:26<07:29, 28.09s/trial, best loss: -0.5824]
742
  85%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 85/100 [49:47<06:30, 26.06s/trial, best loss: -0.5824]
743
  86%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 86/100 [50:44<08:15, 35.36s/trial, best loss: -0.5824]
744
  87%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 87/100 [51:23<07:53, 36.46s/trial, best loss: -0.5824]
745
  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 88/100 [51:46<06:28, 32.41s/trial, best loss: -0.5824]
746
  89%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 89/100 [52:11<05:32, 30.19s/trial, best loss: -0.5824]
747
  90%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 90/100 [52:32<04:34, 27.47s/trial, best loss: -0.5824]
748
  91%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 91/100 [52:57<04:00, 26.68s/trial, best loss: -0.5824]
749
  92%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 92/100 [53:34<03:57, 29.64s/trial, best loss: -0.5824]
750
  93%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž| 93/100 [54:12<03:45, 32.28s/trial, best loss: -0.5824]
751
  94%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 94/100 [54:43<03:11, 31.88s/trial, best loss: -0.5824]
752
  95%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ| 95/100 [55:31<03:04, 36.86s/trial, best loss: -0.5824]
753
  96%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ| 96/100 [55:57<02:14, 33.56s/trial, best loss: -0.5824]
754
  97%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹| 97/100 [56:19<01:29, 29.99s/trial, best loss: -0.5824]
755
  98%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š| 98/100 [56:47<00:59, 29.54s/trial, best loss: -0.5824]
756
  99%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰| 99/100 [57:09<00:27, 27.11s/trial, best loss: -0.5824]
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ nohup: ignoring input
2
+ /bin/bash: /opt/conda/lib/libtinfo.so.6: no version information available (required by /bin/bash)
3
+ ==========================================
4
+ XGB CTGAN10000 ํŒŒ์ผ ์‹คํ–‰ ์‹œ์ž‘
5
+ ์‹œ์ž‘ ์‹œ๊ฐ„: 2025-12-28 04:31:17
6
+ GPU: 0๋ฒˆ (CUDA_VISIBLE_DEVICES=0)
7
+ ==========================================
8
+
9
+ ----------------------------------------
10
+ ์‹คํ–‰ ์ค‘: xgb_ctgan10000/XGB_ctgan10000_busan.py
11
+ ์‹œ์ž‘ ์‹œ๊ฐ„: 2025-12-28 04:31:17
12
+ ----------------------------------------
13
+ ๋ฐ์ดํ„ฐ ๋กœ๋”ฉ ์ค‘...
14
+ ๋ฐ์ดํ„ฐ ์ „์ฒ˜๋ฆฌ ์ค‘...
15
+ ํ•˜์ดํผํŒŒ๋ผ๋ฏธํ„ฐ ์ตœ์ ํ™” ์‹œ์ž‘...
16
+
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
17
  0%| | 0/100 [00:00<?, ?trial/s, best loss=?]
18
  1%| | 1/100 [01:00<1:39:06, 60.06s/trial, best loss: -0.4522]
19
  2%|โ– | 2/100 [01:27<1:06:28, 40.70s/trial, best loss: -0.4709]
20
  3%|โ–Ž | 3/100 [02:00<1:00:22, 37.35s/trial, best loss: -0.4806]
21
  4%|โ– | 4/100 [02:36<58:57, 36.85s/trial, best loss: -0.4806]
22
  5%|โ–Œ | 5/100 [02:59<50:07, 31.66s/trial, best loss: -0.4822]
23
  6%|โ–Œ | 6/100 [03:46<57:59, 37.02s/trial, best loss: -0.4822]
24
  7%|โ–‹ | 7/100 [04:12<51:49, 33.43s/trial, best loss: -0.4822]
25
  8%|โ–Š | 8/100 [04:40<48:45, 31.80s/trial, best loss: -0.4822]
26
  9%|โ–‰ | 9/100 [05:37<1:00:09, 39.66s/trial, best loss: -0.4822]
27
  10%|โ–ˆ | 10/100 [06:13<57:38, 38.43s/trial, best loss: -0.4822]
28
  11%|โ–ˆ | 11/100 [06:34<49:07, 33.12s/trial, best loss: -0.4822]
29
  12%|โ–ˆโ– | 12/100 [07:20<54:22, 37.07s/trial, best loss: -0.4822]
30
  13%|โ–ˆโ–Ž | 13/100 [08:01<55:35, 38.34s/trial, best loss: -0.4822]
31
  14%|โ–ˆโ– | 14/100 [08:34<52:25, 36.57s/trial, best loss: -0.4822]
32
  15%|โ–ˆโ–Œ | 15/100 [09:03<48:30, 34.24s/trial, best loss: -0.4822]
33
  16%|โ–ˆโ–Œ | 16/100 [09:29<44:45, 31.97s/trial, best loss: -0.4822]
34
  17%|โ–ˆโ–‹ | 17/100 [10:29<55:53, 40.40s/trial, best loss: -0.4822]
35
  18%|โ–ˆโ–Š | 18/100 [10:46<45:13, 33.10s/trial, best loss: -0.4822]
36
  19%|โ–ˆโ–‰ | 19/100 [11:11<41:26, 30.70s/trial, best loss: -0.4822]
37
  20%|โ–ˆโ–ˆ | 20/100 [11:37<39:10, 29.38s/trial, best loss: -0.4822]
38
  21%|โ–ˆโ–ˆ | 21/100 [12:17<42:42, 32.43s/trial, best loss: -0.4822]
39
  22%|โ–ˆโ–ˆโ– | 22/100 [13:23<55:18, 42.55s/trial, best loss: -0.4822]
40
  23%|โ–ˆโ–ˆโ–Ž | 23/100 [13:58<51:48, 40.37s/trial, best loss: -0.4822]
41
  24%|โ–ˆโ–ˆโ– | 24/100 [14:29<47:44, 37.69s/trial, best loss: -0.4822]
42
  25%|โ–ˆโ–ˆโ–Œ | 25/100 [16:19<1:14:11, 59.35s/trial, best loss: -0.4822]
43
  26%|โ–ˆโ–ˆโ–Œ | 26/100 [16:57<1:05:04, 52.76s/trial, best loss: -0.4822]
44
  27%|โ–ˆโ–ˆโ–‹ | 27/100 [17:39<1:00:28, 49.70s/trial, best loss: -0.4822]
45
  28%|โ–ˆโ–ˆโ–Š | 28/100 [18:11<53:04, 44.23s/trial, best loss: -0.4822]
46
  29%|โ–ˆโ–ˆโ–‰ | 29/100 [18:34<44:58, 38.01s/trial, best loss: -0.4822]
47
  30%|โ–ˆโ–ˆโ–ˆ | 30/100 [19:28<49:57, 42.82s/trial, best loss: -0.4822]
48
  31%|โ–ˆโ–ˆโ–ˆ | 31/100 [20:07<47:46, 41.54s/trial, best loss: -0.4822]
49
  32%|โ–ˆโ–ˆโ–ˆโ– | 32/100 [20:43<45:24, 40.07s/trial, best loss: -0.4822]
50
  33%|โ–ˆโ–ˆโ–ˆโ–Ž | 33/100 [21:19<43:07, 38.62s/trial, best loss: -0.4822]
51
  34%|โ–ˆโ–ˆโ–ˆโ– | 34/100 [21:48<39:24, 35.83s/trial, best loss: -0.4822]
52
  35%|โ–ˆโ–ˆโ–ˆโ–Œ | 35/100 [22:31<41:08, 37.98s/trial, best loss: -0.4822]
53
  36%|โ–ˆโ–ˆโ–ˆโ–Œ | 36/100 [23:04<39:03, 36.62s/trial, best loss: -0.4822]
54
  37%|โ–ˆโ–ˆโ–ˆโ–‹ | 37/100 [23:23<32:46, 31.22s/trial, best loss: -0.4822]
55
  38%|โ–ˆโ–ˆโ–ˆโ–Š | 38/100 [24:18<39:43, 38.44s/trial, best loss: -0.4822]
56
  39%|โ–ˆโ–ˆโ–ˆโ–‰ | 39/100 [24:56<38:44, 38.10s/trial, best loss: -0.4822]
57
  40%|โ–ˆโ–ˆโ–ˆโ–ˆ | 40/100 [25:22<34:34, 34.57s/trial, best loss: -0.4822]
58
  41%|โ–ˆโ–ˆโ–ˆโ–ˆ | 41/100 [26:22<41:38, 42.35s/trial, best loss: -0.4822]
59
  42%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 42/100 [26:55<38:01, 39.34s/trial, best loss: -0.4822]
60
  43%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 43/100 [27:18<32:39, 34.38s/trial, best loss: -0.4822]
61
  44%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 44/100 [27:47<30:33, 32.74s/trial, best loss: -0.4822]
62
  45%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 45/100 [28:19<29:49, 32.54s/trial, best loss: -0.4822]
63
  46%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 46/100 [28:45<27:34, 30.64s/trial, best loss: -0.4822]
64
  47%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 47/100 [29:14<26:38, 30.15s/trial, best loss: -0.4822]
65
  48%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 48/100 [29:46<26:33, 30.65s/trial, best loss: -0.4822]
66
  49%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 49/100 [30:25<28:21, 33.36s/trial, best loss: -0.4822]
67
  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 50/100 [31:31<35:53, 43.06s/trial, best loss: -0.4822]
68
  51%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 51/100 [31:58<31:21, 38.40s/trial, best loss: -0.4822]
69
  52%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 52/100 [32:28<28:27, 35.58s/trial, best loss: -0.4822]
70
  53%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 53/100 [33:11<29:43, 37.96s/trial, best loss: -0.4822]
71
  54%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 54/100 [33:55<30:23, 39.63s/trial, best loss: -0.4822]
72
  55%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 55/100 [34:24<27:21, 36.48s/trial, best loss: -0.4822]
73
  56%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 56/100 [34:51<24:49, 33.84s/trial, best loss: -0.4822]
74
  57%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 57/100 [35:28<24:50, 34.66s/trial, best loss: -0.4822]
75
  58%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 58/100 [36:06<25:02, 35.78s/trial, best loss: -0.4822]
76
  59%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 59/100 [36:42<24:24, 35.72s/trial, best loss: -0.4822]
77
  60%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 60/100 [37:06<21:31, 32.29s/trial, best loss: -0.4822]
78
  61%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 61/100 [37:32<19:40, 30.28s/trial, best loss: -0.4822]
79
  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 62/100 [38:46<27:34, 43.54s/trial, best loss: -0.4822]
80
  63%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 63/100 [39:13<23:43, 38.47s/trial, best loss: -0.4822]
81
  64%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 64/100 [39:56<23:52, 39.79s/trial, best loss: -0.4822]
82
  65%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 65/100 [40:47<25:10, 43.16s/trial, best loss: -0.4822]
83
  66%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 66/100 [41:09<20:56, 36.97s/trial, best loss: -0.4822]
84
  67%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 67/100 [41:44<19:56, 36.27s/trial, best loss: -0.4822]
85
  68%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 68/100 [42:13<18:06, 33.96s/trial, best loss: -0.4822]
86
  69%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 69/100 [42:38<16:17, 31.53s/trial, best loss: -0.4822]
87
  70%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 70/100 [43:17<16:46, 33.55s/trial, best loss: -0.4822]
88
  71%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 71/100 [44:05<18:23, 38.06s/trial, best loss: -0.4822]
89
  72%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 72/100 [44:36<16:42, 35.80s/trial, best loss: -0.4822]
90
  73%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 73/100 [44:57<14:11, 31.55s/trial, best loss: -0.4822]
91
  74%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 74/100 [45:29<13:43, 31.66s/trial, best loss: -0.4822]
92
  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 75/100 [45:50<11:52, 28.50s/trial, best loss: -0.4822]
93
  76%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 76/100 [46:19<11:22, 28.43s/trial, best loss: -0.4822]
94
  77%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 77/100 [46:44<10:32, 27.51s/trial, best loss: -0.4822]
95
  78%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 78/100 [47:10<09:56, 27.11s/trial, best loss: -0.4822]
96
  79%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 79/100 [47:56<11:27, 32.75s/trial, best loss: -0.4822]
97
  80%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 80/100 [48:24<10:24, 31.23s/trial, best loss: -0.4822]
98
  81%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 81/100 [48:43<08:45, 27.68s/trial, best loss: -0.4822]
99
  82%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 82/100 [49:12<08:25, 28.09s/trial, best loss: -0.4822]
100
  83%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 83/100 [49:39<07:49, 27.62s/trial, best loss: -0.4822]
101
  84%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 84/100 [50:07<07:24, 27.78s/trial, best loss: -0.4822]
102
  85%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 85/100 [50:55<08:25, 33.72s/trial, best loss: -0.4822]
103
  86%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 86/100 [51:11<06:38, 28.47s/trial, best loss: -0.4845]
104
  87%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 87/100 [51:30<05:33, 25.68s/trial, best loss: -0.4845]
105
  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 88/100 [52:03<05:34, 27.85s/trial, best loss: -0.4845]
106
  89%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 89/100 [52:36<05:23, 29.37s/trial, best loss: -0.4845]
107
  90%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 90/100 [53:00<04:38, 27.88s/trial, best loss: -0.4845]
108
  91%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 91/100 [53:23<03:56, 26.31s/trial, best loss: -0.4845]
109
  92%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 92/100 [54:16<04:34, 34.36s/trial, best loss: -0.4845]
110
  93%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž| 93/100 [54:44<03:47, 32.57s/trial, best loss: -0.4845]
111
  94%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 94/100 [55:04<02:52, 28.71s/trial, best loss: -0.4845]
112
  95%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ| 95/100 [55:47<02:45, 33.04s/trial, best loss: -0.4845]
113
  96%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ| 96/100 [56:11<02:01, 30.30s/trial, best loss: -0.4845]
114
  97%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹| 97/100 [56:42<01:31, 30.51s/trial, best loss: -0.4845]
115
  98%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š| 98/100 [57:01<00:53, 26.91s/trial, best loss: -0.4845]
116
  99%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰| 99/100 [57:30<00:27, 27.60s/trial, best loss: -0.4881]
117
+
118
+ ์ตœ์ ํ™” ์™„๋ฃŒ. ์ตœ์  ํŒŒ๋ผ๋ฏธํ„ฐ: {'colsample_bytree': 0.6875780545091519, 'gamma': 2.658982028747467, 'learning_rate': 0.11595019019771602, 'max_depth': 12.0, 'min_child_weight': 18.0, 'reg_alpha': 0.9071038284958559, 'reg_lambda': 0.2880553949579837, 'subsample': 0.7100915343806586}
119
+ ์ตœ์  CSI ์ ์ˆ˜: 0.4881 (loss: -0.4881)
120
+
121
+ ์ตœ์ ํ™” ๊ณผ์ • ์š”์•ฝ:
122
+ - ์ด ์‹œ๋„ ํšŸ์ˆ˜: 100
123
+ - ์„ฑ๊ณตํ•œ ์‹œ๋„: 100
124
+ - ์ตœ์ดˆ CSI: 0.4522
125
+ - ์ตœ์ข… CSI: 0.4780
126
+ - ์ตœ๊ณ  CSI: 0.4881
127
+ - ์ตœ์ € CSI: 0.4459
128
+ - ํ‰๊ท  CSI: 0.4737
129
+
130
+ ์ตœ์ ํ™” Trials ๊ฐ์ฒด๊ฐ€ /workspace/visibility_prediction/Analysis_code/optimization_history/xgb_ctgan10000_busan_trials.pkl์— ์ €์žฅ๋˜์—ˆ์Šต๋‹ˆ๋‹ค.
131
+ ์ตœ์ข… ๋ชจ๋ธ ํ•™์Šต ์‹œ์ž‘...
132
+ Fold 1 ํ•™์Šต ์ค‘... (ํ•™์Šต ์—ฐ๋„: [2018, 2019], ๊ฒ€์ฆ ์—ฐ๋„: 2020)
133
+ Fold 1 ๊ฒ€์ฆ CSI: 0.4329
134
+ Fold 2 ํ•™์Šต ์ค‘... (ํ•™์Šต ์—ฐ๋„: [2018, 2020], ๊ฒ€์ฆ ์—ฐ๋„: 2019)
135
+ Fold 2 ๊ฒ€์ฆ CSI: 0.5007
136
+ Fold 3 ํ•™์Šต ์ค‘... (ํ•™์Šต ์—ฐ๋„: [2019, 2020], ๊ฒ€์ฆ ์—ฐ๋„: 2018)
137
+ Fold 3 ๊ฒ€์ฆ CSI: 0.5306
138
+ ๋ชจ๋ธ ์ €์žฅ ์ค‘...
139
+ ๋ชจ๋ธ์ด /workspace/visibility_prediction/Analysis_code/save_model/xgb_optima/xgb_ctgan10000_busan.pkl์— ์ €์žฅ๋˜์—ˆ์Šต๋‹ˆ๋‹ค.
140
+
141
+ โœ“ ์™„๋ฃŒ: xgb_ctgan10000/XGB_ctgan10000_busan.py (์†Œ์š” ์‹œ๊ฐ„: 3501์ดˆ)
142
+
143
+ ----------------------------------------
144
+ ์‹คํ–‰ ์ค‘: xgb_ctgan10000/XGB_ctgan10000_daegu.py
145
+ ์‹œ์ž‘ ์‹œ๊ฐ„: 2025-12-28 05:29:38
146
+ ----------------------------------------
147
+ ๋ฐ์ดํ„ฐ ๋กœ๋”ฉ ์ค‘...
148
+ ๋ฐ์ดํ„ฐ ์ „์ฒ˜๋ฆฌ ์ค‘...
149
+ ํ•˜์ดํผํŒŒ๋ผ๋ฏธํ„ฐ ์ตœ์ ํ™” ์‹œ์ž‘...
150
+
151
  0%| | 0/100 [00:00<?, ?trial/s, best loss=?]
152
  1%| | 1/100 [00:44<1:13:09, 44.34s/trial, best loss: -0.4037]
153
  2%|โ– | 2/100 [01:13<58:05, 35.57s/trial, best loss: -0.4037]
154
  3%|โ–Ž | 3/100 [01:31<44:34, 27.57s/trial, best loss: -0.4037]
155
  4%|โ– | 4/100 [02:03<46:37, 29.14s/trial, best loss: -0.427]
156
  5%|โ–Œ | 5/100 [02:28<43:56, 27.75s/trial, best loss: -0.427]
157
  6%|โ–Œ | 6/100 [03:09<50:15, 32.08s/trial, best loss: -0.427]
158
  7%|โ–‹ | 7/100 [03:47<52:46, 34.05s/trial, best loss: -0.427]
159
  8%|โ–Š | 8/100 [04:35<59:09, 38.58s/trial, best loss: -0.427]
160
  9%|โ–‰ | 9/100 [05:06<55:05, 36.32s/trial, best loss: -0.427]
161
  10%|โ–ˆ | 10/100 [05:26<46:43, 31.15s/trial, best loss: -0.427]
162
  11%|โ–ˆ | 11/100 [05:59<47:10, 31.80s/trial, best loss: -0.427]
163
  12%|โ–ˆโ– | 12/100 [06:38<49:41, 33.88s/trial, best loss: -0.427]
164
  13%|โ–ˆโ–Ž | 13/100 [07:14<49:58, 34.47s/trial, best loss: -0.427]
165
  14%|โ–ˆโ– | 14/100 [07:46<48:22, 33.75s/trial, best loss: -0.427]
166
  15%|โ–ˆโ–Œ | 15/100 [08:53<1:02:15, 43.95s/trial, best loss: -0.427]
167
  16%|โ–ˆโ–Œ | 16/100 [09:27<57:04, 40.77s/trial, best loss: -0.427]
168
  17%|โ–ˆโ–‹ | 17/100 [09:54<50:35, 36.57s/trial, best loss: -0.427]
169
  18%|โ–ˆโ–Š | 18/100 [10:31<50:22, 36.86s/trial, best loss: -0.427]
170
  19%|โ–ˆโ–‰ | 19/100 [11:01<46:58, 34.80s/trial, best loss: -0.427]
171
  20%|โ–ˆโ–ˆ | 20/100 [11:33<45:04, 33.81s/trial, best loss: -0.4356]
172
  21%|โ–ˆโ–ˆ | 21/100 [11:58<41:05, 31.21s/trial, best loss: -0.4356]
173
  22%|โ–ˆโ–ˆโ– | 22/100 [12:28<40:14, 30.96s/trial, best loss: -0.4356]
174
  23%|โ–ˆโ–ˆโ–Ž | 23/100 [12:59<39:36, 30.86s/trial, best loss: -0.4356]
175
  24%|โ–ˆโ–ˆโ– | 24/100 [13:22<36:20, 28.69s/trial, best loss: -0.4356]
176
  25%|โ–ˆโ–ˆโ–Œ | 25/100 [13:43<32:45, 26.20s/trial, best loss: -0.4356]
177
  26%|โ–ˆโ–ˆโ–Œ | 26/100 [14:31<40:32, 32.87s/trial, best loss: -0.4356]
178
  27%|โ–ˆโ–ˆโ–‹ | 27/100 [15:03<39:37, 32.57s/trial, best loss: -0.4356]
179
  28%|โ–ˆโ–ˆโ–Š | 28/100 [15:44<42:03, 35.05s/trial, best loss: -0.4356]
180
  29%|โ–ˆโ–ˆโ–‰ | 29/100 [16:06<36:44, 31.04s/trial, best loss: -0.4356]
181
  30%|โ–ˆโ–ˆโ–ˆ | 30/100 [16:31<34:04, 29.21s/trial, best loss: -0.4356]
182
  31%|โ–ˆโ–ˆโ–ˆ | 31/100 [17:21<40:48, 35.48s/trial, best loss: -0.4356]
183
  32%|โ–ˆโ–ˆโ–ˆโ– | 32/100 [17:53<38:59, 34.40s/trial, best loss: -0.4356]
184
  33%|โ–ˆโ–ˆโ–ˆโ–Ž | 33/100 [18:25<37:36, 33.68s/trial, best loss: -0.4356]
185
  34%|โ–ˆโ–ˆโ–ˆโ– | 34/100 [19:02<38:21, 34.87s/trial, best loss: -0.4356]
186
  35%|โ–ˆโ–ˆโ–ˆโ–Œ | 35/100 [19:46<40:41, 37.56s/trial, best loss: -0.4356]
187
  36%|โ–ˆโ–ˆโ–ˆโ–Œ | 36/100 [20:19<38:39, 36.24s/trial, best loss: -0.4356]
188
  37%|โ–ˆโ–ˆโ–ˆโ–‹ | 37/100 [20:58<38:45, 36.92s/trial, best loss: -0.4356]
189
  38%|โ–ˆโ–ˆโ–ˆโ–Š | 38/100 [21:35<38:17, 37.06s/trial, best loss: -0.4356]
190
  39%|โ–ˆโ–ˆโ–ˆโ–‰ | 39/100 [22:13<37:55, 37.30s/trial, best loss: -0.4356]
191
  40%|โ–ˆโ–ˆโ–ˆโ–ˆ | 40/100 [22:50<37:13, 37.22s/trial, best loss: -0.4356]
192
  41%|โ–ˆโ–ˆโ–ˆโ–ˆ | 41/100 [23:24<35:32, 36.15s/trial, best loss: -0.4356]
193
  42%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 42/100 [24:04<36:02, 37.29s/trial, best loss: -0.4356]
194
  43%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 43/100 [24:49<37:45, 39.75s/trial, best loss: -0.4356]
195
  44%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 44/100 [25:16<33:24, 35.80s/trial, best loss: -0.4356]
196
  45%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 45/100 [26:10<37:56, 41.39s/trial, best loss: -0.4356]
197
  46%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 46/100 [26:50<36:48, 40.90s/trial, best loss: -0.4356]
198
  47%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 47/100 [27:14<31:46, 35.97s/trial, best loss: -0.4356]
199
  48%|โ–ˆโ–ˆโ–ˆ๏ฟฝ๏ฟฝ๏ฟฝโ–Š | 48/100 [27:47<30:19, 35.00s/trial, best loss: -0.4356]
200
  49%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 49/100 [28:32<32:12, 37.89s/trial, best loss: -0.4356]
201
  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 50/100 [29:28<36:14, 43.50s/trial, best loss: -0.4356]
202
  51%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 51/100 [30:21<37:40, 46.14s/trial, best loss: -0.4356]
203
  52%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 52/100 [31:09<37:22, 46.71s/trial, best loss: -0.4356]
204
  53%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 53/100 [32:18<41:53, 53.48s/trial, best loss: -0.4356]
205
  54%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 54/100 [32:59<38:09, 49.77s/trial, best loss: -0.4356]
206
  55%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 55/100 [33:27<32:22, 43.16s/trial, best loss: -0.4356]
207
  56%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 56/100 [33:57<28:47, 39.26s/trial, best loss: -0.4356]
208
  57%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 57/100 [34:23<25:14, 35.22s/trial, best loss: -0.4356]
209
  58%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 58/100 [34:48<22:39, 32.38s/trial, best loss: -0.4356]
210
  59%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 59/100 [35:24<22:48, 33.38s/trial, best loss: -0.4356]
211
  60%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 60/100 [36:06<23:54, 35.87s/trial, best loss: -0.4356]
212
  61%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 61/100 [36:30<20:57, 32.23s/trial, best loss: -0.4356]
213
  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 62/100 [37:49<29:19, 46.31s/trial, best loss: -0.4356]
214
  63%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 63/100 [38:30<27:42, 44.93s/trial, best loss: -0.4356]
215
  64%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 64/100 [39:13<26:27, 44.09s/trial, best loss: -0.4356]
216
  65%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 65/100 [40:08<27:38, 47.39s/trial, best loss: -0.4356]
217
  66%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 66/100 [40:29<22:22, 39.48s/trial, best loss: -0.4356]
218
  67%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 67/100 [40:47<18:14, 33.17s/trial, best loss: -0.4356]
219
  68%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 68/100 [41:12<16:25, 30.80s/trial, best loss: -0.4356]
220
  69%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 69/100 [41:34<14:30, 28.09s/trial, best loss: -0.4356]
221
  70%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 70/100 [41:55<12:53, 25.80s/trial, best loss: -0.4356]
222
  71%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 71/100 [42:33<14:15, 29.51s/trial, best loss: -0.4356]
223
  72%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 72/100 [43:08<14:35, 31.26s/trial, best loss: -0.4356]
224
  73%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 73/100 [43:38<13:51, 30.79s/trial, best loss: -0.4356]
225
  74%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 74/100 [44:06<12:57, 29.92s/trial, best loss: -0.4356]
226
  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 75/100 [44:40<13:04, 31.37s/trial, best loss: -0.4356]
227
  76%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 76/100 [45:08<12:05, 30.22s/trial, best loss: -0.4356]
228
  77%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 77/100 [45:38<11:33, 30.17s/trial, best loss: -0.4392]
229
  78%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 78/100 [46:12<11:27, 31.26s/trial, best loss: -0.4392]
230
  79%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 79/100 [46:52<11:55, 34.05s/trial, best loss: -0.4392]
231
  80%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 80/100 [47:46<13:18, 39.93s/trial, best loss: -0.4392]
232
  81%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 81/100 [48:28<12:49, 40.49s/trial, best loss: -0.4392]
233
  82%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 82/100 [49:20<13:11, 43.98s/trial, best loss: -0.4392]
234
  83%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 83/100 [49:44<10:44, 37.90s/trial, best loss: -0.4392]
235
  84%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 84/100 [50:14<09:32, 35.78s/trial, best loss: -0.4392]
236
  85%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 85/100 [50:59<09:38, 38.55s/trial, best loss: -0.4392]
237
  86%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 86/100 [51:33<08:39, 37.09s/trial, best loss: -0.4392]
238
  87%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 87/100 [51:53<06:53, 31.80s/trial, best loss: -0.4392]
239
  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 88/100 [52:14<05:45, 28.78s/trial, best loss: -0.4392]
240
  89%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 89/100 [52:47<05:28, 29.87s/trial, best loss: -0.4392]
241
  90%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 90/100 [53:16<04:56, 29.61s/trial, best loss: -0.4392]
242
  91%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 91/100 [53:43<04:21, 29.03s/trial, best loss: -0.4392]
243
  92%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 92/100 [54:14<03:54, 29.37s/trial, best loss: -0.4392]
244
  93%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž| 93/100 [54:35<03:08, 26.99s/trial, best loss: -0.4392]
245
  94%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 94/100 [54:59<02:36, 26.00s/trial, best loss: -0.4392]
246
  95%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ| 95/100 [55:37<02:28, 29.75s/trial, best loss: -0.4392]
247
  96%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ| 96/100 [55:55<01:45, 26.28s/trial, best loss: -0.4392]
248
  97%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹| 97/100 [56:31<01:27, 29.00s/trial, best loss: -0.4392]
249
  98%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š| 98/100 [56:54<00:54, 27.17s/trial, best loss: -0.4392]
250
  99%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰| 99/100 [57:34<00:31, 31.01s/trial, best loss: -0.4392]
251
+
252
+ ์ตœ์ ํ™” ์™„๋ฃŒ. ์ตœ์  ํŒŒ๋ผ๋ฏธํ„ฐ: {'colsample_bytree': 0.8557253370653987, 'gamma': 1.1563957561197729, 'learning_rate': 0.19232018363683898, 'max_depth': 10.0, 'min_child_weight': 8.0, 'reg_alpha': 0.21149066093980878, 'reg_lambda': 0.2690618200166374, 'subsample': 0.714526167464626}
253
+ ์ตœ์  CSI ์ ์ˆ˜: 0.4392 (loss: -0.4392)
254
+
255
+ ์ตœ์ ํ™” ๊ณผ์ • ์š”์•ฝ:
256
+ - ์ด ์‹œ๋„ ํšŸ์ˆ˜: 100
257
+ - ์„ฑ๊ณต๏ฟฝ๏ฟฝ๏ฟฝ ์‹œ๋„: 100
258
+ - ์ตœ์ดˆ CSI: 0.4037
259
+ - ์ตœ์ข… CSI: 0.4027
260
+ - ์ตœ๊ณ  CSI: 0.4392
261
+ - ์ตœ์ € CSI: 0.3123
262
+ - ํ‰๊ท  CSI: 0.4163
263
+
264
+ ์ตœ์ ํ™” Trials ๊ฐ์ฒด๊ฐ€ /workspace/visibility_prediction/Analysis_code/optimization_history/xgb_ctgan10000_daegu_trials.pkl์— ์ €์žฅ๋˜์—ˆ์Šต๋‹ˆ๋‹ค.
265
+ ์ตœ์ข… ๋ชจ๋ธ ํ•™์Šต ์‹œ์ž‘...
266
+ Fold 1 ํ•™์Šต ์ค‘... (ํ•™์Šต ์—ฐ๋„: [2018, 2019], ๊ฒ€์ฆ ์—ฐ๋„: 2020)
267
+ Fold 1 ๊ฒ€์ฆ CSI: 0.4690
268
+ Fold 2 ํ•™์Šต ์ค‘... (ํ•™์Šต ์—ฐ๋„: [2018, 2020], ๊ฒ€์ฆ ์—ฐ๋„: 2019)
269
+ Fold 2 ๊ฒ€์ฆ CSI: 0.4544
270
+ Fold 3 ํ•™์Šต ์ค‘... (ํ•™์Šต ์—ฐ๋„: [2019, 2020], ๊ฒ€์ฆ ์—ฐ๋„: 2018)
271
+ Fold 3 ๊ฒ€์ฆ CSI: 0.3943
272
+ ๋ชจ๋ธ ์ €์žฅ ์ค‘...
273
+ ๋ชจ๋ธ์ด /workspace/visibility_prediction/Analysis_code/save_model/xgb_optima/xgb_ctgan10000_daegu.pkl์— ์ €์žฅ๋˜์—ˆ์Šต๋‹ˆ๋‹ค.
274
+
275
+ โœ“ ์™„๋ฃŒ: xgb_ctgan10000/XGB_ctgan10000_daegu.py (์†Œ์š” ์‹œ๊ฐ„: 3515์ดˆ)
276
+
277
+ ----------------------------------------
278
+ ์‹คํ–‰ ์ค‘: xgb_ctgan10000/XGB_ctgan10000_daejeon.py
279
+ ์‹œ์ž‘ ์‹œ๊ฐ„: 2025-12-28 06:28:13
280
+ ----------------------------------------
281
+ ๋ฐ์ดํ„ฐ ๋กœ๋”ฉ ์ค‘...
282
+ ๋ฐ์ดํ„ฐ ์ „์ฒ˜๋ฆฌ ์ค‘...
283
+ ํ•˜์ดํผํŒŒ๋ผ๋ฏธํ„ฐ ์ตœ์ ํ™” ์‹œ์ž‘...
284
+
285
  0%| | 0/100 [00:00<?, ?trial/s, best loss=?]
286
  1%| | 1/100 [00:37<1:02:28, 37.86s/trial, best loss: -0.4839]
287
  2%|โ– | 2/100 [01:13<59:40, 36.53s/trial, best loss: -0.4839]
288
  3%|โ–Ž | 3/100 [01:51<1:00:22, 37.34s/trial, best loss: -0.4865]
289
  4%|โ– | 4/100 [02:59<1:19:11, 49.49s/trial, best loss: -0.4865]
290
  5%|โ–Œ | 5/100 [04:05<1:27:35, 55.32s/trial, best loss: -0.4953]
291
  6%|โ–Œ | 6/100 [04:39<1:15:30, 48.19s/trial, best loss: -0.4953]
292
  7%|โ–‹ | 7/100 [05:08<1:04:51, 41.84s/trial, best loss: -0.4953]
293
  8%|โ–Š | 8/100 [05:51<1:04:45, 42.23s/trial, best loss: -0.4953]
294
  9%|โ–‰ | 9/100 [06:43<1:08:41, 45.30s/trial, best loss: -0.4953]
295
  10%|โ–ˆ | 10/100 [07:11<1:00:00, 40.00s/trial, best loss: -0.4953]
296
  11%|โ–ˆ | 11/100 [07:50<58:33, 39.47s/trial, best loss: -0.4953]
297
  12%|โ–ˆโ– | 12/100 [08:40<1:02:40, 42.74s/trial, best loss: -0.502]
298
  13%|โ–ˆโ–Ž | 13/100 [09:11<56:49, 39.19s/trial, best loss: -0.502]
299
  14%|โ–ˆโ– | 14/100 [10:06<1:03:07, 44.04s/trial, best loss: -0.502]
300
  15%|โ–ˆโ–Œ | 15/100 [10:59<1:06:00, 46.60s/trial, best loss: -0.502]
301
  16%|โ–ˆโ–Œ | 16/100 [11:49<1:06:55, 47.80s/trial, best loss: -0.502]
302
  17%|โ–ˆโ–‹ | 17/100 [13:07<1:18:45, 56.93s/trial, best loss: -0.502]
303
  18%|โ–ˆโ–Š | 18/100 [13:24<1:01:13, 44.79s/trial, best loss: -0.502]
304
  19%|โ–ˆโ–‰ | 19/100 [13:55<54:42, 40.53s/trial, best loss: -0.502]
305
  20%|โ–ˆโ–ˆ | 20/100 [14:36<54:26, 40.83s/trial, best loss: -0.502]
306
  21%|โ–ˆโ–ˆ | 21/100 [15:25<57:02, 43.32s/trial, best loss: -0.502]
307
  22%|โ–ˆโ–ˆโ– | 22/100 [15:51<49:20, 37.95s/trial, best loss: -0.502]
308
  23%|โ–ˆโ–ˆโ–Ž | 23/100 [16:26<47:50, 37.28s/trial, best loss: -0.502]
309
  24%|โ–ˆโ–ˆโ– | 24/100 [16:53<43:12, 34.11s/trial, best loss: -0.502]
310
  25%|โ–ˆโ–ˆโ–Œ | 25/100 [17:17<38:47, 31.04s/trial, best loss: -0.502]
311
  26%|โ–ˆโ–ˆโ–Œ | 26/100 [17:53<39:57, 32.41s/trial, best loss: -0.502]
312
  27%|โ–ˆโ–ˆโ–‹ | 27/100 [18:24<39:06, 32.14s/trial, best loss: -0.502]
313
  28%|โ–ˆโ–ˆโ–Š | 28/100 [19:03<40:56, 34.12s/trial, best loss: -0.502]
314
  29%|โ–ˆโ–ˆโ–‰ | 29/100 [19:45<43:05, 36.42s/trial, best loss: -0.5029]
315
  30%|โ–ˆโ–ˆโ–ˆ | 30/100 [20:21<42:37, 36.54s/trial, best loss: -0.5029]
316
  31%|โ–ˆโ–ˆโ–ˆ | 31/100 [20:55<40:57, 35.62s/trial, best loss: -0.5029]
317
  32%|โ–ˆโ–ˆโ–ˆโ– | 32/100 [21:32<40:42, 35.92s/trial, best loss: -0.5029]
318
  33%|โ–ˆโ–ˆโ–ˆโ–Ž | 33/100 [22:06<39:42, 35.55s/trial, best loss: -0.5029]
319
  34%|โ–ˆโ–ˆโ–ˆโ– | 34/100 [22:48<41:01, 37.30s/trial, best loss: -0.5029]
320
  35%|โ–ˆโ–ˆโ–ˆโ–Œ | 35/100 [23:25<40:19, 37.23s/trial, best loss: -0.5029]
321
  36%|โ–ˆโ–ˆโ–ˆโ–Œ | 36/100 [24:00<38:58, 36.54s/trial, best loss: -0.5029]
322
  37%|โ–ˆโ–ˆโ–ˆโ–‹ | 37/100 [24:24<34:28, 32.83s/trial, best loss: -0.5029]
323
  38%|โ–ˆโ–ˆโ–ˆโ–Š | 38/100 [24:57<34:06, 33.01s/trial, best loss: -0.5029]
324
  39%|โ–ˆโ–ˆโ–ˆโ–‰ | 39/100 [25:44<37:50, 37.22s/trial, best loss: -0.5029]
325
  40%|โ–ˆโ–ˆโ–ˆโ–ˆ | 40/100 [26:30<39:40, 39.68s/trial, best loss: -0.5029]
326
  41%|โ–ˆโ–ˆโ–ˆโ–ˆ | 41/100 [27:20<42:07, 42.84s/trial, best loss: -0.5029]
327
  42%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 42/100 [27:51<38:06, 39.41s/trial, best loss: -0.5029]
328
  43%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 43/100 [28:15<33:02, 34.79s/trial, best loss: -0.5029]
329
  44%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 44/100 [29:30<43:38, 46.75s/trial, best loss: -0.5029]
330
  45%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 45/100 [30:15<42:20, 46.19s/trial, best loss: -0.5029]
331
  46%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 46/100 [30:53<39:26, 43.82s/trial, best loss: -0.5029]
332
  47%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 47/100 [31:15<32:57, 37.32s/trial, best loss: -0.5029]
333
  48%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 48/100 [31:43<29:44, 34.32s/trial, best loss: -0.5029]
334
  49%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 49/100 [32:11<27:32, 32.40s/trial, best loss: -0.5029]
335
  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 50/100 [32:38<25:52, 31.05s/trial, best loss: -0.5029]
336
  51%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 51/100 [33:21<28:12, 34.55s/trial, best loss: -0.5029]
337
  52%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 52/100 [33:56<27:48, 34.77s/trial, best loss: -0.5029]
338
  53%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 53/100 [34:35<28:10, 35.98s/trial, best loss: -0.5029]
339
  54%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 54/100 [35:06<26:20, 34.36s/trial, best loss: -0.5029]
340
  55%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 55/100 [35:38<25:22, 33.84s/trial, best loss: -0.5029]
341
  56%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 56/100 [36:30<28:49, 39.30s/trial, best loss: -0.5029]
342
  57%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 57/100 [37:21<30:29, 42.55s/trial, best loss: -0.5029]
343
  58%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 58/100 [38:01<29:24, 42.00s/trial, best loss: -0.5029]
344
  59%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 59/100 [38:39<27:43, 40.57s/trial, best loss: -0.5029]
345
  60%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 60/100 [39:17<26:36, 39.92s/trial, best loss: -0.5029]
346
  61%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 61/100 [40:33<33:02, 50.83s/trial, best loss: -0.5029]
347
  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 62/100 [41:01<27:54, 44.05s/trial, best loss: -0.5029]
348
  63%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 63/100 [41:30<24:15, 39.33s/trial, best loss: -0.5029]
349
  64%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 64/100 [42:06<22:58, 38.29s/trial, best loss: -0.5029]
350
  65%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 65/100 [42:37<21:10, 36.30s/trial, best loss: -0.5029]
351
  66%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 66/100 [43:07<19:29, 34.39s/trial, best loss: -0.5029]
352
  67%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 67/100 [43:41<18:52, 34.31s/trial, best loss: -0.5029]
353
  68%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 68/100 [44:11<17:29, 32.80s/trial, best loss: -0.5029]
354
  69%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 69/100 [44:39<16:10, 31.32s/trial, best loss: -0.5029]
355
  70%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 70/100 [45:18<16:51, 33.72s/trial, best loss: -0.5029]
356
  71%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 71/100 [46:03<17:59, 37.22s/trial, best loss: -0.5029]
357
  72%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 72/100 [46:37<16:54, 36.22s/trial, best loss: -0.5029]
358
  73%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 73/100 [47:05<15:07, 33.61s/trial, best loss: -0.5029]
359
  74%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 74/100 [47:28<13:13, 30.51s/trial, best loss: -0.5029]
360
  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 75/100 [48:09<14:03, 33.75s/trial, best loss: -0.5029]
361
  76%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 76/100 [48:34<12:28, 31.19s/trial, best loss: -0.5029]
362
  77%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 77/100 [49:12<12:40, 33.05s/trial, best loss: -0.5029]
363
  78%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 78/100 [49:46<12:17, 33.50s/trial, best loss: -0.5029]
364
  79%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 79/100 [50:25<12:18, 35.15s/trial, best loss: -0.5029]
365
  80%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 80/100 [51:02<11:49, 35.46s/trial, best loss: -0.5029]
366
  81%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 81/100 [52:07<14:07, 44.61s/trial, best loss: -0.5029]
367
  82%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 82/100 [52:39<12:13, 40.76s/trial, best loss: -0.5029]
368
  83%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 83/100 [53:41<13:21, 47.14s/trial, best loss: -0.5029]
369
  84%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 84/100 [54:31<12:47, 47.94s/trial, best loss: -0.5029]
370
  85%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 85/100 [54:54<10:06, 40.42s/trial, best loss: -0.5029]
371
  86%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 86/100 [55:25<08:46, 37.60s/trial, best loss: -0.5029]
372
  87%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 87/100 [55:54<07:35, 35.01s/trial, best loss: -0.5029]
373
  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 88/100 [56:45<07:56, 39.74s/trial, best loss: -0.5029]
374
  89%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 89/100 [57:25<07:18, 39.87s/trial, best loss: -0.5029]
375
  90%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 90/100 [58:02<06:31, 39.12s/trial, best loss: -0.5029]
376
  91%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 91/100 [58:38<05:42, 38.08s/trial, best loss: -0.5029]
377
  92%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 92/100 [59:05<04:39, 34.90s/trial, best loss: -0.5029]
378
  93%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž| 93/100 [1:00:12<05:10, 44.39s/trial, best loss: -0.5029]
379
  94%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 94/100 [1:00:53<04:19, 43.29s/trial, best loss: -0.5029]
380
  95%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ| 95/100 [1:01:48<03:54, 46.95s/trial, best loss: -0.5029]
381
  96%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ| 96/100 [1:02:42<03:16, 49.08s/trial, best loss: -0.5029]
382
  97%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹| 97/100 [1:03:52<02:46, 55.36s/trial, best loss: -0.5029]
383
  98%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š| 98/100 [1:04:30<01:39, 49.96s/trial, best loss: -0.5029]
384
  99%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰| 99/100 [1:05:12<00:47, 47.59s/trial, best loss: -0.5029]
385
+
386
+ ์ตœ์ ํ™” ์™„๋ฃŒ. ์ตœ์  ํŒŒ๋ผ๋ฏธํ„ฐ: {'colsample_bytree': 0.7816067762051363, 'gamma': 0.5799629095615334, 'learning_rate': 0.06287412401679013, 'max_depth': 3.0, 'min_child_weight': 5.0, 'reg_alpha': 0.36731169488772253, 'reg_lambda': 0.03192020366519255, 'subsample': 0.6004605601176048}
387
+ ์ตœ์  CSI ์ ์ˆ˜: 0.5029 (loss: -0.5029)
388
+
389
+ ์ตœ์ ํ™” ๊ณผ์ • ์š”์•ฝ:
390
+ - ์ด ์‹œ๋„ ํšŸ์ˆ˜: 100
391
+ - ์„ฑ๊ณตํ•œ ์‹œ๋„: 100
392
+ - ์ตœ์ดˆ CSI: 0.4839
393
+ - ์ตœ์ข… CSI: 0.4873
394
+ - ์ตœ๊ณ  CSI: 0.5029
395
+ - ์ตœ์ € CSI: 0.4796
396
+ - ํ‰๊ท  CSI: 0.4918
397
+
398
+ ์ตœ์ ํ™” Trials ๊ฐ์ฒด๊ฐ€ /workspace/visibility_prediction/Analysis_code/optimization_history/xgb_ctgan10000_daejeon_trials.pkl์— ์ €์žฅ๋˜์—ˆ์Šต๋‹ˆ๋‹ค.
399
+ ์ตœ์ข… ๋ชจ๋ธ ํ•™์Šต ์‹œ์ž‘...
400
+ Fold 1 ํ•™์Šต ์ค‘... (ํ•™์Šต ์—ฐ๋„: [2018, 2019], ๊ฒ€์ฆ ์—ฐ๋„: 2020)
401
+ Fold 1 ๊ฒ€์ฆ CSI: 0.4534
402
+ Fold 2 ํ•™์Šต ์ค‘... (ํ•™์Šต ์—ฐ๋„: [2018, 2020], ๊ฒ€์ฆ ์—ฐ๋„: 2019)
403
+ Fold 2 ๊ฒ€์ฆ CSI: 0.4712
404
+ Fold 3 ํ•™์Šต ์ค‘... (ํ•™์Šต ์—ฐ๋„: [2019, 2020], ๊ฒ€์ฆ ์—ฐ๋„: 2018)
405
+ Fold 3 ๊ฒ€์ฆ CSI: 0.5842
406
+ ๋ชจ๋ธ ์ €์žฅ ์ค‘...
407
+ ๋ชจ๋ธ์ด /workspace/visibility_prediction/Analysis_code/save_model/xgb_optima/xgb_ctgan10000_daejeon.pkl์— ์ €์žฅ๋˜์—ˆ์Šต๋‹ˆ๋‹ค.
408
+
409
+ โœ“ ์™„๋ฃŒ: xgb_ctgan10000/XGB_ctgan10000_daejeon.py (์†Œ์š” ์‹œ๊ฐ„: 3996์ดˆ)
410
+
411
+ ----------------------------------------
412
+ ์‹คํ–‰ ์ค‘: xgb_ctgan10000/XGB_ctgan10000_gwangju.py
413
+ ์‹œ์ž‘ ์‹œ๊ฐ„: 2025-12-28 07:34:49
414
+ ----------------------------------------
415
+ ๋ฐ์ดํ„ฐ ๋กœ๋”ฉ ์ค‘...
416
+ ๋ฐ์ดํ„ฐ ์ „์ฒ˜๋ฆฌ ์ค‘...
417
+ ํ•˜์ดํผํŒŒ๋ผ๋ฏธํ„ฐ ์ตœ์ ํ™” ์‹œ์ž‘...
418
+
419
  0%| | 0/100 [00:00<?, ?trial/s, best loss=?]
420
  1%| | 1/100 [00:25<41:41, 25.27s/trial, best loss: -0.4941]
421
  2%|โ– | 2/100 [01:28<1:17:46, 47.61s/trial, best loss: -0.4941]
422
  3%|โ–Ž | 3/100 [02:09<1:11:52, 44.46s/trial, best loss: -0.4941]
423
  4%|โ– | 4/100 [03:21<1:28:25, 55.27s/trial, best loss: -0.4941]
424
  5%|โ–Œ | 5/100 [04:15<1:26:54, 54.89s/trial, best loss: -0.4941]
425
  6%|โ–Œ | 6/100 [04:47<1:14:05, 47.29s/trial, best loss: -0.4941]
426
  7%|โ–‹ | 7/100 [05:30<1:11:03, 45.85s/trial, best loss: -0.4941]
427
  8%|โ–Š | 8/100 [06:17<1:10:33, 46.01s/trial, best loss: -0.4941]
428
  9%|โ–‰ | 9/100 [06:38<58:16, 38.42s/trial, best loss: -0.4941]
429
  10%|โ–ˆ | 10/100 [07:21<59:33, 39.70s/trial, best loss: -0.4941]
430
  11%|โ–ˆ | 11/100 [08:11<1:03:31, 42.82s/trial, best loss: -0.4941]
431
  12%|โ–ˆโ– | 12/100 [08:40<56:37, 38.61s/trial, best loss: -0.4941]
432
  13%|โ–ˆโ–Ž | 13/100 [09:29<1:00:31, 41.74s/trial, best loss: -0.4941]
433
  14%|โ–ˆโ– | 14/100 [09:52<51:46, 36.12s/trial, best loss: -0.4941]
434
  15%|โ–ˆโ–Œ | 15/100 [10:31<52:22, 36.96s/trial, best loss: -0.4941]
435
  16%|โ–ˆโ–Œ | 16/100 [11:05<50:37, 36.16s/trial, best loss: -0.4941]
436
  17%|โ–ˆโ–‹ | 17/100 [12:46<1:16:56, 55.62s/trial, best loss: -0.4941]
437
  18%|โ–ˆโ–Š | 18/100 [13:14<1:04:51, 47.46s/trial, best loss: -0.4941]
438
  19%|โ–ˆโ–‰ | 19/100 [13:50<59:23, 44.00s/trial, best loss: -0.4941]
439
  20%|โ–ˆโ–ˆ | 20/100 [14:43<1:02:07, 46.59s/trial, best loss: -0.4941]
440
  21%|โ–ˆโ–ˆ | 21/100 [15:08<52:40, 40.00s/trial, best loss: -0.4941]
441
  22%|โ–ˆโ–ˆโ– | 22/100 [15:46<51:25, 39.56s/trial, best loss: -0.4941]
442
  23%|โ–ˆโ–ˆโ–Ž | 23/100 [16:16<47:05, 36.70s/trial, best loss: -0.4975]
443
  24%|โ–ˆโ–ˆโ– | 24/100 [16:56<47:48, 37.75s/trial, best loss: -0.4975]
444
  25%|โ–ˆโ–ˆโ–Œ | 25/100 [17:26<44:15, 35.41s/trial, best loss: -0.4975]
445
  26%|โ–ˆโ–ˆโ–Œ | 26/100 [17:53<40:27, 32.81s/trial, best loss: -0.4975]
446
  27%|โ–ˆโ–ˆโ–‹ | 27/100 [18:16<36:21, 29.89s/trial, best loss: -0.4975]
447
  28%|โ–ˆโ–ˆโ–Š | 28/100 [18:58<40:12, 33.50s/trial, best loss: -0.4975]
448
  29%|โ–ˆโ–ˆโ–‰ | 29/100 [19:58<48:53, 41.32s/trial, best loss: -0.4975]
449
  30%|โ–ˆโ–ˆโ–ˆ | 30/100 [20:29<44:54, 38.49s/trial, best loss: -0.4975]
450
  31%|โ–ˆโ–ˆโ–ˆ | 31/100 [21:09<44:27, 38.66s/trial, best loss: -0.4975]
451
  32%|โ–ˆโ–ˆโ–ˆโ– | 32/100 [21:48<44:08, 38.94s/trial, best loss: -0.4991]
452
  33%|โ–ˆโ–ˆโ–ˆโ–Ž | 33/100 [22:18<40:26, 36.21s/trial, best loss: -0.4991]
453
  34%|โ–ˆโ–ˆโ–ˆโ– | 34/100 [22:47<37:32, 34.13s/trial, best loss: -0.4991]
454
  35%|โ–ˆโ–ˆโ–ˆโ–Œ | 35/100 [23:14<34:32, 31.88s/trial, best loss: -0.4991]
455
  36%|โ–ˆโ–ˆโ–ˆโ–Œ | 36/100 [23:39<31:40, 29.70s/trial, best loss: -0.4991]
456
  37%|โ–ˆโ–ˆโ–ˆโ–‹ | 37/100 [24:20<34:47, 33.13s/trial, best loss: -0.4991]
457
  38%|โ–ˆโ–ˆโ–ˆโ–Š | 38/100 [24:54<34:35, 33.47s/trial, best loss: -0.4991]
458
  39%|โ–ˆโ–ˆโ–ˆโ–‰ | 39/100 [25:26<33:35, 33.05s/trial, best loss: -0.4991]
459
  40%|โ–ˆโ–ˆโ–ˆโ–ˆ | 40/100 [26:03<34:11, 34.19s/trial, best loss: -0.4991]
460
  41%|โ–ˆโ–ˆโ–ˆโ–ˆ | 41/100 [26:45<35:55, 36.54s/trial, best loss: -0.4991]
461
  42%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 42/100 [27:12<32:38, 33.76s/trial, best loss: -0.4991]
462
  43%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 43/100 [28:18<41:16, 43.45s/trial, best loss: -0.4991]
463
  44%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 44/100 [28:46<36:11, 38.77s/trial, best loss: -0.4991]
464
  45%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 45/100 [29:38<39:08, 42.71s/trial, best loss: -0.4991]
465
  46%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 46/100 [30:24<39:16, 43.64s/trial, best loss: -0.4991]
466
  47%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 47/100 [30:48<33:24, 37.83s/trial, best loss: -0.4991]
467
  48%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 48/100 [31:18<30:43, 35.45s/trial, best loss: -0.4991]
468
  49%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 49/100 [32:28<38:51, 45.71s/trial, best loss: -0.4991]
469
  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 50/100 [32:56<33:50, 40.60s/trial, best loss: -0.4991]
470
  51%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 51/100 [33:45<35:11, 43.09s/trial, best loss: -0.4991]
471
  52%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 52/100 [34:45<38:28, 48.10s/trial, best loss: -0.4991]
472
  53%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 53/100 [35:06<31:25, 40.11s/trial, best loss: -0.4991]
473
  54%|โ–ˆ๏ฟฝ๏ฟฝ๏ฟฝโ–ˆโ–ˆโ–ˆโ– | 54/100 [35:50<31:31, 41.13s/trial, best loss: -0.4991]
474
  55%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 55/100 [36:31<30:51, 41.15s/trial, best loss: -0.4991]
475
  56%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 56/100 [36:51<25:32, 34.83s/trial, best loss: -0.4991]
476
  57%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 57/100 [37:30<25:48, 36.00s/trial, best loss: -0.4991]
477
  58%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 58/100 [38:18<27:43, 39.60s/trial, best loss: -0.4991]
478
  59%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 59/100 [38:42<23:51, 34.91s/trial, best loss: -0.4991]
479
  60%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 60/100 [39:10<21:51, 32.80s/trial, best loss: -0.4991]
480
  61%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 61/100 [40:10<26:39, 41.02s/trial, best loss: -0.4991]
481
  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 62/100 [40:54<26:28, 41.80s/trial, best loss: -0.4991]
482
  63%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 63/100 [41:14<21:46, 35.32s/trial, best loss: -0.4991]
483
  64%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 64/100 [41:41<19:48, 33.02s/trial, best loss: -0.4991]
484
  65%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 65/100 [42:14<19:07, 32.80s/trial, best loss: -0.4991]
485
  66%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 66/100 [42:50<19:10, 33.83s/trial, best loss: -0.4991]
486
  67%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 67/100 [43:20<18:03, 32.84s/trial, best loss: -0.4991]
487
  68%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 68/100 [43:49<16:47, 31.49s/trial, best loss: -0.4991]
488
  69%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 69/100 [44:17<15:43, 30.42s/trial, best loss: -0.4991]
489
  70%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 70/100 [44:43<14:36, 29.21s/trial, best loss: -0.4991]
490
  71%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 71/100 [45:10<13:43, 28.40s/trial, best loss: -0.4991]
491
  72%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 72/100 [45:32<12:25, 26.64s/trial, best loss: -0.4991]
492
  73%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 73/100 [46:05<12:50, 28.55s/trial, best loss: -0.4991]
493
  74%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 74/100 [46:38<12:53, 29.74s/trial, best loss: -0.4991]
494
  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 75/100 [47:08<12:28, 29.93s/trial, best loss: -0.4991]
495
  76%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 76/100 [47:36<11:40, 29.19s/trial, best loss: -0.4999]
496
  77%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 77/100 [47:58<10:25, 27.18s/trial, best loss: -0.4999]
497
  78%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 78/100 [48:32<10:40, 29.13s/trial, best loss: -0.4999]
498
  79%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 79/100 [48:55<09:34, 27.34s/trial, best loss: -0.4999]
499
  80%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 80/100 [49:24<09:18, 27.92s/trial, best loss: -0.4999]
500
  81%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 81/100 [49:43<07:58, 25.18s/trial, best loss: -0.4999]
501
  82%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 82/100 [50:03<07:03, 23.55s/trial, best loss: -0.4999]
502
  83%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 83/100 [50:25<06:35, 23.24s/trial, best loss: -0.4999]
503
  84%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 84/100 [50:55<06:41, 25.11s/trial, best loss: -0.4999]
504
  85%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 85/100 [51:15<05:57, 23.82s/trial, best loss: -0.4999]
505
  86%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 86/100 [52:06<07:24, 31.75s/trial, best loss: -0.4999]
506
  87%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 87/100 [52:29<06:20, 29.29s/trial, best loss: -0.4999]
507
  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 88/100 [52:56<05:42, 28.56s/trial, best loss: -0.4999]
508
  89%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 89/100 [53:27<05:23, 29.39s/trial, best loss: -0.4999]
509
  90%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 90/100 [53:55<04:47, 28.75s/trial, best loss: -0.4999]
510
  91%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 91/100 [54:28<04:30, 30.04s/trial, best loss: -0.4999]
511
  92%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 92/100 [55:22<04:58, 37.30s/trial, best loss: -0.4999]
512
  93%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž| 93/100 [56:11<04:45, 40.74s/trial, best loss: -0.4999]
513
  94%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 94/100 [56:39<03:41, 36.98s/trial, best loss: -0.4999]
514
  95%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ| 95/100 [57:03<02:44, 32.98s/trial, best loss: -0.4999]
515
  96%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ| 96/100 [57:33<02:08, 32.24s/trial, best loss: -0.4999]
516
  97%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹| 97/100 [57:51<01:23, 27.84s/trial, best loss: -0.4999]
517
  98%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š| 98/100 [58:14<00:52, 26.39s/trial, best loss: -0.4999]
518
  99%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰| 99/100 [58:35<00:24, 24.80s/trial, best loss: -0.4999]
519
+
520
+ ์ตœ์ ํ™” ์™„๋ฃŒ. ์ตœ์  ํŒŒ๋ผ๋ฏธํ„ฐ: {'colsample_bytree': 0.9825715751506052, 'gamma': 0.029399796024525915, 'learning_rate': 0.08575762330828458, 'max_depth': 11.0, 'min_child_weight': 8.0, 'reg_alpha': 0.8534545581720909, 'reg_lambda': 0.43478744549007325, 'subsample': 0.7629247503643918}
521
+ ์ตœ์  CSI ์ ์ˆ˜: 0.4999 (loss: -0.4999)
522
+
523
+ ์ตœ์ ํ™” ๊ณผ์ • ์š”์•ฝ:
524
+ - ์ด ์‹œ๋„ ํšŸ์ˆ˜: 100
525
+ - ์„ฑ๊ณตํ•œ ์‹œ๋„: 100
526
+ - ์ตœ์ดˆ CSI: 0.4941
527
+ - ์ตœ์ข… CSI: 0.4935
528
+ - ์ตœ๊ณ  CSI: 0.4999
529
+ - ์ตœ์ € CSI: 0.4364
530
+ - ํ‰๊ท  CSI: 0.4867
531
+
532
+ ์ตœ์ ํ™” Trials ๊ฐ์ฒด๊ฐ€ /workspace/visibility_prediction/Analysis_code/optimization_history/xgb_ctgan10000_gwangju_trials.pkl์— ์ €์žฅ๋˜์—ˆ์Šต๋‹ˆ๋‹ค.
533
+ ์ตœ์ข… ๋ชจ๋ธ ํ•™์Šต ์‹œ์ž‘...
534
+ Fold 1 ํ•™์Šต ์ค‘... (ํ•™์Šต ์—ฐ๋„: [2018, 2019], ๊ฒ€์ฆ ์—ฐ๋„: 2020)
535
+ Fold 1 ๊ฒ€์ฆ CSI: 0.4102
536
+ Fold 2 ํ•™์Šต ์ค‘... (ํ•™์Šต ์—ฐ๋„: [2018, 2020], ๊ฒ€์ฆ ์—ฐ๋„: 2019)
537
+ Fold 2 ๊ฒ€์ฆ CSI: 0.5658
538
+ Fold 3 ํ•™์Šต ์ค‘... (ํ•™์Šต ์—ฐ๋„: [2019, 2020], ๊ฒ€์ฆ ์—ฐ๋„: 2018)
539
+ Fold 3 ๊ฒ€์ฆ CSI: 0.5239
540
+ ๋ชจ๋ธ ์ €์žฅ ์ค‘...
541
+ ๋ชจ๋ธ์ด /workspace/visibility_prediction/Analysis_code/save_model/xgb_optima/xgb_ctgan10000_gwangju.pkl์— ์ €์žฅ๋˜์—ˆ์Šต๋‹ˆ๋‹ค.
542
+
543
+ โœ“ ์™„๋ฃŒ: xgb_ctgan10000/XGB_ctgan10000_gwangju.py (์†Œ์š” ์‹œ๊ฐ„: 3571์ดˆ)
544
+
545
+ ----------------------------------------
546
+ ์‹คํ–‰ ์ค‘: xgb_ctgan10000/XGB_ctgan10000_incheon.py
547
+ ์‹œ์ž‘ ์‹œ๊ฐ„: 2025-12-28 08:34:20
548
+ ----------------------------------------
549
+ ๋ฐ์ดํ„ฐ ๋กœ๋”ฉ ์ค‘...
550
+ ๋ฐ์ดํ„ฐ ์ „์ฒ˜๋ฆฌ ์ค‘...
551
+ ํ•˜์ดํผํŒŒ๋ผ๋ฏธํ„ฐ ์ตœ์ ํ™” ์‹œ์ž‘...
552
+
553
  0%| | 0/100 [00:00<?, ?trial/s, best loss=?]
554
  1%| | 1/100 [00:20<34:14, 20.76s/trial, best loss: -0.5632]
555
  2%|โ– | 2/100 [00:37<30:03, 18.41s/trial, best loss: -0.5632]
556
  3%|โ–Ž | 3/100 [01:03<35:30, 21.96s/trial, best loss: -0.5632]
557
  4%|โ– | 4/100 [01:29<37:51, 23.66s/trial, best loss: -0.5632]
558
  5%|โ–Œ | 5/100 [01:52<36:56, 23.33s/trial, best loss: -0.5632]
559
  6%|โ–Œ | 6/100 [02:47<53:33, 34.18s/trial, best loss: -0.5632]
560
  7%|โ–‹ | 7/100 [03:23<53:40, 34.62s/trial, best loss: -0.5633]
561
  8%|โ–Š | 8/100 [04:16<1:01:57, 40.41s/trial, best loss: -0.5633]
562
  9%|โ–‰ | 9/100 [04:34<50:47, 33.49s/trial, best loss: -0.5633]
563
  10%|โ–ˆ | 10/100 [05:16<54:10, 36.11s/trial, best loss: -0.5633]
564
  11%|โ–ˆ | 11/100 [05:43<49:17, 33.23s/trial, best loss: -0.5633]
565
  12%|โ–ˆโ– | 12/100 [06:37<57:55, 39.49s/trial, best loss: -0.5633]
566
  13%|โ–ˆโ–Ž | 13/100 [07:17<57:38, 39.75s/trial, best loss: -0.5633]
567
  14%|โ–ˆโ– | 14/100 [07:53<55:28, 38.71s/trial, best loss: -0.5633]
568
  15%|โ–ˆโ–Œ | 15/100 [08:29<53:39, 37.87s/trial, best loss: -0.5633]
569
  16%|โ–ˆโ–Œ | 16/100 [08:55<47:53, 34.21s/trial, best loss: -0.5633]
570
  17%|โ–ˆโ–‹ | 17/100 [09:19<42:58, 31.06s/trial, best loss: -0.5633]
571
  18%|โ–ˆโ–Š | 18/100 [10:25<56:45, 41.54s/trial, best loss: -0.5633]
572
  19%|โ–ˆโ–‰ | 19/100 [10:47<48:32, 35.95s/trial, best loss: -0.5633]
573
  20%|โ–ˆโ–ˆ | 20/100 [11:12<43:15, 32.45s/trial, best loss: -0.5633]
574
  21%|โ–ˆโ–ˆ | 21/100 [11:35<39:02, 29.65s/trial, best loss: -0.5633]
575
  22%|โ–ˆโ–ˆโ– | 22/100 [11:55<34:38, 26.64s/trial, best loss: -0.5633]
576
  23%|โ–ˆโ–ˆโ–Ž | 23/100 [12:16<32:13, 25.11s/trial, best loss: -0.5633]
577
  24%|โ–ˆโ–ˆโ– | 24/100 [12:47<33:55, 26.78s/trial, best loss: -0.5633]
578
  25%|โ–ˆโ–ˆโ–Œ | 25/100 [13:49<46:58, 37.58s/trial, best loss: -0.5633]
579
  26%|โ–ˆโ–ˆโ–Œ | 26/100 [14:16<42:20, 34.33s/trial, best loss: -0.5633]
580
  27%|โ–ˆโ–ˆโ–‹ | 27/100 [14:45<39:33, 32.51s/trial, best loss: -0.5633]
581
  28%|โ–ˆโ–ˆโ–Š | 28/100 [15:10<36:39, 30.55s/trial, best loss: -0.5633]
582
  29%|โ–ˆโ–ˆโ–‰ | 29/100 [15:42<36:29, 30.84s/trial, best loss: -0.5633]
583
  30%|โ–ˆโ–ˆโ–ˆ | 30/100 [16:04<32:59, 28.27s/trial, best loss: -0.5633]
584
  31%|โ–ˆโ–ˆโ–ˆ | 31/100 [16:38<34:23, 29.91s/trial, best loss: -0.5645]
585
  32%|โ–ˆโ–ˆโ–ˆโ– | 32/100 [17:22<38:46, 34.21s/trial, best loss: -0.5706]
586
  33%|โ–ˆโ–ˆโ–ˆโ–Ž | 33/100 [18:15<44:24, 39.76s/trial, best loss: -0.5706]
587
  34%|โ–ˆโ–ˆโ–ˆโ– | 34/100 [19:01<45:49, 41.65s/trial, best loss: -0.5706]
588
  35%|โ–ˆโ–ˆโ–ˆโ–Œ | 35/100 [19:35<42:44, 39.45s/trial, best loss: -0.5714]
589
  36%|โ–ˆโ–ˆโ–ˆโ–Œ | 36/100 [20:19<43:18, 40.60s/trial, best loss: -0.5714]
590
  37%|โ–ˆโ–ˆโ–ˆโ–‹ | 37/100 [20:54<40:58, 39.02s/trial, best loss: -0.5728]
591
  38%|โ–ˆโ–ˆโ–ˆโ–Š | 38/100 [21:20<36:23, 35.21s/trial, best loss: -0.5728]
592
  39%|โ–ˆโ–ˆโ–ˆโ–‰ | 39/100 [22:31<46:32, 45.77s/trial, best loss: -0.5728]
593
  40%|โ–ˆโ–ˆโ–ˆโ–ˆ | 40/100 [23:00<40:50, 40.84s/trial, best loss: -0.5728]
594
  41%|โ–ˆโ–ˆโ–ˆโ–ˆ | 41/100 [23:50<42:55, 43.65s/trial, best loss: -0.5728]
595
  42%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 42/100 [24:25<39:33, 40.92s/trial, best loss: -0.5728]
596
  43%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 43/100 [25:12<40:33, 42.68s/trial, best loss: -0.5728]
597
  44%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 44/100 [25:44<36:53, 39.53s/trial, best loss: -0.5728]
598
  45%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 45/100 [26:27<37:07, 40.50s/trial, best loss: -0.5728]
599
  46%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 46/100 [26:55<33:11, 36.89s/trial, best loss: -0.5728]
600
  47%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 47/100 [27:29<31:48, 36.00s/trial, best loss: -0.5752]
601
  48%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 48/100 [28:12<32:56, 38.02s/trial, best loss: -0.5752]
602
  49%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 49/100 [29:03<35:42, 42.00s/trial, best loss: -0.5752]
603
  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 50/100 [29:44<34:41, 41.64s/trial, best loss: -0.5752]
604
  51%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 51/100 [30:31<35:24, 43.36s/trial, best loss: -0.5752]
605
  52%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 52/100 [31:10<33:37, 42.03s/trial, best loss: -0.5752]
606
  53%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 53/100 [32:15<38:25, 49.04s/trial, best loss: -0.5752]
607
  54%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 54/100 [33:01<36:43, 47.91s/trial, best loss: -0.5752]
608
  55%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 55/100 [33:49<36:06, 48.15s/trial, best loss: -0.5752]
609
  56%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 56/100 [34:14<30:07, 41.07s/trial, best loss: -0.5752]
610
  57%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 57/100 [35:00<30:34, 42.67s/trial, best loss: -0.5752]
611
  58%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 58/100 [35:40<29:10, 41.68s/trial, best loss: -0.5752]
612
  59%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 59/100 [36:03<24:48, 36.30s/trial, best loss: -0.5752]
613
  60%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 60/100 [36:36<23:29, 35.23s/trial, best loss: -0.5752]
614
  61%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 61/100 [37:05<21:41, 33.38s/trial, best loss: -0.5752]
615
  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 62/100 [37:54<24:06, 38.07s/trial, best loss: -0.5752]
616
  63%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 63/100 [38:44<25:39, 41.62s/trial, best loss: -0.5752]
617
  64%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 64/100 [39:31<25:51, 43.10s/trial, best loss: -0.5752]
618
  65%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 65/100 [40:19<26:01, 44.62s/trial, best loss: -0.5752]
619
  66%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 66/100 [40:58<24:23, 43.04s/trial, best loss: -0.5752]
620
  67%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 67/100 [41:51<25:12, 45.84s/trial, best loss: -0.5752]
621
  68%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 68/100 [42:34<24:06, 45.19s/trial, best loss: -0.5752]
622
  69%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 69/100 [43:11<22:05, 42.75s/trial, best loss: -0.5752]
623
  70%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 70/100 [43:52<20:59, 41.99s/trial, best loss: -0.5752]
624
  71%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 71/100 [44:35<20:27, 42.32s/trial, best loss: -0.5752]
625
  72%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 72/100 [44:58<17:02, 36.50s/trial, best loss: -0.5752]
626
  73%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 73/100 [45:17<14:03, 31.24s/trial, best loss: -0.5752]
627
  74%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 74/100 [45:58<14:54, 34.42s/trial, best loss: -0.5752]
628
  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 75/100 [46:29<13:49, 33.19s/trial, best loss: -0.5752]
629
  76%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 76/100 [46:50<11:49, 29.56s/trial, best loss: -0.5752]
630
  77%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 77/100 [47:37<13:24, 34.96s/trial, best loss: -0.5752]
631
  78%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 78/100 [48:10<12:32, 34.23s/trial, best loss: -0.5752]
632
  79%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 79/100 [48:29<10:21, 29.59s/trial, best loss: -0.5752]
633
  80%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 80/100 [48:48<08:47, 26.39s/trial, best loss: -0.5752]
634
  81%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 81/100 [49:21<09:03, 28.62s/trial, best loss: -0.5752]
635
  82%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 82/100 [50:05<09:58, 33.23s/trial, best loss: -0.5752]
636
  83%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 83/100 [50:31<08:45, 30.90s/trial, best loss: -0.5752]
637
  84%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 84/100 [51:08<08:44, 32.80s/trial, best loss: -0.5752]
638
  85%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 85/100 [51:39<08:03, 32.23s/trial, best loss: -0.5752]
639
  86%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 86/100 [52:06<07:07, 30.56s/trial, best loss: -0.5752]
640
  87%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 87/100 [52:34<06:26, 29.76s/trial, best loss: -0.5752]
641
  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 88/100 [54:13<10:08, 50.68s/trial, best loss: -0.5752]
642
  89%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 89/100 [54:46<08:17, 45.21s/trial, best loss: -0.5752]
643
  90%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 90/100 [55:12<06:34, 39.45s/trial, best loss: -0.5752]
644
  91%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 91/100 [55:50<05:53, 39.23s/trial, best loss: -0.5752]
645
  92%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 92/100 [56:14<04:35, 34.50s/trial, best loss: -0.5752]
646
  93%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž| 93/100 [56:38<03:40, 31.57s/trial, best loss: -0.5752]
647
  94%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 94/100 [57:13<03:14, 32.49s/trial, best loss: -0.5752]
648
  95%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ| 95/100 [57:49<02:47, 33.54s/trial, best loss: -0.5752]
649
  96%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ| 96/100 [58:46<02:42, 40.69s/trial, best loss: -0.5752]
650
  97%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹| 97/100 [59:20<01:55, 38.56s/trial, best loss: -0.5752]
651
  98%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š| 98/100 [59:58<01:16, 38.38s/trial, best loss: -0.5752]
652
  99%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰| 99/100 [1:00:25<00:35, 35.02s/trial, best loss: -0.5752]
653
+
654
+ ์ตœ์ ํ™” ์™„๋ฃŒ. ์ตœ์  ํŒŒ๋ผ๋ฏธํ„ฐ: {'colsample_bytree': 0.9876604099689714, 'gamma': 2.7259563165720655, 'learning_rate': 0.014353110732979967, 'max_depth': 5.0, 'min_child_weight': 8.0, 'reg_alpha': 0.43412935826888077, 'reg_lambda': 0.45790677460553664, 'subsample': 0.6390967315026312}
655
+ ์ตœ์  CSI ์ ์ˆ˜: 0.5752 (loss: -0.5752)
656
+
657
+ ์ตœ์ ํ™” ๊ณผ์ • ์š”์•ฝ:
658
+ - ์ด ์‹œ๋„ ํšŸ์ˆ˜: 100
659
+ - ์„ฑ๊ณตํ•œ ์‹œ๋„: 100
660
+ - ์ตœ์ดˆ CSI: 0.5632
661
+ - ์ตœ์ข… CSI: 0.5595
662
+ - ์ตœ๊ณ  CSI: 0.5752
663
+ - ์ตœ์ € CSI: 0.5385
664
+ - ํ‰๊ท  CSI: 0.5582
665
+
666
+ ์ตœ์ ํ™” Trials ๊ฐ์ฒด๊ฐ€ /workspace/visibility_prediction/Analysis_code/optimization_history/xgb_ctgan10000_incheon_trials.pkl์— ์ €์žฅ๋˜์—ˆ์Šต๋‹ˆ๋‹ค.
667
+ ์ตœ์ข… ๋ชจ๋ธ ํ•™์Šต ์‹œ์ž‘...
668
+ Fold 1 ํ•™์Šต ์ค‘... (ํ•™์Šต ์—ฐ๋„: [2018, 2019], ๊ฒ€์ฆ ์—ฐ๋„: 2020)
669
+ Fold 1 ๊ฒ€์ฆ CSI: 0.5292
670
+ Fold 2 ํ•™์Šต ์ค‘... (ํ•™์Šต ์—ฐ๋„: [2018, 2020], ๊ฒ€์ฆ ์—ฐ๋„: 2019)
671
+ Fold 2 ๊ฒ€์ฆ CSI: 0.6124
672
+ Fold 3 ํ•™์Šต ์ค‘... (ํ•™์Šต ์—ฐ๋„: [2019, 2020], ๊ฒ€์ฆ ์—ฐ๋„: 2018)
673
+ Fold 3 ๊ฒ€์ฆ CSI: 0.5840
674
+ ๋ชจ๋ธ ์ €์žฅ ์ค‘...
675
+ ๋ชจ๋ธ์ด /workspace/visibility_prediction/Analysis_code/save_model/xgb_optima/xgb_ctgan10000_incheon.pkl๏ฟฝ๏ฟฝ๏ฟฝ ์ €์žฅ๋˜์—ˆ์Šต๋‹ˆ๋‹ค.
676
+
677
+ โœ“ ์™„๋ฃŒ: xgb_ctgan10000/XGB_ctgan10000_incheon.py (์†Œ์š” ์‹œ๊ฐ„: 3691์ดˆ)
678
+
679
+ ----------------------------------------
680
+ ์‹คํ–‰ ์ค‘: xgb_ctgan10000/XGB_ctgan10000_seoul.py
681
+ ์‹œ์ž‘ ์‹œ๊ฐ„: 2025-12-28 09:35:51
682
+ ----------------------------------------
683
+ ๋ฐ์ดํ„ฐ ๋กœ๋”ฉ ์ค‘...
684
+ ๋ฐ์ดํ„ฐ ์ „์ฒ˜๋ฆฌ ์ค‘...
685
+ ํ•˜์ดํผํŒŒ๋ผ๋ฏธํ„ฐ ์ตœ์ ํ™” ์‹œ์ž‘...
686
+
687
  0%| | 0/100 [00:00<?, ?trial/s, best loss=?]
688
  1%| | 1/100 [00:26<44:04, 26.71s/trial, best loss: -0.5553]
689
  2%|โ– | 2/100 [01:25<1:14:19, 45.50s/trial, best loss: -0.5578]
690
  3%|โ–Ž | 3/100 [01:43<53:05, 32.84s/trial, best loss: -0.5642]
691
  4%|โ– | 4/100 [02:23<57:11, 35.74s/trial, best loss: -0.5722]
692
  5%|โ–Œ | 5/100 [03:14<1:05:13, 41.19s/trial, best loss: -0.5722]
693
  6%|โ–Œ | 6/100 [03:53<1:03:36, 40.60s/trial, best loss: -0.5722]
694
  7%|โ–‹ | 7/100 [04:34<1:03:04, 40.69s/trial, best loss: -0.5722]
695
  8%|โ–Š | 8/100 [05:56<1:22:33, 53.85s/trial, best loss: -0.5722]
696
  9%|โ–‰ | 9/100 [06:33<1:13:50, 48.69s/trial, best loss: -0.5722]
697
  10%|โ–ˆ | 10/100 [07:35<1:19:14, 52.83s/trial, best loss: -0.5722]
698
  11%|โ–ˆ | 11/100 [08:04<1:07:21, 45.41s/trial, best loss: -0.5722]
699
  12%|โ–ˆโ– | 12/100 [08:37<1:01:12, 41.74s/trial, best loss: -0.5722]
700
  13%|โ–ˆโ–Ž | 13/100 [09:20<1:00:55, 42.02s/trial, best loss: -0.5722]
701
  14%|โ–ˆโ– | 14/100 [09:48<53:56, 37.64s/trial, best loss: -0.5722]
702
  15%|โ–ˆโ–Œ | 15/100 [10:32<56:09, 39.64s/trial, best loss: -0.5722]
703
  16%|โ–ˆโ–Œ | 16/100 [10:50<46:20, 33.10s/trial, best loss: -0.5722]
704
  17%|โ–ˆโ–‹ | 17/100 [12:02<1:02:10, 44.95s/trial, best loss: -0.5722]
705
  18%|โ–ˆโ–Š | 18/100 [12:32<55:19, 40.49s/trial, best loss: -0.5733]
706
  19%|โ–ˆโ–‰ | 19/100 [13:24<59:17, 43.91s/trial, best loss: -0.5733]
707
  20%|โ–ˆโ–ˆ | 20/100 [13:59<54:50, 41.13s/trial, best loss: -0.5733]
708
  21%|โ–ˆโ–ˆ | 21/100 [14:32<51:00, 38.74s/trial, best loss: -0.5746]
709
  22%|โ–ˆโ–ˆโ– | 22/100 [15:02<47:06, 36.24s/trial, best loss: -0.5746]
710
  23%|โ–ˆโ–ˆโ–Ž | 23/100 [15:27<42:08, 32.83s/trial, best loss: -0.5746]
711
  24%|โ–ˆโ–ˆโ– | 24/100 [16:08<44:35, 35.20s/trial, best loss: -0.5755]
712
  25%|โ–ˆโ–ˆโ–Œ | 25/100 [16:32<39:49, 31.86s/trial, best loss: -0.5755]
713
  26%|โ–ˆโ–ˆโ–Œ | 26/100 [17:09<41:12, 33.42s/trial, best loss: -0.5755]
714
  27%|โ–ˆโ–ˆโ–‹ | 27/100 [17:38<38:48, 31.90s/trial, best loss: -0.5755]
715
  28%|โ–ˆโ–ˆโ–Š | 28/100 [18:12<39:05, 32.58s/trial, best loss: -0.5755]
716
  29%|โ–ˆโ–ˆโ–‰ | 29/100 [18:37<35:55, 30.36s/trial, best loss: -0.5755]
717
  30%|โ–ˆโ–ˆโ–ˆ | 30/100 [19:01<33:14, 28.50s/trial, best loss: -0.5755]
718
  31%|โ–ˆโ–ˆโ–ˆ | 31/100 [19:44<37:34, 32.68s/trial, best loss: -0.5755]
719
  32%|โ–ˆโ–ˆโ–ˆโ– | 32/100 [20:22<39:02, 34.45s/trial, best loss: -0.5756]
720
  33%|โ–ˆโ–ˆโ–ˆโ–Ž | 33/100 [21:26<48:30, 43.44s/trial, best loss: -0.5756]
721
  34%|โ–ˆโ–ˆโ–ˆโ– | 34/100 [22:10<47:57, 43.60s/trial, best loss: -0.5756]
722
  35%|โ–ˆโ–ˆโ–ˆโ–Œ | 35/100 [22:53<46:44, 43.14s/trial, best loss: -0.5765]
723
  36%|โ–ˆโ–ˆโ–ˆโ–Œ | 36/100 [23:22<41:39, 39.06s/trial, best loss: -0.5765]
724
  37%|โ–ˆโ–ˆโ–ˆโ–‹ | 37/100 [23:59<40:26, 38.52s/trial, best loss: -0.5765]
725
  38%|โ–ˆโ–ˆโ–ˆโ–Š | 38/100 [24:33<38:21, 37.12s/trial, best loss: -0.5765]
726
  39%|โ–ˆโ–ˆโ–ˆโ–‰ | 39/100 [24:59<34:25, 33.87s/trial, best loss: -0.5765]
727
  40%|โ–ˆโ–ˆโ–ˆโ–ˆ | 40/100 [25:43<36:46, 36.77s/trial, best loss: -0.5765]
728
  41%|โ–ˆโ–ˆโ–ˆโ–ˆ | 41/100 [26:10<33:16, 33.83s/trial, best loss: -0.5765]
729
  42%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 42/100 [26:48<33:59, 35.16s/trial, best loss: -0.5795]
730
  43%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 43/100 [27:34<36:30, 38.44s/trial, best loss: -0.5795]
731
  44%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 44/100 [28:07<34:18, 36.75s/trial, best loss: -0.5795]
732
  45%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 45/100 [29:03<38:56, 42.49s/trial, best loss: -0.5795]
733
  46%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 46/100 [30:11<45:07, 50.14s/trial, best loss: -0.5795]
734
  47%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 47/100 [30:41<38:58, 44.12s/trial, best loss: -0.5795]
735
  48%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 48/100 [31:09<34:00, 39.25s/trial, best loss: -0.5795]
736
  49%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 49/100 [31:36<30:15, 35.60s/trial, best loss: -0.5795]
737
  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 50/100 [32:00<26:38, 31.96s/trial, best loss: -0.5795]
738
  51%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 51/100 [32:38<27:48, 34.04s/trial, best loss: -0.5795]
739
  52%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 52/100 [33:11<26:53, 33.62s/trial, best loss: -0.5795]
740
  53%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 53/100 [34:06<31:27, 40.15s/trial, best loss: -0.5795]
741
  54%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 54/100 [34:35<28:05, 36.63s/trial, best loss: -0.5795]
742
  55%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 55/100 [35:03<25:27, 33.96s/trial, best loss: -0.5795]
743
  56%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 56/100 [35:32<23:48, 32.47s/trial, best loss: -0.5795]
744
  57%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 57/100 [36:16<25:55, 36.18s/trial, best loss: -0.5795]
745
  58%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 58/100 [36:39<22:28, 32.12s/trial, best loss: -0.5795]
746
  59%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 59/100 [37:05<20:46, 30.41s/trial, best loss: -0.5795]
747
  60%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ๏ฟฝ๏ฟฝ | 60/100 [37:46<22:14, 33.37s/trial, best loss: -0.5795]
748
  61%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 61/100 [38:24<22:40, 34.89s/trial, best loss: -0.5795]
749
  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 62/100 [39:05<23:12, 36.64s/trial, best loss: -0.5795]
750
  63%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 63/100 [39:57<25:27, 41.29s/trial, best loss: -0.5795]
751
  64%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 64/100 [40:19<21:21, 35.59s/trial, best loss: -0.5795]
752
  65%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 65/100 [40:52<20:16, 34.76s/trial, best loss: -0.5795]
753
  66%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 66/100 [41:14<17:26, 30.79s/trial, best loss: -0.5795]
754
  67%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 67/100 [41:44<16:53, 30.70s/trial, best loss: -0.5795]
755
  68%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 68/100 [42:07<15:10, 28.45s/trial, best loss: -0.5795]
756
  69%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 69/100 [42:27<13:23, 25.92s/trial, best loss: -0.5795]
757
  70%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 70/100 [42:55<13:15, 26.52s/trial, best loss: -0.5797]
758
  71%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 71/100 [43:20<12:29, 25.85s/trial, best loss: -0.5824]
759
  72%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 72/100 [43:50<12:40, 27.17s/trial, best loss: -0.5824]
760
  73%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 73/100 [44:17<12:11, 27.08s/trial, best loss: -0.5824]
761
  74%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 74/100 [44:38<10:59, 25.37s/trial, best loss: -0.5824]
762
  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 75/100 [45:08<11:10, 26.80s/trial, best loss: -0.5824]
763
  76%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 76/100 [45:54<12:56, 32.36s/trial, best loss: -0.5824]
764
  77%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 77/100 [46:12<10:48, 28.20s/trial, best loss: -0.5824]
765
  78%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 78/100 [46:36<09:51, 26.88s/trial, best loss: -0.5824]
766
  79%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 79/100 [46:59<08:58, 25.63s/trial, best loss: -0.5824]
767
  80%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 80/100 [47:29<09:04, 27.20s/trial, best loss: -0.5824]
768
  81%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 81/100 [47:55<08:26, 26.67s/trial, best loss: -0.5824]
769
  82%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 82/100 [48:35<09:13, 30.73s/trial, best loss: -0.5824]
770
  83%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 83/100 [48:59<08:06, 28.60s/trial, best loss: -0.5824]
771
  84%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 84/100 [49:26<07:29, 28.09s/trial, best loss: -0.5824]
772
  85%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 85/100 [49:47<06:30, 26.06s/trial, best loss: -0.5824]
773
  86%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 86/100 [50:44<08:15, 35.36s/trial, best loss: -0.5824]
774
  87%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 87/100 [51:23<07:53, 36.46s/trial, best loss: -0.5824]
775
  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 88/100 [51:46<06:28, 32.41s/trial, best loss: -0.5824]
776
  89%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 89/100 [52:11<05:32, 30.19s/trial, best loss: -0.5824]
777
  90%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 90/100 [52:32<04:34, 27.47s/trial, best loss: -0.5824]
778
  91%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 91/100 [52:57<04:00, 26.68s/trial, best loss: -0.5824]
779
  92%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 92/100 [53:34<03:57, 29.64s/trial, best loss: -0.5824]
780
  93%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž| 93/100 [54:12<03:45, 32.28s/trial, best loss: -0.5824]
781
  94%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 94/100 [54:43<03:11, 31.88s/trial, best loss: -0.5824]
782
  95%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ| 95/100 [55:31<03:04, 36.86s/trial, best loss: -0.5824]
783
  96%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ| 96/100 [55:57<02:14, 33.56s/trial, best loss: -0.5824]
784
  97%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹| 97/100 [56:19<01:29, 29.99s/trial, best loss: -0.5824]
785
  98%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š| 98/100 [56:47<00:59, 29.54s/trial, best loss: -0.5824]
786
  99%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰| 99/100 [57:09<00:27, 27.11s/trial, best loss: -0.5824]
787
+
788
+ ์ตœ์ ํ™” ์™„๋ฃŒ. ์ตœ์  ํŒŒ๋ผ๋ฏธํ„ฐ: {'colsample_bytree': 0.8837225390968168, 'gamma': 0.1115044781500254, 'learning_rate': 0.10805110293567466, 'max_depth': 12.0, 'min_child_weight': 4.0, 'reg_alpha': 0.02183712172236562, 'reg_lambda': 0.6932207560084631, 'subsample': 0.6767341133785678}
789
+ ์ตœ์  CSI ์ ์ˆ˜: 0.5824 (loss: -0.5824)
790
+
791
+ ์ตœ์ ํ™” ๊ณผ์ • ์š”์•ฝ:
792
+ - ์ด ์‹œ๋„ ํšŸ์ˆ˜: 100
793
+ - ์„ฑ๊ณตํ•œ ์‹œ๋„: 100
794
+ - ์ตœ์ดˆ CSI: 0.5553
795
+ - ์ตœ์ข… CSI: 0.5700
796
+ - ์ตœ๊ณ  CSI: 0.5824
797
+ - ์ตœ์ € CSI: 0.5435
798
+ - ํ‰๊ท  CSI: 0.5687
799
+
800
+ ์ตœ์ ํ™” Trials ๊ฐ์ฒด๊ฐ€ /workspace/visibility_prediction/Analysis_code/optimization_history/xgb_ctgan10000_seoul_trials.pkl์— ์ €์žฅ๋˜์—ˆ์Šต๋‹ˆ๋‹ค.
801
+ ์ตœ์ข… ๋ชจ๋ธ ํ•™์Šต ์‹œ์ž‘...
802
+ Fold 1 ํ•™์Šต ์ค‘... (ํ•™์Šต ์—ฐ๋„: [2018, 2019], ๊ฒ€์ฆ ์—ฐ๋„: 2020)
803
+ Fold 1 ๊ฒ€์ฆ CSI: 0.5165
804
+ Fold 2 ํ•™์Šต ์ค‘... (ํ•™์Šต ์—ฐ๋„: [2018, 2020], ๊ฒ€์ฆ ์—ฐ๋„: 2019)
805
+ Fold 2 ๊ฒ€์ฆ CSI: 0.6230
806
+ Fold 3 ํ•™์Šต ์ค‘... (ํ•™์Šต ์—ฐ๋„: [2019, 2020], ๊ฒ€์ฆ ์—ฐ๋„: 2018)
807
+ Fold 3 ๊ฒ€์ฆ CSI: 0.6077
808
+ ๋ชจ๋ธ ์ €์žฅ ์ค‘...
809
+ ๋ชจ๋ธ์ด /workspace/visibility_prediction/Analysis_code/save_model/xgb_optima/xgb_ctgan10000_seoul.pkl์— ์ €์žฅ๋˜์—ˆ์Šต๋‹ˆ๋‹ค.
810
+
811
+ โœ“ ์™„๋ฃŒ: xgb_ctgan10000/XGB_ctgan10000_seoul.py (์†Œ์š” ์‹œ๊ฐ„: 3488์ดˆ)
812
+
813
+ ==========================================
814
+ XGB CTGAN10000 ํŒŒ์ผ ์‹คํ–‰ ์™„๋ฃŒ
815
+ ์ข…๋ฃŒ ์‹œ๊ฐ„: 2025-12-28 10:33:59
816
+ ์ด ์†Œ์š” ์‹œ๊ฐ„: 6์‹œ๊ฐ„ 2๋ถ„ 42์ดˆ
817
+ ์„ฑ๊ณต: 6๊ฐœ
818
+ ์‹คํŒจ: 0๊ฐœ
819
+ ==========================================
Analysis_code/5.optima/xgb_ctgan10000/XGB_ctgan10000_daegu.py ADDED
@@ -0,0 +1,305 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ import pandas as pd
2
+ import os
3
+ import numpy as np
4
+ import joblib
5
+ from xgboost import XGBClassifier
6
+ from warnings import filterwarnings
7
+ filterwarnings('ignore')
8
+ from sklearn.metrics import confusion_matrix
9
+ from hyperopt import fmin, tpe, Trials, hp
10
+
11
+ # ์ƒ์ˆ˜ ์ •์˜
12
+ RANDOM_STATE = 42
13
+ N_ESTIMATORS = 4000
14
+ EARLY_STOPPING_ROUNDS = 400
15
+ MAX_EVALS = 100
16
+
17
+ # Fold ์„ค์ •: (train_years, val_year)
18
+ FOLD_CONFIGS = [
19
+ ([2018, 2019], 2020), # Fold 1
20
+ ([2018, 2020], 2019), # Fold 2
21
+ ([2019, 2020], 2018), # Fold 3
22
+ ]
23
+
24
+ def calculate_csi(Y_test, pred):
25
+ """CSI(Critical Success Index) ์ ์ˆ˜๋ฅผ ๊ณ„์‚ฐํ•ฉ๋‹ˆ๋‹ค.
26
+
27
+ Args:
28
+ Y_test: ์‹ค์ œ ๋ ˆ์ด๋ธ”
29
+ pred: ์˜ˆ์ธก ๋ ˆ์ด๋ธ”
30
+
31
+ Returns:
32
+ CSI ์ ์ˆ˜ (0~1 ์‚ฌ์ด์˜ ๊ฐ’)
33
+ """
34
+ cm = confusion_matrix(Y_test, pred)
35
+ H = (cm[0, 0] + cm[1, 1])
36
+ F = (cm[1, 0] + cm[2, 0] + cm[0, 1] + cm[2, 1])
37
+ M = (cm[0, 2] + cm[1, 2])
38
+ CSI = H / (H + F + M + 1e-10)
39
+ return CSI
40
+
41
+ def eval_metric_csi(y_true, pred_prob):
42
+ """XGBoost์šฉ CSI ๋ฉ”ํŠธ๋ฆญ ํ•จ์ˆ˜.
43
+
44
+ Args:
45
+ y_true: ์‹ค์ œ ๋ ˆ์ด๋ธ”
46
+ pred_prob: ์˜ˆ์ธก ํ™•๋ฅ 
47
+
48
+ Returns:
49
+ CSI ์ ์ˆ˜์˜ ์Œ์ˆ˜๊ฐ’
50
+ """
51
+ pred = np.argmax(pred_prob, axis=1)
52
+ csi = calculate_csi(y_true, pred)
53
+ return -1*csi
54
+
55
+ def add_derived_features(df: pd.DataFrame) -> pd.DataFrame:
56
+ """
57
+ ์ œ๊ฑฐํ–ˆ๋˜ ํŒŒ์ƒ ๋ณ€์ˆ˜๋“ค์„ ๋ณต๊ตฌ
58
+
59
+ Args:
60
+ df: ๋ฐ์ดํ„ฐํ”„๋ ˆ์ž„
61
+
62
+ Returns:
63
+ ํŒŒ์ƒ ๋ณ€์ˆ˜๊ฐ€ ์ถ”๊ฐ€๋œ ๋ฐ์ดํ„ฐํ”„๋ ˆ์ž„
64
+ """
65
+ df = df.copy()
66
+ df['hour_sin'] = np.sin(2 * np.pi * df['hour'] / 24)
67
+ df['hour_cos'] = np.cos(2 * np.pi * df['hour'] / 24)
68
+ df['month_sin'] = np.sin(2 * np.pi * df['month'] / 12)
69
+ df['month_cos'] = np.cos(2 * np.pi * df['month'] / 12)
70
+ df['ground_temp - temp_C'] = df['groundtemp'] - df['temp_C']
71
+ return df
72
+
73
+ def preprocessing(df):
74
+ """๋ฐ์ดํ„ฐ ์ „์ฒ˜๋ฆฌ ํ•จ์ˆ˜.
75
+
76
+ Args:
77
+ df: ์›๋ณธ ๋ฐ์ดํ„ฐํ”„๋ ˆ์ž„
78
+
79
+ Returns:
80
+ ์ „์ฒ˜๋ฆฌ๋œ ๋ฐ์ดํ„ฐํ”„๋ ˆ์ž„
81
+ """
82
+ df = df[df.columns].copy()
83
+ df['year'] = df['year'].astype('int')
84
+ df['month'] = df['month'].astype('int')
85
+ df['hour'] = df['hour'].astype('int')
86
+ df = add_derived_features(df).copy()
87
+ df['multi_class'] = df['multi_class'].astype('int')
88
+ df.loc[df['wind_dir']=='์ •์˜จ', 'wind_dir'] = "0"
89
+ df['wind_dir'] = df['wind_dir'].astype('int')
90
+ df = df[['temp_C', 'precip_mm', 'wind_speed', 'wind_dir', 'hm',
91
+ 'vap_pressure', 'dewpoint_C', 'loc_pressure', 'sea_pressure',
92
+ 'solarRad', 'snow_cm', 'cloudcover', 'lm_cloudcover', 'low_cloudbase',
93
+ 'groundtemp', 'O3', 'NO2', 'PM10', 'PM25', 'year',
94
+ 'month', 'hour', 'ground_temp - temp_C', 'hour_sin', 'hour_cos',
95
+ 'month_sin', 'month_cos','multi_class']].copy()
96
+ return df
97
+
98
+ def create_xgb_model(search_space=None, best_params=None):
99
+ """XGBoost ๋ชจ๋ธ์„ ์ƒ์„ฑํ•ฉ๋‹ˆ๋‹ค.
100
+
101
+ Args:
102
+ search_space: ํ•˜์ดํผํŒŒ๋ผ๋ฏธํ„ฐ ๊ฒ€์ƒ‰ ๊ณต๊ฐ„ (objective_func์—์„œ ์‚ฌ์šฉ)
103
+ best_params: ์ตœ์ ํ™”๋œ ํ•˜์ดํผํŒŒ๋ผ๋ฏธํ„ฐ (์ตœ์ข… ๋ชจ๋ธ ํ•™์Šต์—์„œ ์‚ฌ์šฉ)
104
+
105
+ Returns:
106
+ XGBClassifier ์ธ์Šคํ„ด์Šค
107
+ """
108
+ base_params = {
109
+ 'n_estimators': N_ESTIMATORS,
110
+ 'tree_method': 'hist',
111
+ 'device': 'cuda',
112
+ 'enable_categorical': True,
113
+ 'eval_metric': eval_metric_csi,
114
+ 'objective': 'multi:softprob',
115
+ 'random_state': RANDOM_STATE,
116
+ 'early_stopping_rounds': EARLY_STOPPING_ROUNDS,
117
+ }
118
+
119
+ if search_space is not None:
120
+ # ํ•˜์ดํผํŒŒ๋ผ๋ฏธํ„ฐ ์ตœ์ ํ™” ์ค‘
121
+ params = {
122
+ **base_params,
123
+ 'learning_rate': search_space['learning_rate'],
124
+ 'max_depth': int(search_space['max_depth']),
125
+ 'min_child_weight': int(search_space['min_child_weight']),
126
+ 'gamma': search_space['gamma'],
127
+ 'subsample': search_space['subsample'],
128
+ 'colsample_bytree': search_space['colsample_bytree'],
129
+ 'reg_alpha': search_space['reg_alpha'],
130
+ 'reg_lambda': search_space['reg_lambda'],
131
+ }
132
+ elif best_params is not None:
133
+ # ์ตœ์ ํ™”๋œ ํŒŒ๋ผ๋ฏธํ„ฐ๋กœ ์ตœ์ข… ๋ชจ๋ธ ์ƒ์„ฑ
134
+ params = {
135
+ **base_params,
136
+ 'learning_rate': best_params['learning_rate'],
137
+ 'max_depth': int(best_params['max_depth']),
138
+ 'min_child_weight': int(best_params['min_child_weight']),
139
+ 'gamma': best_params['gamma'],
140
+ 'subsample': best_params['subsample'],
141
+ 'colsample_bytree': best_params['colsample_bytree'],
142
+ 'reg_alpha': best_params['reg_alpha'],
143
+ 'reg_lambda': best_params['reg_lambda'],
144
+ }
145
+ else:
146
+ params = base_params
147
+
148
+ return XGBClassifier(**params)
149
+
150
+
151
+ # ๋ฐ์ดํ„ฐ ๋กœ๋”ฉ ๋ฐ ์ „์ฒ˜๋ฆฌ
152
+ print("๋ฐ์ดํ„ฐ ๋กœ๋”ฉ ์ค‘...")
153
+ # ํŒŒ์ผ ์œ„์น˜ ๊ธฐ๋ฐ˜์œผ๋กœ ๋ฐ์ดํ„ฐ ๋””๋ ‰ํ† ๋ฆฌ ๊ฒฝ๋กœ ์„ค์ •
154
+ current_file_dir = os.path.dirname(os.path.abspath(__file__))
155
+ data_base_dir = os.path.abspath(os.path.join(current_file_dir, '../../../data'))
156
+ df_daegu = pd.read_csv(os.path.join(data_base_dir, "data_for_modeling/daegu_train.csv"))
157
+ df_ctgan_daegu_1 = pd.read_csv(os.path.join(data_base_dir, "data_oversampled/ctgan10000/ctgan10000_1_daegu.csv"))
158
+ df_ctgan_daegu_2 = pd.read_csv(os.path.join(data_base_dir, "data_oversampled/ctgan10000/ctgan10000_2_daegu.csv"))
159
+ df_ctgan_daegu_3 = pd.read_csv(os.path.join(data_base_dir, "data_oversampled/ctgan10000/ctgan10000_3_daegu.csv"))
160
+
161
+ print("๋ฐ์ดํ„ฐ ์ „์ฒ˜๋ฆฌ ์ค‘...")
162
+ df_ctgan_daegu_1 = preprocessing(df_ctgan_daegu_1)
163
+ df_ctgan_daegu_2 = preprocessing(df_ctgan_daegu_2)
164
+ df_ctgan_daegu_3 = preprocessing(df_ctgan_daegu_3)
165
+ df_daegu = preprocessing(df_daegu)
166
+
167
+ # CTGAN ๋ฐ์ดํ„ฐ ๋ฆฌ์ŠคํŠธ (fold ์ˆœ์„œ์™€ ์ผ์น˜)
168
+ df_ctgan_list = [df_ctgan_daegu_1, df_ctgan_daegu_2, df_ctgan_daegu_3]
169
+
170
+ def split_data(df_sampled, df_original, train_years, val_year):
171
+ """๋ฐ์ดํ„ฐ๋ฅผ ํ•™์Šต์šฉ๊ณผ ๊ฒ€์ฆ์šฉ์œผ๋กœ ๋ถ„ํ• ํ•ฉ๋‹ˆ๋‹ค.
172
+
173
+ Args:
174
+ df_sampled: ์ƒ˜ํ”Œ๋ง๋œ ๋ฐ์ดํ„ฐํ”„๋ ˆ์ž„
175
+ df_original: ์›๋ณธ ๋ฐ์ดํ„ฐํ”„๋ ˆ์ž„
176
+ train_years: ํ•™์Šต์— ์‚ฌ์šฉํ•  ์—ฐ๋„ ๋ฆฌ์ŠคํŠธ
177
+ val_year: ๊ฒ€์ฆ์— ์‚ฌ์šฉํ•  ์—ฐ๋„
178
+
179
+ Returns:
180
+ (X_train, X_val, y_train, y_val) ํŠœํ”Œ
181
+ """
182
+ # ํ•™์Šต ๋ฐ์ดํ„ฐ: ์ƒ˜ํ”Œ๋ง๋œ ๋ฐ์ดํ„ฐ์—์„œ train_years์— ํ•ด๋‹นํ•˜๋Š” ๋ฐ์ดํ„ฐ
183
+ train_mask = df_sampled['year'].isin(train_years)
184
+ X_train = df_sampled.loc[train_mask, df_sampled.columns != 'multi_class'].copy()
185
+ y_train = df_sampled.loc[train_mask, 'multi_class']
186
+
187
+ # ๊ฒ€์ฆ ๋ฐ์ดํ„ฐ: ์›๋ณธ ๋ฐ์ดํ„ฐ์—์„œ val_year์— ํ•ด๋‹นํ•˜๋Š” ๋ฐ์ดํ„ฐ
188
+ val_mask = df_original['year'] == val_year
189
+ X_val = df_original.loc[val_mask, df_original.columns != 'multi_class'].copy()
190
+ y_val = df_original.loc[val_mask, 'multi_class']
191
+
192
+ X_train.drop(columns=['year'], inplace=True)
193
+ X_val.drop(columns=['year'], inplace=True)
194
+
195
+ return X_train, X_val, y_train, y_val
196
+
197
+
198
+ # ํ•˜์ดํผํŒŒ๋ผ๋ฏธํ„ฐ ๊ฒ€์ƒ‰ ๊ณต๊ฐ„ ์ •์˜
199
+ xgb_search_space = {
200
+ 'learning_rate': hp.loguniform('learning_rate', np.log(0.01), np.log(0.2)),
201
+ 'max_depth': hp.quniform('max_depth', 3, 12, 1),
202
+ 'min_child_weight': hp.quniform('min_child_weight', 1, 20, 1),
203
+ 'gamma': hp.uniform('gamma', 0, 5), # ํŠธ๋ฆฌ ๋ถ„ํ• ์„ ์œ„ํ•œ ์ตœ์†Œ ์†์‹ค ๊ฐ์†Œ ๊ฐ’
204
+ 'subsample': hp.uniform('subsample', 0.6, 1.0),
205
+ 'colsample_bytree': hp.uniform('colsample_bytree', 0.6, 1.0),
206
+ 'reg_alpha': hp.uniform('reg_alpha', 0.0, 1.0),
207
+ 'reg_lambda': hp.uniform('reg_lambda', 0.0, 1.0)
208
+ }
209
+
210
+ def objective_func(search_space):
211
+ """ํ•˜์ดํผํŒŒ๋ผ๋ฏธํ„ฐ ์ตœ์ ํ™”๋ฅผ ์œ„ํ•œ ๋ชฉ์  ํ•จ์ˆ˜.
212
+
213
+ Args:
214
+ search_space: ํ•˜์ดํผํŒŒ๋ผ๋ฏธํ„ฐ ๊ฒ€์ƒ‰ ๊ณต๊ฐ„
215
+
216
+ Returns:
217
+ ํ‰๊ท  CSI ์ ์ˆ˜์˜ ์Œ์ˆ˜๊ฐ’ (hyperopt๋Š” ์ตœ์†Œํ™”๋ฅผ ์ˆ˜ํ–‰ํ•˜๋ฏ€๋กœ)
218
+ """
219
+ xgb_model = create_xgb_model(search_space=search_space)
220
+ csi_scores = []
221
+
222
+ # ๊ฐ fold์— ๋Œ€ํ•ด ๊ต์ฐจ ๊ฒ€์ฆ ์ˆ˜ํ–‰
223
+ for df_sampled, (train_years, val_year) in zip(df_ctgan_list, FOLD_CONFIGS):
224
+ X_train, X_val, y_train, y_val = split_data(
225
+ df_sampled, df_daegu, train_years, val_year
226
+ )
227
+
228
+ xgb_model.fit(X_train, y_train, eval_set=[(X_val, y_val)], verbose=False)
229
+ csi = calculate_csi(y_val, xgb_model.predict(X_val))
230
+ csi_scores.append(csi)
231
+
232
+ return -1*round(np.mean(csi_scores), 4)
233
+
234
+
235
+ # ํ•˜์ดํผํŒŒ๋ผ๋ฏธํ„ฐ ์ตœ์ ํ™”
236
+ print("ํ•˜์ดํผํŒŒ๋ผ๋ฏธํ„ฐ ์ตœ์ ํ™” ์‹œ์ž‘...")
237
+ trials = Trials()
238
+ xgb_best = fmin(
239
+ fn=objective_func,
240
+ space=xgb_search_space,
241
+ algo=tpe.suggest,
242
+ max_evals=MAX_EVALS,
243
+ trials=trials
244
+ )
245
+
246
+ # ์ตœ์ ํ™” ๊ฒฐ๊ณผ ๋ถ„์„ ๋ฐ ์ถœ๋ ฅ
247
+ print(f"\n์ตœ์ ํ™” ์™„๋ฃŒ. ์ตœ์  ํŒŒ๋ผ๋ฏธํ„ฐ: {xgb_best}")
248
+
249
+ # Best loss (CSI ์ ์ˆ˜์˜ ์Œ์ˆ˜๊ฐ’์ด๋ฏ€๋กœ, ์‹ค์ œ CSI๋Š” -loss)
250
+ best_loss = trials.best_trial['result']['loss']
251
+ best_csi = -best_loss
252
+ print(f"์ตœ์  CSI ์ ์ˆ˜: {best_csi:.4f} (loss: {best_loss:.4f})")
253
+
254
+ # ๋ชจ๋“  trial์˜ loss ๊ฐ’ ์ถ”์ถœ
255
+ losses = [trial['result']['loss'] for trial in trials.trials if trial['result']['status'] == 'ok']
256
+ csi_scores = [-loss for loss in losses]
257
+
258
+ print(f"\n์ตœ์ ํ™” ๊ณผ์ • ์š”์•ฝ:")
259
+ print(f" - ์ด ์‹œ๋„ ํšŸ์ˆ˜: {len(trials.trials)}")
260
+ print(f" - ์„ฑ๊ณตํ•œ ์‹œ๋„: {len(losses)}")
261
+ print(f" - ์ตœ์ดˆ CSI: {csi_scores[0]:.4f}")
262
+ print(f" - ์ตœ์ข… CSI: {csi_scores[-1]:.4f}")
263
+ print(f" - ์ตœ๊ณ  CSI: {max(csi_scores):.4f}")
264
+ print(f" - ์ตœ์ € CSI: {min(csi_scores):.4f}")
265
+ print(f" - ํ‰๊ท  CSI: {np.mean(csi_scores):.4f}")
266
+
267
+ # Trials ๊ฐ์ฒด ์ €์žฅ
268
+ # ํŒŒ์ผ ์œ„์น˜ ๊ธฐ๋ฐ˜์œผ๋กœ base ๋””๋ ‰ํ† ๋ฆฌ ๊ฒฝ๋กœ ์„ค์ •
269
+ current_file_dir = os.path.dirname(os.path.abspath(__file__))
270
+ base_dir = os.path.dirname(os.path.dirname(current_file_dir)) # 5.optima ๋””๋ ‰ํ† ๋ฆฌ
271
+ os.makedirs(os.path.join(base_dir, "optimization_history"), exist_ok=True)
272
+ trials_path = os.path.join(base_dir, "optimization_history/xgb_ctgan10000_daegu_trials.pkl")
273
+ joblib.dump(trials, trials_path)
274
+ print(f"\n์ตœ์ ํ™” Trials ๊ฐ์ฒด๊ฐ€ {trials_path}์— ์ €์žฅ๋˜์—ˆ์Šต๋‹ˆ๋‹ค.")
275
+
276
+ # ์ตœ์ ํ™”๋œ ํ•˜์ดํผํŒŒ๋ผ๋ฏธํ„ฐ๋กœ ์ตœ์ข… ๋ชจ๋ธ ํ•™์Šต
277
+ print("์ตœ์ข… ๋ชจ๋ธ ํ•™์Šต ์‹œ์ž‘...")
278
+ models = []
279
+
280
+ for fold_idx, (df_sampled, (train_years, val_year)) in enumerate(
281
+ zip(df_ctgan_list, FOLD_CONFIGS), start=1
282
+ ):
283
+ print(f"Fold {fold_idx} ํ•™์Šต ์ค‘... (ํ•™์Šต ์—ฐ๋„: {train_years}, ๊ฒ€์ฆ ์—ฐ๋„: {val_year})")
284
+
285
+ X_train, X_val, y_train, y_val = split_data(
286
+ df_sampled, df_daegu, train_years, val_year
287
+ )
288
+
289
+ xgb_model = create_xgb_model(best_params=xgb_best)
290
+ xgb_model.fit(X_train, y_train, eval_set=[(X_val, y_val)], verbose=False)
291
+
292
+ # ๊ฒ€์ฆ ์„ฑ๋Šฅ ์ถœ๋ ฅ
293
+ val_csi = calculate_csi(y_val, xgb_model.predict(X_val))
294
+ print(f"Fold {fold_idx} ๊ฒ€์ฆ CSI: {val_csi:.4f}")
295
+
296
+ models.append(xgb_model)
297
+
298
+
299
+ # ๋ชจ๋ธ ์ €์žฅ
300
+ print("๋ชจ๋ธ ์ €์žฅ ์ค‘...")
301
+ os.makedirs(os.path.join(base_dir, "save_model/xgb_optima"), exist_ok=True)
302
+ model_save_path = os.path.join(base_dir, "save_model/xgb_optima/xgb_ctgan10000_daegu.pkl")
303
+ joblib.dump(models, model_save_path)
304
+ print(f"๋ชจ๋ธ์ด {model_save_path}์— ์ €์žฅ๋˜์—ˆ์Šต๋‹ˆ๋‹ค.")
305
+
Analysis_code/5.optima/xgb_ctgan10000/XGB_ctgan10000_daejeon.py ADDED
@@ -0,0 +1,305 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ import pandas as pd
2
+ import os
3
+ import numpy as np
4
+ import joblib
5
+ from xgboost import XGBClassifier
6
+ from warnings import filterwarnings
7
+ filterwarnings('ignore')
8
+ from sklearn.metrics import confusion_matrix
9
+ from hyperopt import fmin, tpe, Trials, hp
10
+
11
+ # ์ƒ์ˆ˜ ์ •์˜
12
+ RANDOM_STATE = 42
13
+ N_ESTIMATORS = 4000
14
+ EARLY_STOPPING_ROUNDS = 400
15
+ MAX_EVALS = 100
16
+
17
+ # Fold ์„ค์ •: (train_years, val_year)
18
+ FOLD_CONFIGS = [
19
+ ([2018, 2019], 2020), # Fold 1
20
+ ([2018, 2020], 2019), # Fold 2
21
+ ([2019, 2020], 2018), # Fold 3
22
+ ]
23
+
24
+ def calculate_csi(Y_test, pred):
25
+ """CSI(Critical Success Index) ์ ์ˆ˜๋ฅผ ๊ณ„์‚ฐํ•ฉ๋‹ˆ๋‹ค.
26
+
27
+ Args:
28
+ Y_test: ์‹ค์ œ ๋ ˆ์ด๋ธ”
29
+ pred: ์˜ˆ์ธก ๋ ˆ์ด๋ธ”
30
+
31
+ Returns:
32
+ CSI ์ ์ˆ˜ (0~1 ์‚ฌ์ด์˜ ๊ฐ’)
33
+ """
34
+ cm = confusion_matrix(Y_test, pred)
35
+ H = (cm[0, 0] + cm[1, 1])
36
+ F = (cm[1, 0] + cm[2, 0] + cm[0, 1] + cm[2, 1])
37
+ M = (cm[0, 2] + cm[1, 2])
38
+ CSI = H / (H + F + M + 1e-10)
39
+ return CSI
40
+
41
+ def eval_metric_csi(y_true, pred_prob):
42
+ """XGBoost์šฉ CSI ๋ฉ”ํŠธ๋ฆญ ํ•จ์ˆ˜.
43
+
44
+ Args:
45
+ y_true: ์‹ค์ œ ๋ ˆ์ด๋ธ”
46
+ pred_prob: ์˜ˆ์ธก ํ™•๋ฅ 
47
+
48
+ Returns:
49
+ CSI ์ ์ˆ˜์˜ ์Œ์ˆ˜๊ฐ’
50
+ """
51
+ pred = np.argmax(pred_prob, axis=1)
52
+ csi = calculate_csi(y_true, pred)
53
+ return -1*csi
54
+
55
+ def add_derived_features(df: pd.DataFrame) -> pd.DataFrame:
56
+ """
57
+ ์ œ๊ฑฐํ–ˆ๋˜ ํŒŒ์ƒ ๋ณ€์ˆ˜๋“ค์„ ๋ณต๊ตฌ
58
+
59
+ Args:
60
+ df: ๋ฐ์ดํ„ฐํ”„๋ ˆ์ž„
61
+
62
+ Returns:
63
+ ํŒŒ์ƒ ๋ณ€์ˆ˜๊ฐ€ ์ถ”๊ฐ€๋œ ๋ฐ์ดํ„ฐํ”„๋ ˆ์ž„
64
+ """
65
+ df = df.copy()
66
+ df['hour_sin'] = np.sin(2 * np.pi * df['hour'] / 24)
67
+ df['hour_cos'] = np.cos(2 * np.pi * df['hour'] / 24)
68
+ df['month_sin'] = np.sin(2 * np.pi * df['month'] / 12)
69
+ df['month_cos'] = np.cos(2 * np.pi * df['month'] / 12)
70
+ df['ground_temp - temp_C'] = df['groundtemp'] - df['temp_C']
71
+ return df
72
+
73
+ def preprocessing(df):
74
+ """๋ฐ์ดํ„ฐ ์ „์ฒ˜๋ฆฌ ํ•จ์ˆ˜.
75
+
76
+ Args:
77
+ df: ์›๋ณธ ๋ฐ์ดํ„ฐํ”„๋ ˆ์ž„
78
+
79
+ Returns:
80
+ ์ „์ฒ˜๋ฆฌ๋œ ๋ฐ์ดํ„ฐํ”„๋ ˆ์ž„
81
+ """
82
+ df = df[df.columns].copy()
83
+ df['year'] = df['year'].astype('int')
84
+ df['month'] = df['month'].astype('int')
85
+ df['hour'] = df['hour'].astype('int')
86
+ df = add_derived_features(df).copy()
87
+ df['multi_class'] = df['multi_class'].astype('int')
88
+ df.loc[df['wind_dir']=='์ •์˜จ', 'wind_dir'] = "0"
89
+ df['wind_dir'] = df['wind_dir'].astype('int')
90
+ df = df[['temp_C', 'precip_mm', 'wind_speed', 'wind_dir', 'hm',
91
+ 'vap_pressure', 'dewpoint_C', 'loc_pressure', 'sea_pressure',
92
+ 'solarRad', 'snow_cm', 'cloudcover', 'lm_cloudcover', 'low_cloudbase',
93
+ 'groundtemp', 'O3', 'NO2', 'PM10', 'PM25', 'year',
94
+ 'month', 'hour', 'ground_temp - temp_C', 'hour_sin', 'hour_cos',
95
+ 'month_sin', 'month_cos','multi_class']].copy()
96
+ return df
97
+
98
+ def create_xgb_model(search_space=None, best_params=None):
99
+ """XGBoost ๋ชจ๋ธ์„ ์ƒ์„ฑํ•ฉ๋‹ˆ๋‹ค.
100
+
101
+ Args:
102
+ search_space: ํ•˜์ดํผํŒŒ๋ผ๋ฏธํ„ฐ ๊ฒ€์ƒ‰ ๊ณต๊ฐ„ (objective_func์—์„œ ์‚ฌ์šฉ)
103
+ best_params: ์ตœ์ ํ™”๋œ ํ•˜์ดํผํŒŒ๋ผ๋ฏธํ„ฐ (์ตœ์ข… ๋ชจ๋ธ ํ•™์Šต์—์„œ ์‚ฌ์šฉ)
104
+
105
+ Returns:
106
+ XGBClassifier ์ธ์Šคํ„ด์Šค
107
+ """
108
+ base_params = {
109
+ 'n_estimators': N_ESTIMATORS,
110
+ 'tree_method': 'hist',
111
+ 'device': 'cuda',
112
+ 'enable_categorical': True,
113
+ 'eval_metric': eval_metric_csi,
114
+ 'objective': 'multi:softprob',
115
+ 'random_state': RANDOM_STATE,
116
+ 'early_stopping_rounds': EARLY_STOPPING_ROUNDS,
117
+ }
118
+
119
+ if search_space is not None:
120
+ # ํ•˜์ดํผํŒŒ๋ผ๋ฏธํ„ฐ ์ตœ์ ํ™” ์ค‘
121
+ params = {
122
+ **base_params,
123
+ 'learning_rate': search_space['learning_rate'],
124
+ 'max_depth': int(search_space['max_depth']),
125
+ 'min_child_weight': int(search_space['min_child_weight']),
126
+ 'gamma': search_space['gamma'],
127
+ 'subsample': search_space['subsample'],
128
+ 'colsample_bytree': search_space['colsample_bytree'],
129
+ 'reg_alpha': search_space['reg_alpha'],
130
+ 'reg_lambda': search_space['reg_lambda'],
131
+ }
132
+ elif best_params is not None:
133
+ # ์ตœ์ ํ™”๋œ ํŒŒ๋ผ๋ฏธํ„ฐ๋กœ ์ตœ์ข… ๋ชจ๋ธ ์ƒ์„ฑ
134
+ params = {
135
+ **base_params,
136
+ 'learning_rate': best_params['learning_rate'],
137
+ 'max_depth': int(best_params['max_depth']),
138
+ 'min_child_weight': int(best_params['min_child_weight']),
139
+ 'gamma': best_params['gamma'],
140
+ 'subsample': best_params['subsample'],
141
+ 'colsample_bytree': best_params['colsample_bytree'],
142
+ 'reg_alpha': best_params['reg_alpha'],
143
+ 'reg_lambda': best_params['reg_lambda'],
144
+ }
145
+ else:
146
+ params = base_params
147
+
148
+ return XGBClassifier(**params)
149
+
150
+
151
+ # ๋ฐ์ดํ„ฐ ๋กœ๋”ฉ ๋ฐ ์ „์ฒ˜๋ฆฌ
152
+ print("๋ฐ์ดํ„ฐ ๋กœ๋”ฉ ์ค‘...")
153
+ # ํŒŒ์ผ ์œ„์น˜ ๊ธฐ๋ฐ˜์œผ๋กœ ๋ฐ์ดํ„ฐ ๋””๋ ‰ํ† ๋ฆฌ ๊ฒฝ๋กœ ์„ค์ •
154
+ current_file_dir = os.path.dirname(os.path.abspath(__file__))
155
+ data_base_dir = os.path.abspath(os.path.join(current_file_dir, '../../../data'))
156
+ df_daejeon = pd.read_csv(os.path.join(data_base_dir, "data_for_modeling/daejeon_train.csv"))
157
+ df_ctgan_daejeon_1 = pd.read_csv(os.path.join(data_base_dir, "data_oversampled/ctgan10000/ctgan10000_1_daejeon.csv"))
158
+ df_ctgan_daejeon_2 = pd.read_csv(os.path.join(data_base_dir, "data_oversampled/ctgan10000/ctgan10000_2_daejeon.csv"))
159
+ df_ctgan_daejeon_3 = pd.read_csv(os.path.join(data_base_dir, "data_oversampled/ctgan10000/ctgan10000_3_daejeon.csv"))
160
+
161
+ print("๋ฐ์ดํ„ฐ ์ „์ฒ˜๋ฆฌ ์ค‘...")
162
+ df_ctgan_daejeon_1 = preprocessing(df_ctgan_daejeon_1)
163
+ df_ctgan_daejeon_2 = preprocessing(df_ctgan_daejeon_2)
164
+ df_ctgan_daejeon_3 = preprocessing(df_ctgan_daejeon_3)
165
+ df_daejeon = preprocessing(df_daejeon)
166
+
167
+ # CTGAN ๋ฐ์ดํ„ฐ ๋ฆฌ์ŠคํŠธ (fold ์ˆœ์„œ์™€ ์ผ์น˜)
168
+ df_ctgan_list = [df_ctgan_daejeon_1, df_ctgan_daejeon_2, df_ctgan_daejeon_3]
169
+
170
+ def split_data(df_sampled, df_original, train_years, val_year):
171
+ """๋ฐ์ดํ„ฐ๋ฅผ ํ•™์Šต์šฉ๊ณผ ๊ฒ€์ฆ์šฉ์œผ๋กœ ๋ถ„ํ• ํ•ฉ๋‹ˆ๋‹ค.
172
+
173
+ Args:
174
+ df_sampled: ์ƒ˜ํ”Œ๋ง๋œ ๋ฐ์ดํ„ฐํ”„๋ ˆ์ž„
175
+ df_original: ์›๋ณธ ๋ฐ์ดํ„ฐํ”„๋ ˆ์ž„
176
+ train_years: ํ•™์Šต์— ์‚ฌ์šฉํ•  ์—ฐ๋„ ๋ฆฌ์ŠคํŠธ
177
+ val_year: ๊ฒ€์ฆ์— ์‚ฌ์šฉํ•  ์—ฐ๋„
178
+
179
+ Returns:
180
+ (X_train, X_val, y_train, y_val) ํŠœํ”Œ
181
+ """
182
+ # ํ•™์Šต ๋ฐ์ดํ„ฐ: ์ƒ˜ํ”Œ๋ง๋œ ๋ฐ์ดํ„ฐ์—์„œ train_years์— ํ•ด๋‹นํ•˜๋Š” ๋ฐ์ดํ„ฐ
183
+ train_mask = df_sampled['year'].isin(train_years)
184
+ X_train = df_sampled.loc[train_mask, df_sampled.columns != 'multi_class'].copy()
185
+ y_train = df_sampled.loc[train_mask, 'multi_class']
186
+
187
+ # ๊ฒ€์ฆ ๋ฐ์ดํ„ฐ: ์›๋ณธ ๋ฐ์ดํ„ฐ์—์„œ val_year์— ํ•ด๋‹นํ•˜๋Š” ๋ฐ์ดํ„ฐ
188
+ val_mask = df_original['year'] == val_year
189
+ X_val = df_original.loc[val_mask, df_original.columns != 'multi_class'].copy()
190
+ y_val = df_original.loc[val_mask, 'multi_class']
191
+
192
+ X_train.drop(columns=['year'], inplace=True)
193
+ X_val.drop(columns=['year'], inplace=True)
194
+
195
+ return X_train, X_val, y_train, y_val
196
+
197
+
198
+ # ํ•˜์ดํผํŒŒ๋ผ๋ฏธํ„ฐ ๊ฒ€์ƒ‰ ๊ณต๊ฐ„ ์ •์˜
199
+ xgb_search_space = {
200
+ 'learning_rate': hp.loguniform('learning_rate', np.log(0.01), np.log(0.2)),
201
+ 'max_depth': hp.quniform('max_depth', 3, 12, 1),
202
+ 'min_child_weight': hp.quniform('min_child_weight', 1, 20, 1),
203
+ 'gamma': hp.uniform('gamma', 0, 5), # ํŠธ๋ฆฌ ๋ถ„ํ• ์„ ์œ„ํ•œ ์ตœ์†Œ ์†์‹ค ๊ฐ์†Œ ๊ฐ’
204
+ 'subsample': hp.uniform('subsample', 0.6, 1.0),
205
+ 'colsample_bytree': hp.uniform('colsample_bytree', 0.6, 1.0),
206
+ 'reg_alpha': hp.uniform('reg_alpha', 0.0, 1.0),
207
+ 'reg_lambda': hp.uniform('reg_lambda', 0.0, 1.0)
208
+ }
209
+
210
+ def objective_func(search_space):
211
+ """ํ•˜์ดํผํŒŒ๋ผ๋ฏธํ„ฐ ์ตœ์ ํ™”๋ฅผ ์œ„ํ•œ ๋ชฉ์  ํ•จ์ˆ˜.
212
+
213
+ Args:
214
+ search_space: ํ•˜์ดํผํŒŒ๋ผ๋ฏธํ„ฐ ๊ฒ€์ƒ‰ ๊ณต๊ฐ„
215
+
216
+ Returns:
217
+ ํ‰๊ท  CSI ์ ์ˆ˜์˜ ์Œ์ˆ˜๊ฐ’ (hyperopt๋Š” ์ตœ์†Œํ™”๋ฅผ ์ˆ˜ํ–‰ํ•˜๋ฏ€๋กœ)
218
+ """
219
+ xgb_model = create_xgb_model(search_space=search_space)
220
+ csi_scores = []
221
+
222
+ # ๊ฐ fold์— ๋Œ€ํ•ด ๊ต์ฐจ ๊ฒ€์ฆ ์ˆ˜ํ–‰
223
+ for df_sampled, (train_years, val_year) in zip(df_ctgan_list, FOLD_CONFIGS):
224
+ X_train, X_val, y_train, y_val = split_data(
225
+ df_sampled, df_daejeon, train_years, val_year
226
+ )
227
+
228
+ xgb_model.fit(X_train, y_train, eval_set=[(X_val, y_val)], verbose=False)
229
+ csi = calculate_csi(y_val, xgb_model.predict(X_val))
230
+ csi_scores.append(csi)
231
+
232
+ return -1*round(np.mean(csi_scores), 4)
233
+
234
+
235
+ # ํ•˜์ดํผํŒŒ๋ผ๋ฏธํ„ฐ ์ตœ์ ํ™”
236
+ print("ํ•˜์ดํผํŒŒ๋ผ๋ฏธํ„ฐ ์ตœ์ ํ™” ์‹œ์ž‘...")
237
+ trials = Trials()
238
+ xgb_best = fmin(
239
+ fn=objective_func,
240
+ space=xgb_search_space,
241
+ algo=tpe.suggest,
242
+ max_evals=MAX_EVALS,
243
+ trials=trials
244
+ )
245
+
246
+ # ์ตœ์ ํ™” ๊ฒฐ๊ณผ ๋ถ„์„ ๋ฐ ์ถœ๋ ฅ
247
+ print(f"\n์ตœ์ ํ™” ์™„๋ฃŒ. ์ตœ์  ํŒŒ๋ผ๋ฏธํ„ฐ: {xgb_best}")
248
+
249
+ # Best loss (CSI ์ ์ˆ˜์˜ ์Œ์ˆ˜๊ฐ’์ด๋ฏ€๋กœ, ์‹ค์ œ CSI๋Š” -loss)
250
+ best_loss = trials.best_trial['result']['loss']
251
+ best_csi = -best_loss
252
+ print(f"์ตœ์  CSI ์ ์ˆ˜: {best_csi:.4f} (loss: {best_loss:.4f})")
253
+
254
+ # ๋ชจ๋“  trial์˜ loss ๊ฐ’ ์ถ”์ถœ
255
+ losses = [trial['result']['loss'] for trial in trials.trials if trial['result']['status'] == 'ok']
256
+ csi_scores = [-loss for loss in losses]
257
+
258
+ print(f"\n์ตœ์ ํ™” ๊ณผ์ • ์š”์•ฝ:")
259
+ print(f" - ์ด ์‹œ๋„ ํšŸ์ˆ˜: {len(trials.trials)}")
260
+ print(f" - ์„ฑ๊ณตํ•œ ์‹œ๋„: {len(losses)}")
261
+ print(f" - ์ตœ์ดˆ CSI: {csi_scores[0]:.4f}")
262
+ print(f" - ์ตœ์ข… CSI: {csi_scores[-1]:.4f}")
263
+ print(f" - ์ตœ๊ณ  CSI: {max(csi_scores):.4f}")
264
+ print(f" - ์ตœ์ € CSI: {min(csi_scores):.4f}")
265
+ print(f" - ํ‰๊ท  CSI: {np.mean(csi_scores):.4f}")
266
+
267
+ # Trials ๊ฐ์ฒด ์ €์žฅ
268
+ # ํŒŒ์ผ ์œ„์น˜ ๊ธฐ๋ฐ˜์œผ๋กœ base ๋””๋ ‰ํ† ๋ฆฌ ๊ฒฝ๋กœ ์„ค์ •
269
+ current_file_dir = os.path.dirname(os.path.abspath(__file__))
270
+ base_dir = os.path.dirname(os.path.dirname(current_file_dir)) # 5.optima ๋””๋ ‰ํ† ๋ฆฌ
271
+ os.makedirs(os.path.join(base_dir, "optimization_history"), exist_ok=True)
272
+ trials_path = os.path.join(base_dir, "optimization_history/xgb_ctgan10000_daejeon_trials.pkl")
273
+ joblib.dump(trials, trials_path)
274
+ print(f"\n์ตœ์ ํ™” Trials ๊ฐ์ฒด๊ฐ€ {trials_path}์— ์ €์žฅ๋˜์—ˆ์Šต๋‹ˆ๋‹ค.")
275
+
276
+ # ์ตœ์ ํ™”๋œ ํ•˜์ดํผํŒŒ๋ผ๋ฏธํ„ฐ๋กœ ์ตœ์ข… ๋ชจ๋ธ ํ•™์Šต
277
+ print("์ตœ์ข… ๋ชจ๋ธ ํ•™์Šต ์‹œ์ž‘...")
278
+ models = []
279
+
280
+ for fold_idx, (df_sampled, (train_years, val_year)) in enumerate(
281
+ zip(df_ctgan_list, FOLD_CONFIGS), start=1
282
+ ):
283
+ print(f"Fold {fold_idx} ํ•™์Šต ์ค‘... (ํ•™์Šต ์—ฐ๋„: {train_years}, ๊ฒ€์ฆ ์—ฐ๋„: {val_year})")
284
+
285
+ X_train, X_val, y_train, y_val = split_data(
286
+ df_sampled, df_daejeon, train_years, val_year
287
+ )
288
+
289
+ xgb_model = create_xgb_model(best_params=xgb_best)
290
+ xgb_model.fit(X_train, y_train, eval_set=[(X_val, y_val)], verbose=False)
291
+
292
+ # ๊ฒ€์ฆ ์„ฑ๋Šฅ ์ถœ๋ ฅ
293
+ val_csi = calculate_csi(y_val, xgb_model.predict(X_val))
294
+ print(f"Fold {fold_idx} ๊ฒ€์ฆ CSI: {val_csi:.4f}")
295
+
296
+ models.append(xgb_model)
297
+
298
+
299
+ # ๋ชจ๋ธ ์ €์žฅ
300
+ print("๋ชจ๋ธ ์ €์žฅ ์ค‘...")
301
+ os.makedirs(os.path.join(base_dir, "save_model/xgb_optima"), exist_ok=True)
302
+ model_save_path = os.path.join(base_dir, "save_model/xgb_optima/xgb_ctgan10000_daejeon.pkl")
303
+ joblib.dump(models, model_save_path)
304
+ print(f"๋ชจ๋ธ์ด {model_save_path}์— ์ €์žฅ๋˜์—ˆ์Šต๋‹ˆ๋‹ค.")
305
+
Analysis_code/5.optima/xgb_ctgan10000/XGB_ctgan10000_gwangju.py ADDED
@@ -0,0 +1,305 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ import pandas as pd
2
+ import os
3
+ import numpy as np
4
+ import joblib
5
+ from xgboost import XGBClassifier
6
+ from warnings import filterwarnings
7
+ filterwarnings('ignore')
8
+ from sklearn.metrics import confusion_matrix
9
+ from hyperopt import fmin, tpe, Trials, hp
10
+
11
+ # ์ƒ์ˆ˜ ์ •์˜
12
+ RANDOM_STATE = 42
13
+ N_ESTIMATORS = 4000
14
+ EARLY_STOPPING_ROUNDS = 400
15
+ MAX_EVALS = 100
16
+
17
+ # Fold ์„ค์ •: (train_years, val_year)
18
+ FOLD_CONFIGS = [
19
+ ([2018, 2019], 2020), # Fold 1
20
+ ([2018, 2020], 2019), # Fold 2
21
+ ([2019, 2020], 2018), # Fold 3
22
+ ]
23
+
24
+ def calculate_csi(Y_test, pred):
25
+ """CSI(Critical Success Index) ์ ์ˆ˜๋ฅผ ๊ณ„์‚ฐํ•ฉ๋‹ˆ๋‹ค.
26
+
27
+ Args:
28
+ Y_test: ์‹ค์ œ ๋ ˆ์ด๋ธ”
29
+ pred: ์˜ˆ์ธก ๋ ˆ์ด๋ธ”
30
+
31
+ Returns:
32
+ CSI ์ ์ˆ˜ (0~1 ์‚ฌ์ด์˜ ๊ฐ’)
33
+ """
34
+ cm = confusion_matrix(Y_test, pred)
35
+ H = (cm[0, 0] + cm[1, 1])
36
+ F = (cm[1, 0] + cm[2, 0] + cm[0, 1] + cm[2, 1])
37
+ M = (cm[0, 2] + cm[1, 2])
38
+ CSI = H / (H + F + M + 1e-10)
39
+ return CSI
40
+
41
+ def eval_metric_csi(y_true, pred_prob):
42
+ """XGBoost์šฉ CSI ๋ฉ”ํŠธ๋ฆญ ํ•จ์ˆ˜.
43
+
44
+ Args:
45
+ y_true: ์‹ค์ œ ๋ ˆ์ด๋ธ”
46
+ pred_prob: ์˜ˆ์ธก ํ™•๋ฅ 
47
+
48
+ Returns:
49
+ CSI ์ ์ˆ˜์˜ ์Œ์ˆ˜๊ฐ’
50
+ """
51
+ pred = np.argmax(pred_prob, axis=1)
52
+ csi = calculate_csi(y_true, pred)
53
+ return -1*csi
54
+
55
+ def add_derived_features(df: pd.DataFrame) -> pd.DataFrame:
56
+ """
57
+ ์ œ๊ฑฐํ–ˆ๋˜ ํŒŒ์ƒ ๋ณ€์ˆ˜๋“ค์„ ๋ณต๊ตฌ
58
+
59
+ Args:
60
+ df: ๋ฐ์ดํ„ฐํ”„๋ ˆ์ž„
61
+
62
+ Returns:
63
+ ํŒŒ์ƒ ๋ณ€์ˆ˜๊ฐ€ ์ถ”๊ฐ€๋œ ๋ฐ์ดํ„ฐํ”„๋ ˆ์ž„
64
+ """
65
+ df = df.copy()
66
+ df['hour_sin'] = np.sin(2 * np.pi * df['hour'] / 24)
67
+ df['hour_cos'] = np.cos(2 * np.pi * df['hour'] / 24)
68
+ df['month_sin'] = np.sin(2 * np.pi * df['month'] / 12)
69
+ df['month_cos'] = np.cos(2 * np.pi * df['month'] / 12)
70
+ df['ground_temp - temp_C'] = df['groundtemp'] - df['temp_C']
71
+ return df
72
+
73
+ def preprocessing(df):
74
+ """๋ฐ์ดํ„ฐ ์ „์ฒ˜๋ฆฌ ํ•จ์ˆ˜.
75
+
76
+ Args:
77
+ df: ์›๋ณธ ๋ฐ์ดํ„ฐํ”„๋ ˆ์ž„
78
+
79
+ Returns:
80
+ ์ „์ฒ˜๋ฆฌ๋œ ๋ฐ์ดํ„ฐํ”„๋ ˆ์ž„
81
+ """
82
+ df = df[df.columns].copy()
83
+ df['year'] = df['year'].astype('int')
84
+ df['month'] = df['month'].astype('int')
85
+ df['hour'] = df['hour'].astype('int')
86
+ df = add_derived_features(df).copy()
87
+ df['multi_class'] = df['multi_class'].astype('int')
88
+ df.loc[df['wind_dir']=='์ •์˜จ', 'wind_dir'] = "0"
89
+ df['wind_dir'] = df['wind_dir'].astype('int')
90
+ df = df[['temp_C', 'precip_mm', 'wind_speed', 'wind_dir', 'hm',
91
+ 'vap_pressure', 'dewpoint_C', 'loc_pressure', 'sea_pressure',
92
+ 'solarRad', 'snow_cm', 'cloudcover', 'lm_cloudcover', 'low_cloudbase',
93
+ 'groundtemp', 'O3', 'NO2', 'PM10', 'PM25', 'year',
94
+ 'month', 'hour', 'ground_temp - temp_C', 'hour_sin', 'hour_cos',
95
+ 'month_sin', 'month_cos','multi_class']].copy()
96
+ return df
97
+
98
+ def create_xgb_model(search_space=None, best_params=None):
99
+ """XGBoost ๋ชจ๋ธ์„ ์ƒ์„ฑํ•ฉ๋‹ˆ๋‹ค.
100
+
101
+ Args:
102
+ search_space: ํ•˜์ดํผํŒŒ๋ผ๋ฏธํ„ฐ ๊ฒ€์ƒ‰ ๊ณต๊ฐ„ (objective_func์—์„œ ์‚ฌ์šฉ)
103
+ best_params: ์ตœ์ ํ™”๋œ ํ•˜์ดํผํŒŒ๋ผ๋ฏธํ„ฐ (์ตœ์ข… ๋ชจ๋ธ ํ•™์Šต์—์„œ ์‚ฌ์šฉ)
104
+
105
+ Returns:
106
+ XGBClassifier ์ธ์Šคํ„ด์Šค
107
+ """
108
+ base_params = {
109
+ 'n_estimators': N_ESTIMATORS,
110
+ 'tree_method': 'hist',
111
+ 'device': 'cuda',
112
+ 'enable_categorical': True,
113
+ 'eval_metric': eval_metric_csi,
114
+ 'objective': 'multi:softprob',
115
+ 'random_state': RANDOM_STATE,
116
+ 'early_stopping_rounds': EARLY_STOPPING_ROUNDS,
117
+ }
118
+
119
+ if search_space is not None:
120
+ # ํ•˜์ดํผํŒŒ๋ผ๋ฏธํ„ฐ ์ตœ์ ํ™” ์ค‘
121
+ params = {
122
+ **base_params,
123
+ 'learning_rate': search_space['learning_rate'],
124
+ 'max_depth': int(search_space['max_depth']),
125
+ 'min_child_weight': int(search_space['min_child_weight']),
126
+ 'gamma': search_space['gamma'],
127
+ 'subsample': search_space['subsample'],
128
+ 'colsample_bytree': search_space['colsample_bytree'],
129
+ 'reg_alpha': search_space['reg_alpha'],
130
+ 'reg_lambda': search_space['reg_lambda'],
131
+ }
132
+ elif best_params is not None:
133
+ # ์ตœ์ ํ™”๋œ ํŒŒ๋ผ๋ฏธํ„ฐ๋กœ ์ตœ์ข… ๋ชจ๋ธ ์ƒ์„ฑ
134
+ params = {
135
+ **base_params,
136
+ 'learning_rate': best_params['learning_rate'],
137
+ 'max_depth': int(best_params['max_depth']),
138
+ 'min_child_weight': int(best_params['min_child_weight']),
139
+ 'gamma': best_params['gamma'],
140
+ 'subsample': best_params['subsample'],
141
+ 'colsample_bytree': best_params['colsample_bytree'],
142
+ 'reg_alpha': best_params['reg_alpha'],
143
+ 'reg_lambda': best_params['reg_lambda'],
144
+ }
145
+ else:
146
+ params = base_params
147
+
148
+ return XGBClassifier(**params)
149
+
150
+
151
+ # ๋ฐ์ดํ„ฐ ๋กœ๋”ฉ ๋ฐ ์ „์ฒ˜๋ฆฌ
152
+ print("๋ฐ์ดํ„ฐ ๋กœ๋”ฉ ์ค‘...")
153
+ # ํŒŒ์ผ ์œ„์น˜ ๊ธฐ๋ฐ˜์œผ๋กœ ๋ฐ์ดํ„ฐ ๋””๋ ‰ํ† ๋ฆฌ ๊ฒฝ๋กœ ์„ค์ •
154
+ current_file_dir = os.path.dirname(os.path.abspath(__file__))
155
+ data_base_dir = os.path.abspath(os.path.join(current_file_dir, '../../../data'))
156
+ df_gwangju = pd.read_csv(os.path.join(data_base_dir, "data_for_modeling/gwangju_train.csv"))
157
+ df_ctgan_gwangju_1 = pd.read_csv(os.path.join(data_base_dir, "data_oversampled/ctgan10000/ctgan10000_1_gwangju.csv"))
158
+ df_ctgan_gwangju_2 = pd.read_csv(os.path.join(data_base_dir, "data_oversampled/ctgan10000/ctgan10000_2_gwangju.csv"))
159
+ df_ctgan_gwangju_3 = pd.read_csv(os.path.join(data_base_dir, "data_oversampled/ctgan10000/ctgan10000_3_gwangju.csv"))
160
+
161
+ print("๋ฐ์ดํ„ฐ ์ „์ฒ˜๋ฆฌ ์ค‘...")
162
+ df_ctgan_gwangju_1 = preprocessing(df_ctgan_gwangju_1)
163
+ df_ctgan_gwangju_2 = preprocessing(df_ctgan_gwangju_2)
164
+ df_ctgan_gwangju_3 = preprocessing(df_ctgan_gwangju_3)
165
+ df_gwangju = preprocessing(df_gwangju)
166
+
167
+ # CTGAN ๋ฐ์ดํ„ฐ ๋ฆฌ์ŠคํŠธ (fold ์ˆœ์„œ์™€ ์ผ์น˜)
168
+ df_ctgan_list = [df_ctgan_gwangju_1, df_ctgan_gwangju_2, df_ctgan_gwangju_3]
169
+
170
+ def split_data(df_sampled, df_original, train_years, val_year):
171
+ """๋ฐ์ดํ„ฐ๋ฅผ ํ•™์Šต์šฉ๊ณผ ๊ฒ€์ฆ์šฉ์œผ๋กœ ๋ถ„ํ• ํ•ฉ๋‹ˆ๋‹ค.
172
+
173
+ Args:
174
+ df_sampled: ์ƒ˜ํ”Œ๋ง๋œ ๋ฐ์ดํ„ฐํ”„๋ ˆ์ž„
175
+ df_original: ์›๋ณธ ๋ฐ์ดํ„ฐํ”„๋ ˆ์ž„
176
+ train_years: ํ•™์Šต์— ์‚ฌ์šฉํ•  ์—ฐ๋„ ๋ฆฌ์ŠคํŠธ
177
+ val_year: ๊ฒ€์ฆ์— ์‚ฌ์šฉํ•  ์—ฐ๋„
178
+
179
+ Returns:
180
+ (X_train, X_val, y_train, y_val) ํŠœํ”Œ
181
+ """
182
+ # ํ•™์Šต ๋ฐ์ดํ„ฐ: ์ƒ˜ํ”Œ๋ง๋œ ๋ฐ์ดํ„ฐ์—์„œ train_years์— ํ•ด๋‹นํ•˜๋Š” ๋ฐ์ดํ„ฐ
183
+ train_mask = df_sampled['year'].isin(train_years)
184
+ X_train = df_sampled.loc[train_mask, df_sampled.columns != 'multi_class'].copy()
185
+ y_train = df_sampled.loc[train_mask, 'multi_class']
186
+
187
+ # ๊ฒ€์ฆ ๋ฐ์ดํ„ฐ: ์›๋ณธ ๋ฐ์ดํ„ฐ์—์„œ val_year์— ํ•ด๋‹นํ•˜๋Š” ๋ฐ์ดํ„ฐ
188
+ val_mask = df_original['year'] == val_year
189
+ X_val = df_original.loc[val_mask, df_original.columns != 'multi_class'].copy()
190
+ y_val = df_original.loc[val_mask, 'multi_class']
191
+
192
+ X_train.drop(columns=['year'], inplace=True)
193
+ X_val.drop(columns=['year'], inplace=True)
194
+
195
+ return X_train, X_val, y_train, y_val
196
+
197
+
198
+ # ํ•˜์ดํผํŒŒ๋ผ๋ฏธํ„ฐ ๊ฒ€์ƒ‰ ๊ณต๊ฐ„ ์ •์˜
199
+ xgb_search_space = {
200
+ 'learning_rate': hp.loguniform('learning_rate', np.log(0.01), np.log(0.2)),
201
+ 'max_depth': hp.quniform('max_depth', 3, 12, 1),
202
+ 'min_child_weight': hp.quniform('min_child_weight', 1, 20, 1),
203
+ 'gamma': hp.uniform('gamma', 0, 5), # ํŠธ๋ฆฌ ๋ถ„ํ• ์„ ์œ„ํ•œ ์ตœ์†Œ ์†์‹ค ๊ฐ์†Œ ๊ฐ’
204
+ 'subsample': hp.uniform('subsample', 0.6, 1.0),
205
+ 'colsample_bytree': hp.uniform('colsample_bytree', 0.6, 1.0),
206
+ 'reg_alpha': hp.uniform('reg_alpha', 0.0, 1.0),
207
+ 'reg_lambda': hp.uniform('reg_lambda', 0.0, 1.0)
208
+ }
209
+
210
+ def objective_func(search_space):
211
+ """ํ•˜์ดํผํŒŒ๋ผ๋ฏธํ„ฐ ์ตœ์ ํ™”๋ฅผ ์œ„ํ•œ ๋ชฉ์  ํ•จ์ˆ˜.
212
+
213
+ Args:
214
+ search_space: ํ•˜์ดํผํŒŒ๋ผ๋ฏธํ„ฐ ๊ฒ€์ƒ‰ ๊ณต๊ฐ„
215
+
216
+ Returns:
217
+ ํ‰๊ท  CSI ์ ์ˆ˜์˜ ์Œ์ˆ˜๊ฐ’ (hyperopt๋Š” ์ตœ์†Œํ™”๋ฅผ ์ˆ˜ํ–‰ํ•˜๋ฏ€๋กœ)
218
+ """
219
+ xgb_model = create_xgb_model(search_space=search_space)
220
+ csi_scores = []
221
+
222
+ # ๊ฐ fold์— ๋Œ€ํ•ด ๊ต์ฐจ ๊ฒ€์ฆ ์ˆ˜ํ–‰
223
+ for df_sampled, (train_years, val_year) in zip(df_ctgan_list, FOLD_CONFIGS):
224
+ X_train, X_val, y_train, y_val = split_data(
225
+ df_sampled, df_gwangju, train_years, val_year
226
+ )
227
+
228
+ xgb_model.fit(X_train, y_train, eval_set=[(X_val, y_val)], verbose=False)
229
+ csi = calculate_csi(y_val, xgb_model.predict(X_val))
230
+ csi_scores.append(csi)
231
+
232
+ return -1*round(np.mean(csi_scores), 4)
233
+
234
+
235
+ # ํ•˜์ดํผํŒŒ๋ผ๋ฏธํ„ฐ ์ตœ์ ํ™”
236
+ print("ํ•˜์ดํผํŒŒ๋ผ๋ฏธํ„ฐ ์ตœ์ ํ™” ์‹œ์ž‘...")
237
+ trials = Trials()
238
+ xgb_best = fmin(
239
+ fn=objective_func,
240
+ space=xgb_search_space,
241
+ algo=tpe.suggest,
242
+ max_evals=MAX_EVALS,
243
+ trials=trials
244
+ )
245
+
246
+ # ์ตœ์ ํ™” ๊ฒฐ๊ณผ ๋ถ„์„ ๋ฐ ์ถœ๋ ฅ
247
+ print(f"\n์ตœ์ ํ™” ์™„๋ฃŒ. ์ตœ์  ํŒŒ๋ผ๋ฏธํ„ฐ: {xgb_best}")
248
+
249
+ # Best loss (CSI ์ ์ˆ˜์˜ ์Œ์ˆ˜๊ฐ’์ด๋ฏ€๋กœ, ์‹ค์ œ CSI๋Š” -loss)
250
+ best_loss = trials.best_trial['result']['loss']
251
+ best_csi = -best_loss
252
+ print(f"์ตœ์  CSI ์ ์ˆ˜: {best_csi:.4f} (loss: {best_loss:.4f})")
253
+
254
+ # ๋ชจ๋“  trial์˜ loss ๊ฐ’ ์ถ”์ถœ
255
+ losses = [trial['result']['loss'] for trial in trials.trials if trial['result']['status'] == 'ok']
256
+ csi_scores = [-loss for loss in losses]
257
+
258
+ print(f"\n์ตœ์ ํ™” ๊ณผ์ • ์š”์•ฝ:")
259
+ print(f" - ์ด ์‹œ๋„ ํšŸ์ˆ˜: {len(trials.trials)}")
260
+ print(f" - ์„ฑ๊ณตํ•œ ์‹œ๋„: {len(losses)}")
261
+ print(f" - ์ตœ์ดˆ CSI: {csi_scores[0]:.4f}")
262
+ print(f" - ์ตœ์ข… CSI: {csi_scores[-1]:.4f}")
263
+ print(f" - ์ตœ๊ณ  CSI: {max(csi_scores):.4f}")
264
+ print(f" - ์ตœ์ € CSI: {min(csi_scores):.4f}")
265
+ print(f" - ํ‰๊ท  CSI: {np.mean(csi_scores):.4f}")
266
+
267
+ # Trials ๊ฐ์ฒด ์ €์žฅ
268
+ # ํŒŒ์ผ ์œ„์น˜ ๊ธฐ๋ฐ˜์œผ๋กœ base ๋””๋ ‰ํ† ๋ฆฌ ๊ฒฝ๋กœ ์„ค์ •
269
+ current_file_dir = os.path.dirname(os.path.abspath(__file__))
270
+ base_dir = os.path.dirname(os.path.dirname(current_file_dir)) # 5.optima ๋””๋ ‰ํ† ๋ฆฌ
271
+ os.makedirs(os.path.join(base_dir, "optimization_history"), exist_ok=True)
272
+ trials_path = os.path.join(base_dir, "optimization_history/xgb_ctgan10000_gwangju_trials.pkl")
273
+ joblib.dump(trials, trials_path)
274
+ print(f"\n์ตœ์ ํ™” Trials ๊ฐ์ฒด๊ฐ€ {trials_path}์— ์ €์žฅ๋˜์—ˆ์Šต๋‹ˆ๋‹ค.")
275
+
276
+ # ์ตœ์ ํ™”๋œ ํ•˜์ดํผํŒŒ๋ผ๋ฏธํ„ฐ๋กœ ์ตœ์ข… ๋ชจ๋ธ ํ•™์Šต
277
+ print("์ตœ์ข… ๋ชจ๋ธ ํ•™์Šต ์‹œ์ž‘...")
278
+ models = []
279
+
280
+ for fold_idx, (df_sampled, (train_years, val_year)) in enumerate(
281
+ zip(df_ctgan_list, FOLD_CONFIGS), start=1
282
+ ):
283
+ print(f"Fold {fold_idx} ํ•™์Šต ์ค‘... (ํ•™์Šต ์—ฐ๋„: {train_years}, ๊ฒ€์ฆ ์—ฐ๋„: {val_year})")
284
+
285
+ X_train, X_val, y_train, y_val = split_data(
286
+ df_sampled, df_gwangju, train_years, val_year
287
+ )
288
+
289
+ xgb_model = create_xgb_model(best_params=xgb_best)
290
+ xgb_model.fit(X_train, y_train, eval_set=[(X_val, y_val)], verbose=False)
291
+
292
+ # ๊ฒ€์ฆ ์„ฑ๋Šฅ ์ถœ๋ ฅ
293
+ val_csi = calculate_csi(y_val, xgb_model.predict(X_val))
294
+ print(f"Fold {fold_idx} ๊ฒ€์ฆ CSI: {val_csi:.4f}")
295
+
296
+ models.append(xgb_model)
297
+
298
+
299
+ # ๋ชจ๋ธ ์ €์žฅ
300
+ print("๋ชจ๋ธ ์ €์žฅ ์ค‘...")
301
+ os.makedirs(os.path.join(base_dir, "save_model/xgb_optima"), exist_ok=True)
302
+ model_save_path = os.path.join(base_dir, "save_model/xgb_optima/xgb_ctgan10000_gwangju.pkl")
303
+ joblib.dump(models, model_save_path)
304
+ print(f"๋ชจ๋ธ์ด {model_save_path}์— ์ €์žฅ๋˜์—ˆ์Šต๋‹ˆ๋‹ค.")
305
+
Analysis_code/5.optima/xgb_ctgan10000/XGB_ctgan10000_incheon.py ADDED
@@ -0,0 +1,305 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ import pandas as pd
2
+ import os
3
+ import numpy as np
4
+ import joblib
5
+ from xgboost import XGBClassifier
6
+ from warnings import filterwarnings
7
+ filterwarnings('ignore')
8
+ from sklearn.metrics import confusion_matrix
9
+ from hyperopt import fmin, tpe, Trials, hp
10
+
11
+ # ์ƒ์ˆ˜ ์ •์˜
12
+ RANDOM_STATE = 42
13
+ N_ESTIMATORS = 4000
14
+ EARLY_STOPPING_ROUNDS = 400
15
+ MAX_EVALS = 100
16
+
17
+ # Fold ์„ค์ •: (train_years, val_year)
18
+ FOLD_CONFIGS = [
19
+ ([2018, 2019], 2020), # Fold 1
20
+ ([2018, 2020], 2019), # Fold 2
21
+ ([2019, 2020], 2018), # Fold 3
22
+ ]
23
+
24
+ def calculate_csi(Y_test, pred):
25
+ """CSI(Critical Success Index) ์ ์ˆ˜๋ฅผ ๊ณ„์‚ฐํ•ฉ๋‹ˆ๋‹ค.
26
+
27
+ Args:
28
+ Y_test: ์‹ค์ œ ๋ ˆ์ด๋ธ”
29
+ pred: ์˜ˆ์ธก ๋ ˆ์ด๋ธ”
30
+
31
+ Returns:
32
+ CSI ์ ์ˆ˜ (0~1 ์‚ฌ์ด์˜ ๊ฐ’)
33
+ """
34
+ cm = confusion_matrix(Y_test, pred)
35
+ H = (cm[0, 0] + cm[1, 1])
36
+ F = (cm[1, 0] + cm[2, 0] + cm[0, 1] + cm[2, 1])
37
+ M = (cm[0, 2] + cm[1, 2])
38
+ CSI = H / (H + F + M + 1e-10)
39
+ return CSI
40
+
41
+ def eval_metric_csi(y_true, pred_prob):
42
+ """XGBoost์šฉ CSI ๋ฉ”ํŠธ๋ฆญ ํ•จ์ˆ˜.
43
+
44
+ Args:
45
+ y_true: ์‹ค์ œ ๋ ˆ์ด๋ธ”
46
+ pred_prob: ์˜ˆ์ธก ํ™•๋ฅ 
47
+
48
+ Returns:
49
+ CSI ์ ์ˆ˜์˜ ์Œ์ˆ˜๊ฐ’
50
+ """
51
+ pred = np.argmax(pred_prob, axis=1)
52
+ csi = calculate_csi(y_true, pred)
53
+ return -1*csi
54
+
55
+ def add_derived_features(df: pd.DataFrame) -> pd.DataFrame:
56
+ """
57
+ ์ œ๊ฑฐํ–ˆ๋˜ ํŒŒ์ƒ ๋ณ€์ˆ˜๋“ค์„ ๋ณต๊ตฌ
58
+
59
+ Args:
60
+ df: ๋ฐ์ดํ„ฐํ”„๋ ˆ์ž„
61
+
62
+ Returns:
63
+ ํŒŒ์ƒ ๋ณ€์ˆ˜๊ฐ€ ์ถ”๊ฐ€๋œ ๋ฐ์ดํ„ฐํ”„๋ ˆ์ž„
64
+ """
65
+ df = df.copy()
66
+ df['hour_sin'] = np.sin(2 * np.pi * df['hour'] / 24)
67
+ df['hour_cos'] = np.cos(2 * np.pi * df['hour'] / 24)
68
+ df['month_sin'] = np.sin(2 * np.pi * df['month'] / 12)
69
+ df['month_cos'] = np.cos(2 * np.pi * df['month'] / 12)
70
+ df['ground_temp - temp_C'] = df['groundtemp'] - df['temp_C']
71
+ return df
72
+
73
+ def preprocessing(df):
74
+ """๋ฐ์ดํ„ฐ ์ „์ฒ˜๋ฆฌ ํ•จ์ˆ˜.
75
+
76
+ Args:
77
+ df: ์›๋ณธ ๋ฐ์ดํ„ฐํ”„๋ ˆ์ž„
78
+
79
+ Returns:
80
+ ์ „์ฒ˜๋ฆฌ๋œ ๋ฐ์ดํ„ฐํ”„๋ ˆ์ž„
81
+ """
82
+ df = df[df.columns].copy()
83
+ df['year'] = df['year'].astype('int')
84
+ df['month'] = df['month'].astype('int')
85
+ df['hour'] = df['hour'].astype('int')
86
+ df = add_derived_features(df).copy()
87
+ df['multi_class'] = df['multi_class'].astype('int')
88
+ df.loc[df['wind_dir']=='์ •์˜จ', 'wind_dir'] = "0"
89
+ df['wind_dir'] = df['wind_dir'].astype('int')
90
+ df = df[['temp_C', 'precip_mm', 'wind_speed', 'wind_dir', 'hm',
91
+ 'vap_pressure', 'dewpoint_C', 'loc_pressure', 'sea_pressure',
92
+ 'solarRad', 'snow_cm', 'cloudcover', 'lm_cloudcover', 'low_cloudbase',
93
+ 'groundtemp', 'O3', 'NO2', 'PM10', 'PM25', 'year',
94
+ 'month', 'hour', 'ground_temp - temp_C', 'hour_sin', 'hour_cos',
95
+ 'month_sin', 'month_cos','multi_class']].copy()
96
+ return df
97
+
98
+ def create_xgb_model(search_space=None, best_params=None):
99
+ """XGBoost ๋ชจ๋ธ์„ ์ƒ์„ฑํ•ฉ๋‹ˆ๋‹ค.
100
+
101
+ Args:
102
+ search_space: ํ•˜์ดํผํŒŒ๋ผ๋ฏธํ„ฐ ๊ฒ€์ƒ‰ ๊ณต๊ฐ„ (objective_func์—์„œ ์‚ฌ์šฉ)
103
+ best_params: ์ตœ์ ํ™”๋œ ํ•˜์ดํผํŒŒ๋ผ๋ฏธํ„ฐ (์ตœ์ข… ๋ชจ๋ธ ํ•™์Šต์—์„œ ์‚ฌ์šฉ)
104
+
105
+ Returns:
106
+ XGBClassifier ์ธ์Šคํ„ด์Šค
107
+ """
108
+ base_params = {
109
+ 'n_estimators': N_ESTIMATORS,
110
+ 'tree_method': 'hist',
111
+ 'device': 'cuda',
112
+ 'enable_categorical': True,
113
+ 'eval_metric': eval_metric_csi,
114
+ 'objective': 'multi:softprob',
115
+ 'random_state': RANDOM_STATE,
116
+ 'early_stopping_rounds': EARLY_STOPPING_ROUNDS,
117
+ }
118
+
119
+ if search_space is not None:
120
+ # ํ•˜์ดํผํŒŒ๋ผ๋ฏธํ„ฐ ์ตœ์ ํ™” ์ค‘
121
+ params = {
122
+ **base_params,
123
+ 'learning_rate': search_space['learning_rate'],
124
+ 'max_depth': int(search_space['max_depth']),
125
+ 'min_child_weight': int(search_space['min_child_weight']),
126
+ 'gamma': search_space['gamma'],
127
+ 'subsample': search_space['subsample'],
128
+ 'colsample_bytree': search_space['colsample_bytree'],
129
+ 'reg_alpha': search_space['reg_alpha'],
130
+ 'reg_lambda': search_space['reg_lambda'],
131
+ }
132
+ elif best_params is not None:
133
+ # ์ตœ์ ํ™”๋œ ํŒŒ๋ผ๋ฏธํ„ฐ๋กœ ์ตœ์ข… ๋ชจ๋ธ ์ƒ์„ฑ
134
+ params = {
135
+ **base_params,
136
+ 'learning_rate': best_params['learning_rate'],
137
+ 'max_depth': int(best_params['max_depth']),
138
+ 'min_child_weight': int(best_params['min_child_weight']),
139
+ 'gamma': best_params['gamma'],
140
+ 'subsample': best_params['subsample'],
141
+ 'colsample_bytree': best_params['colsample_bytree'],
142
+ 'reg_alpha': best_params['reg_alpha'],
143
+ 'reg_lambda': best_params['reg_lambda'],
144
+ }
145
+ else:
146
+ params = base_params
147
+
148
+ return XGBClassifier(**params)
149
+
150
+
151
+ # ๋ฐ์ดํ„ฐ ๋กœ๋”ฉ ๋ฐ ์ „์ฒ˜๋ฆฌ
152
+ print("๋ฐ์ดํ„ฐ ๋กœ๋”ฉ ์ค‘...")
153
+ # ํŒŒ์ผ ์œ„์น˜ ๊ธฐ๋ฐ˜์œผ๋กœ ๋ฐ์ดํ„ฐ ๋””๋ ‰ํ† ๋ฆฌ ๊ฒฝ๋กœ ์„ค์ •
154
+ current_file_dir = os.path.dirname(os.path.abspath(__file__))
155
+ data_base_dir = os.path.abspath(os.path.join(current_file_dir, '../../../data'))
156
+ df_incheon = pd.read_csv(os.path.join(data_base_dir, "data_for_modeling/incheon_train.csv"))
157
+ df_ctgan_incheon_1 = pd.read_csv(os.path.join(data_base_dir, "data_oversampled/ctgan10000/ctgan10000_1_incheon.csv"))
158
+ df_ctgan_incheon_2 = pd.read_csv(os.path.join(data_base_dir, "data_oversampled/ctgan10000/ctgan10000_2_incheon.csv"))
159
+ df_ctgan_incheon_3 = pd.read_csv(os.path.join(data_base_dir, "data_oversampled/ctgan10000/ctgan10000_3_incheon.csv"))
160
+
161
+ print("๋ฐ์ดํ„ฐ ์ „์ฒ˜๋ฆฌ ์ค‘...")
162
+ df_ctgan_incheon_1 = preprocessing(df_ctgan_incheon_1)
163
+ df_ctgan_incheon_2 = preprocessing(df_ctgan_incheon_2)
164
+ df_ctgan_incheon_3 = preprocessing(df_ctgan_incheon_3)
165
+ df_incheon = preprocessing(df_incheon)
166
+
167
+ # CTGAN ๋ฐ์ดํ„ฐ ๋ฆฌ์ŠคํŠธ (fold ์ˆœ์„œ์™€ ์ผ์น˜)
168
+ df_ctgan_list = [df_ctgan_incheon_1, df_ctgan_incheon_2, df_ctgan_incheon_3]
169
+
170
+ def split_data(df_sampled, df_original, train_years, val_year):
171
+ """๋ฐ์ดํ„ฐ๋ฅผ ํ•™์Šต์šฉ๊ณผ ๊ฒ€์ฆ์šฉ์œผ๋กœ ๋ถ„ํ• ํ•ฉ๋‹ˆ๋‹ค.
172
+
173
+ Args:
174
+ df_sampled: ์ƒ˜ํ”Œ๋ง๋œ ๋ฐ์ดํ„ฐํ”„๋ ˆ์ž„
175
+ df_original: ์›๋ณธ ๋ฐ์ดํ„ฐํ”„๋ ˆ์ž„
176
+ train_years: ํ•™์Šต์— ์‚ฌ์šฉํ•  ์—ฐ๋„ ๋ฆฌ์ŠคํŠธ
177
+ val_year: ๊ฒ€์ฆ์— ์‚ฌ์šฉํ•  ์—ฐ๋„
178
+
179
+ Returns:
180
+ (X_train, X_val, y_train, y_val) ํŠœํ”Œ
181
+ """
182
+ # ํ•™์Šต ๋ฐ์ดํ„ฐ: ์ƒ˜ํ”Œ๋ง๋œ ๋ฐ์ดํ„ฐ์—์„œ train_years์— ํ•ด๋‹นํ•˜๋Š” ๋ฐ์ดํ„ฐ
183
+ train_mask = df_sampled['year'].isin(train_years)
184
+ X_train = df_sampled.loc[train_mask, df_sampled.columns != 'multi_class'].copy()
185
+ y_train = df_sampled.loc[train_mask, 'multi_class']
186
+
187
+ # ๊ฒ€์ฆ ๋ฐ์ดํ„ฐ: ์›๋ณธ ๋ฐ์ดํ„ฐ์—์„œ val_year์— ํ•ด๋‹นํ•˜๋Š” ๋ฐ์ดํ„ฐ
188
+ val_mask = df_original['year'] == val_year
189
+ X_val = df_original.loc[val_mask, df_original.columns != 'multi_class'].copy()
190
+ y_val = df_original.loc[val_mask, 'multi_class']
191
+
192
+ X_train.drop(columns=['year'], inplace=True)
193
+ X_val.drop(columns=['year'], inplace=True)
194
+
195
+ return X_train, X_val, y_train, y_val
196
+
197
+
198
+ # ํ•˜์ดํผํŒŒ๋ผ๋ฏธํ„ฐ ๊ฒ€์ƒ‰ ๊ณต๊ฐ„ ์ •์˜
199
+ xgb_search_space = {
200
+ 'learning_rate': hp.loguniform('learning_rate', np.log(0.01), np.log(0.2)),
201
+ 'max_depth': hp.quniform('max_depth', 3, 12, 1),
202
+ 'min_child_weight': hp.quniform('min_child_weight', 1, 20, 1),
203
+ 'gamma': hp.uniform('gamma', 0, 5), # ํŠธ๋ฆฌ ๋ถ„ํ• ์„ ์œ„ํ•œ ์ตœ์†Œ ์†์‹ค ๊ฐ์†Œ ๊ฐ’
204
+ 'subsample': hp.uniform('subsample', 0.6, 1.0),
205
+ 'colsample_bytree': hp.uniform('colsample_bytree', 0.6, 1.0),
206
+ 'reg_alpha': hp.uniform('reg_alpha', 0.0, 1.0),
207
+ 'reg_lambda': hp.uniform('reg_lambda', 0.0, 1.0)
208
+ }
209
+
210
+ def objective_func(search_space):
211
+ """ํ•˜์ดํผํŒŒ๋ผ๋ฏธํ„ฐ ์ตœ์ ํ™”๋ฅผ ์œ„ํ•œ ๋ชฉ์  ํ•จ์ˆ˜.
212
+
213
+ Args:
214
+ search_space: ํ•˜์ดํผํŒŒ๋ผ๋ฏธํ„ฐ ๊ฒ€์ƒ‰ ๊ณต๊ฐ„
215
+
216
+ Returns:
217
+ ํ‰๊ท  CSI ์ ์ˆ˜์˜ ์Œ์ˆ˜๊ฐ’ (hyperopt๋Š” ์ตœ์†Œํ™”๋ฅผ ์ˆ˜ํ–‰ํ•˜๋ฏ€๋กœ)
218
+ """
219
+ xgb_model = create_xgb_model(search_space=search_space)
220
+ csi_scores = []
221
+
222
+ # ๊ฐ fold์— ๋Œ€ํ•ด ๊ต์ฐจ ๊ฒ€์ฆ ์ˆ˜ํ–‰
223
+ for df_sampled, (train_years, val_year) in zip(df_ctgan_list, FOLD_CONFIGS):
224
+ X_train, X_val, y_train, y_val = split_data(
225
+ df_sampled, df_incheon, train_years, val_year
226
+ )
227
+
228
+ xgb_model.fit(X_train, y_train, eval_set=[(X_val, y_val)], verbose=False)
229
+ csi = calculate_csi(y_val, xgb_model.predict(X_val))
230
+ csi_scores.append(csi)
231
+
232
+ return -1*round(np.mean(csi_scores), 4)
233
+
234
+
235
+ # ํ•˜์ดํผํŒŒ๋ผ๋ฏธํ„ฐ ์ตœ์ ํ™”
236
+ print("ํ•˜์ดํผํŒŒ๋ผ๋ฏธํ„ฐ ์ตœ์ ํ™” ์‹œ์ž‘...")
237
+ trials = Trials()
238
+ xgb_best = fmin(
239
+ fn=objective_func,
240
+ space=xgb_search_space,
241
+ algo=tpe.suggest,
242
+ max_evals=MAX_EVALS,
243
+ trials=trials
244
+ )
245
+
246
+ # ์ตœ์ ํ™” ๊ฒฐ๊ณผ ๋ถ„์„ ๋ฐ ์ถœ๋ ฅ
247
+ print(f"\n์ตœ์ ํ™” ์™„๋ฃŒ. ์ตœ์  ํŒŒ๋ผ๋ฏธํ„ฐ: {xgb_best}")
248
+
249
+ # Best loss (CSI ์ ์ˆ˜์˜ ์Œ์ˆ˜๊ฐ’์ด๋ฏ€๋กœ, ์‹ค์ œ CSI๋Š” -loss)
250
+ best_loss = trials.best_trial['result']['loss']
251
+ best_csi = -best_loss
252
+ print(f"์ตœ์  CSI ์ ์ˆ˜: {best_csi:.4f} (loss: {best_loss:.4f})")
253
+
254
+ # ๋ชจ๋“  trial์˜ loss ๊ฐ’ ์ถ”์ถœ
255
+ losses = [trial['result']['loss'] for trial in trials.trials if trial['result']['status'] == 'ok']
256
+ csi_scores = [-loss for loss in losses]
257
+
258
+ print(f"\n์ตœ์ ํ™” ๊ณผ์ • ์š”์•ฝ:")
259
+ print(f" - ์ด ์‹œ๋„ ํšŸ์ˆ˜: {len(trials.trials)}")
260
+ print(f" - ์„ฑ๊ณตํ•œ ์‹œ๋„: {len(losses)}")
261
+ print(f" - ์ตœ์ดˆ CSI: {csi_scores[0]:.4f}")
262
+ print(f" - ์ตœ์ข… CSI: {csi_scores[-1]:.4f}")
263
+ print(f" - ์ตœ๊ณ  CSI: {max(csi_scores):.4f}")
264
+ print(f" - ์ตœ์ € CSI: {min(csi_scores):.4f}")
265
+ print(f" - ํ‰๊ท  CSI: {np.mean(csi_scores):.4f}")
266
+
267
+ # Trials ๊ฐ์ฒด ์ €์žฅ
268
+ # ํŒŒ์ผ ์œ„์น˜ ๊ธฐ๋ฐ˜์œผ๋กœ base ๋””๋ ‰ํ† ๋ฆฌ ๊ฒฝ๋กœ ์„ค์ •
269
+ current_file_dir = os.path.dirname(os.path.abspath(__file__))
270
+ base_dir = os.path.dirname(os.path.dirname(current_file_dir)) # 5.optima ๋””๋ ‰ํ† ๋ฆฌ
271
+ os.makedirs(os.path.join(base_dir, "optimization_history"), exist_ok=True)
272
+ trials_path = os.path.join(base_dir, "optimization_history/xgb_ctgan10000_incheon_trials.pkl")
273
+ joblib.dump(trials, trials_path)
274
+ print(f"\n์ตœ์ ํ™” Trials ๊ฐ์ฒด๊ฐ€ {trials_path}์— ์ €์žฅ๋˜์—ˆ์Šต๋‹ˆ๋‹ค.")
275
+
276
+ # ์ตœ์ ํ™”๋œ ํ•˜์ดํผํŒŒ๋ผ๋ฏธํ„ฐ๋กœ ์ตœ์ข… ๋ชจ๋ธ ํ•™์Šต
277
+ print("์ตœ์ข… ๋ชจ๋ธ ํ•™์Šต ์‹œ์ž‘...")
278
+ models = []
279
+
280
+ for fold_idx, (df_sampled, (train_years, val_year)) in enumerate(
281
+ zip(df_ctgan_list, FOLD_CONFIGS), start=1
282
+ ):
283
+ print(f"Fold {fold_idx} ํ•™์Šต ์ค‘... (ํ•™์Šต ์—ฐ๋„: {train_years}, ๊ฒ€์ฆ ์—ฐ๋„: {val_year})")
284
+
285
+ X_train, X_val, y_train, y_val = split_data(
286
+ df_sampled, df_incheon, train_years, val_year
287
+ )
288
+
289
+ xgb_model = create_xgb_model(best_params=xgb_best)
290
+ xgb_model.fit(X_train, y_train, eval_set=[(X_val, y_val)], verbose=False)
291
+
292
+ # ๊ฒ€์ฆ ์„ฑ๋Šฅ ์ถœ๋ ฅ
293
+ val_csi = calculate_csi(y_val, xgb_model.predict(X_val))
294
+ print(f"Fold {fold_idx} ๊ฒ€์ฆ CSI: {val_csi:.4f}")
295
+
296
+ models.append(xgb_model)
297
+
298
+
299
+ # ๋ชจ๋ธ ์ €์žฅ
300
+ print("๋ชจ๋ธ ์ €์žฅ ์ค‘...")
301
+ os.makedirs(os.path.join(base_dir, "save_model/xgb_optima"), exist_ok=True)
302
+ model_save_path = os.path.join(base_dir, "save_model/xgb_optima/xgb_ctgan10000_incheon.pkl")
303
+ joblib.dump(models, model_save_path)
304
+ print(f"๋ชจ๋ธ์ด {model_save_path}์— ์ €์žฅ๋˜์—ˆ์Šต๋‹ˆ๋‹ค.")
305
+
Analysis_code/5.optima/xgb_ctgan10000/XGB_ctgan10000_seoul.py ADDED
@@ -0,0 +1,305 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ import pandas as pd
2
+ import os
3
+ import numpy as np
4
+ import joblib
5
+ from xgboost import XGBClassifier
6
+ from warnings import filterwarnings
7
+ filterwarnings('ignore')
8
+ from sklearn.metrics import confusion_matrix
9
+ from hyperopt import fmin, tpe, Trials, hp
10
+
11
+ # ์ƒ์ˆ˜ ์ •์˜
12
+ RANDOM_STATE = 42
13
+ N_ESTIMATORS = 4000
14
+ EARLY_STOPPING_ROUNDS = 400
15
+ MAX_EVALS = 100
16
+
17
+ # Fold ์„ค์ •: (train_years, val_year)
18
+ FOLD_CONFIGS = [
19
+ ([2018, 2019], 2020), # Fold 1
20
+ ([2018, 2020], 2019), # Fold 2
21
+ ([2019, 2020], 2018), # Fold 3
22
+ ]
23
+
24
+ def calculate_csi(Y_test, pred):
25
+ """CSI(Critical Success Index) ์ ์ˆ˜๋ฅผ ๊ณ„์‚ฐํ•ฉ๋‹ˆ๋‹ค.
26
+
27
+ Args:
28
+ Y_test: ์‹ค์ œ ๋ ˆ์ด๋ธ”
29
+ pred: ์˜ˆ์ธก ๋ ˆ์ด๋ธ”
30
+
31
+ Returns:
32
+ CSI ์ ์ˆ˜ (0~1 ์‚ฌ์ด์˜ ๊ฐ’)
33
+ """
34
+ cm = confusion_matrix(Y_test, pred)
35
+ H = (cm[0, 0] + cm[1, 1])
36
+ F = (cm[1, 0] + cm[2, 0] + cm[0, 1] + cm[2, 1])
37
+ M = (cm[0, 2] + cm[1, 2])
38
+ CSI = H / (H + F + M + 1e-10)
39
+ return CSI
40
+
41
+ def eval_metric_csi(y_true, pred_prob):
42
+ """XGBoost์šฉ CSI ๋ฉ”ํŠธ๋ฆญ ํ•จ์ˆ˜.
43
+
44
+ Args:
45
+ y_true: ์‹ค์ œ ๋ ˆ์ด๋ธ”
46
+ pred_prob: ์˜ˆ์ธก ํ™•๋ฅ 
47
+
48
+ Returns:
49
+ CSI ์ ์ˆ˜์˜ ์Œ์ˆ˜๊ฐ’
50
+ """
51
+ pred = np.argmax(pred_prob, axis=1)
52
+ csi = calculate_csi(y_true, pred)
53
+ return -1*csi
54
+
55
+ def add_derived_features(df: pd.DataFrame) -> pd.DataFrame:
56
+ """
57
+ ์ œ๊ฑฐํ–ˆ๋˜ ํŒŒ์ƒ ๋ณ€์ˆ˜๋“ค์„ ๋ณต๊ตฌ
58
+
59
+ Args:
60
+ df: ๋ฐ์ดํ„ฐํ”„๋ ˆ์ž„
61
+
62
+ Returns:
63
+ ํŒŒ์ƒ ๋ณ€์ˆ˜๊ฐ€ ์ถ”๊ฐ€๋œ ๋ฐ์ดํ„ฐํ”„๋ ˆ์ž„
64
+ """
65
+ df = df.copy()
66
+ df['hour_sin'] = np.sin(2 * np.pi * df['hour'] / 24)
67
+ df['hour_cos'] = np.cos(2 * np.pi * df['hour'] / 24)
68
+ df['month_sin'] = np.sin(2 * np.pi * df['month'] / 12)
69
+ df['month_cos'] = np.cos(2 * np.pi * df['month'] / 12)
70
+ df['ground_temp - temp_C'] = df['groundtemp'] - df['temp_C']
71
+ return df
72
+
73
+ def preprocessing(df):
74
+ """๋ฐ์ดํ„ฐ ์ „์ฒ˜๋ฆฌ ํ•จ์ˆ˜.
75
+
76
+ Args:
77
+ df: ์›๋ณธ ๋ฐ์ดํ„ฐํ”„๋ ˆ์ž„
78
+
79
+ Returns:
80
+ ์ „์ฒ˜๋ฆฌ๋œ ๋ฐ์ดํ„ฐํ”„๋ ˆ์ž„
81
+ """
82
+ df = df[df.columns].copy()
83
+ df['year'] = df['year'].astype('int')
84
+ df['month'] = df['month'].astype('int')
85
+ df['hour'] = df['hour'].astype('int')
86
+ df = add_derived_features(df).copy()
87
+ df['multi_class'] = df['multi_class'].astype('int')
88
+ df.loc[df['wind_dir']=='์ •์˜จ', 'wind_dir'] = "0"
89
+ df['wind_dir'] = df['wind_dir'].astype('int')
90
+ df = df[['temp_C', 'precip_mm', 'wind_speed', 'wind_dir', 'hm',
91
+ 'vap_pressure', 'dewpoint_C', 'loc_pressure', 'sea_pressure',
92
+ 'solarRad', 'snow_cm', 'cloudcover', 'lm_cloudcover', 'low_cloudbase',
93
+ 'groundtemp', 'O3', 'NO2', 'PM10', 'PM25', 'year',
94
+ 'month', 'hour', 'ground_temp - temp_C', 'hour_sin', 'hour_cos',
95
+ 'month_sin', 'month_cos','multi_class']].copy()
96
+ return df
97
+
98
+ def create_xgb_model(search_space=None, best_params=None):
99
+ """XGBoost ๋ชจ๋ธ์„ ์ƒ์„ฑํ•ฉ๋‹ˆ๋‹ค.
100
+
101
+ Args:
102
+ search_space: ํ•˜์ดํผํŒŒ๋ผ๋ฏธํ„ฐ ๊ฒ€์ƒ‰ ๊ณต๊ฐ„ (objective_func์—์„œ ์‚ฌ์šฉ)
103
+ best_params: ์ตœ์ ํ™”๋œ ํ•˜์ดํผํŒŒ๋ผ๋ฏธํ„ฐ (์ตœ์ข… ๋ชจ๋ธ ํ•™์Šต์—์„œ ์‚ฌ์šฉ)
104
+
105
+ Returns:
106
+ XGBClassifier ์ธ์Šคํ„ด์Šค
107
+ """
108
+ base_params = {
109
+ 'n_estimators': N_ESTIMATORS,
110
+ 'tree_method': 'hist',
111
+ 'device': 'cuda',
112
+ 'enable_categorical': True,
113
+ 'eval_metric': eval_metric_csi,
114
+ 'objective': 'multi:softprob',
115
+ 'random_state': RANDOM_STATE,
116
+ 'early_stopping_rounds': EARLY_STOPPING_ROUNDS,
117
+ }
118
+
119
+ if search_space is not None:
120
+ # ํ•˜์ดํผํŒŒ๋ผ๋ฏธํ„ฐ ์ตœ์ ํ™” ์ค‘
121
+ params = {
122
+ **base_params,
123
+ 'learning_rate': search_space['learning_rate'],
124
+ 'max_depth': int(search_space['max_depth']),
125
+ 'min_child_weight': int(search_space['min_child_weight']),
126
+ 'gamma': search_space['gamma'],
127
+ 'subsample': search_space['subsample'],
128
+ 'colsample_bytree': search_space['colsample_bytree'],
129
+ 'reg_alpha': search_space['reg_alpha'],
130
+ 'reg_lambda': search_space['reg_lambda'],
131
+ }
132
+ elif best_params is not None:
133
+ # ์ตœ์ ํ™”๋œ ํŒŒ๋ผ๋ฏธํ„ฐ๋กœ ์ตœ์ข… ๋ชจ๋ธ ์ƒ์„ฑ
134
+ params = {
135
+ **base_params,
136
+ 'learning_rate': best_params['learning_rate'],
137
+ 'max_depth': int(best_params['max_depth']),
138
+ 'min_child_weight': int(best_params['min_child_weight']),
139
+ 'gamma': best_params['gamma'],
140
+ 'subsample': best_params['subsample'],
141
+ 'colsample_bytree': best_params['colsample_bytree'],
142
+ 'reg_alpha': best_params['reg_alpha'],
143
+ 'reg_lambda': best_params['reg_lambda'],
144
+ }
145
+ else:
146
+ params = base_params
147
+
148
+ return XGBClassifier(**params)
149
+
150
+
151
+ # ๋ฐ์ดํ„ฐ ๋กœ๋”ฉ ๋ฐ ์ „์ฒ˜๋ฆฌ
152
+ print("๋ฐ์ดํ„ฐ ๋กœ๋”ฉ ์ค‘...")
153
+ # ํŒŒ์ผ ์œ„์น˜ ๊ธฐ๋ฐ˜์œผ๋กœ ๋ฐ์ดํ„ฐ ๋””๋ ‰ํ† ๋ฆฌ ๊ฒฝ๋กœ ์„ค์ •
154
+ current_file_dir = os.path.dirname(os.path.abspath(__file__))
155
+ data_base_dir = os.path.abspath(os.path.join(current_file_dir, '../../../data'))
156
+ df_seoul = pd.read_csv(os.path.join(data_base_dir, "data_for_modeling/seoul_train.csv"))
157
+ df_ctgan_seoul_1 = pd.read_csv(os.path.join(data_base_dir, "data_oversampled/ctgan10000/ctgan10000_1_seoul.csv"))
158
+ df_ctgan_seoul_2 = pd.read_csv(os.path.join(data_base_dir, "data_oversampled/ctgan10000/ctgan10000_2_seoul.csv"))
159
+ df_ctgan_seoul_3 = pd.read_csv(os.path.join(data_base_dir, "data_oversampled/ctgan10000/ctgan10000_3_seoul.csv"))
160
+
161
+ print("๋ฐ์ดํ„ฐ ์ „์ฒ˜๋ฆฌ ์ค‘...")
162
+ df_ctgan_seoul_1 = preprocessing(df_ctgan_seoul_1)
163
+ df_ctgan_seoul_2 = preprocessing(df_ctgan_seoul_2)
164
+ df_ctgan_seoul_3 = preprocessing(df_ctgan_seoul_3)
165
+ df_seoul = preprocessing(df_seoul)
166
+
167
+ # CTGAN ๋ฐ์ดํ„ฐ ๋ฆฌ์ŠคํŠธ (fold ์ˆœ์„œ์™€ ์ผ์น˜)
168
+ df_ctgan_list = [df_ctgan_seoul_1, df_ctgan_seoul_2, df_ctgan_seoul_3]
169
+
170
+ def split_data(df_sampled, df_original, train_years, val_year):
171
+ """๋ฐ์ดํ„ฐ๋ฅผ ํ•™์Šต์šฉ๊ณผ ๊ฒ€์ฆ์šฉ์œผ๋กœ ๋ถ„ํ• ํ•ฉ๋‹ˆ๋‹ค.
172
+
173
+ Args:
174
+ df_sampled: ์ƒ˜ํ”Œ๋ง๋œ ๋ฐ์ดํ„ฐํ”„๋ ˆ์ž„
175
+ df_original: ์›๋ณธ ๋ฐ์ดํ„ฐํ”„๋ ˆ์ž„
176
+ train_years: ํ•™์Šต์— ์‚ฌ์šฉํ•  ์—ฐ๋„ ๋ฆฌ์ŠคํŠธ
177
+ val_year: ๊ฒ€์ฆ์— ์‚ฌ์šฉํ•  ์—ฐ๋„
178
+
179
+ Returns:
180
+ (X_train, X_val, y_train, y_val) ํŠœํ”Œ
181
+ """
182
+ # ํ•™์Šต ๋ฐ์ดํ„ฐ: ์ƒ˜ํ”Œ๋ง๋œ ๋ฐ์ดํ„ฐ์—์„œ train_years์— ํ•ด๋‹นํ•˜๋Š” ๋ฐ์ดํ„ฐ
183
+ train_mask = df_sampled['year'].isin(train_years)
184
+ X_train = df_sampled.loc[train_mask, df_sampled.columns != 'multi_class'].copy()
185
+ y_train = df_sampled.loc[train_mask, 'multi_class']
186
+
187
+ # ๊ฒ€์ฆ ๋ฐ์ดํ„ฐ: ์›๋ณธ ๋ฐ์ดํ„ฐ์—์„œ val_year์— ํ•ด๋‹นํ•˜๋Š” ๋ฐ์ดํ„ฐ
188
+ val_mask = df_original['year'] == val_year
189
+ X_val = df_original.loc[val_mask, df_original.columns != 'multi_class'].copy()
190
+ y_val = df_original.loc[val_mask, 'multi_class']
191
+
192
+ X_train.drop(columns=['year'], inplace=True)
193
+ X_val.drop(columns=['year'], inplace=True)
194
+
195
+ return X_train, X_val, y_train, y_val
196
+
197
+
198
+ # ํ•˜์ดํผํŒŒ๋ผ๋ฏธํ„ฐ ๊ฒ€์ƒ‰ ๊ณต๊ฐ„ ์ •์˜
199
+ xgb_search_space = {
200
+ 'learning_rate': hp.loguniform('learning_rate', np.log(0.01), np.log(0.2)),
201
+ 'max_depth': hp.quniform('max_depth', 3, 12, 1),
202
+ 'min_child_weight': hp.quniform('min_child_weight', 1, 20, 1),
203
+ 'gamma': hp.uniform('gamma', 0, 5), # ํŠธ๋ฆฌ ๋ถ„ํ• ์„ ์œ„ํ•œ ์ตœ์†Œ ์†์‹ค ๊ฐ์†Œ ๊ฐ’
204
+ 'subsample': hp.uniform('subsample', 0.6, 1.0),
205
+ 'colsample_bytree': hp.uniform('colsample_bytree', 0.6, 1.0),
206
+ 'reg_alpha': hp.uniform('reg_alpha', 0.0, 1.0),
207
+ 'reg_lambda': hp.uniform('reg_lambda', 0.0, 1.0)
208
+ }
209
+
210
+ def objective_func(search_space):
211
+ """ํ•˜์ดํผํŒŒ๋ผ๋ฏธํ„ฐ ์ตœ์ ํ™”๋ฅผ ์œ„ํ•œ ๋ชฉ์  ํ•จ์ˆ˜.
212
+
213
+ Args:
214
+ search_space: ํ•˜์ดํผํŒŒ๋ผ๋ฏธํ„ฐ ๊ฒ€์ƒ‰ ๊ณต๊ฐ„
215
+
216
+ Returns:
217
+ ํ‰๊ท  CSI ์ ์ˆ˜์˜ ์Œ์ˆ˜๊ฐ’ (hyperopt๋Š” ์ตœ์†Œํ™”๋ฅผ ์ˆ˜ํ–‰ํ•˜๋ฏ€๋กœ)
218
+ """
219
+ xgb_model = create_xgb_model(search_space=search_space)
220
+ csi_scores = []
221
+
222
+ # ๊ฐ fold์— ๋Œ€ํ•ด ๊ต์ฐจ ๊ฒ€์ฆ ์ˆ˜ํ–‰
223
+ for df_sampled, (train_years, val_year) in zip(df_ctgan_list, FOLD_CONFIGS):
224
+ X_train, X_val, y_train, y_val = split_data(
225
+ df_sampled, df_seoul, train_years, val_year
226
+ )
227
+
228
+ xgb_model.fit(X_train, y_train, eval_set=[(X_val, y_val)], verbose=False)
229
+ csi = calculate_csi(y_val, xgb_model.predict(X_val))
230
+ csi_scores.append(csi)
231
+
232
+ return -1*round(np.mean(csi_scores), 4)
233
+
234
+
235
+ # ํ•˜์ดํผํŒŒ๋ผ๋ฏธํ„ฐ ์ตœ์ ํ™”
236
+ print("ํ•˜์ดํผํŒŒ๋ผ๋ฏธํ„ฐ ์ตœ์ ํ™” ์‹œ์ž‘...")
237
+ trials = Trials()
238
+ xgb_best = fmin(
239
+ fn=objective_func,
240
+ space=xgb_search_space,
241
+ algo=tpe.suggest,
242
+ max_evals=MAX_EVALS,
243
+ trials=trials
244
+ )
245
+
246
+ # ์ตœ์ ํ™” ๊ฒฐ๊ณผ ๋ถ„์„ ๋ฐ ์ถœ๋ ฅ
247
+ print(f"\n์ตœ์ ํ™” ์™„๋ฃŒ. ์ตœ์  ํŒŒ๋ผ๋ฏธํ„ฐ: {xgb_best}")
248
+
249
+ # Best loss (CSI ์ ์ˆ˜์˜ ์Œ์ˆ˜๊ฐ’์ด๋ฏ€๋กœ, ์‹ค์ œ CSI๋Š” -loss)
250
+ best_loss = trials.best_trial['result']['loss']
251
+ best_csi = -best_loss
252
+ print(f"์ตœ์  CSI ์ ์ˆ˜: {best_csi:.4f} (loss: {best_loss:.4f})")
253
+
254
+ # ๋ชจ๋“  trial์˜ loss ๊ฐ’ ์ถ”์ถœ
255
+ losses = [trial['result']['loss'] for trial in trials.trials if trial['result']['status'] == 'ok']
256
+ csi_scores = [-loss for loss in losses]
257
+
258
+ print(f"\n์ตœ์ ํ™” ๊ณผ์ • ์š”์•ฝ:")
259
+ print(f" - ์ด ์‹œ๋„ ํšŸ์ˆ˜: {len(trials.trials)}")
260
+ print(f" - ์„ฑ๊ณตํ•œ ์‹œ๋„: {len(losses)}")
261
+ print(f" - ์ตœ์ดˆ CSI: {csi_scores[0]:.4f}")
262
+ print(f" - ์ตœ์ข… CSI: {csi_scores[-1]:.4f}")
263
+ print(f" - ์ตœ๊ณ  CSI: {max(csi_scores):.4f}")
264
+ print(f" - ์ตœ์ € CSI: {min(csi_scores):.4f}")
265
+ print(f" - ํ‰๊ท  CSI: {np.mean(csi_scores):.4f}")
266
+
267
+ # Trials ๊ฐ์ฒด ์ €์žฅ
268
+ # ํŒŒ์ผ ์œ„์น˜ ๊ธฐ๋ฐ˜์œผ๋กœ base ๋””๋ ‰ํ† ๋ฆฌ ๊ฒฝ๋กœ ์„ค์ •
269
+ current_file_dir = os.path.dirname(os.path.abspath(__file__))
270
+ base_dir = os.path.dirname(os.path.dirname(current_file_dir)) # 5.optima ๋””๋ ‰ํ† ๋ฆฌ
271
+ os.makedirs(os.path.join(base_dir, "optimization_history"), exist_ok=True)
272
+ trials_path = os.path.join(base_dir, "optimization_history/xgb_ctgan10000_seoul_trials.pkl")
273
+ joblib.dump(trials, trials_path)
274
+ print(f"\n์ตœ์ ํ™” Trials ๊ฐ์ฒด๊ฐ€ {trials_path}์— ์ €์žฅ๋˜์—ˆ์Šต๋‹ˆ๋‹ค.")
275
+
276
+ # ์ตœ์ ํ™”๋œ ํ•˜์ดํผํŒŒ๋ผ๋ฏธํ„ฐ๋กœ ์ตœ์ข… ๋ชจ๋ธ ํ•™์Šต
277
+ print("์ตœ์ข… ๋ชจ๋ธ ํ•™์Šต ์‹œ์ž‘...")
278
+ models = []
279
+
280
+ for fold_idx, (df_sampled, (train_years, val_year)) in enumerate(
281
+ zip(df_ctgan_list, FOLD_CONFIGS), start=1
282
+ ):
283
+ print(f"Fold {fold_idx} ํ•™์Šต ์ค‘... (ํ•™์Šต ์—ฐ๋„: {train_years}, ๊ฒ€์ฆ ์—ฐ๋„: {val_year})")
284
+
285
+ X_train, X_val, y_train, y_val = split_data(
286
+ df_sampled, df_seoul, train_years, val_year
287
+ )
288
+
289
+ xgb_model = create_xgb_model(best_params=xgb_best)
290
+ xgb_model.fit(X_train, y_train, eval_set=[(X_val, y_val)], verbose=False)
291
+
292
+ # ๊ฒ€์ฆ ์„ฑ๋Šฅ ์ถœ๋ ฅ
293
+ val_csi = calculate_csi(y_val, xgb_model.predict(X_val))
294
+ print(f"Fold {fold_idx} ๊ฒ€์ฆ CSI: {val_csi:.4f}")
295
+
296
+ models.append(xgb_model)
297
+
298
+
299
+ # ๋ชจ๋ธ ์ €์žฅ
300
+ print("๋ชจ๋ธ ์ €์žฅ ์ค‘...")
301
+ os.makedirs(os.path.join(base_dir, "save_model/xgb_optima"), exist_ok=True)
302
+ model_save_path = os.path.join(base_dir, "save_model/xgb_optima/xgb_ctgan10000_seoul.pkl")
303
+ joblib.dump(models, model_save_path)
304
+ print(f"๋ชจ๋ธ์ด {model_save_path}์— ์ €์žฅ๋˜์—ˆ์Šต๋‹ˆ๋‹ค.")
305
+
Analysis_code/6.optima_models_analysis/analysis_for_.ipynb ADDED
The diff for this file is too large to render. See raw diff
 
Analysis_code/6.optima_models_analysis/best_samples_best_datasample_per_model_per_region.csv ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ model,data_sample,region,optimization_library,best_csi,n_trials,best_params
2
+ ft_transformer,ctgan10000,seoul,optuna,0.5936576575682742,100,"{'d_token': 224, 'n_blocks': 4, 'n_heads': 8, 'attention_dropout': 0.15689079322421481, 'ffn_dropout': 0.27970845546044715, 'lr': 0.00011858823893766563, 'weight_decay': 0.02942637540327823, 'batch_size': 64}"
3
+ xgb,smote,seoul,hyperopt,0.5914,100,"{'colsample_bytree': 0.9204650350059359, 'gamma': 0.006794691671452219, 'learning_rate': 0.08811009219503893, 'max_depth': 12.0, 'min_child_weight': 3.0, 'reg_alpha': 0.6690476963880017, 'reg_lambda': 0.5388102924254845, 'subsample': 0.8320339664880525}"
4
+ lgb,smote,seoul,hyperopt,0.5895,100,"{'colsample_bytree': 0.7712993813350446, 'learning_rate': 0.014764448164722338, 'max_depth': 13.0, 'min_child_weight': 2.0, 'num_leaves': 144.0, 'reg_alpha': 0.9375760221934153, 'reg_lambda': 0.6881109653195318, 'subsample': 0.6932106255794361}"
5
+ resnet_like,ctgan10000,seoul,optuna,0.5889744558864985,100,"{'d_main': 160, 'd_hidden': 128, 'n_blocks': 4, 'dropout_first': 0.24169683403631037, 'dropout_second': 0.018646743579449815, 'lr': 0.003891520111503718, 'weight_decay': 0.09736563298725749, 'batch_size': 128}"
6
+ deepgbm,smotenc_ctgan20000,seoul,optuna,0.5657974901513136,100,"{'d_main': 128, 'd_hidden': 64, 'n_blocks': 5, 'dropout': 0.1024240157205574, 'lr': 0.009019177625524915, 'weight_decay': 0.08874117499066106, 'batch_size': 256}"
7
+ xgb,smote,incheon,hyperopt,0.6,100,"{'colsample_bytree': 0.8863531635625073, 'gamma': 1.4432252696586687, 'learning_rate': 0.14431831840673584, 'max_depth': 4.0, 'min_child_weight': 4.0, 'reg_alpha': 0.7656890601027424, 'reg_lambda': 0.5796745106013773, 'subsample': 0.8862819830666011}"
8
+ lgb,smote,incheon,hyperopt,0.5986,100,"{'colsample_bytree': 0.7149911519913482, 'learning_rate': 0.14061649313221522, 'max_depth': 4.0, 'min_child_weight': 4.0, 'num_leaves': 46.0, 'reg_alpha': 0.3323739596170201, 'reg_lambda': 0.3615804769440283, 'subsample': 0.7361106038020775}"
9
+ resnet_like,ctgan10000,incheon,optuna,0.5876200434398301,100,"{'d_main': 160, 'd_hidden': 192, 'n_blocks': 3, 'dropout_first': 0.213366405042877, 'dropout_second': 0.0616930432275245, 'lr': 0.005092968501532562, 'weight_decay': 0.06153947659623341, 'batch_size': 256}"
10
+ ft_transformer,smote,incheon,optuna,0.5674050423289939,100,"{'d_token': 96, 'n_blocks': 3, 'n_heads': 8, 'attention_dropout': 0.3637871224837107, 'ffn_dropout': 0.11479322703553738, 'lr': 0.0003009840584939789, 'weight_decay': 0.0003336039035587163, 'batch_size': 32}"
11
+ deepgbm,ctgan10000,incheon,optuna,0.5644485264432356,100,"{'d_main': 64, 'd_hidden': 192, 'n_blocks': 5, 'dropout': 0.16846849111235224, 'lr': 0.007871644587352598, 'weight_decay': 0.0005399258093557023, 'batch_size': 128}"
12
+ xgb,smote,gwangju,hyperopt,0.53,100,"{'colsample_bytree': 0.7658195937298418, 'gamma': 1.040884657831581, 'learning_rate': 0.04553328563585195, 'max_depth': 7.0, 'min_child_weight': 12.0, 'reg_alpha': 0.8031012977426317, 'reg_lambda': 0.6205464163959697, 'subsample': 0.6524796151581305}"
13
+ lgb,smote,gwangju,hyperopt,0.5297,100,"{'colsample_bytree': 0.9919060649789312, 'learning_rate': 0.054631157314326724, 'max_depth': 15.0, 'min_child_weight': 3.0, 'num_leaves': 47.0, 'reg_alpha': 0.9190252546800255, 'reg_lambda': 0.8800706832709921, 'subsample': 0.7859941375783913}"
14
+ deepgbm,ctgan10000,gwangju,optuna,0.5204031176113428,100,"{'d_main': 128, 'd_hidden': 192, 'n_blocks': 6, 'dropout': 0.3938212564993552, 'lr': 0.007164979269975063, 'weight_decay': 0.0923681134285374, 'batch_size': 64}"
15
+ resnet_like,ctgan10000,gwangju,optuna,0.510302842874457,100,"{'d_main': 64, 'd_hidden': 320, 'n_blocks': 3, 'dropout_first': 0.29522157561687634, 'dropout_second': 0.15684305218104422, 'lr': 0.008180657303015811, 'weight_decay': 0.01303718192830624, 'batch_size': 128}"
16
+ ft_transformer,ctgan10000,gwangju,optuna,0.5052817328725289,100,"{'d_token': 160, 'n_blocks': 3, 'n_heads': 4, 'attention_dropout': 0.21128609103276186, 'ffn_dropout': 0.18610731195171396, 'lr': 0.0019139767886005993, 'weight_decay': 0.03127877612669642, 'batch_size': 128}"
17
+ xgb,smote,daejeon,hyperopt,0.5371,100,"{'colsample_bytree': 0.733236256331133, 'gamma': 0.7990977235867733, 'learning_rate': 0.17558281930946487, 'max_depth': 9.0, 'min_child_weight': 11.0, 'reg_alpha': 0.1596833778659402, 'reg_lambda': 0.9170555745286906, 'subsample': 0.6403574066792026}"
18
+ lgb,smote,daejeon,hyperopt,0.5317,100,"{'colsample_bytree': 0.7585295616897205, 'learning_rate': 0.012807299958074884, 'max_depth': 8.0, 'min_child_weight': 2.0, 'num_leaves': 149.0, 'reg_alpha': 0.8175154308532824, 'reg_lambda': 0.7481509687757377, 'subsample': 0.8155067304500027}"
19
+ resnet_like,ctgan10000,daejeon,optuna,0.5101768615009369,100,"{'d_main': 128, 'd_hidden': 256, 'n_blocks': 5, 'dropout_first': 0.1381181811099212, 'dropout_second': 0.11702484025760711, 'lr': 0.0064016726045039805, 'weight_decay': 0.004366638608686326, 'batch_size': 256}"
20
+ deepgbm,ctgan10000,daejeon,optuna,0.5101248146449113,100,"{'d_main': 64, 'd_hidden': 256, 'n_blocks': 2, 'dropout': 0.2845653149911174, 'lr': 0.0030479748817488737, 'weight_decay': 0.08478209494184558, 'batch_size': 32}"
21
+ ft_transformer,ctgan10000,daejeon,optuna,0.5026041056392309,100,"{'d_token': 64, 'n_blocks': 5, 'n_heads': 8, 'attention_dropout': 0.39639878146052787, 'ffn_dropout': 0.16243660840447227, 'lr': 0.0005258652715359098, 'weight_decay': 0.06319928258911829, 'batch_size': 128}"
22
+ xgb,smote,daegu,hyperopt,0.4672,100,"{'colsample_bytree': 0.8132816721507904, 'gamma': 0.9002659162503241, 'learning_rate': 0.04046864452016672, 'max_depth': 4.0, 'min_child_weight': 17.0, 'reg_alpha': 0.4681545450085154, 'reg_lambda': 0.531313515098387, 'subsample': 0.827198506312037}"
23
+ lgb,smote,daegu,hyperopt,0.4671,100,"{'colsample_bytree': 0.999946333457191, 'learning_rate': 0.07031680296643952, 'max_depth': 4.0, 'min_child_weight': 17.0, 'num_leaves': 32.0, 'reg_alpha': 0.055815317687804816, 'reg_lambda': 0.2293760134119255, 'subsample': 0.6363907923464539}"
24
+ resnet_like,ctgan10000,daegu,optuna,0.46086300130604796,100,"{'d_main': 96, 'd_hidden': 256, 'n_blocks': 3, 'dropout_first': 0.27926914874893893, 'dropout_second': 0.13114004557533837, 'lr': 0.004133395383387492, 'weight_decay': 0.05462768451276688, 'batch_size': 32}"
25
+ ft_transformer,ctgan10000,daegu,optuna,0.44918319157422554,100,"{'d_token': 128, 'n_blocks': 4, 'n_heads': 8, 'attention_dropout': 0.1615322006432558, 'ffn_dropout': 0.14353691142809796, 'lr': 0.00025225999310114116, 'weight_decay': 0.002948085679186959, 'batch_size': 32}"
26
+ deepgbm,ctgan10000,daegu,optuna,0.4390250453058284,100,"{'d_main': 64, 'd_hidden': 192, 'n_blocks': 2, 'dropout': 0.29112938728448373, 'lr': 0.002745246324742509, 'weight_decay': 0.07823286969698617, 'batch_size': 32}"
27
+ ft_transformer,ctgan10000,busan,optuna,0.4960458104166546,100,"{'d_token': 224, 'n_blocks': 2, 'n_heads': 8, 'attention_dropout': 0.3873943566967484, 'ffn_dropout': 0.14296280926606936, 'lr': 0.0007665967810279031, 'weight_decay': 0.00878158688959246, 'batch_size': 32}"
28
+ xgb,pure,busan,hyperopt,0.4949,100,"{'colsample_bytree': 0.8651175745135303, 'gamma': 2.0220518303820976, 'learning_rate': 0.04196437449161767, 'max_depth': 7.0, 'min_child_weight': 17.0, 'reg_alpha': 0.9213159636887744, 'reg_lambda': 0.9407811453878014, 'subsample': 0.7200034080497129}"
29
+ resnet_like,ctgan10000,busan,optuna,0.49363300915248276,100,"{'d_main': 128, 'd_hidden': 512, 'n_blocks': 2, 'dropout_first': 0.3784300740258752, 'dropout_second': 0.026029354045211155, 'lr': 0.008483242466300268, 'weight_decay': 0.00016367394584020504, 'batch_size': 128}"
30
+ lgb,pure,busan,hyperopt,0.4849,100,"{'colsample_bytree': 0.9406061312055983, 'learning_rate': 0.17468151642796886, 'max_depth': 6.0, 'min_child_weight': 17.0, 'num_leaves': 138.0, 'reg_alpha': 0.4593420461637059, 'reg_lambda': 0.5948987302333338, 'subsample': 0.6557839186758097}"
31
+ deepgbm,ctgan10000,busan,optuna,0.475435864212341,100,"{'d_main': 128, 'd_hidden': 128, 'n_blocks': 2, 'dropout': 0.1477619274404685, 'lr': 0.00606559205480389, 'weight_decay': 0.08582651929034574, 'batch_size': 64}"
Analysis_code/6.optima_models_analysis/extract_result.ipynb DELETED
@@ -1,690 +0,0 @@
1
- {
2
- "cells": [
3
- {
4
- "cell_type": "code",
5
- "execution_count": null,
6
- "id": "70effd7a",
7
- "metadata": {},
8
- "outputs": [],
9
- "source": [
10
- "import pandas as pd\n",
11
- "import numpy as np\n",
12
- "import joblib\n",
13
- "import os\n",
14
- "import re\n",
15
- "from glob import glob\n",
16
- "import matplotlib.pyplot as plt\n",
17
- "import seaborn as sns"
18
- ]
19
- },
20
- {
21
- "cell_type": "code",
22
- "execution_count": 2,
23
- "id": "2942ba86",
24
- "metadata": {},
25
- "outputs": [],
26
- "source": [
27
- "optimization_history_dir = \"../optimization_history/\""
28
- ]
29
- },
30
- {
31
- "cell_type": "code",
32
- "execution_count": 3,
33
- "id": "d55af59c",
34
- "metadata": {},
35
- "outputs": [],
36
- "source": [
37
- "MODELS = ['ft_transformer', 'resnet_like', 'deepgbm', 'lgb', 'xgb']\n",
38
- "REGIONS = ['seoul', 'busan', 'incheon', 'daegu', 'daejeon', 'gwangju']\n",
39
- "\n",
40
- "pkl_files = glob(os.path.join(optimization_history_dir, \"*_trials.pkl\"))\n",
41
- "\n",
42
- "def parse_filename(filename):\n",
43
- " basename = os.path.basename(filename)\n",
44
- " name_without_ext = basename.replace('_trials.pkl', '')\n",
45
- " model = None\n",
46
- " for m in MODELS:\n",
47
- " if name_without_ext.startswith(m + '_'):\n",
48
- " model = m\n",
49
- " break\n",
50
- " region = None\n",
51
- " for r in REGIONS:\n",
52
- " if name_without_ext.endswith('_' + r):\n",
53
- " region = r\n",
54
- " data_sample = name_without_ext[len(model) + 1:-(len(region) + 1)]\n",
55
- " break\n",
56
- " return model, data_sample, region\n"
57
- ]
58
- },
59
- {
60
- "cell_type": "code",
61
- "execution_count": 4,
62
- "id": "832eb50a",
63
- "metadata": {},
64
- "outputs": [],
65
- "source": [
66
- "def extract_optimization_info(obj):\n",
67
- " if hasattr(obj, 'best_value') and hasattr(obj, 'best_params') and hasattr(obj, 'trials'):\n",
68
- " return extract_optuna_info(obj)\n",
69
- " elif hasattr(obj, 'best_trial') and hasattr(obj, 'trials'):\n",
70
- " return extract_hyperopt_info(obj)\n",
71
- " return None\n",
72
- "\n",
73
- "def extract_optuna_info(study):\n",
74
- " best_csi = study.best_value\n",
75
- " best_params = study.best_params\n",
76
- " n_trials = len(study.trials)\n",
77
- " successful_trials = [t for t in study.trials if t.value is not None]\n",
78
- " n_successful = len(successful_trials)\n",
79
- " csi_scores = [t.value for t in successful_trials]\n",
80
- " \n",
81
- " if len(csi_scores) > 0:\n",
82
- " stats = {\n",
83
- " 'first_csi': csi_scores[0],\n",
84
- " 'last_csi': csi_scores[-1],\n",
85
- " 'max_csi': max(csi_scores),\n",
86
- " 'min_csi': min(csi_scores),\n",
87
- " 'mean_csi': np.mean(csi_scores),\n",
88
- " 'std_csi': np.std(csi_scores) if len(csi_scores) > 1 else 0.0\n",
89
- " }\n",
90
- " else:\n",
91
- " stats = {\n",
92
- " 'first_csi': None, 'last_csi': None, 'max_csi': None,\n",
93
- " 'min_csi': None, 'mean_csi': None, 'std_csi': None\n",
94
- " }\n",
95
- " \n",
96
- " return {\n",
97
- " 'best_csi': best_csi,\n",
98
- " 'best_loss': None,\n",
99
- " 'n_trials': n_trials,\n",
100
- " 'n_successful': n_successful,\n",
101
- " 'best_params': best_params,\n",
102
- " 'optimization_library': 'optuna',\n",
103
- " **stats\n",
104
- " }\n",
105
- "\n",
106
- "def extract_hyperopt_info(trials):\n",
107
- " best_trial = trials.best_trial\n",
108
- " best_loss = best_trial['result']['loss']\n",
109
- " best_csi = -best_loss\n",
110
- " n_trials = len(trials.trials)\n",
111
- " successful_trials = [t for t in trials.trials if t['result']['status'] == 'ok']\n",
112
- " n_successful = len(successful_trials)\n",
113
- " losses = [t['result']['loss'] for t in successful_trials]\n",
114
- " csi_scores = [-loss for loss in losses]\n",
115
- " \n",
116
- " if len(csi_scores) > 0:\n",
117
- " stats = {\n",
118
- " 'first_csi': csi_scores[0],\n",
119
- " 'last_csi': csi_scores[-1],\n",
120
- " 'max_csi': max(csi_scores),\n",
121
- " 'min_csi': min(csi_scores),\n",
122
- " 'mean_csi': np.mean(csi_scores),\n",
123
- " 'std_csi': np.std(csi_scores) if len(csi_scores) > 1 else 0.0\n",
124
- " }\n",
125
- " else:\n",
126
- " stats = {\n",
127
- " 'first_csi': None, 'last_csi': None, 'max_csi': None,\n",
128
- " 'min_csi': None, 'mean_csi': None, 'std_csi': None\n",
129
- " }\n",
130
- " \n",
131
- " best_params = {}\n",
132
- " if 'misc' in best_trial and 'vals' in best_trial['misc']:\n",
133
- " for key, value_list in best_trial['misc']['vals'].items():\n",
134
- " if len(value_list) > 0:\n",
135
- " best_params[key] = value_list[0]\n",
136
- " \n",
137
- " return {\n",
138
- " 'best_csi': best_csi,\n",
139
- " 'best_loss': best_loss,\n",
140
- " 'n_trials': n_trials,\n",
141
- " 'n_successful': n_successful,\n",
142
- " 'best_params': best_params,\n",
143
- " 'optimization_library': 'hyperopt',\n",
144
- " **stats\n",
145
- " }"
146
- ]
147
- },
148
- {
149
- "cell_type": "code",
150
- "execution_count": 5,
151
- "id": "2b22a08b",
152
- "metadata": {},
153
- "outputs": [],
154
- "source": [
155
- "results = []\n",
156
- "\n",
157
- "for pkl_file in pkl_files:\n",
158
- " model, data_sample, region = parse_filename(pkl_file)\n",
159
- " if model is None or data_sample is None or region is None:\n",
160
- " continue\n",
161
- " \n",
162
- " obj = joblib.load(pkl_file)\n",
163
- " info = extract_optimization_info(obj)\n",
164
- " if info is None:\n",
165
- " continue\n",
166
- " \n",
167
- " result = {\n",
168
- " 'model': model,\n",
169
- " 'data_sample': data_sample,\n",
170
- " 'region': region,\n",
171
- " 'filename': os.path.basename(pkl_file),\n",
172
- " **info\n",
173
- " }\n",
174
- " results.append(result)"
175
- ]
176
- },
177
- {
178
- "cell_type": "code",
179
- "execution_count": 6,
180
- "id": "095f2637",
181
- "metadata": {},
182
- "outputs": [],
183
- "source": [
184
- "df_optimization = pd.DataFrame(results)\n",
185
- "column_order = [\n",
186
- " 'model', 'data_sample', 'region', 'optimization_library',\n",
187
- " 'best_csi', 'n_trials','best_params'\n",
188
- "]\n",
189
- "available_columns = [col for col in column_order if col in df_optimization.columns]\n",
190
- "df_optimization = df_optimization[available_columns + [col for col in df_optimization.columns if col not in available_columns]]\n",
191
- "df_optimization = df_optimization.loc[:, column_order]"
192
- ]
193
- },
194
- {
195
- "cell_type": "code",
196
- "execution_count": 7,
197
- "id": "ff111ec3",
198
- "metadata": {},
199
- "outputs": [
200
- {
201
- "data": {
202
- "text/plain": [
203
- "ft_transformer 19\n",
204
- "xgb 19\n",
205
- "resnet_like 19\n",
206
- "lgb 19\n",
207
- "deepgbm 19\n",
208
- "Name: model, dtype: int64"
209
- ]
210
- },
211
- "execution_count": 7,
212
- "metadata": {},
213
- "output_type": "execute_result"
214
- }
215
- ],
216
- "source": [
217
- "df_optimization['model'].value_counts()"
218
- ]
219
- },
220
- {
221
- "cell_type": "code",
222
- "execution_count": 8,
223
- "id": "753ebaf5",
224
- "metadata": {},
225
- "outputs": [
226
- {
227
- "data": {
228
- "text/plain": [
229
- "busan 20\n",
230
- "daegu 15\n",
231
- "seoul 15\n",
232
- "gwangju 15\n",
233
- "daejeon 15\n",
234
- "incheon 15\n",
235
- "Name: region, dtype: int64"
236
- ]
237
- },
238
- "execution_count": 8,
239
- "metadata": {},
240
- "output_type": "execute_result"
241
- }
242
- ],
243
- "source": [
244
- "df_optimization['region'].value_counts()"
245
- ]
246
- },
247
- {
248
- "cell_type": "code",
249
- "execution_count": 16,
250
- "id": "7472bb4e",
251
- "metadata": {},
252
- "outputs": [
253
- {
254
- "data": {
255
- "text/html": [
256
- "<div>\n",
257
- "<style scoped>\n",
258
- " .dataframe tbody tr th:only-of-type {\n",
259
- " vertical-align: middle;\n",
260
- " }\n",
261
- "\n",
262
- " .dataframe tbody tr th {\n",
263
- " vertical-align: top;\n",
264
- " }\n",
265
- "\n",
266
- " .dataframe thead th {\n",
267
- " text-align: right;\n",
268
- " }\n",
269
- "</style>\n",
270
- "<table border=\"1\" class=\"dataframe\">\n",
271
- " <thead>\n",
272
- " <tr style=\"text-align: right;\">\n",
273
- " <th></th>\n",
274
- " <th>model</th>\n",
275
- " <th>data_sample</th>\n",
276
- " <th>region</th>\n",
277
- " <th>optimization_library</th>\n",
278
- " <th>best_csi</th>\n",
279
- " <th>n_trials</th>\n",
280
- " <th>best_params</th>\n",
281
- " </tr>\n",
282
- " </thead>\n",
283
- " <tbody>\n",
284
- " <tr>\n",
285
- " <th>0</th>\n",
286
- " <td>ft_transformer</td>\n",
287
- " <td>smote</td>\n",
288
- " <td>busan</td>\n",
289
- " <td>optuna</td>\n",
290
- " <td>0.452471</td>\n",
291
- " <td>100</td>\n",
292
- " <td>{'d_token': 96, 'n_blocks': 2, 'n_heads': 4, '...</td>\n",
293
- " </tr>\n",
294
- " <tr>\n",
295
- " <th>1</th>\n",
296
- " <td>ft_transformer</td>\n",
297
- " <td>pure</td>\n",
298
- " <td>daegu</td>\n",
299
- " <td>optuna</td>\n",
300
- " <td>0.384659</td>\n",
301
- " <td>100</td>\n",
302
- " <td>{'d_token': 224, 'n_blocks': 2, 'n_heads': 8, ...</td>\n",
303
- " </tr>\n",
304
- " <tr>\n",
305
- " <th>2</th>\n",
306
- " <td>xgb</td>\n",
307
- " <td>smotenc_ctgan20000</td>\n",
308
- " <td>daegu</td>\n",
309
- " <td>hyperopt</td>\n",
310
- " <td>0.427700</td>\n",
311
- " <td>100</td>\n",
312
- " <td>{'colsample_bytree': 0.7114033147242765, 'gamm...</td>\n",
313
- " </tr>\n",
314
- " <tr>\n",
315
- " <th>3</th>\n",
316
- " <td>resnet_like</td>\n",
317
- " <td>pure</td>\n",
318
- " <td>seoul</td>\n",
319
- " <td>optuna</td>\n",
320
- " <td>0.556676</td>\n",
321
- " <td>100</td>\n",
322
- " <td>{'d_main': 96, 'd_hidden': 512, 'n_blocks': 2,...</td>\n",
323
- " </tr>\n",
324
- " <tr>\n",
325
- " <th>4</th>\n",
326
- " <td>resnet_like</td>\n",
327
- " <td>smote</td>\n",
328
- " <td>gwangju</td>\n",
329
- " <td>optuna</td>\n",
330
- " <td>0.486711</td>\n",
331
- " <td>100</td>\n",
332
- " <td>{'d_main': 96, 'd_hidden': 64, 'n_blocks': 4, ...</td>\n",
333
- " </tr>\n",
334
- " </tbody>\n",
335
- "</table>\n",
336
- "</div>"
337
- ],
338
- "text/plain": [
339
- " model data_sample region optimization_library best_csi \\\n",
340
- "0 ft_transformer smote busan optuna 0.452471 \n",
341
- "1 ft_transformer pure daegu optuna 0.384659 \n",
342
- "2 xgb smotenc_ctgan20000 daegu hyperopt 0.427700 \n",
343
- "3 resnet_like pure seoul optuna 0.556676 \n",
344
- "4 resnet_like smote gwangju optuna 0.486711 \n",
345
- "\n",
346
- " n_trials best_params \n",
347
- "0 100 {'d_token': 96, 'n_blocks': 2, 'n_heads': 4, '... \n",
348
- "1 100 {'d_token': 224, 'n_blocks': 2, 'n_heads': 8, ... \n",
349
- "2 100 {'colsample_bytree': 0.7114033147242765, 'gamm... \n",
350
- "3 100 {'d_main': 96, 'd_hidden': 512, 'n_blocks': 2,... \n",
351
- "4 100 {'d_main': 96, 'd_hidden': 64, 'n_blocks': 4, ... "
352
- ]
353
- },
354
- "execution_count": 16,
355
- "metadata": {},
356
- "output_type": "execute_result"
357
- }
358
- ],
359
- "source": [
360
- "df_optimization.head()"
361
- ]
362
- },
363
- {
364
- "cell_type": "code",
365
- "execution_count": 17,
366
- "id": "b6245ef4",
367
- "metadata": {},
368
- "outputs": [
369
- {
370
- "data": {
371
- "text/html": [
372
- "<div>\n",
373
- "<style scoped>\n",
374
- " .dataframe tbody tr th:only-of-type {\n",
375
- " vertical-align: middle;\n",
376
- " }\n",
377
- "\n",
378
- " .dataframe tbody tr th {\n",
379
- " vertical-align: top;\n",
380
- " }\n",
381
- "\n",
382
- " .dataframe thead th {\n",
383
- " text-align: right;\n",
384
- " }\n",
385
- "</style>\n",
386
- "<table border=\"1\" class=\"dataframe\">\n",
387
- " <thead>\n",
388
- " <tr style=\"text-align: right;\">\n",
389
- " <th></th>\n",
390
- " <th>model</th>\n",
391
- " <th>data_sample</th>\n",
392
- " <th>region</th>\n",
393
- " <th>optimization_library</th>\n",
394
- " <th>best_csi</th>\n",
395
- " <th>n_trials</th>\n",
396
- " <th>best_params</th>\n",
397
- " </tr>\n",
398
- " </thead>\n",
399
- " <tbody>\n",
400
- " <tr>\n",
401
- " <th>0</th>\n",
402
- " <td>ft_transformer</td>\n",
403
- " <td>smote</td>\n",
404
- " <td>busan</td>\n",
405
- " <td>optuna</td>\n",
406
- " <td>0.452471</td>\n",
407
- " <td>100</td>\n",
408
- " <td>{'d_token': 96, 'n_blocks': 2, 'n_heads': 4, '...</td>\n",
409
- " </tr>\n",
410
- " <tr>\n",
411
- " <th>1</th>\n",
412
- " <td>ft_transformer</td>\n",
413
- " <td>pure</td>\n",
414
- " <td>daegu</td>\n",
415
- " <td>optuna</td>\n",
416
- " <td>0.384659</td>\n",
417
- " <td>100</td>\n",
418
- " <td>{'d_token': 224, 'n_blocks': 2, 'n_heads': 8, ...</td>\n",
419
- " </tr>\n",
420
- " <tr>\n",
421
- " <th>2</th>\n",
422
- " <td>xgb</td>\n",
423
- " <td>smotenc_ctgan20000</td>\n",
424
- " <td>daegu</td>\n",
425
- " <td>hyperopt</td>\n",
426
- " <td>0.427700</td>\n",
427
- " <td>100</td>\n",
428
- " <td>{'colsample_bytree': 0.7114033147242765, 'gamm...</td>\n",
429
- " </tr>\n",
430
- " <tr>\n",
431
- " <th>3</th>\n",
432
- " <td>resnet_like</td>\n",
433
- " <td>pure</td>\n",
434
- " <td>seoul</td>\n",
435
- " <td>optuna</td>\n",
436
- " <td>0.556676</td>\n",
437
- " <td>100</td>\n",
438
- " <td>{'d_main': 96, 'd_hidden': 512, 'n_blocks': 2,...</td>\n",
439
- " </tr>\n",
440
- " <tr>\n",
441
- " <th>4</th>\n",
442
- " <td>resnet_like</td>\n",
443
- " <td>smote</td>\n",
444
- " <td>gwangju</td>\n",
445
- " <td>optuna</td>\n",
446
- " <td>0.486711</td>\n",
447
- " <td>100</td>\n",
448
- " <td>{'d_main': 96, 'd_hidden': 64, 'n_blocks': 4, ...</td>\n",
449
- " </tr>\n",
450
- " <tr>\n",
451
- " <th>...</th>\n",
452
- " <td>...</td>\n",
453
- " <td>...</td>\n",
454
- " <td>...</td>\n",
455
- " <td>...</td>\n",
456
- " <td>...</td>\n",
457
- " <td>...</td>\n",
458
- " <td>...</td>\n",
459
- " </tr>\n",
460
- " <tr>\n",
461
- " <th>90</th>\n",
462
- " <td>resnet_like</td>\n",
463
- " <td>smote</td>\n",
464
- " <td>daegu</td>\n",
465
- " <td>optuna</td>\n",
466
- " <td>0.395593</td>\n",
467
- " <td>100</td>\n",
468
- " <td>{'d_main': 96, 'd_hidden': 64, 'n_blocks': 4, ...</td>\n",
469
- " </tr>\n",
470
- " <tr>\n",
471
- " <th>91</th>\n",
472
- " <td>deepgbm</td>\n",
473
- " <td>smotenc_ctgan20000</td>\n",
474
- " <td>daejeon</td>\n",
475
- " <td>optuna</td>\n",
476
- " <td>0.484893</td>\n",
477
- " <td>100</td>\n",
478
- " <td>{'d_main': 96, 'd_hidden': 64, 'n_blocks': 6, ...</td>\n",
479
- " </tr>\n",
480
- " <tr>\n",
481
- " <th>92</th>\n",
482
- " <td>resnet_like</td>\n",
483
- " <td>smotenc_ctgan20000</td>\n",
484
- " <td>daejeon</td>\n",
485
- " <td>optuna</td>\n",
486
- " <td>0.482239</td>\n",
487
- " <td>100</td>\n",
488
- " <td>{'d_main': 256, 'd_hidden': 128, 'n_blocks': 2...</td>\n",
489
- " </tr>\n",
490
- " <tr>\n",
491
- " <th>93</th>\n",
492
- " <td>deepgbm</td>\n",
493
- " <td>pure</td>\n",
494
- " <td>daegu</td>\n",
495
- " <td>optuna</td>\n",
496
- " <td>0.357045</td>\n",
497
- " <td>100</td>\n",
498
- " <td>{'d_main': 160, 'd_hidden': 64, 'n_blocks': 4,...</td>\n",
499
- " </tr>\n",
500
- " <tr>\n",
501
- " <th>94</th>\n",
502
- " <td>resnet_like</td>\n",
503
- " <td>pure</td>\n",
504
- " <td>daegu</td>\n",
505
- " <td>optuna</td>\n",
506
- " <td>0.407522</td>\n",
507
- " <td>100</td>\n",
508
- " <td>{'d_main': 192, 'd_hidden': 64, 'n_blocks': 3,...</td>\n",
509
- " </tr>\n",
510
- " </tbody>\n",
511
- "</table>\n",
512
- "<p>95 rows ร— 7 columns</p>\n",
513
- "</div>"
514
- ],
515
- "text/plain": [
516
- " model data_sample region optimization_library \\\n",
517
- "0 ft_transformer smote busan optuna \n",
518
- "1 ft_transformer pure daegu optuna \n",
519
- "2 xgb smotenc_ctgan20000 daegu hyperopt \n",
520
- "3 resnet_like pure seoul optuna \n",
521
- "4 resnet_like smote gwangju optuna \n",
522
- ".. ... ... ... ... \n",
523
- "90 resnet_like smote daegu optuna \n",
524
- "91 deepgbm smotenc_ctgan20000 daejeon optuna \n",
525
- "92 resnet_like smotenc_ctgan20000 daejeon optuna \n",
526
- "93 deepgbm pure daegu optuna \n",
527
- "94 resnet_like pure daegu optuna \n",
528
- "\n",
529
- " best_csi n_trials best_params \n",
530
- "0 0.452471 100 {'d_token': 96, 'n_blocks': 2, 'n_heads': 4, '... \n",
531
- "1 0.384659 100 {'d_token': 224, 'n_blocks': 2, 'n_heads': 8, ... \n",
532
- "2 0.427700 100 {'colsample_bytree': 0.7114033147242765, 'gamm... \n",
533
- "3 0.556676 100 {'d_main': 96, 'd_hidden': 512, 'n_blocks': 2,... \n",
534
- "4 0.486711 100 {'d_main': 96, 'd_hidden': 64, 'n_blocks': 4, ... \n",
535
- ".. ... ... ... \n",
536
- "90 0.395593 100 {'d_main': 96, 'd_hidden': 64, 'n_blocks': 4, ... \n",
537
- "91 0.484893 100 {'d_main': 96, 'd_hidden': 64, 'n_blocks': 6, ... \n",
538
- "92 0.482239 100 {'d_main': 256, 'd_hidden': 128, 'n_blocks': 2... \n",
539
- "93 0.357045 100 {'d_main': 160, 'd_hidden': 64, 'n_blocks': 4,... \n",
540
- "94 0.407522 100 {'d_main': 192, 'd_hidden': 64, 'n_blocks': 3,... \n",
541
- "\n",
542
- "[95 rows x 7 columns]"
543
- ]
544
- },
545
- "execution_count": 17,
546
- "metadata": {},
547
- "output_type": "execute_result"
548
- }
549
- ],
550
- "source": [
551
- "df_optimization"
552
- ]
553
- },
554
- {
555
- "cell_type": "code",
556
- "execution_count": null,
557
- "id": "580e5ae9",
558
- "metadata": {},
559
- "outputs": [],
560
- "source": [
561
- "# ๋ชจ๋ธ๋ณ„ best_csi๋ฅผ region๋ณ„๋กœ ์‹œ๊ฐํ™”\n",
562
- "# ์ฐธ๊ณ : analysis_for_oversampling_data.ipynb์˜ Cell 12 ํŒจํ„ด\n",
563
- "\n",
564
- "# ๋ฐ์ดํ„ฐ ๋ณต์‚ฌ ๋ฐ ๋ชจ๋ธ๋ช… ๋งคํ•‘ (ํ‘œ์‹œ์šฉ)\n",
565
- "df_plot = df_optimization.copy()\n",
566
- "\n",
567
- "# ๋ชจ๋ธ๋ช… ๋งคํ•‘: 'lgb' -> 'lightgbm', 'xgb' -> 'xgboost'\n",
568
- "model_mapping = {\n",
569
- " 'lgb': 'lightgbm',\n",
570
- " 'xgb': 'xgboost',\n",
571
- " 'ft_transformer': 'ft_transformer',\n",
572
- " 'resnet_like': 'resnet_like',\n",
573
- " 'deepgbm': 'deepgbm'\n",
574
- "}\n",
575
- "df_plot['model_display'] = df_plot['model'].map(model_mapping)\n",
576
- "\n",
577
- "# region์„ category๋กœ ๋ณ€ํ™˜ํ•˜์—ฌ ์ •๋ ฌ\n",
578
- "df_plot['region'] = df_plot['region'].astype('category')\n",
579
- "df_plot['region'] = df_plot['region'].cat.reorder_categories(sorted(df_plot['region'].cat.categories))\n",
580
- "\n",
581
- "# ๋ชจ๋ธ ๋ชฉ๋ก (ํ‘œ์‹œ ์ˆœ์„œ)\n",
582
- "models_display = ['xgboost', 'lightgbm', 'resnet_like', 'ft_transformer', 'deepgbm']\n",
583
- "\n",
584
- "# 2ํ–‰ 3์—ด subplot ์ƒ์„ฑ (5๊ฐœ ๋ชจ๋ธ)\n",
585
- "fig, axes = plt.subplots(2, 3, figsize=(20, 12))\n",
586
- "fig.suptitle('Best CSI Score by Region (Grouped by Data Sample)', \n",
587
- " fontsize=16, fontweight='bold', y=0.995)\n",
588
- "\n",
589
- "# axes๋ฅผ 1์ฐจ์› ๋ฐฐ์—ด๋กœ ๋ณ€ํ™˜\n",
590
- "axes_flat = axes.flatten()\n",
591
- "\n",
592
- "# ๊ฐ ๋ชจ๋ธ๋ณ„๋กœ plot ์ƒ์„ฑ\n",
593
- "for model_idx, model_display in enumerate(models_display):\n",
594
- " ax = axes_flat[model_idx]\n",
595
- " \n",
596
- " # ํ•ด๋‹น ๋ชจ๋ธ์˜ ๋ฐ์ดํ„ฐ๋งŒ ํ•„ํ„ฐ๋ง\n",
597
- " model_df = df_plot[df_plot['model_display'] == model_display]\n",
598
- " \n",
599
- " # ๋ฐ์ดํ„ฐ๊ฐ€ ์žˆ๋Š” ๊ฒฝ์šฐ์—๋งŒ plot\n",
600
- " if len(model_df) > 0:\n",
601
- " # Seaborn lineplot ์‚ฌ์šฉ\n",
602
- " sns.lineplot(\n",
603
- " data=model_df,\n",
604
- " x='region',\n",
605
- " y='best_csi',\n",
606
- " hue='data_sample',\n",
607
- " marker='o',\n",
608
- " markersize=8,\n",
609
- " linewidth=2.5,\n",
610
- " palette='tab20', # data_sample๋ณ„ ์ƒ‰์ƒ\n",
611
- " ax=ax\n",
612
- " )\n",
613
- " \n",
614
- " ax.set_title(f'{model_display}', fontsize=14, fontweight='bold', pad=15)\n",
615
- " ax.set_xlabel('Region', fontsize=12)\n",
616
- " ax.set_ylabel('Best CSI Score', fontsize=12)\n",
617
- " ax.tick_params(axis='x', rotation=45)\n",
618
- " ax.grid(True, alpha=0.3, linestyle='--')\n",
619
- " ax.legend(bbox_to_anchor=(1.05, 1), loc='upper left', fontsize=9, framealpha=0.9)\n",
620
- "\n",
621
- "# ๋งˆ์ง€๋ง‰ subplot (6๋ฒˆ์งธ)๋Š” ์‚ฌ์šฉํ•˜์ง€ ์•Š์œผ๋ฏ€๋กœ ์ˆจ๊น€\n",
622
- "axes_flat[5].axis('off')\n",
623
- "\n",
624
- "plt.tight_layout()\n",
625
- "plt.show()\n"
626
- ]
627
- },
628
- {
629
- "cell_type": "code",
630
- "execution_count": null,
631
- "id": "19a5df01",
632
- "metadata": {},
633
- "outputs": [],
634
- "source": []
635
- },
636
- {
637
- "cell_type": "code",
638
- "execution_count": null,
639
- "id": "b3e304d4",
640
- "metadata": {},
641
- "outputs": [],
642
- "source": []
643
- },
644
- {
645
- "cell_type": "code",
646
- "execution_count": null,
647
- "id": "e3212d50",
648
- "metadata": {},
649
- "outputs": [],
650
- "source": []
651
- },
652
- {
653
- "cell_type": "code",
654
- "execution_count": null,
655
- "id": "c7bb66c6",
656
- "metadata": {},
657
- "outputs": [],
658
- "source": []
659
- },
660
- {
661
- "cell_type": "code",
662
- "execution_count": null,
663
- "id": "d55581c3",
664
- "metadata": {},
665
- "outputs": [],
666
- "source": []
667
- }
668
- ],
669
- "metadata": {
670
- "kernelspec": {
671
- "display_name": "py39",
672
- "language": "python",
673
- "name": "python3"
674
- },
675
- "language_info": {
676
- "codemirror_mode": {
677
- "name": "ipython",
678
- "version": 3
679
- },
680
- "file_extension": ".py",
681
- "mimetype": "text/x-python",
682
- "name": "python",
683
- "nbconvert_exporter": "python",
684
- "pygments_lexer": "ipython3",
685
- "version": "3.9.18"
686
- }
687
- },
688
- "nbformat": 4,
689
- "nbformat_minor": 5
690
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
Analysis_code/6.optima_models_analysis/extract_result_from_omptimized_models.ipynb ADDED
The diff for this file is too large to render. See raw diff
 
Analysis_code/6.optima_models_analysis/optimization_result.csv ADDED
@@ -0,0 +1,121 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ model,data_sample,region,optimization_library,best_csi,n_trials,best_params
2
+ ft_transformer,smote,busan,optuna,0.4524714686603366,100,"{'d_token': 96, 'n_blocks': 2, 'n_heads': 4, 'attention_dropout': 0.39058519125437824, 'ffn_dropout': 0.35781462874340314, 'lr': 0.0006705029713893173, 'weight_decay': 0.0001426209011329072, 'batch_size': 32}"
3
+ ft_transformer,pure,daegu,optuna,0.3846594392002736,100,"{'d_token': 224, 'n_blocks': 2, 'n_heads': 8, 'attention_dropout': 0.2747124536980523, 'ffn_dropout': 0.1909754518903343, 'lr': 0.00016739997447268043, 'weight_decay': 0.027811856175591093, 'batch_size': 32}"
4
+ xgb,smotenc_ctgan20000,daegu,hyperopt,0.4277,100,"{'colsample_bytree': 0.7114033147242765, 'gamma': 0.9625212091684073, 'learning_rate': 0.029642239831837253, 'max_depth': 12.0, 'min_child_weight': 10.0, 'reg_alpha': 0.1587708255877442, 'reg_lambda': 0.4648399906011745, 'subsample': 0.90006374997474}"
5
+ resnet_like,pure,seoul,optuna,0.5566756722322981,100,"{'d_main': 96, 'd_hidden': 512, 'n_blocks': 2, 'dropout_first': 0.3834324386470386, 'dropout_second': 0.029813309707734794, 'lr': 0.0005002634113960448, 'weight_decay': 0.05408195750724482, 'batch_size': 32}"
6
+ resnet_like,smote,gwangju,optuna,0.48671080174496345,100,"{'d_main': 96, 'd_hidden': 64, 'n_blocks': 4, 'dropout_first': 0.2808602138036661, 'dropout_second': 0.14619910058769206, 'lr': 0.0055368090707776305, 'weight_decay': 0.001341561695377514, 'batch_size': 256}"
7
+ resnet_like,smotenc_ctgan20000,busan,optuna,0.45568873098715307,100,"{'d_main': 256, 'd_hidden': 512, 'n_blocks': 3, 'dropout_first': 0.1045169105881141, 'dropout_second': 0.05372596450552944, 'lr': 0.00943776593390798, 'weight_decay': 0.0010575459741554466, 'batch_size': 128}"
8
+ ft_transformer,smote,daegu,optuna,0.40272068323222654,100,"{'d_token': 96, 'n_blocks': 3, 'n_heads': 8, 'attention_dropout': 0.2530528162951749, 'ffn_dropout': 0.1899328578250674, 'lr': 0.0013866055842525612, 'weight_decay': 0.00020752948982868583, 'batch_size': 64}"
9
+ xgb,ctgan10000,daejeon,hyperopt,0.5029,100,"{'colsample_bytree': 0.7816067762051363, 'gamma': 0.5799629095615334, 'learning_rate': 0.06287412401679013, 'max_depth': 3.0, 'min_child_weight': 5.0, 'reg_alpha': 0.36731169488772253, 'reg_lambda': 0.03192020366519255, 'subsample': 0.6004605601176048}"
10
+ resnet_like,smotenc_ctgan20000,gwangju,optuna,0.4937343167803819,100,"{'d_main': 64, 'd_hidden': 256, 'n_blocks': 3, 'dropout_first': 0.3792559101674334, 'dropout_second': 0.19251437428644594, 'lr': 0.00405325576056642, 'weight_decay': 0.0005628495861261046, 'batch_size': 128}"
11
+ lgb,smote,seoul,hyperopt,0.5895,100,"{'colsample_bytree': 0.7712993813350446, 'learning_rate': 0.014764448164722338, 'max_depth': 13.0, 'min_child_weight': 2.0, 'num_leaves': 144.0, 'reg_alpha': 0.9375760221934153, 'reg_lambda': 0.6881109653195318, 'subsample': 0.6932106255794361}"
12
+ ft_transformer,pure,busan,optuna,0.44685896765010097,100,"{'d_token': 192, 'n_blocks': 3, 'n_heads': 8, 'attention_dropout': 0.11973480060658612, 'ffn_dropout': 0.15614454735278546, 'lr': 0.00016413327466283583, 'weight_decay': 0.002548468041818763, 'batch_size': 64}"
13
+ ft_transformer,ctgan10000,gwangju,optuna,0.5052817328725289,100,"{'d_token': 160, 'n_blocks': 3, 'n_heads': 4, 'attention_dropout': 0.21128609103276186, 'ffn_dropout': 0.18610731195171396, 'lr': 0.0019139767886005993, 'weight_decay': 0.03127877612669642, 'batch_size': 128}"
14
+ xgb,ctgan10000,gwangju,hyperopt,0.4999,100,"{'colsample_bytree': 0.9825715751506052, 'gamma': 0.029399796024525915, 'learning_rate': 0.08575762330828458, 'max_depth': 11.0, 'min_child_weight': 8.0, 'reg_alpha': 0.8534545581720909, 'reg_lambda': 0.43478744549007325, 'subsample': 0.7629247503643918}"
15
+ resnet_like,smote,daejeon,optuna,0.48175460460533026,100,"{'d_main': 192, 'd_hidden': 64, 'n_blocks': 4, 'dropout_first': 0.3137027413848088, 'dropout_second': 0.18760941198412298, 'lr': 0.00565595693998524, 'weight_decay': 0.04866049178978196, 'batch_size': 128}"
16
+ ft_transformer,smotenc_ctgan20000,busan,optuna,0.4767443843216419,100,"{'d_token': 128, 'n_blocks': 2, 'n_heads': 8, 'attention_dropout': 0.1711218539171086, 'ffn_dropout': 0.2636519595986711, 'lr': 0.004358575253869887, 'weight_decay': 0.00046754184762985804, 'batch_size': 256}"
17
+ xgb,ctgan10000,daegu,hyperopt,0.4392,100,"{'colsample_bytree': 0.8557253370653987, 'gamma': 1.1563957561197729, 'learning_rate': 0.19232018363683898, 'max_depth': 10.0, 'min_child_weight': 8.0, 'reg_alpha': 0.21149066093980878, 'reg_lambda': 0.2690618200166374, 'subsample': 0.714526167464626}"
18
+ deepgbm,smote,gwangju,optuna,0.45804386918458945,100,"{'d_main': 160, 'd_hidden': 64, 'n_blocks': 2, 'dropout': 0.1698480826585593, 'lr': 0.0003762961039889282, 'weight_decay': 0.0014343061148430866, 'batch_size': 64}"
19
+ ft_transformer,ctgan10000,seoul,optuna,0.5936576575682742,100,"{'d_token': 224, 'n_blocks': 4, 'n_heads': 8, 'attention_dropout': 0.15689079322421481, 'ffn_dropout': 0.27970845546044715, 'lr': 0.00011858823893766563, 'weight_decay': 0.02942637540327823, 'batch_size': 64}"
20
+ lgb,smote,daejeon,hyperopt,0.5317,100,"{'colsample_bytree': 0.7585295616897205, 'learning_rate': 0.012807299958074884, 'max_depth': 8.0, 'min_child_weight': 2.0, 'num_leaves': 149.0, 'reg_alpha': 0.8175154308532824, 'reg_lambda': 0.7481509687757377, 'subsample': 0.8155067304500027}"
21
+ resnet_like,pure,incheon,optuna,0.5717111423727251,100,"{'d_main': 224, 'd_hidden': 256, 'n_blocks': 4, 'dropout_first': 0.3502671083503836, 'dropout_second': 0.15938013319711236, 'lr': 0.0006801289543741389, 'weight_decay': 0.005292744372677132, 'batch_size': 128}"
22
+ lgb,ctgan10000,daejeon,hyperopt,0.4908,100,"{'colsample_bytree': 0.7077604272501928, 'learning_rate': 0.10351387699107398, 'max_depth': 6.0, 'min_child_weight': 4.0, 'num_leaves': 51.0, 'reg_alpha': 0.06973941883143871, 'reg_lambda': 0.8477821589656351, 'subsample': 0.8664583588640111}"
23
+ lgb,smotenc_ctgan20000,daegu,hyperopt,0.4455,100,"{'colsample_bytree': 0.9935566129264934, 'learning_rate': 0.011803766157843702, 'max_depth': 10.0, 'min_child_weight': 18.0, 'num_leaves': 78.0, 'reg_alpha': 0.5555179443217245, 'reg_lambda': 0.23478947295729824, 'subsample': 0.7059612447576378}"
24
+ deepgbm,smotenc_ctgan20000,busan,optuna,0.40671898361820197,100,"{'d_main': 64, 'd_hidden': 256, 'n_blocks': 3, 'dropout': 0.2843714965028271, 'lr': 0.009315324608427497, 'weight_decay': 0.022174119634941862, 'batch_size': 128}"
25
+ ft_transformer,smotenc_ctgan20000,daejeon,optuna,0.4794390839030278,100,"{'d_token': 64, 'n_blocks': 3, 'n_heads': 4, 'attention_dropout': 0.13096961306141697, 'ffn_dropout': 0.10368225384926379, 'lr': 0.0008212785631177437, 'weight_decay': 0.0007599672775598784, 'batch_size': 32}"
26
+ lgb,ctgan10000,busan,hyperopt,0.4836,100,"{'colsample_bytree': 0.7243835590014314, 'learning_rate': 0.052472053724070156, 'max_depth': 15.0, 'min_child_weight': 9.0, 'num_leaves': 120.0, 'reg_alpha': 0.566895668532905, 'reg_lambda': 0.9659771198744264, 'subsample': 0.8425484904296862}"
27
+ ft_transformer,pure,daejeon,optuna,0.4655886251588111,100,"{'d_token': 64, 'n_blocks': 4, 'n_heads': 8, 'attention_dropout': 0.24759508454949322, 'ffn_dropout': 0.2013907953941948, 'lr': 0.0003711331440914647, 'weight_decay': 0.06954769328501528, 'batch_size': 32}"
28
+ xgb,pure,gwangju,hyperopt,0.5016,100,"{'colsample_bytree': 0.9713207386536029, 'gamma': 2.2482753887012703, 'learning_rate': 0.16732973947259167, 'max_depth': 8.0, 'min_child_weight': 3.0, 'reg_alpha': 0.2664406256084806, 'reg_lambda': 0.7263114796775476, 'subsample': 0.6483131273031051}"
29
+ ft_transformer,pure,seoul,optuna,0.562070126103511,100,"{'d_token': 256, 'n_blocks': 2, 'n_heads': 4, 'attention_dropout': 0.2855445640312001, 'ffn_dropout': 0.20563167448836292, 'lr': 7.430025637172839e-05, 'weight_decay': 0.012136192435211931, 'batch_size': 32}"
30
+ resnet_like,smote,busan,optuna,0.4473603019416436,100,"{'d_main': 128, 'd_hidden': 256, 'n_blocks': 5, 'dropout_first': 0.37677375956516684, 'dropout_second': 0.18705700465884292, 'lr': 0.005004477317296484, 'weight_decay': 0.00012190453086381686, 'batch_size': 64}"
31
+ deepgbm,pure,incheon,optuna,0.5622375492647842,100,"{'d_main': 64, 'd_hidden': 256, 'n_blocks': 2, 'dropout': 0.3553750103803738, 'lr': 0.0017038392317957017, 'weight_decay': 0.04010324241876258, 'batch_size': 32}"
32
+ ft_transformer,smote,gwangju,optuna,0.48424711598330084,100,"{'d_token': 96, 'n_blocks': 4, 'n_heads': 8, 'attention_dropout': 0.19167241349972552, 'ffn_dropout': 0.10372384139481815, 'lr': 0.0003028578585093515, 'weight_decay': 0.021302792376896054, 'batch_size': 32}"
33
+ lgb,pure,busan,hyperopt,0.4849,100,"{'colsample_bytree': 0.9406061312055983, 'learning_rate': 0.17468151642796886, 'max_depth': 6.0, 'min_child_weight': 17.0, 'num_leaves': 138.0, 'reg_alpha': 0.4593420461637059, 'reg_lambda': 0.5948987302333338, 'subsample': 0.6557839186758097}"
34
+ xgb,ctgan10000,seoul,hyperopt,0.5824,100,"{'colsample_bytree': 0.8837225390968168, 'gamma': 0.1115044781500254, 'learning_rate': 0.10805110293567466, 'max_depth': 12.0, 'min_child_weight': 4.0, 'reg_alpha': 0.02183712172236562, 'reg_lambda': 0.6932207560084631, 'subsample': 0.6767341133785678}"
35
+ resnet_like,ctgan10000,gwangju,optuna,0.510302842874457,100,"{'d_main': 64, 'd_hidden': 320, 'n_blocks': 3, 'dropout_first': 0.29522157561687634, 'dropout_second': 0.15684305218104422, 'lr': 0.008180657303015811, 'weight_decay': 0.01303718192830624, 'batch_size': 128}"
36
+ deepgbm,pure,busan,optuna,0.4429286988285861,100,"{'d_main': 192, 'd_hidden': 64, 'n_blocks': 3, 'dropout': 0.2275228702990485, 'lr': 0.002636923316902024, 'weight_decay': 0.05132270066782015, 'batch_size': 32}"
37
+ ft_transformer,ctgan10000,busan,optuna,0.4960458104166546,100,"{'d_token': 224, 'n_blocks': 2, 'n_heads': 8, 'attention_dropout': 0.3873943566967484, 'ffn_dropout': 0.14296280926606936, 'lr': 0.0007665967810279031, 'weight_decay': 0.00878158688959246, 'batch_size': 32}"
38
+ resnet_like,ctgan10000,daejeon,optuna,0.5101768615009369,100,"{'d_main': 128, 'd_hidden': 256, 'n_blocks': 5, 'dropout_first': 0.1381181811099212, 'dropout_second': 0.11702484025760711, 'lr': 0.0064016726045039805, 'weight_decay': 0.004366638608686326, 'batch_size': 256}"
39
+ resnet_like,smotenc_ctgan20000,incheon,optuna,0.5707798446437679,100,"{'d_main': 224, 'd_hidden': 256, 'n_blocks': 4, 'dropout_first': 0.3626907864360457, 'dropout_second': 0.08738106548329602, 'lr': 0.005205322934309404, 'weight_decay': 0.0002577881849067971, 'batch_size': 256}"
40
+ xgb,pure,daegu,hyperopt,0.4409,100,"{'colsample_bytree': 0.8800494992202731, 'gamma': 0.28651615767316957, 'learning_rate': 0.025526450870185433, 'max_depth': 3.0, 'min_child_weight': 5.0, 'reg_alpha': 0.6787273055071508, 'reg_lambda': 0.6641153401816423, 'subsample': 0.7222783789369407}"
41
+ ft_transformer,smotenc_ctgan20000,daegu,optuna,0.4488825045464337,100,"{'d_token': 64, 'n_blocks': 3, 'n_heads': 4, 'attention_dropout': 0.270864990314075, 'ffn_dropout': 0.3735925199999471, 'lr': 0.0016588396308948813, 'weight_decay': 0.00014669112268617685, 'batch_size': 128}"
42
+ resnet_like,ctgan10000,daegu,optuna,0.46086300130604796,100,"{'d_main': 96, 'd_hidden': 256, 'n_blocks': 3, 'dropout_first': 0.27926914874893893, 'dropout_second': 0.13114004557533837, 'lr': 0.004133395383387492, 'weight_decay': 0.05462768451276688, 'batch_size': 32}"
43
+ deepgbm,smote,daegu,optuna,0.3991148650568916,100,"{'d_main': 64, 'd_hidden': 192, 'n_blocks': 5, 'dropout': 0.15327234825163508, 'lr': 0.0021257323880618864, 'weight_decay': 0.06824750948093047, 'batch_size': 32}"
44
+ deepgbm,smote,seoul,optuna,0.5551122990255606,100,"{'d_main': 64, 'd_hidden': 64, 'n_blocks': 2, 'dropout': 0.2869842021080176, 'lr': 0.002077449117732186, 'weight_decay': 0.00019614736051849963, 'batch_size': 32}"
45
+ lgb,smote,incheon,hyperopt,0.5986,100,"{'colsample_bytree': 0.7149911519913482, 'learning_rate': 0.14061649313221522, 'max_depth': 4.0, 'min_child_weight': 4.0, 'num_leaves': 46.0, 'reg_alpha': 0.3323739596170201, 'reg_lambda': 0.3615804769440283, 'subsample': 0.7361106038020775}"
46
+ deepgbm,ctgan10000,daejeon,optuna,0.5101248146449113,100,"{'d_main': 64, 'd_hidden': 256, 'n_blocks': 2, 'dropout': 0.2845653149911174, 'lr': 0.0030479748817488737, 'weight_decay': 0.08478209494184558, 'batch_size': 32}"
47
+ resnet_like,smote,seoul,optuna,0.5589425055467122,100,"{'d_main': 128, 'd_hidden': 512, 'n_blocks': 3, 'dropout_first': 0.3304233130420639, 'dropout_second': 0.14346618645388706, 'lr': 0.006514721583103225, 'weight_decay': 0.0719094067694046, 'batch_size': 64}"
48
+ deepgbm,smote,incheon,optuna,0.5640599235240535,100,"{'d_main': 128, 'd_hidden': 192, 'n_blocks': 4, 'dropout': 0.3785345227219112, 'lr': 0.0018955834640803318, 'weight_decay': 0.02389399379756967, 'batch_size': 32}"
49
+ xgb,smote,gwangju,hyperopt,0.53,100,"{'colsample_bytree': 0.7658195937298418, 'gamma': 1.040884657831581, 'learning_rate': 0.04553328563585195, 'max_depth': 7.0, 'min_child_weight': 12.0, 'reg_alpha': 0.8031012977426317, 'reg_lambda': 0.6205464163959697, 'subsample': 0.6524796151581305}"
50
+ xgb,smotenc_ctgan20000,incheon,hyperopt,0.5653,100,"{'colsample_bytree': 0.780674346441659, 'gamma': 1.066921965325722, 'learning_rate': 0.09975688732352224, 'max_depth': 11.0, 'min_child_weight': 8.0, 'reg_alpha': 0.8401568358231439, 'reg_lambda': 0.6475753573884905, 'subsample': 0.6026764334015118}"
51
+ lgb,pure,gwangju,hyperopt,0.4976,100,"{'colsample_bytree': 0.944925569294789, 'learning_rate': 0.014333972349102263, 'max_depth': 13.0, 'min_child_weight': 13.0, 'num_leaves': 70.0, 'reg_alpha': 0.31059473707139207, 'reg_lambda': 0.19125854192836045, 'subsample': 0.6106523377701687}"
52
+ lgb,pure,incheon,hyperopt,0.5617,100,"{'colsample_bytree': 0.7451758674748375, 'learning_rate': 0.012136256520039064, 'max_depth': 10.0, 'min_child_weight': 9.0, 'num_leaves': 89.0, 'reg_alpha': 0.41323940989949803, 'reg_lambda': 0.9961125910856155, 'subsample': 0.7322009271446389}"
53
+ deepgbm,pure,daejeon,optuna,0.45092661677493817,100,"{'d_main': 256, 'd_hidden': 64, 'n_blocks': 2, 'dropout': 0.16512768923755844, 'lr': 0.00013316728360925615, 'weight_decay': 0.0001651587899552549, 'batch_size': 32}"
54
+ xgb,smote,daegu,hyperopt,0.4672,100,"{'colsample_bytree': 0.8132816721507904, 'gamma': 0.9002659162503241, 'learning_rate': 0.04046864452016672, 'max_depth': 4.0, 'min_child_weight': 17.0, 'reg_alpha': 0.4681545450085154, 'reg_lambda': 0.531313515098387, 'subsample': 0.827198506312037}"
55
+ ft_transformer,ctgan10000,daegu,optuna,0.44918319157422554,100,"{'d_token': 128, 'n_blocks': 4, 'n_heads': 8, 'attention_dropout': 0.1615322006432558, 'ffn_dropout': 0.14353691142809796, 'lr': 0.00025225999310114116, 'weight_decay': 0.002948085679186959, 'batch_size': 32}"
56
+ ft_transformer,smote,incheon,optuna,0.5674050423289939,100,"{'d_token': 96, 'n_blocks': 3, 'n_heads': 8, 'attention_dropout': 0.3637871224837107, 'ffn_dropout': 0.11479322703553738, 'lr': 0.0003009840584939789, 'weight_decay': 0.0003336039035587163, 'batch_size': 32}"
57
+ deepgbm,ctgan10000,busan,optuna,0.475435864212341,100,"{'d_main': 128, 'd_hidden': 128, 'n_blocks': 2, 'dropout': 0.1477619274404685, 'lr': 0.00606559205480389, 'weight_decay': 0.08582651929034574, 'batch_size': 64}"
58
+ resnet_like,ctgan10000,seoul,optuna,0.5889744558864985,100,"{'d_main': 160, 'd_hidden': 128, 'n_blocks': 4, 'dropout_first': 0.24169683403631037, 'dropout_second': 0.018646743579449815, 'lr': 0.003891520111503718, 'weight_decay': 0.09736563298725749, 'batch_size': 128}"
59
+ ft_transformer,smotenc_ctgan20000,seoul,optuna,0.5675273679868712,100,"{'d_token': 192, 'n_blocks': 4, 'n_heads': 8, 'attention_dropout': 0.10255871141670557, 'ffn_dropout': 0.3735851591876593, 'lr': 0.00038893486056538687, 'weight_decay': 0.0020864133600508325, 'batch_size': 128}"
60
+ lgb,smotenc_ctgan20000,incheon,hyperopt,0.5827,100,"{'colsample_bytree': 0.8256738533611337, 'learning_rate': 0.03224794137518454, 'max_depth': 12.0, 'min_child_weight': 6.0, 'num_leaves': 128.0, 'reg_alpha': 0.1310437036184594, 'reg_lambda': 0.6161059673451368, 'subsample': 0.8412610992284884}"
61
+ deepgbm,smotenc_ctgan20000,incheon,optuna,0.5515777046032605,100,"{'d_main': 64, 'd_hidden': 256, 'n_blocks': 6, 'dropout': 0.10014845072807586, 'lr': 0.008578508208533469, 'weight_decay': 0.07361767414227417, 'batch_size': 256}"
62
+ lgb,smote,busan,hyperopt,0.4798,100,"{'colsample_bytree': 0.8798108126736107, 'learning_rate': 0.018973645502331604, 'max_depth': 15.0, 'min_child_weight': 12.0, 'num_leaves': 147.0, 'reg_alpha': 0.03444822116314217, 'reg_lambda': 0.19407225134838502, 'subsample': 0.7009485341014761}"
63
+ lgb,ctgan10000,daegu,hyperopt,0.4339,100,"{'colsample_bytree': 0.885595994008888, 'learning_rate': 0.010106842270671093, 'max_depth': 14.0, 'min_child_weight': 1.0, 'num_leaves': 122.0, 'reg_alpha': 0.12648188723964116, 'reg_lambda': 0.873682924904797, 'subsample': 0.7806598236159817}"
64
+ lgb,ctgan10000,gwangju,hyperopt,0.4994,100,"{'colsample_bytree': 0.9974290644555891, 'learning_rate': 0.03488079849604818, 'max_depth': 15.0, 'min_child_weight': 13.0, 'num_leaves': 47.0, 'reg_alpha': 0.22968749134640387, 'reg_lambda': 0.42745540115072206, 'subsample': 0.9875948361694687}"
65
+ deepgbm,smotenc_ctgan20000,daegu,optuna,0.43407422794617584,100,"{'d_main': 160, 'd_hidden': 192, 'n_blocks': 2, 'dropout': 0.2100809214334562, 'lr': 0.0045042768238180075, 'weight_decay': 0.09966580216480231, 'batch_size': 32}"
66
+ deepgbm,pure,gwangju,optuna,0.4507852210916714,100,"{'d_main': 96, 'd_hidden': 256, 'n_blocks': 4, 'dropout': 0.22201246225002172, 'lr': 0.0018802322915298384, 'weight_decay': 0.04341402361540322, 'batch_size': 64}"
67
+ lgb,smote,daegu,hyperopt,0.4671,100,"{'colsample_bytree': 0.999946333457191, 'learning_rate': 0.07031680296643952, 'max_depth': 4.0, 'min_child_weight': 17.0, 'num_leaves': 32.0, 'reg_alpha': 0.055815317687804816, 'reg_lambda': 0.2293760134119255, 'subsample': 0.6363907923464539}"
68
+ lgb,smotenc_ctgan20000,daejeon,hyperopt,0.5056,100,"{'colsample_bytree': 0.7827606965781482, 'learning_rate': 0.013695421561409111, 'max_depth': 13.0, 'min_child_weight': 6.0, 'num_leaves': 147.0, 'reg_alpha': 0.11677800966310199, 'reg_lambda': 0.7741495746536297, 'subsample': 0.7509016581783318}"
69
+ xgb,pure,incheon,hyperopt,0.566,100,"{'colsample_bytree': 0.7546508432340249, 'gamma': 1.043370422174196, 'learning_rate': 0.015864658027101238, 'max_depth': 11.0, 'min_child_weight': 6.0, 'reg_alpha': 0.7662203770275335, 'reg_lambda': 0.5754328276715727, 'subsample': 0.6332898543620008}"
70
+ deepgbm,smotenc_ctgan20000,gwangju,optuna,0.4832850681063274,100,"{'d_main': 192, 'd_hidden': 128, 'n_blocks': 5, 'dropout': 0.3184031589315668, 'lr': 0.00908394353608693, 'weight_decay': 0.005195807637314873, 'batch_size': 64}"
71
+ lgb,smotenc_ctgan20000,gwangju,hyperopt,0.5098,100,"{'colsample_bytree': 0.9823131365674758, 'learning_rate': 0.09913135171477433, 'max_depth': 12.0, 'min_child_weight': 9.0, 'num_leaves': 123.0, 'reg_alpha': 0.7300219334294252, 'reg_lambda': 0.1069375287034794, 'subsample': 0.6733134215038767}"
72
+ deepgbm,ctgan10000,incheon,optuna,0.5644485264432356,100,"{'d_main': 64, 'd_hidden': 192, 'n_blocks': 5, 'dropout': 0.16846849111235224, 'lr': 0.007871644587352598, 'weight_decay': 0.0005399258093557023, 'batch_size': 128}"
73
+ ft_transformer,pure,gwangju,optuna,0.46517686569307726,100,"{'d_token': 64, 'n_blocks': 3, 'n_heads': 4, 'attention_dropout': 0.22191677554696004, 'ffn_dropout': 0.3593673195268826, 'lr': 0.001039914773988631, 'weight_decay': 0.002578609852830777, 'batch_size': 64}"
74
+ xgb,smotenc_ctgan20000,seoul,hyperopt,0.5595,100,"{'colsample_bytree': 0.8639896996820762, 'gamma': 1.3315807011964704, 'learning_rate': 0.15781883407025307, 'max_depth': 4.0, 'min_child_weight': 8.0, 'reg_alpha': 0.4792043224918665, 'reg_lambda': 0.2705699063386674, 'subsample': 0.6068794375013623}"
75
+ lgb,smotenc_ctgan20000,busan,hyperopt,0.4447,100,"{'colsample_bytree': 0.6317882901026403, 'learning_rate': 0.16009804087232835, 'max_depth': 12.0, 'min_child_weight': 7.0, 'num_leaves': 79.0, 'reg_alpha': 0.7559497285087418, 'reg_lambda': 0.36818298791457293, 'subsample': 0.6759358549390172}"
76
+ ft_transformer,ctgan10000,daejeon,optuna,0.5026041056392309,100,"{'d_token': 64, 'n_blocks': 5, 'n_heads': 8, 'attention_dropout': 0.39639878146052787, 'ffn_dropout': 0.16243660840447227, 'lr': 0.0005258652715359098, 'weight_decay': 0.06319928258911829, 'batch_size': 128}"
77
+ lgb,pure,seoul,hyperopt,0.5561,100,"{'colsample_bytree': 0.9656226027993231, 'learning_rate': 0.19802455575535455, 'max_depth': 9.0, 'min_child_weight': 20.0, 'num_leaves': 40.0, 'reg_alpha': 0.9688960116885452, 'reg_lambda': 0.8497573873429717, 'subsample': 0.9553638492982583}"
78
+ ft_transformer,pure,incheon,optuna,0.5673234518633549,100,"{'d_token': 96, 'n_blocks': 4, 'n_heads': 4, 'attention_dropout': 0.12006219567079585, 'ffn_dropout': 0.19152888035195653, 'lr': 0.0011919865831209798, 'weight_decay': 0.00010616617862067153, 'batch_size': 128}"
79
+ xgb,smote,daejeon,hyperopt,0.5371,100,"{'colsample_bytree': 0.733236256331133, 'gamma': 0.7990977235867733, 'learning_rate': 0.17558281930946487, 'max_depth': 9.0, 'min_child_weight': 11.0, 'reg_alpha': 0.1596833778659402, 'reg_lambda': 0.9170555745286906, 'subsample': 0.6403574066792026}"
80
+ xgb,pure,seoul,hyperopt,0.5722,100,"{'colsample_bytree': 0.9998832589057977, 'gamma': 1.1284338309478381, 'learning_rate': 0.07547053757720854, 'max_depth': 11.0, 'min_child_weight': 3.0, 'reg_alpha': 0.005163550196038334, 'reg_lambda': 0.7838372117209551, 'subsample': 0.6965117137201219}"
81
+ deepgbm,smote,daejeon,optuna,0.4669846754411795,100,"{'d_main': 128, 'd_hidden': 192, 'n_blocks': 2, 'dropout': 0.17471030464369763, 'lr': 0.0034006630423833845, 'weight_decay': 0.008657423885357477, 'batch_size': 32}"
82
+ lgb,ctgan10000,seoul,hyperopt,0.5671,100,"{'colsample_bytree': 0.661683034534645, 'learning_rate': 0.02117850018558707, 'max_depth': 15.0, 'min_child_weight': 16.0, 'num_leaves': 83.0, 'reg_alpha': 0.6438462886327296, 'reg_lambda': 0.8929153518940249, 'subsample': 0.9547922722157274}"
83
+ resnet_like,smotenc_ctgan20000,daegu,optuna,0.43482923124906,100,"{'d_main': 192, 'd_hidden': 128, 'n_blocks': 3, 'dropout_first': 0.38064877864842067, 'dropout_second': 0.011258432283909839, 'lr': 0.003421315789279206, 'weight_decay': 0.0004979175699002674, 'batch_size': 64}"
84
+ ft_transformer,smote,seoul,optuna,0.5788930444782093,100,"{'d_token': 96, 'n_blocks': 5, 'n_heads': 8, 'attention_dropout': 0.3074211243640513, 'ffn_dropout': 0.27614330827417055, 'lr': 0.0008013502604362781, 'weight_decay': 0.07731586815781724, 'batch_size': 32}"
85
+ xgb,smote,incheon,hyperopt,0.6,100,"{'colsample_bytree': 0.8863531635625073, 'gamma': 1.4432252696586687, 'learning_rate': 0.14431831840673584, 'max_depth': 4.0, 'min_child_weight': 4.0, 'reg_alpha': 0.7656890601027424, 'reg_lambda': 0.5796745106013773, 'subsample': 0.8862819830666011}"
86
+ ft_transformer,smotenc_ctgan20000,gwangju,optuna,0.49840606228991896,100,"{'d_token': 160, 'n_blocks': 3, 'n_heads': 8, 'attention_dropout': 0.13369638195384545, 'ffn_dropout': 0.25693944180246137, 'lr': 0.00046073450640759476, 'weight_decay': 0.0005511169366746759, 'batch_size': 32}"
87
+ lgb,ctgan10000,incheon,hyperopt,0.5592,100,"{'colsample_bytree': 0.7615743363801121, 'learning_rate': 0.032013705340192794, 'max_depth': 12.0, 'min_child_weight': 4.0, 'num_leaves': 135.0, 'reg_alpha': 0.07355917150019742, 'reg_lambda': 0.7693270890686972, 'subsample': 0.8491133431153928}"
88
+ xgb,ctgan10000,incheon,hyperopt,0.5752,100,"{'colsample_bytree': 0.9876604099689714, 'gamma': 2.7259563165720655, 'learning_rate': 0.014353110732979967, 'max_depth': 5.0, 'min_child_weight': 8.0, 'reg_alpha': 0.43412935826888077, 'reg_lambda': 0.45790677460553664, 'subsample': 0.6390967315026312}"
89
+ lgb,smote,gwangju,hyperopt,0.5297,100,"{'colsample_bytree': 0.9919060649789312, 'learning_rate': 0.054631157314326724, 'max_depth': 15.0, 'min_child_weight': 3.0, 'num_leaves': 47.0, 'reg_alpha': 0.9190252546800255, 'reg_lambda': 0.8800706832709921, 'subsample': 0.7859941375783913}"
90
+ deepgbm,smote,busan,optuna,0.44276076380851953,100,"{'d_main': 64, 'd_hidden': 192, 'n_blocks': 3, 'dropout': 0.3745726718399158, 'lr': 0.005338808759265471, 'weight_decay': 0.06558728678415406, 'batch_size': 32}"
91
+ xgb,smotenc_ctgan20000,gwangju,hyperopt,0.5012,100,"{'colsample_bytree': 0.9791354222802998, 'gamma': 1.1338312824344885, 'learning_rate': 0.06507978835501058, 'max_depth': 7.0, 'min_child_weight': 20.0, 'reg_alpha': 0.4224203070076331, 'reg_lambda': 0.548023995725087, 'subsample': 0.6318874518405971}"
92
+ resnet_like,pure,daejeon,optuna,0.4661049144479625,100,"{'d_main': 128, 'd_hidden': 128, 'n_blocks': 5, 'dropout_first': 0.17640987113900017, 'dropout_second': 0.07455114486955416, 'lr': 0.0014433413138854976, 'weight_decay': 0.002550708908998169, 'batch_size': 32}"
93
+ deepgbm,pure,seoul,optuna,0.5441091848294762,100,"{'d_main': 96, 'd_hidden': 256, 'n_blocks': 2, 'dropout': 0.38755576686685356, 'lr': 0.001481020211477321, 'weight_decay': 0.0036076992783665223, 'batch_size': 32}"
94
+ deepgbm,ctgan10000,daegu,optuna,0.4390250453058284,100,"{'d_main': 64, 'd_hidden': 192, 'n_blocks': 2, 'dropout': 0.29112938728448373, 'lr': 0.002745246324742509, 'weight_decay': 0.07823286969698617, 'batch_size': 32}"
95
+ ft_transformer,smotenc_ctgan20000,incheon,optuna,0.5658689261675397,100,"{'d_token': 64, 'n_blocks': 6, 'n_heads': 4, 'attention_dropout': 0.3014135618352386, 'ffn_dropout': 0.2377846194971104, 'lr': 0.0023493513093616647, 'weight_decay': 0.0983836135411264, 'batch_size': 256}"
96
+ xgb,smotenc_ctgan20000,busan,hyperopt,0.4764,100,"{'colsample_bytree': 0.6617270669071449, 'gamma': 1.8648711247698304, 'learning_rate': 0.116012512145597, 'max_depth': 5.0, 'min_child_weight': 8.0, 'reg_alpha': 0.0033591561849573015, 'reg_lambda': 0.6137037380779208, 'subsample': 0.6181654880316922}"
97
+ ft_transformer,smote,daejeon,optuna,0.482035457043179,100,"{'d_token': 64, 'n_blocks': 3, 'n_heads': 8, 'attention_dropout': 0.3951058265943127, 'ffn_dropout': 0.15816355519966163, 'lr': 0.0011481409855838528, 'weight_decay': 0.00011134016766733501, 'batch_size': 64}"
98
+ resnet_like,smote,incheon,optuna,0.5677136089270878,100,"{'d_main': 192, 'd_hidden': 256, 'n_blocks': 3, 'dropout_first': 0.29114464826990016, 'dropout_second': 0.1740467381980997, 'lr': 0.0013843537735809836, 'weight_decay': 0.032020003146016864, 'batch_size': 128}"
99
+ xgb,smote,busan,hyperopt,0.4773,100,"{'colsample_bytree': 0.7955102167770075, 'gamma': 0.16947237102826285, 'learning_rate': 0.04201247161970075, 'max_depth': 11.0, 'min_child_weight': 4.0, 'reg_alpha': 0.9136392250501164, 'reg_lambda': 0.4323511178052387, 'subsample': 0.6554957061124282}"
100
+ xgb,pure,busan,hyperopt,0.4949,100,"{'colsample_bytree': 0.8651175745135303, 'gamma': 2.0220518303820976, 'learning_rate': 0.04196437449161767, 'max_depth': 7.0, 'min_child_weight': 17.0, 'reg_alpha': 0.9213159636887744, 'reg_lambda': 0.9407811453878014, 'subsample': 0.7200034080497129}"
101
+ resnet_like,smotenc_ctgan20000,seoul,optuna,0.5571199836340152,100,"{'d_main': 192, 'd_hidden': 64, 'n_blocks': 5, 'dropout_first': 0.2550924108208247, 'dropout_second': 0.1294554884955162, 'lr': 0.0046329086177801316, 'weight_decay': 0.012820236692231602, 'batch_size': 64}"
102
+ deepgbm,ctgan10000,seoul,optuna,0.5652632820174084,100,"{'d_main': 160, 'd_hidden': 64, 'n_blocks': 3, 'dropout': 0.2113225708109025, 'lr': 0.0038029027900849553, 'weight_decay': 0.0005824342055366228, 'batch_size': 32}"
103
+ xgb,smote,seoul,hyperopt,0.5914,100,"{'colsample_bytree': 0.9204650350059359, 'gamma': 0.006794691671452219, 'learning_rate': 0.08811009219503893, 'max_depth': 12.0, 'min_child_weight': 3.0, 'reg_alpha': 0.6690476963880017, 'reg_lambda': 0.5388102924254845, 'subsample': 0.8320339664880525}"
104
+ resnet_like,ctgan10000,busan,optuna,0.49363300915248276,100,"{'d_main': 128, 'd_hidden': 512, 'n_blocks': 2, 'dropout_first': 0.3784300740258752, 'dropout_second': 0.026029354045211155, 'lr': 0.008483242466300268, 'weight_decay': 0.00016367394584020504, 'batch_size': 128}"
105
+ resnet_like,pure,gwangju,optuna,0.48295928519708414,100,"{'d_main': 224, 'd_hidden': 448, 'n_blocks': 5, 'dropout_first': 0.19145077532270985, 'dropout_second': 0.17709489175426982, 'lr': 0.0013336041583887023, 'weight_decay': 0.012922488005108791, 'batch_size': 32}"
106
+ lgb,pure,daegu,hyperopt,0.405,100,"{'colsample_bytree': 0.7032353545561223, 'learning_rate': 0.027019407889171166, 'max_depth': 3.0, 'min_child_weight': 4.0, 'num_leaves': 134.0, 'reg_alpha': 0.3506952189889989, 'reg_lambda': 0.46506999012541095, 'subsample': 0.9411873767438697}"
107
+ deepgbm,smotenc_ctgan20000,seoul,optuna,0.5657974901513136,100,"{'d_main': 128, 'd_hidden': 64, 'n_blocks': 5, 'dropout': 0.1024240157205574, 'lr': 0.009019177625524915, 'weight_decay': 0.08874117499066106, 'batch_size': 256}"
108
+ resnet_like,ctgan10000,incheon,optuna,0.5876200434398301,100,"{'d_main': 160, 'd_hidden': 192, 'n_blocks': 3, 'dropout_first': 0.213366405042877, 'dropout_second': 0.0616930432275245, 'lr': 0.005092968501532562, 'weight_decay': 0.06153947659623341, 'batch_size': 256}"
109
+ xgb,smotenc_ctgan20000,daejeon,hyperopt,0.4957,100,"{'colsample_bytree': 0.839455487096683, 'gamma': 0.6837674570637463, 'learning_rate': 0.059254118154918205, 'max_depth': 12.0, 'min_child_weight': 16.0, 'reg_alpha': 0.741156478605324, 'reg_lambda': 0.21565422560180894, 'subsample': 0.6536276314951073}"
110
+ xgb,pure,daejeon,hyperopt,0.5098,100,"{'colsample_bytree': 0.7188993723348515, 'gamma': 0.8312229248711611, 'learning_rate': 0.13636264607406778, 'max_depth': 4.0, 'min_child_weight': 4.0, 'reg_alpha': 0.8193564485724522, 'reg_lambda': 0.796595038878536, 'subsample': 0.6408013744463261}"
111
+ xgb,ctgan10000,busan,hyperopt,0.4881,100,"{'colsample_bytree': 0.6875780545091519, 'gamma': 2.658982028747467, 'learning_rate': 0.11595019019771602, 'max_depth': 12.0, 'min_child_weight': 18.0, 'reg_alpha': 0.9071038284958559, 'reg_lambda': 0.2880553949579837, 'subsample': 0.7100915343806586}"
112
+ lgb,smotenc_ctgan20000,seoul,hyperopt,0.5622,100,"{'colsample_bytree': 0.6345219883667235, 'learning_rate': 0.010708867004743688, 'max_depth': 14.0, 'min_child_weight': 14.0, 'num_leaves': 111.0, 'reg_alpha': 0.12632598375404414, 'reg_lambda': 0.632120993668035, 'subsample': 0.6705295797223814}"
113
+ lgb,pure,daejeon,hyperopt,0.4963,100,"{'colsample_bytree': 0.8561310986458904, 'learning_rate': 0.04190098150317689, 'max_depth': 13.0, 'min_child_weight': 10.0, 'num_leaves': 20.0, 'reg_alpha': 0.8699443310189154, 'reg_lambda': 0.6437824460768218, 'subsample': 0.7878286207681128}"
114
+ resnet_like,pure,busan,optuna,0.4542970487265281,100,"{'d_main': 160, 'd_hidden': 128, 'n_blocks': 3, 'dropout_first': 0.3972607776862854, 'dropout_second': 0.13044016240028491, 'lr': 0.009478600883696408, 'weight_decay': 0.009976371611112884, 'batch_size': 64}"
115
+ resnet_like,smote,daegu,optuna,0.39559298655454533,100,"{'d_main': 96, 'd_hidden': 64, 'n_blocks': 4, 'dropout_first': 0.3420738859809193, 'dropout_second': 0.1494827111234321, 'lr': 0.008042182880401372, 'weight_decay': 0.00036799147801704795, 'batch_size': 32}"
116
+ deepgbm,smotenc_ctgan20000,daejeon,optuna,0.4848928597361463,100,"{'d_main': 96, 'd_hidden': 64, 'n_blocks': 6, 'dropout': 0.2751230389403302, 'lr': 0.007765569142416956, 'weight_decay': 0.019237770834817113, 'batch_size': 128}"
117
+ resnet_like,smotenc_ctgan20000,daejeon,optuna,0.48223852799636385,100,"{'d_main': 256, 'd_hidden': 128, 'n_blocks': 2, 'dropout_first': 0.1346841434587851, 'dropout_second': 0.09633438692418629, 'lr': 0.008312402405575084, 'weight_decay': 0.00017010818801516423, 'batch_size': 256}"
118
+ deepgbm,pure,daegu,optuna,0.3570454117885781,100,"{'d_main': 160, 'd_hidden': 64, 'n_blocks': 4, 'dropout': 0.39867335991930597, 'lr': 0.002428396450034936, 'weight_decay': 0.05750366129158036, 'batch_size': 32}"
119
+ resnet_like,pure,daegu,optuna,0.4075222542316909,100,"{'d_main': 192, 'd_hidden': 64, 'n_blocks': 3, 'dropout_first': 0.10590946492415504, 'dropout_second': 0.10708545709499212, 'lr': 0.0012544175963123808, 'weight_decay': 0.08314171375285831, 'batch_size': 32}"
120
+ deepgbm,ctgan10000,gwangju,optuna,0.5204031176113428,100,"{'d_main': 128, 'd_hidden': 192, 'n_blocks': 6, 'dropout': 0.3938212564993552, 'lr': 0.007164979269975063, 'weight_decay': 0.0923681134285374, 'batch_size': 64}"
121
+ ft_transformer,ctgan10000,incheon,optuna,0.5643832267965512,100,"{'d_token': 128, 'n_blocks': 6, 'n_heads': 4, 'attention_dropout': 0.1369145590780379, 'ffn_dropout': 0.16996780951611673, 'lr': 0.0003662598943307626, 'weight_decay': 0.000729119254134465, 'batch_size': 256}"
Analysis_code/6.optima_models_analysis/utils.py ADDED
@@ -0,0 +1,1077 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ from joblib import load
2
+ import pandas as pd
3
+ import numpy as np
4
+ import matplotlib.pyplot as plt
5
+ import os
6
+ import sys
7
+ from contextlib import contextmanager
8
+ from io import StringIO
9
+ from typing import Optional, Tuple, List, Dict, Any
10
+ from sklearn.metrics import confusion_matrix
11
+ from sklearn.preprocessing import LabelEncoder
12
+ import shap
13
+ import torch
14
+ import warnings
15
+ # ๋ชจ๋“  ๊ฒฝ๊ณ  ๋ฌด์‹œ
16
+ warnings.filterwarnings('ignore')
17
+ # SHAP ๊ด€๋ จ ๊ฒฝ๊ณ  ๋ฌด์‹œ (LayerNorm ๋“ฑ unrecognized nn.Module ๊ฒฝ๊ณ )
18
+ warnings.filterwarnings('ignore', category=UserWarning, message='.*unrecognized nn.Module.*')
19
+ warnings.filterwarnings('ignore', category=UserWarning, message='.*LayerNorm.*')
20
+ warnings.filterwarnings('ignore', category=UserWarning, message='.*unrecognized.*')
21
+ # SHAP ๋ชจ๋“ˆ์—์„œ ๋ฐœ์ƒํ•˜๋Š” ๋ชจ๋“  ๊ฒฝ๊ณ  ๋ฌด์‹œ
22
+ warnings.filterwarnings('ignore', module='shap.*')
23
+
24
+ # ๋ชจ๋ธ ํด๋ž˜์Šค import๋ฅผ ์œ„ํ•œ ๊ฒฝ๋กœ ์„ค์ • (PyTorch ๋ชจ๋ธ ๋กœ๋“œ๋ฅผ ์œ„ํ•ด ํ•„์š”)
25
+ # ๋…ธํŠธ๋ถ ํ™˜๊ฒฝ์—์„œ๋„ ์ž‘๋™ํ•˜๋„๋ก ์—ฌ๋Ÿฌ ๋ฐฉ๋ฒ• ์‹œ๋„
26
+ try:
27
+ # ๋ฐฉ๋ฒ• 1: __file__ ์‚ฌ์šฉ (์ผ๋ฐ˜ Python ์Šคํฌ๋ฆฝํŠธ)
28
+ current_file_dir = os.path.dirname(os.path.abspath(__file__))
29
+ models_path = os.path.abspath(os.path.join(current_file_dir, '../models'))
30
+ except NameError:
31
+ # ๋ฐฉ๋ฒ• 2: __file__์ด ์—†๋Š” ๊ฒฝ์šฐ (๋…ธํŠธ๋ถ ํ™˜๊ฒฝ) - ํ˜„์žฌ ์ž‘์—… ๋””๋ ‰ํ† ๋ฆฌ ๊ธฐ์ค€
32
+ cwd = os.getcwd()
33
+ # Analysis_code ๋””๋ ‰ํ† ๋ฆฌ๋ฅผ ์ฐพ๊ธฐ
34
+ if 'Analysis_code' in cwd:
35
+ analysis_code_dir = cwd[:cwd.index('Analysis_code') + len('Analysis_code')]
36
+ models_path = os.path.join(analysis_code_dir, 'models')
37
+ else:
38
+ # ๋ฐฉ๋ฒ• 3: ์ ˆ๋Œ€ ๊ฒฝ๋กœ ์‚ฌ์šฉ
39
+ models_path = '/workspace/visibility_prediction/Analysis_code/models'
40
+
41
+
42
+ if models_path not in sys.path:
43
+ sys.path.insert(0, models_path)
44
+
45
+ from ft_transformer import FTTransformer
46
+ from resnet_like import ResNetLike
47
+ from deepgbm import DeepGBM
48
+
49
+ # ==========================================
50
+ # ์ƒ์ˆ˜ ์ •์˜
51
+ # ==========================================
52
+ FOLD_YEARS = [[2018, 2019], [2018, 2019], [2019, 2020]]
53
+ TEST_YEAR = 2021
54
+ DROP_COLUMNS = ['multi_class', 'year']
55
+ FEATURE_COLUMNS = [
56
+ 'temp_C', 'precip_mm', 'wind_speed', 'wind_dir', 'hm',
57
+ 'vap_pressure', 'dewpoint_C', 'loc_pressure', 'sea_pressure',
58
+ 'solarRad', 'snow_cm', 'cloudcover', 'lm_cloudcover', 'low_cloudbase',
59
+ 'groundtemp', 'O3', 'NO2', 'PM10', 'PM25', 'year',
60
+ 'month', 'hour', 'ground_temp - temp_C', 'hour_sin', 'hour_cos',
61
+ 'month_sin', 'month_cos', 'multi_class'
62
+ ]
63
+
64
+
65
+ # ==========================================
66
+ # ์œ ํ‹ธ๋ฆฌํ‹ฐ ํ•จ์ˆ˜
67
+ # ==========================================
68
+ def calculate_csi(y_true: np.ndarray, y_pred: np.ndarray) -> float:
69
+ """CSI(Critical Success Index) ์ ์ˆ˜๋ฅผ ๊ณ„์‚ฐํ•ฉ๋‹ˆ๋‹ค.
70
+
71
+ Args:
72
+ y_true: ์‹ค์ œ ๋ ˆ์ด๋ธ”
73
+ y_pred: ์˜ˆ์ธก ๋ ˆ์ด๋ธ”
74
+
75
+ Returns:
76
+ CSI ์ ์ˆ˜ (0~1 ์‚ฌ์ด์˜ ๊ฐ’)
77
+ """
78
+ cm = confusion_matrix(y_true, y_pred)
79
+
80
+ # ํ˜ผ๋™ ํ–‰๋ ฌ์—์„œ H(Hit), F(False alarm), M(Miss) ์ถ”์ถœ
81
+ H = cm[0, 0] + cm[1, 1]
82
+ F = cm[1, 0] + cm[2, 0] + cm[0, 1] + cm[2, 1]
83
+ M = cm[0, 2] + cm[1, 2]
84
+
85
+ # CSI ๊ณ„์‚ฐ
86
+ csi = H / (H + F + M + 1e-10)
87
+ return csi
88
+
89
+
90
+ def csi_metric(y_true: np.ndarray, pred_prob: np.ndarray) -> Tuple[str, float, bool]:
91
+ """LightGBM์šฉ CSI ๋ฉ”ํŠธ๋ฆญ ํ•จ์ˆ˜.
92
+
93
+ Args:
94
+ y_true: ์‹ค์ œ ๋ ˆ์ด๋ธ”
95
+ pred_prob: ์˜ˆ์ธก ํ™•๋ฅ  (shape: [n_samples, n_classes])
96
+
97
+ Returns:
98
+ ('CSI', score, higher_better) ํŠœํ”Œ
99
+ """
100
+ y_pred_binary = np.argmax(pred_prob, axis=1)
101
+ score = calculate_csi(y_true, y_pred_binary)
102
+ return 'CSI', score, True
103
+
104
+
105
+ def eval_metric_csi(y_true: np.ndarray, pred_prob: np.ndarray) -> float:
106
+ """XGBoost์šฉ CSI ๋ฉ”ํŠธ๋ฆญ ํ•จ์ˆ˜.
107
+
108
+ Args:
109
+ y_true: ์‹ค์ œ ๋ ˆ์ด๋ธ”
110
+ pred_prob: ์˜ˆ์ธก ํ™•๋ฅ 
111
+
112
+ Returns:
113
+ CSI ์ ์ˆ˜์˜ ์Œ์ˆ˜๊ฐ’
114
+ """
115
+ pred = np.argmax(pred_prob, axis=1)
116
+ csi = calculate_csi(y_true, pred)
117
+ return -1*csi
118
+
119
+ def add_derived_features(df: pd.DataFrame) -> pd.DataFrame:
120
+ """
121
+ ์ œ๊ฑฐํ–ˆ๋˜ ํŒŒ์ƒ ๋ณ€์ˆ˜๋“ค์„ ๋ณต๊ตฌ
122
+
123
+ Args:
124
+ df: ๋ฐ์ดํ„ฐํ”„๋ ˆ์ž„
125
+
126
+ Returns:
127
+ ํŒŒ์ƒ ๋ณ€์ˆ˜๊ฐ€ ์ถ”๊ฐ€๋œ ๋ฐ์ดํ„ฐํ”„๋ ˆ์ž„
128
+ """
129
+ df = df.copy()
130
+ df['hour_sin'] = np.sin(2 * np.pi * df['hour'] / 24)
131
+ df['hour_cos'] = np.cos(2 * np.pi * df['hour'] / 24)
132
+ df['month_sin'] = np.sin(2 * np.pi * df['month'] / 12)
133
+ df['month_cos'] = np.cos(2 * np.pi * df['month'] / 12)
134
+ df['ground_temp - temp_C'] = df['groundtemp'] - df['temp_C']
135
+ return df
136
+
137
+ def preprocessing(df: pd.DataFrame) -> pd.DataFrame:
138
+ """๋ฐ์ดํ„ฐ ์ „์ฒ˜๋ฆฌ ํ•จ์ˆ˜.
139
+
140
+ Args:
141
+ df: ์›๋ณธ ๋ฐ์ดํ„ฐํ”„๋ ˆ์ž„
142
+
143
+ Returns:
144
+ ์ „์ฒ˜๋ฆฌ๋œ ๋ฐ์ดํ„ฐํ”„๋ ˆ์ž„
145
+ """
146
+ df = df[df.columns].copy()
147
+ df['year'] = df['year'].astype('int')
148
+ df['month'] = df['month'].astype('int')
149
+ df['hour'] = df['hour'].astype('int')
150
+ df = add_derived_features(df).copy()
151
+ df['multi_class'] = df['multi_class'].astype('int')
152
+ df.loc[df['wind_dir']=='์ •์˜จ', 'wind_dir'] = "0"
153
+ df['wind_dir'] = df['wind_dir'].astype('int')
154
+ df = df[FEATURE_COLUMNS].copy()
155
+ return df
156
+
157
+ def make_dataset_for_boosting_models(
158
+ region: str,
159
+ data_sample: str,
160
+ fold_num: int
161
+ ) -> Tuple[pd.DataFrame, pd.DataFrame, pd.DataFrame]:
162
+ train_data = pd.read_csv(f"../../data/data_oversampled/{data_sample}/{data_sample}_{fold_num+1}_{region}.csv")
163
+ val_data = pd.read_csv(f"../../data/data_for_modeling/{region}_train.csv")
164
+ test_data = pd.read_csv(f"../../data/data_for_modeling/{region}_test.csv")
165
+
166
+ train_data = preprocessing(train_data).copy()
167
+ val_data = preprocessing(val_data).copy()
168
+ test_data = preprocessing(test_data).copy()
169
+
170
+ train_data = train_data.loc[train_data['year'].isin(FOLD_YEARS[fold_num]), :]
171
+ val_data = val_data.loc[~val_data['year'].isin(FOLD_YEARS[fold_num]), :]
172
+ test_data = test_data.loc[test_data['year'].isin([TEST_YEAR]), :]
173
+
174
+ return train_data, val_data, test_data
175
+
176
+ def load_model(model_name: str, region: str, data_sample: str) -> List[Any]:
177
+ model_path = f"../save_model/{model_name}_optima/{model_name}_{data_sample}_{region}.pkl"
178
+ models = load(model_path)
179
+ return models
180
+
181
+
182
+ # ==========================================
183
+ # Tree-based ๋ชจ๋ธ SHAP ๋ถ„์„ ํ•จ์ˆ˜
184
+ # ==========================================
185
+ def analyze_shap_values_across_folds(
186
+ model_name: str,
187
+ region: str,
188
+ data_sample: str,
189
+ target_class: int = 0,
190
+ n_folds: int = 3,
191
+ figsize: Tuple[int, int] = (20, 10),
192
+ show_plot: bool = True,
193
+ show_train_plot: bool = True,
194
+ show_test_plot: bool = True,
195
+ suppress_warnings: bool = True,
196
+ top_n: int = 3
197
+ ) -> Dict[str, Any]:
198
+ """
199
+ ์—ฌ๋Ÿฌ Fold ๋ชจ๋ธ์— ๋Œ€ํ•ด SHAP ๊ฐ’์„ ๊ณ„์‚ฐํ•˜๊ณ  ์‹œ๊ฐํ™”ํ•˜๋ฉฐ, ์ƒ์œ„ 3๊ฐœ ๋ณ€์ˆ˜์˜ ๊ธฐ์—ฌ๋„๋ฅผ ๋ถ„์„ํ•˜๋Š” ํ•จ์ˆ˜.
200
+ """
201
+
202
+ # ๊ฒฐ๊ณผ๋ฅผ ์ €์žฅํ•  ๋ฆฌ์ŠคํŠธ
203
+ oof_shap_values = []
204
+ oof_X_data = []
205
+ test_shap_values = []
206
+
207
+ # ๋ชจ๋ธ ๋กœ๋“œ
208
+ models = load_model(model_name, region, data_sample)
209
+
210
+ if len(models) != n_folds:
211
+ raise ValueError(f"๋กœ๋“œ๋œ ๋ชจ๋ธ ๊ฐœ์ˆ˜({len(models)})๊ฐ€ n_folds({n_folds})์™€ ์ผ์น˜ํ•˜์ง€ ์•Š์Šต๋‹ˆ๋‹ค.")
212
+
213
+ # ๊ฐ Fold์— ๋Œ€ํ•ด SHAP ๊ฐ’ ๊ณ„์‚ฐ
214
+ for fold_idx in range(n_folds):
215
+ # ๊ฐ Fold์— ํ•ด๋‹นํ•˜๋Š” ๋ฐ์ดํ„ฐ ๋กœ๋“œ
216
+ _, val_data, test_data = make_dataset_for_boosting_models(
217
+ region, data_sample, fold_idx
218
+ )
219
+
220
+ # ๊ฒ€์ฆ ๋ฐ์ดํ„ฐ ์ค€๋น„
221
+ X_val = val_data.drop(columns=DROP_COLUMNS)
222
+
223
+ # ํ…Œ์ŠคํŠธ ๋ฐ์ดํ„ฐ ์ค€๋น„ (์ฒซ ๋ฒˆ์งธ fold์—์„œ๋งŒ ์ €์žฅ, ๋‚˜๋จธ์ง€๋Š” ๋™์ผ)
224
+ if fold_idx == 0:
225
+ X_test = test_data.drop(columns=DROP_COLUMNS)
226
+
227
+ # SHAP Explainer ์ƒ์„ฑ
228
+ if suppress_warnings:
229
+ with warnings.catch_warnings():
230
+ warnings.filterwarnings('ignore', category=UserWarning, message='.*deprecated binary model format.*')
231
+ explainer = shap.TreeExplainer(models[fold_idx].get_booster())
232
+ else:
233
+ explainer = shap.TreeExplainer(models[fold_idx].get_booster())
234
+
235
+ # ๊ฒ€์ฆ ๋ฐ์ดํ„ฐ์— ๋Œ€ํ•œ SHAP ๊ฐ’ ๊ณ„์‚ฐ
236
+ shap_val = explainer.shap_values(X_val)
237
+
238
+ # ํƒ€๊ฒŸ ํด๋ž˜์Šค์— ๋Œ€ํ•œ SHAP ๊ฐ’๋งŒ ์ถ”์ถœ
239
+ if isinstance(shap_val, list):
240
+ oof_shap_values.append(shap_val[target_class])
241
+ else:
242
+ oof_shap_values.append(shap_val)
243
+
244
+ oof_X_data.append(X_val)
245
+
246
+ # ํ…Œ์ŠคํŠธ ๋ฐ์ดํ„ฐ์— ๋Œ€ํ•œ SHAP ๊ฐ’ ๊ณ„์‚ฐ
247
+ shap_test = explainer.shap_values(X_test)
248
+
249
+ # ํƒ€๊ฒŸ ํด๋ž˜์Šค์— ๋Œ€ํ•œ SHAP ๊ฐ’๋งŒ ์ถ”์ถœ
250
+ if isinstance(shap_test, list):
251
+ test_shap_values.append(shap_test[target_class])
252
+ else:
253
+ test_shap_values.append(shap_test)
254
+
255
+ # ==========================================
256
+ # ๋ฐ์ดํ„ฐ ํ†ตํ•ฉ
257
+ # ==========================================
258
+ # ํ›ˆ๋ จ ๊ธฐ๊ฐ„(Train) ํ†ตํ•ฉ
259
+ all_shap_train = np.concatenate(oof_shap_values, axis=0)
260
+ all_X_train = pd.concat(oof_X_data, axis=0)
261
+
262
+ # ํ…Œ์ŠคํŠธ ๊ธฐ๊ฐ„(Test, 2021) ํ†ตํ•ฉ: ํ‰๊ท  ์‚ฌ์šฉ
263
+ all_shap_test = np.mean(test_shap_values, axis=0)
264
+
265
+ # ==========================================
266
+ # ์ƒ์œ„ N๊ฐœ ๋ณ€์ˆ˜ ๊ธฐ์—ฌ๋„(Cumulative Share) ๊ณ„์‚ฐ
267
+ # ==========================================
268
+ feature_names = all_X_train.columns
269
+
270
+ # Train ๋ฐ์ดํ„ฐ ์ค‘์š”๋„ ๊ณ„์‚ฐ
271
+ importance_df_train, top_n_features_train, top_n_share_train = _calculate_cumulative_share(
272
+ all_shap_train, feature_names, top_n, period_name='Train Period'
273
+ )
274
+
275
+ # Test ๋ฐ์ดํ„ฐ ์ค‘์š”๋„ ๊ณ„์‚ฐ
276
+ if all_shap_test is not None:
277
+ importance_df_test, top_n_features_test, top_n_share_test = _calculate_cumulative_share(
278
+ all_shap_test, feature_names, top_n, period_name='Test Period'
279
+ )
280
+ print() # ๋งˆ์ง€๋ง‰์— ๋นˆ ์ค„ ์ถ”๊ฐ€
281
+ else:
282
+ importance_df_test = None
283
+ top_n_share_test = None
284
+ top_n_features_test = None
285
+
286
+ # ==========================================
287
+ # ํ†ตํ•ฉ Feature Importance DataFrame ์ƒ์„ฑ
288
+ # ==========================================
289
+ importance_df_combined = _create_combined_importance_df(
290
+ importance_df_train, importance_df_test, feature_names
291
+ )
292
+
293
+ # ==========================================
294
+ # ์‹œ๊ฐํ™”
295
+ # ==========================================
296
+ if show_plot:
297
+ _plot_shap_summary(
298
+ all_shap_train, all_X_train, all_shap_test, X_test,
299
+ list(all_X_train.columns), target_class, top_n,
300
+ top_n_share_train=top_n_share_train, top_n_share_test=top_n_share_test,
301
+ show_train_plot=show_train_plot, show_test_plot=show_test_plot, figsize=figsize,
302
+ model_name=model_name, data_sample=data_sample, region=region
303
+ )
304
+
305
+ # ๊ฒฐ๊ณผ ๋ฐ˜ํ™˜
306
+ return {
307
+ 'shap_train': all_shap_train,
308
+ 'X_train': all_X_train,
309
+ 'shap_test': all_shap_test,
310
+ 'X_test': X_test,
311
+ 'top_n_features_train': top_n_features_train, # Train ์ƒ์œ„ N๊ฐœ ๋ณ€์ˆ˜ ๋ฆฌ์ŠคํŠธ
312
+ 'top_n_share_train': top_n_share_train, # Train ์ƒ์œ„ N๊ฐœ ๋ˆ„์  ๊ธฐ์—ฌ๋„(%)
313
+ 'importance_df_train': importance_df_train, # Train ์ „์ฒด ์ค‘์š”๋„ ์ˆœ์œ„ํ‘œ
314
+ 'top_n_features_test': top_n_features_test, # Test ์ƒ์œ„ N๊ฐœ ๋ณ€์ˆ˜ ๋ฆฌ์ŠคํŠธ
315
+ 'top_n_share_test': top_n_share_test, # Test ์ƒ์œ„ N๊ฐœ ๋ˆ„์  ๊ธฐ์—ฌ๋„(%)
316
+ 'importance_df_test': importance_df_test, # Test ์ „์ฒด ์ค‘์š”๋„ ์ˆœ์œ„ํ‘œ
317
+ 'importance_df_combined': importance_df_combined # Train/Test ํ†ตํ•ฉ ์ค‘์š”๋„ DataFrame
318
+ }
319
+
320
+
321
+ # ==========================================
322
+ # ๋”ฅ๋Ÿฌ๋‹ ๋ชจ๋ธ SHAP ๋ถ„์„ ํ—ฌํผ ํด๋ž˜์Šค ๋ฐ ํ•จ์ˆ˜
323
+ # ==========================================
324
+
325
+ @contextmanager
326
+ def suppress_shap_output():
327
+ """SHAP DeepExplainer์˜ ์ถœ๋ ฅ์„ ์–ต์ œํ•˜๋Š” ์ปจํ…์ŠคํŠธ ๋งค๋‹ˆ์ €."""
328
+ old_stdout = sys.stdout
329
+ sys.stdout = StringIO()
330
+ try:
331
+ with warnings.catch_warnings():
332
+ warnings.simplefilter('ignore')
333
+ yield
334
+ finally:
335
+ sys.stdout = old_stdout
336
+
337
+
338
+ class ModelWrapper(torch.nn.Module):
339
+ """PyTorch ๋ชจ๋ธ์„ SHAP DeepExplainer์— ๋งž๊ฒŒ ๋ž˜ํ•‘ํ•˜๋Š” ํด๋ž˜์Šค."""
340
+
341
+ def __init__(self, base_model, numerical_cols):
342
+ super().__init__()
343
+ self.base_model = base_model
344
+ self.num_features = len(numerical_cols)
345
+
346
+ def forward(self, *inputs):
347
+ """SHAP์ด ๋ฆฌ์ŠคํŠธ๋กœ ์ „๋‹ฌํ•˜๋Š” ๊ฒฝ์šฐ ์ฒ˜๋ฆฌ"""
348
+ if len(inputs) == 1 and isinstance(inputs[0], (list, tuple)):
349
+ x_num, x_cat = inputs[0]
350
+ elif len(inputs) == 2:
351
+ x_num, x_cat = inputs
352
+ else:
353
+ # ๋‹จ์ผ ์ž…๋ ฅ (ResNet-like์˜ ๊ฒฝ์šฐ)
354
+ x = inputs[0]
355
+ x_num = x[:, :self.num_features]
356
+ x_cat = x[:, self.num_features:].long()
357
+ return self.base_model(x_num, x_cat)
358
+
359
+ # categorical์„ float๋กœ ๋ฐ›์•„์„œ long์œผ๋กœ ๋ณ€ํ™˜ (SHAP gradient ๊ณ„์‚ฐ์„ ์œ„ํ•ด)
360
+ if x_cat.dtype != torch.long:
361
+ x_cat = x_cat.long()
362
+
363
+ return self.base_model(x_num, x_cat)
364
+
365
+
366
+ def _create_shap_explainer(
367
+ model_name: str,
368
+ wrapped_model: torch.nn.Module,
369
+ X_bg_num: torch.Tensor,
370
+ X_bg_cat: torch.Tensor,
371
+ device: str
372
+ ) -> shap.DeepExplainer:
373
+ """SHAP DeepExplainer๋ฅผ ์ƒ์„ฑํ•˜๋Š” ํ—ฌํผ ํ•จ์ˆ˜.
374
+
375
+ Args:
376
+ model_name: ๋ชจ๋ธ ์ด๋ฆ„ ('ft_transformer', 'resnet_like', 'deepgbm')
377
+ wrapped_model: ๋ž˜ํ•‘๋œ PyTorch ๋ชจ๋ธ
378
+ X_bg_num: ๋ฐฐ๊ฒฝ ๋ฐ์ดํ„ฐ (numerical)
379
+ X_bg_cat: ๋ฐฐ๊ฒฝ ๋ฐ์ดํ„ฐ (categorical)
380
+ device: ์—ฐ์‚ฐ ์žฅ์น˜
381
+
382
+ Returns:
383
+ shap.DeepExplainer: ์ƒ์„ฑ๋œ Explainer
384
+ """
385
+ with suppress_shap_output():
386
+ if model_name in ('ft_transformer', 'deepgbm'):
387
+ X_bg_cat_float = X_bg_cat.float()
388
+ explainer = shap.DeepExplainer(wrapped_model, [X_bg_num, X_bg_cat_float])
389
+ elif model_name == 'resnet_like':
390
+ X_bg_combined = torch.cat([X_bg_num, X_bg_cat.float()], dim=1)
391
+ explainer = shap.DeepExplainer(wrapped_model, X_bg_combined)
392
+ else:
393
+ raise ValueError(f"Unknown model_name: {model_name}")
394
+
395
+ return explainer
396
+
397
+
398
+ def _calculate_shap_values(
399
+ explainer: shap.DeepExplainer,
400
+ model_name: str,
401
+ X_sample_num: torch.Tensor,
402
+ X_sample_cat: torch.Tensor,
403
+ device: str
404
+ ) -> Any:
405
+ """SHAP ๊ฐ’์„ ๊ณ„์‚ฐํ•˜๋Š” ํ—ฌํผ ํ•จ์ˆ˜.
406
+
407
+ Args:
408
+ explainer: SHAP DeepExplainer
409
+ model_name: ๋ชจ๋ธ ์ด๋ฆ„ ('ft_transformer', 'resnet_like', 'deepgbm')
410
+ X_sample_num: ์ƒ˜ํ”Œ ๋ฐ์ดํ„ฐ (numerical)
411
+ X_sample_cat: ์ƒ˜ํ”Œ ๋ฐ์ดํ„ฐ (categorical)
412
+ device: ์—ฐ์‚ฐ ์žฅ์น˜
413
+
414
+ Returns:
415
+ SHAP ๊ฐ’ (๋‹ค์–‘ํ•œ ํ˜•ํƒœ ๊ฐ€๋Šฅ)
416
+ """
417
+ with suppress_shap_output():
418
+ if model_name in ('ft_transformer', 'deepgbm'):
419
+ X_sample_cat_float = X_sample_cat.float()
420
+ shap_values = explainer.shap_values([X_sample_num, X_sample_cat_float])
421
+ elif model_name == 'resnet_like':
422
+ X_sample_combined = torch.cat([X_sample_num, X_sample_cat.float()], dim=1)
423
+ shap_values = explainer.shap_values(X_sample_combined)
424
+ else:
425
+ raise ValueError(f"Unknown model_name: {model_name}")
426
+
427
+ return shap_values
428
+
429
+
430
+ def _calculate_cumulative_share(
431
+ shap_values: np.ndarray,
432
+ feature_names: List[str],
433
+ top_n: int,
434
+ period_name: str = ''
435
+ ) -> Tuple[pd.DataFrame, List[str], float]:
436
+ """๋ˆ„์  ์„ค๋ช…๋ ฅ(Cumulative Share)์„ ๊ณ„์‚ฐํ•˜๋Š” ํ—ฌํผ ํ•จ์ˆ˜.
437
+
438
+ Args:
439
+ shap_values: SHAP ๊ฐ’ ๋ฐฐ์—ด
440
+ feature_names: ํ”ผ์ฒ˜ ์ด๋ฆ„ ๋ฆฌ์ŠคํŠธ
441
+ top_n: ์ƒ์œ„ N๊ฐœ ๋ณ€์ˆ˜
442
+ period_name: ๊ธฐ๊ฐ„ ์ด๋ฆ„ (์ฝ˜์†” ์ถœ๋ ฅ์šฉ, ๊ธฐ๋ณธ๊ฐ’: '')
443
+
444
+ Returns:
445
+ tuple: (importance_df, top_n_features, top_n_share)
446
+ """
447
+ # 1. Global Importance ๊ณ„์‚ฐ (์ ˆ๋Œ€๊ฐ’์˜ ํ‰๊ท )
448
+ global_importances = np.abs(shap_values).mean(axis=0)
449
+
450
+ # 2. DataFrame ์ƒ์„ฑ ๋ฐ ์ •๋ ฌ
451
+ importance_df = pd.DataFrame({
452
+ 'feature': feature_names,
453
+ 'importance': global_importances
454
+ }).sort_values('importance', ascending=False)
455
+
456
+ # 3. ์ „์ฒด ์ค‘์š”๋„ ํ•ฉ๊ณ„
457
+ total_importance = importance_df['importance'].sum()
458
+
459
+ # 4. ์ƒ์œ„ N๊ฐœ ๋ณ€์ˆ˜ ์ถ”์ถœ ๋ฐ ๊ธฐ์—ฌ๋„ ๊ณ„์‚ฐ
460
+ top_n_df = importance_df.head(top_n)
461
+ top_n_importance = top_n_df['importance'].sum()
462
+ top_n_share = (top_n_importance / total_importance) * 100
463
+ top_n_features = top_n_df['feature'].tolist()
464
+
465
+ # 5. ์ฝ˜์†” ์ถœ๋ ฅ
466
+ if period_name:
467
+ print(f"{period_name} - Top {top_n} Dominant Features: {top_n_features}")
468
+ print(f"{period_name} - Cumulative Importance Share (Top {top_n}): {top_n_share:.2f}%")
469
+ else:
470
+ print(f"Top {top_n} Dominant Features: {top_n_features}")
471
+ print(f"Cumulative Importance Share (Top {top_n}): {top_n_share:.2f}%")
472
+ print(f"{'-'*40}")
473
+
474
+ return importance_df, top_n_features, top_n_share
475
+
476
+
477
+ def _create_combined_importance_df(
478
+ importance_df_train: Optional[pd.DataFrame],
479
+ importance_df_test: Optional[pd.DataFrame],
480
+ feature_names: List[str]
481
+ ) -> Optional[pd.DataFrame]:
482
+ """Train๊ณผ Test ์ค‘์š”๋„ DataFrame์„ ํ†ตํ•ฉํ•˜๋Š” ํ—ฌํผ ํ•จ์ˆ˜.
483
+
484
+ Args:
485
+ importance_df_train: Train ๋ฐ์ดํ„ฐ ์ค‘์š”๋„ DataFrame
486
+ importance_df_test: Test ๋ฐ์ดํ„ฐ ์ค‘์š”๋„ DataFrame
487
+ feature_names: ํ”ผ์ฒ˜ ์ด๋ฆ„ ๋ฆฌ์ŠคํŠธ
488
+
489
+ Returns:
490
+ ํ†ตํ•ฉ๋œ ์ค‘์š”๋„ DataFrame ๋˜๋Š” None
491
+ """
492
+ if importance_df_train is None and importance_df_test is None:
493
+ return None
494
+
495
+ # Train ๋ฐ์ดํ„ฐ ์ค€๋น„
496
+ if importance_df_train is not None:
497
+ train_df = importance_df_train[['feature', 'importance']].copy()
498
+ train_df.columns = ['feature', 'importance_train']
499
+ total_importance_train = train_df['importance_train'].sum()
500
+ train_df['share_train'] = (train_df['importance_train'] / total_importance_train) * 100
501
+ else:
502
+ train_df = pd.DataFrame({'feature': feature_names})
503
+ train_df['importance_train'] = np.nan
504
+ train_df['share_train'] = np.nan
505
+
506
+ # Test ๋ฐ์ดํ„ฐ ์ค€๋น„
507
+ if importance_df_test is not None:
508
+ test_df = importance_df_test[['feature', 'importance']].copy()
509
+ test_df.columns = ['feature', 'importance_test']
510
+ total_importance_test = test_df['importance_test'].sum()
511
+ test_df['share_test'] = (test_df['importance_test'] / total_importance_test) * 100
512
+ else:
513
+ test_df = pd.DataFrame({'feature': feature_names})
514
+ test_df['importance_test'] = np.nan
515
+ test_df['share_test'] = np.nan
516
+
517
+ # Mergeํ•˜์—ฌ ํ†ตํ•ฉ DataFrame ์ƒ์„ฑ
518
+ importance_df_combined = pd.merge(train_df, test_df, on='feature', how='outer')
519
+
520
+ # ์ •๋ ฌ
521
+ if importance_df_train is not None:
522
+ importance_df_combined = importance_df_combined.sort_values(
523
+ 'importance_train', ascending=False
524
+ ).reset_index(drop=True)
525
+ elif importance_df_test is not None:
526
+ importance_df_combined = importance_df_combined.sort_values(
527
+ 'importance_test', ascending=False
528
+ ).reset_index(drop=True)
529
+ else:
530
+ importance_df_combined = importance_df_combined.sort_values('feature').reset_index(drop=True)
531
+
532
+ return importance_df_combined
533
+
534
+
535
+ def _plot_shap_summary(
536
+ shap_train: Optional[np.ndarray],
537
+ X_train: Optional[pd.DataFrame],
538
+ shap_test: Optional[np.ndarray],
539
+ X_test: Optional[pd.DataFrame],
540
+ feature_names: List[str],
541
+ target_class: int,
542
+ top_n: int,
543
+ top_n_share_train: Optional[float] = None,
544
+ top_n_share_test: Optional[float] = None,
545
+ show_train_plot: bool = True,
546
+ show_test_plot: bool = True,
547
+ figsize: Tuple[int, int] = (12, 8),
548
+ model_name: Optional[str] = None,
549
+ data_sample: Optional[str] = None,
550
+ region: Optional[str] = None
551
+ ) -> None:
552
+ """SHAP summary plot์„ ์ƒ์„ฑํ•˜๋Š” ํ—ฌํผ ํ•จ์ˆ˜.
553
+
554
+ Args:
555
+ shap_train: Train ๋ฐ์ดํ„ฐ SHAP ๊ฐ’
556
+ X_train: Train ๋ฐ์ดํ„ฐ
557
+ shap_test: Test ๋ฐ์ดํ„ฐ SHAP ๊ฐ’
558
+ X_test: Test ๋ฐ์ดํ„ฐ
559
+ feature_names: ํ”ผ์ฒ˜ ์ด๋ฆ„ ๋ฆฌ์ŠคํŠธ
560
+ target_class: ํƒ€๊ฒŸ ํด๋ž˜์Šค
561
+ top_n: ์ƒ์œ„ N๊ฐœ ๋ณ€์ˆ˜
562
+ top_n_share_train: Train ์ƒ์œ„ N๊ฐœ ๋ˆ„์  ๊ธฐ์—ฌ๋„ (๊ธฐ๋ณธ๊ฐ’: None)
563
+ top_n_share_test: Test ์ƒ์œ„ N๊ฐœ ๋ˆ„์  ๊ธฐ์—ฌ๋„ (๊ธฐ๋ณธ๊ฐ’: None)
564
+ show_train_plot: Train plot ํ‘œ์‹œ ์—ฌ๋ถ€
565
+ show_test_plot: Test plot ํ‘œ์‹œ ์—ฌ๋ถ€
566
+ figsize: ๊ทธ๋ฆผ ํฌ๊ธฐ
567
+ model_name: ๋ชจ๋ธ ์ด๋ฆ„ (๊ธฐ๋ณธ๊ฐ’: None)
568
+ data_sample: ๋ฐ์ดํ„ฐ ์ƒ˜ํ”Œ ํƒ€์ž… (๊ธฐ๋ณธ๊ฐ’: None)
569
+ region: ์ง€์—ญ๋ช… (๊ธฐ๋ณธ๊ฐ’: None)
570
+ """
571
+ num_plots = int(show_train_plot and shap_train is not None) + int(show_test_plot and shap_test is not None)
572
+ if num_plots == 0:
573
+ return
574
+
575
+ # Title prefix ์ƒ์„ฑ (๋ชจ๋ธ๋ช…, ๋ฐ์ดํ„ฐ ์ƒ˜ํ”Œ, ์ง€์—ญ ์ •๋ณด)
576
+ title_parts = []
577
+ if model_name is not None:
578
+ title_parts.append(model_name.upper())
579
+ if data_sample is not None:
580
+ title_parts.append(data_sample)
581
+ if region is not None:
582
+ title_parts.append(region.upper())
583
+
584
+ if title_parts:
585
+ title_prefix = " - ".join(title_parts) + "\n"
586
+ else:
587
+ title_prefix = ""
588
+
589
+ if num_plots == 2:
590
+ plt.subplots(1, 2, figsize=figsize)
591
+
592
+ if show_train_plot and shap_train is not None:
593
+ plt.subplot(1, 2, 1)
594
+ shap.summary_plot(shap_train, X_train[feature_names] if isinstance(X_train, pd.DataFrame) else X_train,
595
+ show=False, plot_size=None)
596
+ share_text = f"\nTop {top_n} Share: {top_n_share_train:.1f}%" if top_n_share_train is not None else ""
597
+ plt.title(f"{title_prefix}Train Period (2018-20): Class {target_class}{share_text}")
598
+
599
+ if show_test_plot and shap_test is not None:
600
+ plt.subplot(1, 2, 2)
601
+ shap.summary_plot(shap_test, X_test[feature_names] if isinstance(X_test, pd.DataFrame) else X_test,
602
+ show=False, plot_size=None)
603
+ share_text = f"\nTop {top_n} Share: {top_n_share_test:.1f}%" if top_n_share_test is not None else ""
604
+ plt.title(f"{title_prefix}Test Period (2021): Class {target_class}{share_text}")
605
+ else:
606
+ plt.figure(figsize=(figsize[0]//2, figsize[1]))
607
+ if show_train_plot and shap_train is not None:
608
+ data = X_train[feature_names] if isinstance(X_train, pd.DataFrame) else X_train
609
+ shap_v = shap_train
610
+ share_text = f"\nTop {top_n} Share: {top_n_share_train:.1f}%" if top_n_share_train is not None else ""
611
+ title = f"{title_prefix}Train Period (2018-20): Class {target_class}{share_text}"
612
+ elif show_test_plot and shap_test is not None:
613
+ data = X_test[feature_names] if isinstance(X_test, pd.DataFrame) else X_test
614
+ shap_v = shap_test
615
+ share_text = f"\nTop {top_n} Share: {top_n_share_test:.1f}%" if top_n_share_test is not None else ""
616
+ title = f"{title_prefix}Test Period (2021): Class {target_class}{share_text}"
617
+ else:
618
+ return
619
+
620
+ shap.summary_plot(shap_v, data, show=False)
621
+ plt.title(title)
622
+
623
+ plt.tight_layout()
624
+ plt.show()
625
+
626
+
627
+ def _to_numpy(value: Any) -> np.ndarray:
628
+ """๋‹ค์–‘ํ•œ ํƒ€์ž…์„ numpy array๋กœ ๋ณ€ํ™˜ํ•˜๋Š” ํ—ฌํผ ํ•จ์ˆ˜."""
629
+ if isinstance(value, torch.Tensor):
630
+ return value.cpu().numpy()
631
+ elif isinstance(value, list):
632
+ return np.array(value)
633
+ elif isinstance(value, np.ndarray):
634
+ return value
635
+ else:
636
+ return np.array(value)
637
+
638
+
639
+ def _combine_num_cat_shap(shap_num: Any, shap_cat: Any) -> np.ndarray:
640
+ """Numerical๊ณผ categorical SHAP ๊ฐ’์„ ๊ฒฐํ•ฉํ•˜๋Š” ํ—ฌํผ ํ•จ์ˆ˜."""
641
+ shap_num = _to_numpy(shap_num)
642
+ shap_cat = _to_numpy(shap_cat)
643
+ return np.concatenate([shap_num, shap_cat], axis=-1)
644
+
645
+
646
+ def _extract_from_list_of_tuples(shap_list: List[Tuple]) -> np.ndarray:
647
+ """ํŠœํ”Œ ๋ฆฌ์ŠคํŠธ์—์„œ SHAP ๊ฐ’์„ ์ถ”์ถœํ•˜๋Š” ํ—ฌํผ ํ•จ์ˆ˜."""
648
+ combined = []
649
+ for shap_item in shap_list:
650
+ if isinstance(shap_item, tuple):
651
+ combined.append(_combine_num_cat_shap(shap_item[0], shap_item[1]))
652
+ else:
653
+ combined.append(_to_numpy(shap_item))
654
+ return np.array(combined)
655
+
656
+
657
+ def _extract_from_list(shap_list: List[Any]) -> np.ndarray:
658
+ """๋ฆฌ์ŠคํŠธ์—์„œ SHAP ๊ฐ’์„ ์ถ”์ถœํ•˜๋Š” ํ—ฌํผ ํ•จ์ˆ˜."""
659
+ if len(shap_list) == 0:
660
+ return np.array([])
661
+
662
+ # ํŠœํ”Œ ๋ฆฌ์ŠคํŠธ์ธ ๊ฒฝ์šฐ
663
+ if isinstance(shap_list[0], tuple):
664
+ return _extract_from_list_of_tuples(shap_list)
665
+
666
+ # ๊ธธ์ด๊ฐ€ 2์ด๊ณ  ๊ฐ๊ฐ์ด numerical/categorical์ธ ๊ฒฝ์šฐ
667
+ if len(shap_list) == 2:
668
+ return _combine_num_cat_shap(shap_list[0], shap_list[1])
669
+
670
+ # ์ผ๋ฐ˜ ๋ฆฌ์Šค๏ฟฝ๏ฟฝ๏ฟฝ์ธ ๊ฒฝ์šฐ
671
+ try:
672
+ return np.array([_to_numpy(item) for item in shap_list])
673
+ except (ValueError, TypeError):
674
+ # ํ˜•ํƒœ๊ฐ€ ์ผ์น˜ํ•˜์ง€ ์•Š๋Š” ๊ฒฝ์šฐ, concatenate ์‹œ๋„
675
+ converted = [_to_numpy(item) for item in shap_list]
676
+ if len(converted) == 2:
677
+ return np.concatenate(converted, axis=-1)
678
+ else:
679
+ return np.array(converted)
680
+
681
+
682
+ def extract_shap_values(shap_values: Any, target_class: int = 0) -> np.ndarray:
683
+ """SHAP ๊ฐ’์„ ์ถ”์ถœํ•˜์—ฌ numpy array๋กœ ๋ณ€ํ™˜ํ•˜๋Š” ํ—ฌํผ ํ•จ์ˆ˜.
684
+
685
+ Args:
686
+ shap_values: SHAP ๋ผ์ด๋ธŒ๋Ÿฌ๋ฆฌ์—์„œ ๋ฐ˜ํ™˜๋œ SHAP ๊ฐ’ (๋‹ค์–‘ํ•œ ํ˜•ํƒœ ๊ฐ€๋Šฅ)
687
+ target_class: ๋ถ„์„ํ•  ํด๋ž˜์Šค ์ธ๋ฑ์Šค (๊ธฐ๋ณธ๊ฐ’: 0)
688
+
689
+ Returns:
690
+ numpy.ndarray: ๋ณ€ํ™˜๋œ SHAP ๊ฐ’
691
+ """
692
+ # ํŠœํ”Œ์ธ ๊ฒฝ์šฐ (numerical, categorical ๋ถ„๋ฆฌ)
693
+ if isinstance(shap_values, tuple):
694
+ return _combine_num_cat_shap(shap_values[0], shap_values[1])
695
+
696
+ # ๋ฆฌ์ŠคํŠธ์ธ ๊ฒฝ์šฐ (ํด๋ž˜์Šค๋ณ„ SHAP ๊ฐ’)
697
+ if isinstance(shap_values, list):
698
+ target_shap = shap_values[target_class]
699
+
700
+ # ํŠœํ”Œ์ธ ๊ฒฝ์šฐ
701
+ if isinstance(target_shap, tuple):
702
+ return _combine_num_cat_shap(target_shap[0], target_shap[1])
703
+
704
+ # ๋ฆฌ์ŠคํŠธ์ธ ๊ฒฝ์šฐ
705
+ if isinstance(target_shap, list):
706
+ return _extract_from_list(target_shap)
707
+
708
+ # Tensor ๋˜๋Š” ๊ธฐํƒ€ ํƒ€์ž…
709
+ return _to_numpy(target_shap)
710
+
711
+ # numpy array์ธ ๊ฒฝ์šฐ
712
+ if isinstance(shap_values, np.ndarray):
713
+ if len(shap_values.shape) == 3:
714
+ return shap_values[:, target_class, :]
715
+ return shap_values
716
+
717
+ # ๊ธฐํƒ€ ํƒ€์ž…
718
+ return _to_numpy(shap_values)
719
+
720
+ # ==========================================
721
+ # ๋”ฅ๋Ÿฌ๋‹ ๋ชจ๋ธ ๋ฐ์ดํ„ฐ ๋กœ๋“œ ๋ฐ ์ „์ฒ˜๋ฆฌ ํ•จ์ˆ˜
722
+ # ==========================================
723
+
724
+ def load_scaler(model_name: str, region: str, data_sample: str) -> List[Any]:
725
+ """
726
+ ๊ฐ fold์˜ scaler๋ฅผ ๋กœ๋“œํ•˜๋Š” ํ•จ์ˆ˜.
727
+
728
+ Args:
729
+ model_name: ๋ชจ๋ธ ์ด๋ฆ„ (์˜ˆ: "ft_transformer", "resnet_like", "deepgbm")
730
+ region: ์ง€์—ญ๋ช… (์˜ˆ: "seoul", "busan")
731
+ data_sample: ๋ฐ์ดํ„ฐ ์ƒ˜ํ”Œ ํƒ€์ž… (์˜ˆ: "smote", "ctgan10000")
732
+
733
+ Returns:
734
+ list: ๊ฐ fold์˜ scaler ๋ฆฌ์ŠคํŠธ (3๊ฐœ)
735
+ """
736
+ # ํŒŒ์ผ๋ช… ์ƒ์„ฑ
737
+ if data_sample == 'pure':
738
+ scaler_filename = f'{model_name}_pure_{region}_scaler.pkl'
739
+ else:
740
+ scaler_filename = f'{model_name}_{data_sample}_{region}_scaler.pkl'
741
+
742
+ scaler_path = f'../save_model/{model_name}_optima/scaler/{scaler_filename}'
743
+ scalers = load(scaler_path)
744
+ return scalers
745
+
746
+
747
+ def prepare_dl_data_for_shap(
748
+ region: str,
749
+ data_sample: str,
750
+ fold_idx: int,
751
+ scaler: Any
752
+ ) -> Tuple[pd.DataFrame, pd.DataFrame, pd.DataFrame, pd.Index, pd.Index,
753
+ torch.Tensor, torch.Tensor, torch.Tensor, torch.Tensor, torch.Tensor, torch.Tensor]:
754
+ """
755
+ ๋”ฅ๋Ÿฌ๋‹ ๋ชจ๋ธ์šฉ ๋ฐ์ดํ„ฐ ์ „์ฒ˜๋ฆฌ (scaler ์ ์šฉ, ํ…์„œ ๋ณ€ํ™˜).
756
+
757
+ Args:
758
+ region: ์ง€์—ญ๋ช…
759
+ data_sample: ๋ฐ์ดํ„ฐ ์ƒ˜ํ”Œ ํƒ€์ž…
760
+ fold_idx: Fold ์ธ๋ฑ์Šค (0, 1, 2)
761
+ scaler: ํ•ด๋‹น fold์˜ scaler (QuantileTransformer)
762
+
763
+ Returns:
764
+ tuple: (X_train, X_val, X_test, categorical_cols, numerical_cols,
765
+ X_train_num, X_train_cat, X_val_num, X_val_cat, X_test_num, X_test_cat)
766
+ """
767
+ # ํŒŒ์ผ ๊ฒฝ๋กœ ์„ค์ •
768
+ if data_sample == 'pure':
769
+ dat_path = f"../../data/data_for_modeling/{region}_train.csv"
770
+ train_data = preprocessing(pd.read_csv(dat_path, index_col=0))
771
+ train_data = train_data.loc[~train_data['year'].isin([TEST_YEAR - (fold_idx + 1)]), :]
772
+ else:
773
+ train_data = pd.read_csv(f"../../data/data_oversampled/{data_sample}/{data_sample}_{fold_idx+1}_{region}.csv")
774
+ train_data = preprocessing(train_data)
775
+
776
+ val_data = pd.read_csv(f"../../data/data_for_modeling/{region}_train.csv")
777
+ val_data = preprocessing(val_data)
778
+ val_data = val_data.loc[val_data['year'].isin([TEST_YEAR - (fold_idx + 1)]), :]
779
+
780
+ test_data = pd.read_csv(f"../../data/data_for_modeling/{region}_test.csv")
781
+ test_data = preprocessing(test_data)
782
+ test_data = test_data.loc[test_data['year'].isin([TEST_YEAR]), :]
783
+
784
+ # ์ปฌ๋Ÿผ ์ •๋ ฌ (์ผ๊ด€์„ฑ ์œ ์ง€)
785
+ common_columns = train_data.columns.to_list()
786
+ train_data = train_data[common_columns]
787
+ val_data = val_data[common_columns]
788
+ test_data = test_data[common_columns]
789
+
790
+ # ์„ค๋ช…๋ณ€์ˆ˜ & ํƒ€๊ฒŸ ๋ถ„๋ฆฌ
791
+
792
+ X_train = train_data.drop(columns=DROP_COLUMNS)
793
+ X_val = val_data.drop(columns=DROP_COLUMNS)
794
+ X_test = test_data.drop(columns=DROP_COLUMNS)
795
+
796
+ # ๋ฒ”์ฃผํ˜• & ์—ฐ์†ํ˜• ๋ณ€์ˆ˜ ๋ถ„๋ฆฌ
797
+ categorical_cols = X_train.select_dtypes(include=['object', 'category', 'int64']).columns
798
+ numerical_cols = X_train.select_dtypes(include=['float64']).columns
799
+
800
+ # ๋ฒ”์ฃผํ˜• ๋ณ€์ˆ˜ Label Encoding (train ๋ฐ์ดํ„ฐ ๊ธฐ์ค€์œผ๋กœ ํ•™์Šต)
801
+ label_encoders = {}
802
+ for col in categorical_cols:
803
+ le = LabelEncoder()
804
+ le.fit(X_train[col])
805
+ label_encoders[col] = le
806
+
807
+ # ๋ณ€ํ™˜ ์ ์šฉ
808
+ for col in categorical_cols:
809
+ X_train[col] = label_encoders[col].transform(X_train[col])
810
+ X_val[col] = label_encoders[col].transform(X_val[col])
811
+ X_test[col] = label_encoders[col].transform(X_test[col])
812
+
813
+ # ์—ฐ์†ํ˜• ๋ณ€์ˆ˜ Scaler ๋ณ€ํ™˜ (์ €์žฅ๋œ scaler ์‚ฌ์šฉ)
814
+ X_train[numerical_cols] = scaler.transform(X_train[numerical_cols])
815
+ X_val[numerical_cols] = scaler.transform(X_val[numerical_cols])
816
+ X_test[numerical_cols] = scaler.transform(X_test[numerical_cols])
817
+
818
+ # ํ…์„œ ๋ณ€ํ™˜
819
+ X_train_num = torch.tensor(X_train[numerical_cols].values, dtype=torch.float32)
820
+ X_train_cat = torch.tensor(X_train[categorical_cols].values, dtype=torch.long)
821
+
822
+ X_val_num = torch.tensor(X_val[numerical_cols].values, dtype=torch.float32)
823
+ X_val_cat = torch.tensor(X_val[categorical_cols].values, dtype=torch.long)
824
+
825
+ X_test_num = torch.tensor(X_test[numerical_cols].values, dtype=torch.float32)
826
+ X_test_cat = torch.tensor(X_test[categorical_cols].values, dtype=torch.long)
827
+
828
+ return (X_train, X_val, X_test, categorical_cols, numerical_cols,
829
+ X_train_num, X_train_cat, X_val_num, X_val_cat, X_test_num, X_test_cat)
830
+
831
+
832
+ # ==========================================
833
+ # ๋”ฅ๋Ÿฌ๋‹ ๋ชจ๋ธ SHAP ๋ถ„์„ ๋ฉ”์ธ ํ•จ์ˆ˜
834
+ # ==========================================
835
+
836
+ def analyze_dl_model_shap(
837
+ model_name: str,
838
+ region: str,
839
+ data_sample: str,
840
+ target_class: int = 0,
841
+ n_folds: int = 3,
842
+ n_background_samples: int = 200,
843
+ n_test_samples: int = 500,
844
+ device: str = 'cpu',
845
+ figsize: Tuple[int, int] = (12, 8),
846
+ show_plot: bool = True,
847
+ show_train_plot: bool = True,
848
+ show_test_plot: bool = True,
849
+ top_n: int = 3
850
+ ) -> Optional[Dict[str, Any]]:
851
+ """
852
+ ๋”ฅ๋Ÿฌ๋‹ ๋ชจ๋ธ์˜ SHAP ๊ฐ’์„ ๊ณ„์‚ฐํ•˜๊ณ  ์‹œ๊ฐํ™”ํ•˜๋Š” ํ•จ์ˆ˜.
853
+
854
+ Args:
855
+ model_name: ๋ชจ๋ธ ์ด๋ฆ„ ('ft_transformer', 'resnet_like', 'deepgbm')
856
+ region: ์ง€์—ญ๋ช…
857
+ data_sample: ๋ฐ์ดํ„ฐ ์ƒ˜ํ”Œ ํƒ€์ž…
858
+ target_class: ๋ถ„์„ํ•  ํด๋ž˜์Šค ์ธ๋ฑ์Šค (๊ธฐ๋ณธ๊ฐ’: 0)
859
+ n_folds: Fold ๊ฐœ์ˆ˜ (๊ธฐ๋ณธ๊ฐ’: 3)
860
+ n_background_samples: ๋ฐฐ๊ฒฝ ๋ฐ์ดํ„ฐ ์ƒ˜ํ”Œ ์ˆ˜ (๊ธฐ๋ณธ๊ฐ’: 200)
861
+ n_test_samples: ํ…Œ์ŠคํŠธ ๋ฐ์ดํ„ฐ ์ƒ˜ํ”Œ ์ˆ˜ (๊ธฐ๋ณธ๊ฐ’: 500)
862
+ device: ์—ฐ์‚ฐ ์žฅ์น˜ ('cpu' ๋˜๋Š” 'cuda', ๊ธฐ๋ณธ๊ฐ’: 'cpu')
863
+ figsize: ๊ทธ๋ฆผ ํฌ๊ธฐ (๊ธฐ๋ณธ๊ฐ’: (12, 8))
864
+ show_plot: ์‹œ๊ฐํ™” ํ‘œ์‹œ ์—ฌ๋ถ€ (๊ธฐ๋ณธ๊ฐ’: True)
865
+ show_train_plot: Train(validation) ๋ฐ์ดํ„ฐ ์‹œ๊ฐํ™” ํ‘œ์‹œ ์—ฌ๋ถ€ (๊ธฐ๋ณธ๊ฐ’: True)
866
+ show_test_plot: Test ๋ฐ์ดํ„ฐ ์‹œ๊ฐํ™” ํ‘œ์‹œ ์—ฌ๋ถ€ (๊ธฐ๋ณธ๊ฐ’: True)
867
+ top_n: ์ƒ์œ„ N๊ฐœ ๋ณ€์ˆ˜ ๊ธฐ์—ฌ๋„ ๊ณ„์‚ฐ (๊ธฐ๋ณธ๊ฐ’: 3)
868
+
869
+ Returns:
870
+ dict: SHAP ๊ฐ’ ๋ฐ ๊ด€๋ จ ์ •๋ณด
871
+ - shap_train: Train ๋ฐ์ดํ„ฐ SHAP ๊ฐ’
872
+ - X_train: Train ๋ฐ์ดํ„ฐ
873
+ - shap_test: Test ๋ฐ์ดํ„ฐ SHAP ๊ฐ’
874
+ - X_test: Test ๋ฐ์ดํ„ฐ
875
+ - feature_names: ํ”ผ์ฒ˜ ์ด๋ฆ„ ๋ฆฌ์ŠคํŠธ
876
+ - model_name: ๋ชจ๋ธ ์ด๋ฆ„
877
+ - region: ์ง€์—ญ๋ช…
878
+ - data_sample: ๋ฐ์ดํ„ฐ ์ƒ˜ํ”Œ ํƒ€์ž…
879
+ - top_n_features_train: Train ์ƒ์œ„ N๊ฐœ ๋ณ€์ˆ˜ ๋ฆฌ์ŠคํŠธ
880
+ - top_n_share_train: Train ์ƒ์œ„ N๊ฐœ ๋ˆ„์  ๊ธฐ์—ฌ๋„(%)
881
+ - importance_df_train: Train ์ „์ฒด ์ค‘์š”๋„ ์ˆœ์œ„ํ‘œ
882
+ - top_n_features_test: Test ์ƒ์œ„ N๊ฐœ ๋ณ€์ˆ˜ ๋ฆฌ์ŠคํŠธ
883
+ - top_n_share_test: Test ์ƒ์œ„ N๊ฐœ ๋ˆ„์  ๊ธฐ์—ฌ๋„(%)
884
+ - importance_df_test: Test ์ „์ฒด ์ค‘์š”๋„ ์ˆœ์œ„ํ‘œ
885
+ - importance_df_combined: Train/Test ํ†ตํ•ฉ ์ค‘์š”๋„ DataFrame
886
+ """
887
+ print(f"[{model_name.upper()}] {region} - {data_sample} SHAP Analysis Start...")
888
+
889
+ # ๋ชจ๋ธ ๋ฐ scaler ๋กœ๋“œ
890
+ try:
891
+ models = load_model(model_name, region, data_sample)
892
+ scalers = load_scaler(model_name, region, data_sample)
893
+ except Exception as e:
894
+ print(f"๋ชจ๋ธ ๋˜๋Š” scaler ๋กœ๋“œ ์‹คํŒจ: {e}")
895
+ return None
896
+
897
+ if len(models) != n_folds or len(scalers) != n_folds:
898
+ raise ValueError(f"๋ชจ๋ธ ๊ฐœ์ˆ˜({len(models)}) ๋˜๋Š” scaler ๊ฐœ์ˆ˜({len(scalers)})๊ฐ€ n_folds({n_folds})์™€ ์ผ์น˜ํ•˜์ง€ ์•Š์Šต๋‹ˆ๋‹ค.")
899
+
900
+ # ๊ฐ fold์˜ SHAP ๊ฐ’ ์ €์žฅ (train๊ณผ test ๋ถ„๋ฆฌ)
901
+ all_shap_train = []
902
+ all_shap_test = []
903
+ all_train_data = []
904
+ all_test_data = []
905
+ feature_names = None
906
+
907
+ for fold_idx in range(n_folds):
908
+ print(f" Processing Fold {fold_idx + 1}...")
909
+
910
+ try:
911
+ # ๋ฐ์ดํ„ฐ ์ „์ฒ˜๋ฆฌ
912
+ (X_train, X_val, X_test, categorical_cols, numerical_cols,
913
+ X_train_num, X_train_cat, X_val_num, X_val_cat, X_test_num, X_test_cat) = \
914
+ prepare_dl_data_for_shap(region, data_sample, fold_idx, scalers[fold_idx])
915
+
916
+ # Feature names ์ €์žฅ (์ฒซ ๋ฒˆ์งธ fold์—์„œ๋งŒ)
917
+ if feature_names is None:
918
+ feature_names = list(numerical_cols) + list(categorical_cols)
919
+
920
+ # ๋ชจ๋ธ ์ค€๋น„
921
+ model = models[fold_idx]
922
+ model.to(device)
923
+ model.eval()
924
+
925
+ # ๋ฐฐ๊ฒฝ ๋ฐ์ดํ„ฐ ์ƒ˜ํ”Œ๋ง (validation ๋ฐ์ดํ„ฐ ์‚ฌ์šฉ)
926
+ n_bg = min(n_background_samples, len(X_val_num))
927
+ bg_indices = np.random.choice(len(X_val_num), n_bg, replace=False)
928
+ X_bg_num = X_val_num[bg_indices].to(device)
929
+ X_bg_cat = X_val_cat[bg_indices].to(device)
930
+
931
+ # Validation ๋ฐ์ดํ„ฐ ์ƒ˜ํ”Œ๋ง (train plot์šฉ)
932
+ n_train = min(n_test_samples, len(X_val_num))
933
+ # ๋ฐฐ๊ฒฝ ๋ฐ์ดํ„ฐ์™€ ๊ฒน์น˜์ง€ ์•Š๋„๋ก ์ƒ˜ํ”Œ๋ง
934
+ available_indices = np.setdiff1d(np.arange(len(X_val_num)), bg_indices)
935
+ if len(available_indices) < n_train:
936
+ train_indices = available_indices
937
+ else:
938
+ train_indices = np.random.choice(available_indices, n_train, replace=False)
939
+ X_train_sample_num = X_val_num[train_indices].to(device)
940
+ X_train_sample_cat = X_val_cat[train_indices].to(device)
941
+
942
+ # ํ…Œ์ŠคํŠธ ๋ฐ์ดํ„ฐ ์ƒ˜ํ”Œ๋ง
943
+ n_test = min(n_test_samples, len(X_test_num))
944
+ test_indices = np.random.choice(len(X_test_num), n_test, replace=False)
945
+ X_test_sample_num = X_test_num[test_indices].to(device)
946
+ X_test_sample_cat = X_test_cat[test_indices].to(device)
947
+
948
+ # SHAP Explainer ์ƒ์„ฑ ๋ฐ ๊ณ„์‚ฐ
949
+ try:
950
+ # ๋ชจ๋ธ ๋ž˜ํ•‘
951
+ wrapped_model = ModelWrapper(model, numerical_cols)
952
+ wrapped_model.to(device)
953
+ wrapped_model.eval()
954
+
955
+ # Explainer ์ƒ์„ฑ
956
+ explainer = _create_shap_explainer(model_name, wrapped_model, X_bg_num, X_bg_cat, device)
957
+
958
+ # Validation ๋ฐ์ดํ„ฐ์— ๋Œ€ํ•œ SHAP ๊ฐ’ ๊ณ„์‚ฐ
959
+ shap_values_train = _calculate_shap_values(
960
+ explainer, model_name, X_train_sample_num, X_train_sample_cat, device
961
+ )
962
+ shap_val_train = extract_shap_values(shap_values_train, target_class)
963
+ all_shap_train.append(shap_val_train)
964
+ X_train_original = X_val.iloc[train_indices].copy()
965
+ all_train_data.append(X_train_original)
966
+
967
+ # Test ๋ฐ์ดํ„ฐ์— ๋Œ€ํ•œ SHAP ๊ฐ’ ๊ณ„์‚ฐ
968
+ shap_values_test = _calculate_shap_values(
969
+ explainer, model_name, X_test_sample_num, X_test_sample_cat, device
970
+ )
971
+ shap_val_test = extract_shap_values(shap_values_test, target_class)
972
+ all_shap_test.append(shap_val_test)
973
+ X_test_original = X_test.iloc[test_indices].copy()
974
+ all_test_data.append(X_test_original)
975
+
976
+ except Exception as e:
977
+ print(f" Warning: Fold {fold_idx + 1} SHAP ๊ณ„์‚ฐ ์‹คํŒจ: {e}")
978
+ continue
979
+ except Exception as e:
980
+ print(f" Warning: Fold {fold_idx + 1} ์ฒ˜๋ฆฌ ์‹คํŒจ: {e}")
981
+ continue
982
+
983
+ if len(all_shap_train) == 0 and len(all_shap_test) == 0:
984
+ print(" ๋ชจ๋“  fold์—์„œ SHAP ๊ณ„์‚ฐ ์‹คํŒจ")
985
+ return None
986
+
987
+ # ==========================================
988
+ # ๋ฐ์ดํ„ฐ ํ†ตํ•ฉ
989
+ # ==========================================
990
+ # Train(validation) ๋ฐ์ดํ„ฐ ํ†ตํ•ฉ
991
+ all_shap_train_combined = np.concatenate(all_shap_train, axis=0) if len(all_shap_train) > 0 else None
992
+ all_train_data_combined = pd.concat(all_train_data, axis=0).reset_index(drop=True) if len(all_train_data) > 0 else None
993
+
994
+ # Test ๋ฐ์ดํ„ฐ ํ†ตํ•ฉ: ํ‰๊ท  ์‚ฌ์šฉ
995
+ if len(all_shap_test) > 0:
996
+ all_shap_test_combined = np.mean(all_shap_test, axis=0)
997
+ # Test ๋ฐ์ดํ„ฐ๋Š” ์ฒซ ๋ฒˆ์งธ fold๋งŒ ์‚ฌ์šฉ
998
+ all_test_data_combined = all_test_data[0] if len(all_test_data) > 0 else None
999
+ else:
1000
+ all_shap_test_combined = None
1001
+ all_test_data_combined = None
1002
+
1003
+ # ==========================================
1004
+ # Train ๋ฐ์ดํ„ฐ ์ƒ์œ„ N๊ฐœ ๋ณ€์ˆ˜ ๊ธฐ์—ฌ๋„(Cumulative Share) ๊ณ„์‚ฐ
1005
+ # ==========================================
1006
+ if all_shap_train_combined is not None:
1007
+ importance_df_train, top_n_features_train, top_n_share_train = _calculate_cumulative_share(
1008
+ all_shap_train_combined, feature_names, top_n, period_name='Train Period'
1009
+ )
1010
+ else:
1011
+ importance_df_train = None
1012
+ top_n_share_train = None
1013
+ top_n_features_train = None
1014
+
1015
+ # ==========================================
1016
+ # Test ๋ฐ์ดํ„ฐ ์ƒ์œ„ N๊ฐœ ๋ณ€์ˆ˜ ๊ธฐ์—ฌ๋„(Cumulative Share) ๊ณ„์‚ฐ
1017
+ # ==========================================
1018
+ if all_shap_test_combined is not None:
1019
+ importance_df_test, top_n_features_test, top_n_share_test = _calculate_cumulative_share(
1020
+ all_shap_test_combined, feature_names, top_n, period_name='Test Period'
1021
+ )
1022
+ print() # ๋งˆ์ง€๋ง‰์— ๋นˆ ์ค„ ์ถ”๊ฐ€
1023
+ else:
1024
+ importance_df_test = None
1025
+ top_n_share_test = None
1026
+ top_n_features_test = None
1027
+
1028
+ # ==========================================
1029
+ # ํ†ตํ•ฉ Feature Importance DataFrame ์ƒ์„ฑ
1030
+ # ==========================================
1031
+ importance_df_combined = _create_combined_importance_df(
1032
+ importance_df_train, importance_df_test, feature_names
1033
+ )
1034
+
1035
+ # ==========================================
1036
+ # ์‹œ๊ฐํ™”
1037
+ # ==========================================
1038
+ if show_plot:
1039
+ _plot_shap_summary(
1040
+ all_shap_train_combined, all_train_data_combined, all_shap_test_combined, all_test_data_combined,
1041
+ feature_names, target_class, top_n,
1042
+ top_n_share_train=top_n_share_train, top_n_share_test=top_n_share_test,
1043
+ show_train_plot=show_train_plot, show_test_plot=show_test_plot, figsize=figsize,
1044
+ model_name=model_name, data_sample=data_sample, region=region
1045
+ )
1046
+
1047
+ print(f" [{model_name.upper()}] SHAP Analysis Complete!\n")
1048
+
1049
+ return {
1050
+ 'shap_train': all_shap_train_combined,
1051
+ 'X_train': all_train_data_combined[feature_names] if all_train_data_combined is not None else None,
1052
+ 'shap_test': all_shap_test_combined,
1053
+ 'X_test': all_test_data_combined[feature_names] if all_test_data_combined is not None else None,
1054
+ 'feature_names': feature_names,
1055
+ 'model_name': model_name,
1056
+ 'region': region,
1057
+ 'data_sample': data_sample,
1058
+ 'top_n_features_train': top_n_features_train, # Train ์ƒ์œ„ N๊ฐœ ๋ณ€์ˆ˜ ๋ฆฌ์ŠคํŠธ
1059
+ 'top_n_share_train': top_n_share_train, # Train ์ƒ์œ„ N๊ฐœ ๋ˆ„์  ๊ธฐ์—ฌ๋„(%)
1060
+ 'importance_df_train': importance_df_train, # Train ์ „์ฒด ์ค‘์š”๋„ ์ˆœ์œ„ํ‘œ
1061
+ 'top_n_features_test': top_n_features_test, # Test ์ƒ์œ„ N๊ฐœ ๋ณ€์ˆ˜ ๋ฆฌ์ŠคํŠธ
1062
+ 'top_n_share_test': top_n_share_test, # Test ์ƒ์œ„ N๊ฐœ ๋ˆ„์  ๊ธฐ์—ฌ๋„(%)
1063
+ 'importance_df_test': importance_df_test, # Test ์ „์ฒด ์ค‘์š”๋„ ์ˆœ์œ„ํ‘œ
1064
+ 'importance_df_combined': importance_df_combined # Train/Test ํ†ตํ•ฉ ์ค‘์š”๋„ DataFrame
1065
+ }
1066
+
1067
+ def elbow_plot(result: Dict[str, Any]) -> None:
1068
+ elbow = result['importance_df_combined'].loc[:,['feature','importance_train','share_train']]
1069
+ elbow = elbow.sort_values('importance_train', ascending=False)
1070
+ plt.figure(figsize=(8, 5))
1071
+ plt.plot(range(1, len(elbow) + 1), elbow['share_train'].values, marker='o')
1072
+ plt.xlabel('Feature Rank')
1073
+ plt.ylabel('Share Train (%)')
1074
+ plt.title('Elbow Plot for Feature Importance (share_train)')
1075
+ plt.xticks(range(1, len(elbow) + 1))
1076
+ plt.grid(True, linestyle='--', alpha=0.5)
1077
+ plt.show()
Analysis_code/find_reason/wasserstein_distance.ipynb CHANGED
@@ -2,9 +2,20 @@
2
  "cells": [
3
  {
4
  "cell_type": "code",
5
- "execution_count": 6,
6
  "metadata": {},
7
- "outputs": [],
 
 
 
 
 
 
 
 
 
 
 
8
  "source": [
9
  "# ๋ถ„์„์— ํ•„์š”ํ•œ ๋ผ์ด๋ธŒ๋Ÿฌ๋ฆฌ ์ž„ํฌํŠธ\n",
10
  "import warnings\n",
@@ -33,7 +44,7 @@
33
  },
34
  {
35
  "cell_type": "code",
36
- "execution_count": 7,
37
  "metadata": {},
38
  "outputs": [],
39
  "source": [
@@ -58,7 +69,7 @@
58
  },
59
  {
60
  "cell_type": "code",
61
- "execution_count": 8,
62
  "metadata": {},
63
  "outputs": [
64
  {
@@ -133,7 +144,7 @@
133
  },
134
  {
135
  "cell_type": "code",
136
- "execution_count": 31,
137
  "metadata": {},
138
  "outputs": [],
139
  "source": [
@@ -184,7 +195,7 @@
184
  },
185
  {
186
  "cell_type": "code",
187
- "execution_count": 33,
188
  "metadata": {},
189
  "outputs": [
190
  {
@@ -192,10 +203,10 @@
192
  "output_type": "stream",
193
  "text": [
194
  " 2018 2019 2020 2021\n",
195
- "2018 0.0 0.130217 0.063132 1.081307\n",
196
- "2019 0.130217 0.0 0.059051 0.830648\n",
197
- "2020 0.063132 0.059051 0.0 0.039927\n",
198
- "2021 1.081307 0.830648 0.039927 0.0\n"
199
  ]
200
  }
201
  ],
@@ -235,7 +246,7 @@
235
  },
236
  {
237
  "cell_type": "code",
238
- "execution_count": 23,
239
  "metadata": {},
240
  "outputs": [
241
  {
@@ -243,10 +254,10 @@
243
  "output_type": "stream",
244
  "text": [
245
  " 2018 2019 2020 2021\n",
246
- "2018 0.0 0.116261 0.10445 1.424479\n",
247
- "2019 0.116261 0.0 0.09933 1.164067\n",
248
- "2020 0.10445 0.09933 0.0 1.075336\n",
249
- "2021 1.424479 1.164067 1.075336 0.0\n"
250
  ]
251
  }
252
  ],
@@ -286,7 +297,7 @@
286
  },
287
  {
288
  "cell_type": "code",
289
- "execution_count": 24,
290
  "metadata": {},
291
  "outputs": [
292
  {
@@ -294,10 +305,10 @@
294
  "output_type": "stream",
295
  "text": [
296
  " 2018 2019 2020 2021\n",
297
- "2018 0.0 0.080291 0.074071 0.449094\n",
298
- "2019 0.080291 0.0 0.060171 0.384189\n",
299
- "2020 0.074071 0.060171 0.0 0.04047\n",
300
- "2021 0.449094 0.384189 0.04047 0.0\n"
301
  ]
302
  }
303
  ],
@@ -337,7 +348,7 @@
337
  },
338
  {
339
  "cell_type": "code",
340
- "execution_count": 25,
341
  "metadata": {},
342
  "outputs": [
343
  {
@@ -345,10 +356,10 @@
345
  "output_type": "stream",
346
  "text": [
347
  " 2018 2019 2020 2021\n",
348
- "2018 0.0 0.127512 0.112157 0.731476\n",
349
- "2019 0.127512 0.0 0.094651 0.647071\n",
350
- "2020 0.112157 0.094651 0.0 0.041217\n",
351
- "2021 0.731476 0.647071 0.041217 0.0\n"
352
  ]
353
  }
354
  ],
@@ -388,7 +399,7 @@
388
  },
389
  {
390
  "cell_type": "code",
391
- "execution_count": 26,
392
  "metadata": {},
393
  "outputs": [
394
  {
@@ -396,10 +407,10 @@
396
  "output_type": "stream",
397
  "text": [
398
  " 2018 2019 2020 2021\n",
399
- "2018 0.0 0.273013 0.053969 0.877338\n",
400
- "2019 0.273013 0.0 0.137817 0.780071\n",
401
- "2020 0.053969 0.137817 0.0 0.042294\n",
402
- "2021 0.877338 0.780071 0.042294 0.0\n"
403
  ]
404
  }
405
  ],
@@ -439,7 +450,7 @@
439
  },
440
  {
441
  "cell_type": "code",
442
- "execution_count": 27,
443
  "metadata": {},
444
  "outputs": [
445
  {
@@ -447,10 +458,10 @@
447
  "output_type": "stream",
448
  "text": [
449
  " 2018 2019 2020 2021\n",
450
- "2018 0.0 0.105633 0.08202 1.00155\n",
451
- "2019 0.105633 0.0 0.069322 0.892938\n",
452
- "2020 0.08202 0.069322 0.0 0.480667\n",
453
- "2021 1.00155 0.892938 0.480667 0.0\n"
454
  ]
455
  }
456
  ],
 
2
  "cells": [
3
  {
4
  "cell_type": "code",
5
+ "execution_count": 1,
6
  "metadata": {},
7
+ "outputs": [
8
+ {
9
+ "name": "stderr",
10
+ "output_type": "stream",
11
+ "text": [
12
+ "2025-12-29 07:26:00.319461: I tensorflow/core/util/port.cc:110] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.\n",
13
+ "2025-12-29 07:26:00.343609: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.\n",
14
+ "To enable the following instructions: AVX2 AVX_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.\n",
15
+ "2025-12-29 07:26:00.726272: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT\n"
16
+ ]
17
+ }
18
+ ],
19
  "source": [
20
  "# ๋ถ„์„์— ํ•„์š”ํ•œ ๋ผ์ด๋ธŒ๋Ÿฌ๋ฆฌ ์ž„ํฌํŠธ\n",
21
  "import warnings\n",
 
44
  },
45
  {
46
  "cell_type": "code",
47
+ "execution_count": 2,
48
  "metadata": {},
49
  "outputs": [],
50
  "source": [
 
69
  },
70
  {
71
  "cell_type": "code",
72
+ "execution_count": 3,
73
  "metadata": {},
74
  "outputs": [
75
  {
 
144
  },
145
  {
146
  "cell_type": "code",
147
+ "execution_count": 4,
148
  "metadata": {},
149
  "outputs": [],
150
  "source": [
 
195
  },
196
  {
197
  "cell_type": "code",
198
+ "execution_count": 5,
199
  "metadata": {},
200
  "outputs": [
201
  {
 
203
  "output_type": "stream",
204
  "text": [
205
  " 2018 2019 2020 2021\n",
206
+ "2018 0.0 0.123805 0.065046 1.077025\n",
207
+ "2019 0.123805 0.0 0.0622 0.822734\n",
208
+ "2020 0.065046 0.0622 0.0 0.038563\n",
209
+ "2021 1.077025 0.822734 0.038563 0.0\n"
210
  ]
211
  }
212
  ],
 
246
  },
247
  {
248
  "cell_type": "code",
249
+ "execution_count": 6,
250
  "metadata": {},
251
  "outputs": [
252
  {
 
254
  "output_type": "stream",
255
  "text": [
256
  " 2018 2019 2020 2021\n",
257
+ "2018 0.0 0.121609 0.102711 1.413564\n",
258
+ "2019 0.121609 0.0 0.095984 1.169424\n",
259
+ "2020 0.102711 0.095984 0.0 0.968261\n",
260
+ "2021 1.413564 1.169424 0.968261 0.0\n"
261
  ]
262
  }
263
  ],
 
297
  },
298
  {
299
  "cell_type": "code",
300
+ "execution_count": 7,
301
  "metadata": {},
302
  "outputs": [
303
  {
 
305
  "output_type": "stream",
306
  "text": [
307
  " 2018 2019 2020 2021\n",
308
+ "2018 0.0 0.07773 0.075873 0.452003\n",
309
+ "2019 0.07773 0.0 0.057967 0.388116\n",
310
+ "2020 0.075873 0.057967 0.0 0.038406\n",
311
+ "2021 0.452003 0.388116 0.038406 0.0\n"
312
  ]
313
  }
314
  ],
 
348
  },
349
  {
350
  "cell_type": "code",
351
+ "execution_count": 8,
352
  "metadata": {},
353
  "outputs": [
354
  {
 
356
  "output_type": "stream",
357
  "text": [
358
  " 2018 2019 2020 2021\n",
359
+ "2018 0.0 0.120673 0.119091 0.73603\n",
360
+ "2019 0.120673 0.0 0.094418 0.642491\n",
361
+ "2020 0.119091 0.094418 0.0 0.060314\n",
362
+ "2021 0.73603 0.642491 0.060314 0.0\n"
363
  ]
364
  }
365
  ],
 
399
  },
400
  {
401
  "cell_type": "code",
402
+ "execution_count": 9,
403
  "metadata": {},
404
  "outputs": [
405
  {
 
407
  "output_type": "stream",
408
  "text": [
409
  " 2018 2019 2020 2021\n",
410
+ "2018 0.0 0.28175 0.055327 0.881159\n",
411
+ "2019 0.28175 0.0 0.119729 0.782018\n",
412
+ "2020 0.055327 0.119729 0.0 0.042649\n",
413
+ "2021 0.881159 0.782018 0.042649 0.0\n"
414
  ]
415
  }
416
  ],
 
450
  },
451
  {
452
  "cell_type": "code",
453
+ "execution_count": 10,
454
  "metadata": {},
455
  "outputs": [
456
  {
 
458
  "output_type": "stream",
459
  "text": [
460
  " 2018 2019 2020 2021\n",
461
+ "2018 0.0 0.104899 0.081615 1.013308\n",
462
+ "2019 0.104899 0.0 0.070288 0.89982\n",
463
+ "2020 0.081615 0.070288 0.0 0.840959\n",
464
+ "2021 1.013308 0.89982 0.840959 0.0\n"
465
  ]
466
  }
467
  ],