File size: 29,017 Bytes
500a872
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
e2b68a6
 
500a872
 
e2b68a6
500a872
 
e2b68a6
 
500a872
 
e2b68a6
500a872
 
e2b68a6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
500a872
e2b68a6
 
500a872
e2b68a6
 
 
500a872
 
 
e2b68a6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
500a872
 
 
e2b68a6
 
 
 
 
 
 
 
500a872
e2b68a6
 
 
 
 
 
500a872
e2b68a6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
500a872
e2b68a6
500a872
e2b68a6
 
 
500a872
e2b68a6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
500a872
e2b68a6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
500a872
e2b68a6
 
 
500a872
 
e2b68a6
 
500a872
 
 
e2b68a6
500a872
e2b68a6
 
 
500a872
e2b68a6
500a872
 
e2b68a6
 
 
 
 
 
500a872
 
e2b68a6
500a872
e2b68a6
 
500a872
e2b68a6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
500a872
e2b68a6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
500a872
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
e2b68a6
 
 
 
 
500a872
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
e2b68a6
500a872
 
e2b68a6
 
 
 
500a872
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
e2b68a6
 
 
 
 
 
 
500a872
e2b68a6
 
 
 
500a872
 
 
 
 
 
 
 
e2b68a6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
500a872
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
e2b68a6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
500a872
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
import os
import random
import json
from datetime import datetime, timezone, timedelta
from typing import Dict, List, Optional

import pandas as pd
import numpy as np
from datasets import Dataset, DatasetDict, load_dataset
from huggingface_hub import HfApi
from dotenv import load_dotenv


TARGET_USERS = 20
RECORDS_PER_USER = 500


def require_env(var_name: str) -> str:
    value = os.getenv(var_name)
    if not value:
        raise RuntimeError(f"ํ™˜๊ฒฝ๋ณ€์ˆ˜ {var_name}๊ฐ€ ํ•„์š”ํ•ฉ๋‹ˆ๋‹ค.")
    return value


def jitter(value: float, scale: float = 0.02) -> float:
    """๊ฐ’์— ยฑscale ๋น„์œจ์˜ ๋…ธ์ด์ฆˆ๋ฅผ ์ถ”๊ฐ€"""
    if value is None:
        return None
    return value * (1 + random.uniform(-scale, scale))


def jitter_abs(value: float, amount: float) -> float:
    """์ ˆ๋Œ€๊ฐ’ ๊ธฐ์ค€ ๋…ธ์ด์ฆˆ ์ถ”๊ฐ€"""
    if value is None:
        return None
    return value + random.uniform(-amount, amount)


def augment_sensor_vector(x: float, y: float, z: float, noise: float = 0.02) -> tuple:
    """
    3์ถ• ์„ผ์„œ ๋ฐ์ดํ„ฐ๋ฅผ ๋ฌผ๋ฆฌ์ ์œผ๋กœ ์ž์—ฐ์Šค๋Ÿฝ๊ฒŒ ์ฆํญ
    โ†’ 3์ถ•์€ ๋™์ผํ•œ ๋น„์œจ๋กœ scaling + ๊ฐœ๋ณ„ ์ž‘์€ ๋…ธ์ด์ฆˆ
    """
    if x is None or y is None or z is None:
        return (x, y, z)
    scale = 1 + random.uniform(-noise, noise)
    return (
        round(x * scale + random.uniform(-0.01, 0.01), 4),
        round(y * scale + random.uniform(-0.01, 0.01), 4),
        round(z * scale + random.uniform(-0.01, 0.01), 4),
    )


def compute_rms(x: float, y: float, z: float, base_noise: float = 0.02) -> float:
    """3์ถ• mean ๊ธฐ๋ฐ˜์œผ๋กœ RMS ์žฌ๊ณ„์‚ฐ"""
    if x is None or y is None or z is None:
        return None
    base = np.sqrt(x**2 + y**2 + z**2)
    return round(base * (1 + random.uniform(-base_noise, base_noise)), 4)


def augment_record_strict(row: dict) -> dict:
    """๋ฌผ๋ฆฌ์  ์ œ์•ฝ์„ ์ง€ํ‚ค๋ฉด์„œ ์„ผ์„œ ๋ฐ์ดํ„ฐ๋ฅผ ์ž์—ฐ์Šค๋Ÿฝ๊ฒŒ ์ฆํญ"""
    new = row.copy()
    
    # timestamp jitter
    if "timestamp_utc" in row and isinstance(row["timestamp_utc"], str):
        try:
            t = datetime.fromisoformat(row["timestamp_utc"].replace("Z", "+00:00"))
            t = t + timedelta(milliseconds=random.randint(-150, 150))
            new["timestamp_utc"] = t.isoformat()
        except:
            pass
    
    # window jitter
    if "window_id" in row and row["window_id"] is not None:
        new["window_id"] = int(row["window_id"] + random.randint(-1, 1))
    if "window_start_ms" in row and row["window_start_ms"] is not None:
        new["window_start_ms"] = row["window_start_ms"] + random.randint(-50, 50)
    if "window_end_ms" in row and row["window_end_ms"] is not None:
        new["window_end_ms"] = new["window_start_ms"] + 2000  # window_size_ms์™€ ์ผ์น˜
    
    # --- Accelerometer mean ---
    if all(f in row and row[f] is not None for f in ["acc_x_mean", "acc_y_mean", "acc_z_mean"]):
        new["acc_x_mean"], new["acc_y_mean"], new["acc_z_mean"] = augment_sensor_vector(
            row["acc_x_mean"], row["acc_y_mean"], row["acc_z_mean"], noise=0.03
        )
    
    # --- Gyro mean ---
    if all(f in row and row[f] is not None for f in ["gyro_x_mean", "gyro_y_mean", "gyro_z_mean"]):
        new["gyro_x_mean"], new["gyro_y_mean"], new["gyro_z_mean"] = augment_sensor_vector(
            row["gyro_x_mean"], row["gyro_y_mean"], row["gyro_z_mean"], noise=0.03
        )
    
    # --- Linear accel mean ---
    if all(f in row and row[f] is not None for f in ["linacc_x_mean", "linacc_y_mean", "linacc_z_mean"]):
        new["linacc_x_mean"], new["linacc_y_mean"], new["linacc_z_mean"] = augment_sensor_vector(
            row["linacc_x_mean"], row["linacc_y_mean"], row["linacc_z_mean"], noise=0.03
        )
    
    # --- Gravity vector (๋ฌผ๋ฆฌ์  ์ œ์•ฝ: ํฌ๊ธฐ๊ฐ€ ์•ฝ 9.8) ---
    if all(f in row and row[f] is not None for f in ["gravity_x_mean", "gravity_y_mean", "gravity_z_mean"]):
        gx, gy, gz = augment_sensor_vector(
            row["gravity_x_mean"], row["gravity_y_mean"], row["gravity_z_mean"], noise=0.01
        )
        g_mag = np.sqrt(gx**2 + gy**2 + gz**2)
        if g_mag > 0:
            scale = 9.8 / g_mag
            new["gravity_x_mean"] = round(gx * scale, 4)
            new["gravity_y_mean"] = round(gy * scale, 4)
            new["gravity_z_mean"] = round(gz * scale, 4)
    
    # --- Recompute RMS from sensor means ---
    if all(f in new and new[f] is not None for f in ["acc_x_mean", "acc_y_mean", "acc_z_mean"]):
        new["rms_acc"] = compute_rms(
            new["acc_x_mean"], new["acc_y_mean"], new["acc_z_mean"], base_noise=0.03
        )
    elif "rms_acc" in row and row["rms_acc"] is not None:
        new["rms_acc"] = jitter(row["rms_acc"], 0.03)
    
    if all(f in new and new[f] is not None for f in ["gyro_x_mean", "gyro_y_mean", "gyro_z_mean"]):
        new["rms_gyro"] = compute_rms(
            new["gyro_x_mean"], new["gyro_y_mean"], new["gyro_z_mean"], base_noise=0.03
        )
    elif "rms_gyro" in row and row["rms_gyro"] is not None:
        new["rms_gyro"] = jitter(row["rms_gyro"], 0.03)
    
    # --- std values scale with RMS ---
    if "rms_acc" in new and new["rms_acc"] is not None and "rms_acc" in row and row["rms_acc"] is not None and row["rms_acc"] > 0:
        rms_ratio = new["rms_acc"] / row["rms_acc"]
        for col in ["acc_x_std", "acc_y_std", "acc_z_std"]:
            if col in row and row[col] is not None:
                new[col] = max(0.01, row[col] * rms_ratio * jitter(1, 0.1))
    
    if "rms_gyro" in new and new["rms_gyro"] is not None and "rms_gyro" in row and row["rms_gyro"] is not None and row["rms_gyro"] > 0:
        rms_ratio = new["rms_gyro"] / row["rms_gyro"]
        for col in ["gyro_x_std", "gyro_y_std", "gyro_z_std"]:
            if col in row and row[col] is not None:
                new[col] = max(0.001, row[col] * rms_ratio * jitter(1, 0.1))
    
    # --- frequency (weak positive correlation with RMS) ---
    if "mean_freq_acc" in row and row["mean_freq_acc"] is not None and "rms_acc" in new and new["rms_acc"] is not None:
        new["mean_freq_acc"] = round(jitter_abs(row["mean_freq_acc"], new["rms_acc"] * 0.3), 2)
    elif "mean_freq_acc" in row and row["mean_freq_acc"] is not None:
        new["mean_freq_acc"] = round(jitter(row["mean_freq_acc"], 0.02), 2)
    
    if "mean_freq_gyro" in row and row["mean_freq_gyro"] is not None and "rms_gyro" in new and new["rms_gyro"] is not None:
        new["mean_freq_gyro"] = round(jitter_abs(row["mean_freq_gyro"], new["rms_gyro"] * 0.3), 2)
    elif "mean_freq_gyro" in row and row["mean_freq_gyro"] is not None:
        new["mean_freq_gyro"] = round(jitter(row["mean_freq_gyro"], 0.02), 2)
    
    # --- entropy: increases when RMS increases ---
    if "entropy_acc" in row and row["entropy_acc"] is not None and "rms_acc" in new and new["rms_acc"] is not None and "rms_acc" in row and row["rms_acc"] is not None and row["rms_acc"] > 0:
        new["entropy_acc"] = min(1.0, max(0.05, row["entropy_acc"] * (new["rms_acc"] / row["rms_acc"]) * jitter(1, 0.1)))
    elif "entropy_acc" in row and row["entropy_acc"] is not None:
        new["entropy_acc"] = min(1.0, max(0.05, jitter(row["entropy_acc"], 0.02)))
    
    if "entropy_gyro" in row and row["entropy_gyro"] is not None and "rms_gyro" in new and new["rms_gyro"] is not None and "rms_gyro" in row and row["rms_gyro"] is not None and row["rms_gyro"] > 0:
        new["entropy_gyro"] = min(1.0, max(0.05, row["entropy_gyro"] * (new["rms_gyro"] / row["rms_gyro"]) * jitter(1, 0.1)))
    elif "entropy_gyro" in row and row["entropy_gyro"] is not None:
        new["entropy_gyro"] = min(1.0, max(0.05, jitter(row["entropy_gyro"], 0.02)))
    
    # --- jerk: depends on std and RMS ---
    if "jerk_mean" in row and row["jerk_mean"] is not None:
        if "acc_x_std" in row and row["acc_x_std"] is not None:
            new["jerk_mean"] = round(jitter_abs(row["jerk_mean"], row["acc_x_std"] * 0.3), 4)
        else:
            new["jerk_mean"] = round(jitter(row["jerk_mean"], 0.02), 4)
    
    if "jerk_std" in row and row["jerk_std"] is not None:
        if "acc_x_std" in row and row["acc_x_std"] is not None:
            new["jerk_std"] = max(0.001, round(jitter_abs(row["jerk_std"], row["acc_x_std"] * 0.1), 4))
        else:
            new["jerk_std"] = max(0.001, round(jitter(row["jerk_std"], 0.01), 4))
    
    # --- stability index (inverse to entropy) ---
    entropy_avg = 0.5
    if "entropy_acc" in new and new["entropy_acc"] is not None and "entropy_gyro" in new and new["entropy_gyro"] is not None:
        entropy_avg = (new["entropy_acc"] + new["entropy_gyro"]) / 2
    elif "entropy_acc" in new and new["entropy_acc"] is not None:
        entropy_avg = new["entropy_acc"]
    elif "entropy_gyro" in new and new["entropy_gyro"] is not None:
        entropy_avg = new["entropy_gyro"]
    
    new["stability_index"] = round(max(0.4, min(0.99, 1 - entropy_avg * 0.3)), 4)
    
    # --- fatigue model (RMS, ์ฃผํŒŒ์ˆ˜ ๊ธฐ๋ฐ˜) ---
    # fatigue๋Š” augment_user_data์—์„œ ์‹œ๊ฐ„์  ์—ฐ์†์„ฑ์„ ๊ณ ๋ คํ•˜์—ฌ ๊ณ„์‚ฐ
    # ์—ฌ๊ธฐ์„œ๋Š” ๊ธฐ๋ณธ๊ฐ’๋งŒ ์„ค์ • (๋‚˜์ค‘์— ๋ฎ์–ด์”Œ์›Œ์ง)
    if "fatigue" in row and row["fatigue"] is not None:
        # ๊ธฐ๋ณธ์ ์œผ๋กœ RMS์™€ ์ฃผํŒŒ์ˆ˜ ๊ธฐ๋ฐ˜์œผ๋กœ ์•ฝ๊ฐ„ ์กฐ์ •
        if "rms_acc" in new and new["rms_acc"] is not None and "rms_acc" in row and row["rms_acc"] is not None and row["rms_acc"] > 0.1:
            rms_factor = new["rms_acc"] / row["rms_acc"]
        else:
            rms_factor = 1.0
        
        if "mean_freq_acc" in new and new["mean_freq_acc"] is not None and "mean_freq_acc" in row and row["mean_freq_acc"] is not None and row["mean_freq_acc"] > 1:
            freq_factor = row["mean_freq_acc"] / new["mean_freq_acc"]
        else:
            freq_factor = 1.0
        
        fatigue_delta = rms_factor * 0.05 - freq_factor * 0.03
        new["fatigue"] = min(0.95, max(0.05, row["fatigue"] + fatigue_delta + random.uniform(-0.02, 0.02)))
        new["fatigue_level"] = 0 if new["fatigue"] < 0.3 else 1 if new["fatigue"] < 0.6 else 2
    else:
        # fatigue๊ฐ€ ์—†์œผ๋ฉด ๊ธฐ๋ณธ๊ฐ’ ์„ค์ •
        new["fatigue"] = 0.1
        new["fatigue_level"] = 0
    
    # fatigue_prev๋Š” augment_user_data์—์„œ ์„ค์ •๋จ
    if "fatigue_prev" in row and row["fatigue_prev"] is not None:
        new["fatigue_prev"] = row["fatigue_prev"]
    else:
        new["fatigue_prev"] = 0.05
    
    # --- baseline values (preserve) ---
    if "rms_base" in row:
        new["rms_base"] = row["rms_base"]
    if "freq_base" in row:
        new["freq_base"] = row["freq_base"]
    
    # --- user_emb: NEVER change ---
    if "user_emb" in row:
        new["user_emb"] = row["user_emb"]
    
    # --- other fields ---
    if "overlap_rate" in row and row["overlap_rate"] is not None:
        new["overlap_rate"] = max(0.3, min(0.7, jitter(row["overlap_rate"], 0.02)))
    
    if "window_size_ms" in row:
        new["window_size_ms"] = row.get("window_size_ms", 2000)
    
    if "quality_flag" in row:
        if random.random() < 0.05:  # 5% ํ™•๋ฅ ๋กœ ๋ณ€๊ฒฝ
            new["quality_flag"] = 0 if row["quality_flag"] == 1 else 1
        else:
            new["quality_flag"] = row["quality_flag"]
    
    # session_id ์•ฝ๊ฐ„ ๋ณ€ํ˜•
    if "session_id" in row and row["session_id"]:
        parts = str(row["session_id"]).split("_")
        if len(parts) > 1:
            try:
                session_num = int(parts[-1])
                new["session_id"] = "_".join(parts[:-1]) + "_" + str(session_num + random.randint(-5, 5))
            except:
                new["session_id"] = row["session_id"]
        else:
            new["session_id"] = row["session_id"]
    
    return new


def augment_user_data(df: pd.DataFrame, target_count: int, new_user_id: str = None) -> pd.DataFrame:
    """
    ์‚ฌ์šฉ์ž๋ณ„ ๋ฐ์ดํ„ฐ๋ฅผ ์ฆํญํ•˜์—ฌ ๋ชฉํ‘œ ๊ฐœ์ˆ˜๋งŒํผ ์ƒ์„ฑ
    ์ƒˆ๋กœ์šด ์‚ฌ์šฉ์ž์ธ ๊ฒฝ์šฐ ์‹œ๊ฐ„์  ์—ฐ์†์„ฑ์„ ์œ ์ง€
    """
    if len(df) >= target_count:
        return df.head(target_count)
    
    need = target_count - len(df)
    
    # ์ƒˆ๋กœ์šด ์‚ฌ์šฉ์ž์ธ ๊ฒฝ์šฐ (๊ธฐ์กด ๋ฐ์ดํ„ฐ๊ฐ€ ์—†๊ฑฐ๋‚˜ ์ƒˆ ์‚ฌ์šฉ์ž ID๊ฐ€ ์ œ๊ณต๋œ ๊ฒฝ์šฐ)
    is_new_user = new_user_id is not None or len(df) == 0
    
    if is_new_user and len(df) > 0:
        # ์ƒˆ๋กœ์šด ์‚ฌ์šฉ์ž๋Š” ํ•ญ์ƒ target_count๋งŒํผ ์ƒ์„ฑ (์ฐธ์กฐ ๋ฐ์ดํ„ฐ ๊ธธ์ด์™€ ๋ฌด๊ด€)
        base_row = df.iloc[0].to_dict()
        new_rows = []
        
        # ์‹œ๊ฐ„ ๊ธฐ๋ฐ˜ ์ดˆ๊ธฐ๊ฐ’ ์„ค์ •
        if "timestamp_utc" in base_row and base_row["timestamp_utc"]:
            try:
                base_time = datetime.fromisoformat(str(base_row["timestamp_utc"]).replace("Z", "+00:00"))
            except:
                base_time = datetime.now(timezone.utc)
        else:
            base_time = datetime.now(timezone.utc)
        
        base_window_id = 1  # ์ƒˆ ์‚ฌ์šฉ์ž๋Š” window_id๋ฅผ 1๋ถ€ํ„ฐ ์‹œ์ž‘
        base_window_start = 0  # ์ƒˆ ์‚ฌ์šฉ์ž๋Š” window_start_ms๋ฅผ 0๋ถ€ํ„ฐ ์‹œ์ž‘
        prev_fatigue = base_row.get("fatigue", 0.1) if base_row.get("fatigue") is not None else 0.1
        
        # ์ƒˆ๋กœ์šด ์‚ฌ์šฉ์ž๋Š” ํ•ญ์ƒ target_count๋งŒํผ ์ƒ์„ฑ
        for i in range(target_count):
            # ์ƒ˜ํ”Œ ๋ ˆ์ฝ”๋“œ ์„ ํƒ
            sample_idx = random.randint(0, len(df) - 1)
            sample = df.iloc[sample_idx].to_dict()
            
            # ์ƒˆ๋กœ์šด ๋ ˆ์ฝ”๋“œ ์ƒ์„ฑ
            new_row = augment_record_strict(sample)
            
            # ์ƒˆ๋กœ์šด ์‚ฌ์šฉ์ž ID ์„ค์ •
            if new_user_id:
                new_row["user_id"] = new_user_id
            
            # ์‹œ๊ฐ„์  ์—ฐ์†์„ฑ ์œ ์ง€
            window_interval = 2000  # window_size_ms
            new_row["window_id"] = base_window_id + i
            new_row["window_start_ms"] = base_window_start + i * window_interval
            new_row["window_end_ms"] = new_row["window_start_ms"] + window_interval
            
            # timestamp ์—ฐ์†์„ฑ ์œ ์ง€
            new_row["timestamp_utc"] = (base_time + timedelta(milliseconds=i * window_interval)).isoformat()
            
            # ํ”ผ๋กœ๋„ ์—ฐ์†์„ฑ ์œ ์ง€ (์ด์ „ ํ”ผ๋กœ๋„๋Š” ์ง์ „ ๋ ˆ์ฝ”๋“œ์˜ ํ”ผ๋กœ๋„)
            if i > 0:
                new_row["fatigue_prev"] = prev_fatigue
            else:
                # ์ฒซ ๋ ˆ์ฝ”๋“œ๋Š” ์ฐธ์กฐ ๋ฐ์ดํ„ฐ์˜ ํ”ผ๋กœ๋„์—์„œ ์•ฝ๊ฐ„ ๋‚ฎ๊ฒŒ ์‹œ์ž‘
                new_row["fatigue_prev"] = max(0.05, prev_fatigue - random.uniform(0, 0.05))
            
            # ํ˜„์žฌ ํ”ผ๋กœ๋„๋Š” ์ด์ „ ํ”ผ๋กœ๋„ ๊ธฐ๋ฐ˜์œผ๋กœ ์•ฝ๊ฐ„ ์ฆ๊ฐ€ํ•˜๋Š” ๊ฒฝํ–ฅ (์‹ค์ œ ์ธก์ •๊ณผ ์œ ์‚ฌ)
            if "fatigue" in new_row and new_row["fatigue"] is not None:
                # ํ”ผ๋กœ๋„๋Š” ์‹œ๊ฐ„์— ๋”ฐ๋ผ ์ ์ง„์ ์œผ๋กœ ์ฆ๊ฐ€ํ•˜๋Š” ๊ฒฝํ–ฅ
                fatigue_base = new_row["fatigue_prev"] if "fatigue_prev" in new_row else prev_fatigue
                # ์•ฝ๊ฐ„์˜ ์ฆ๊ฐ€ + ๋…ธ์ด์ฆˆ
                fatigue_increase = random.uniform(0, 0.02)  # ์‹œ๊ฐ„์— ๋”ฐ๋ฅธ ์ ์ง„์  ์ฆ๊ฐ€
                new_row["fatigue"] = min(0.95, max(0.05, fatigue_base + fatigue_increase + random.uniform(-0.01, 0.01)))
                new_row["fatigue_level"] = 0 if new_row["fatigue"] < 0.3 else 1 if new_row["fatigue"] < 0.6 else 2
                prev_fatigue = new_row["fatigue"]
            
            # ์„ธ์…˜ ID ์ƒ์„ฑ (์ƒˆ ์‚ฌ์šฉ์ž์ด๋ฏ€๋กœ ์ƒˆ๋กœ์šด ์„ธ์…˜)
            if "session_id" in new_row:
                new_row["session_id"] = f"session_{i // 10 + 1:03d}"  # 10๊ฐœ ๋ ˆ์ฝ”๋“œ๋‹น ์„ธ์…˜
            
            # measure_date๋Š” ๊ธฐ์กด ๋ฐ์ดํ„ฐ์— ์žˆ๋Š” ๊ฒฝ์šฐ์—๋งŒ ์„ค์ •
            if "measure_date" in sample:
                try:
                    measure_time = datetime.fromisoformat(new_row["timestamp_utc"].replace("Z", "+00:00"))
                    new_row["measure_date"] = measure_time.strftime("%Y-%m-%d")
                except:
                    new_row["measure_date"] = base_time.strftime("%Y-%m-%d")
            
            new_rows.append(new_row)
        
        return pd.DataFrame(new_rows)
    
    else:
        # ๊ธฐ์กด ์‚ฌ์šฉ์ž ๋ฐ์ดํ„ฐ ์ฆํญ (์‹œ๊ฐ„์  ์—ฐ์†์„ฑ ์œ ์ง€)
        new_rows = []
        last_row = df.iloc[-1].to_dict()
        
        # ๋งˆ์ง€๋ง‰ ๋ ˆ์ฝ”๋“œ์˜ ์‹œ๊ฐ„ ์ •๋ณด ๊ฐ€์ ธ์˜ค๊ธฐ
        if "timestamp_utc" in last_row and last_row["timestamp_utc"]:
            try:
                last_time = datetime.fromisoformat(str(last_row["timestamp_utc"]).replace("Z", "+00:00"))
            except:
                last_time = datetime.now(timezone.utc)
        else:
            last_time = datetime.now(timezone.utc)
        
        last_window_id = last_row.get("window_id", 0) if last_row.get("window_id") is not None else 0
        last_window_start = last_row.get("window_end_ms", 0) if last_row.get("window_end_ms") is not None else 0
        prev_fatigue = last_row.get("fatigue", 0.1) if last_row.get("fatigue") is not None else 0.1
        
        for i in range(need):
            # ์ƒ˜ํ”Œ ๋ ˆ์ฝ”๋“œ ์„ ํƒ
            sample_idx = random.randint(0, len(df) - 1)
            sample = df.iloc[sample_idx].to_dict()
            
            # ์ƒˆ๋กœ์šด ๋ ˆ์ฝ”๋“œ ์ƒ์„ฑ
            new_row = augment_record_strict(sample)
            
            # ์‹œ๊ฐ„์  ์—ฐ์†์„ฑ ์œ ์ง€
            window_interval = 2000
            new_row["window_id"] = last_window_id + i + 1
            new_row["window_start_ms"] = last_window_start + i * window_interval
            new_row["window_end_ms"] = new_row["window_start_ms"] + window_interval
            
            # timestamp ์—ฐ์†์„ฑ ์œ ์ง€
            new_row["timestamp_utc"] = (last_time + timedelta(milliseconds=(i + 1) * window_interval)).isoformat()
            
            # ํ”ผ๋กœ๋„ ์—ฐ์†์„ฑ ์œ ์ง€
            new_row["fatigue_prev"] = prev_fatigue
            if "fatigue" in new_row and new_row["fatigue"] is not None:
                # ํ”ผ๋กœ๋„๋Š” ์‹œ๊ฐ„์— ๋”ฐ๋ผ ์ ์ง„์ ์œผ๋กœ ์ฆ๊ฐ€ํ•˜๋Š” ๊ฒฝํ–ฅ
                fatigue_increase = random.uniform(0, 0.02)  # ์‹œ๊ฐ„์— ๋”ฐ๋ฅธ ์ ์ง„์  ์ฆ๊ฐ€
                new_row["fatigue"] = min(0.95, max(0.05, prev_fatigue + fatigue_increase + random.uniform(-0.01, 0.01)))
                new_row["fatigue_level"] = 0 if new_row["fatigue"] < 0.3 else 1 if new_row["fatigue"] < 0.6 else 2
                prev_fatigue = new_row["fatigue"]
            
            # measure_date๋Š” ๊ธฐ์กด ๋ฐ์ดํ„ฐ์— ์žˆ๋Š” ๊ฒฝ์šฐ์—๋งŒ ์„ค์ •
            if "measure_date" in sample:
                try:
                    measure_time = datetime.fromisoformat(new_row["timestamp_utc"].replace("Z", "+00:00"))
                    new_row["measure_date"] = measure_time.strftime("%Y-%m-%d")
                except:
                    new_row["measure_date"] = last_time.strftime("%Y-%m-%d")
            
            new_rows.append(new_row)
        
        return pd.concat([df, pd.DataFrame(new_rows)], ignore_index=True)


def main():
    load_dotenv()
    
    repo_id = require_env("HF_DATA_REPO_ID")
    token = require_env("HF_DATA_TOKEN")
    
    print(f"๐Ÿ“‚ ๊ธฐ์กด ๋ฐ์ดํ„ฐ์…‹ ๋กœ๋“œ ์ค‘: {repo_id}")
    
    # ๊ฐœ๋ณ„ parquet ํŒŒ์ผ์„ ๋ชจ๋‘ ๋กœ๋“œ (user๋กœ ์‹œ์ž‘ํ•˜์ง€ ์•Š๋Š” ํŒŒ์ผ๋„ ํฌํ•จ)
    api = HfApi()
    try:
        files = api.list_repo_files(repo_id=repo_id, repo_type="dataset", token=token)
        # ๋ชจ๋“  parquet ํŒŒ์ผ ํ•„ํ„ฐ๋ง (user๋กœ ์‹œ์ž‘ํ•˜์ง€ ์•Š๋Š” ๊ฒƒ๋„ ํฌํ•จ)
        parquet_files = [f for f in files if f.endswith(".parquet")]
        print(f"๐Ÿ“Š Parquet ํŒŒ์ผ ์ˆ˜: {len(parquet_files)}")
        
        existing = DatasetDict()
        for file_path in parquet_files:
                try:
                    # ํŒŒ์ผ๋ช…์—์„œ ์‚ฌ์šฉ์ž ID ์ถ”์ถœ
                    # ํ˜•์‹: data/user_xxx.parquet ๋˜๋Š” data/user_xxx-00000-of-00001.parquet
                    filename = file_path.split("/")[-1] if "/" in file_path else file_path
                    # .parquet ํ™•์žฅ์ž ์ œ๊ฑฐ
                    filename_no_ext = filename.replace(".parquet", "")
                    # -00000-of-00001 ๋ถ€๋ถ„์ด ์žˆ์œผ๋ฉด ์ œ๊ฑฐ, ์—†์œผ๋ฉด ๊ทธ๋Œ€๋กœ ์‚ฌ์šฉ
                    if "-" in filename_no_ext:
                        user_id = filename_no_ext.split("-")[0]
                    else:
                        user_id = filename_no_ext
                    
                    # local_user๋กœ ์‹œ์ž‘ํ•˜๋Š” ํŒŒ์ผ์€ ์ œ์™ธ
                    if user_id.startswith("local_user"):
                        print(f"โญ๏ธ {user_id}: local_user๋กœ ์‹œ์ž‘ํ•˜๋Š” ํŒŒ์ผ์€ ์ œ์™ธ")
                        continue
                    
                    # ๊ฐœ๋ณ„ ํŒŒ์ผ์„ pandas๋กœ ์ง์ ‘ ๋กœ๋“œ
                    from huggingface_hub import hf_hub_download
                    import tempfile
                    
                    # ํŒŒ์ผ ๋‹ค์šด๋กœ๋“œ
                    local_path = hf_hub_download(
                        repo_id=repo_id,
                        filename=file_path,
                        repo_type="dataset",
                        token=token
                    )
                    
                    # pandas๋กœ ์ง์ ‘ ์ฝ๊ธฐ
                    df = pd.read_parquet(local_path)
                    if len(df) > 0:
                        existing[user_id] = Dataset.from_pandas(df, preserve_index=False)
                        print(f"โœ… {user_id}: {len(df)} ๋ ˆ์ฝ”๋“œ ๋กœ๋“œ")
                    else:
                        print(f"โš ๏ธ {user_id}: ๋นˆ ๋ฐ์ดํ„ฐ์…‹, ๊ฑด๋„ˆ๋œ€")
                except Exception as e2:
                    print(f"โš ๏ธ {file_path}: ๋กœ๋“œ ์‹คํŒจ ({str(e2)[:100]}), ๊ฑด๋„ˆ๋œ€")
                    continue
    except Exception as e3:
        print(f"โŒ ๋ฐ์ดํ„ฐ์…‹ ๋กœ๋“œ ์™„์ „ ์‹คํŒจ: {e3}")
        return
    
    # ์œ ํšจํ•œ ์‚ฌ์šฉ์ž๋งŒ ํ•„ํ„ฐ๋ง (๋ฐ์ดํ„ฐ๊ฐ€ ์žˆ๋Š” ์‚ฌ์šฉ์ž๋งŒ, local_user ์ œ์™ธ)
    valid_users = {}
    for user_id in existing.keys():
        # local_user๋กœ ์‹œ์ž‘ํ•˜๋Š” ์‚ฌ์šฉ์ž๋Š” ์ œ์™ธ
        if user_id.startswith("local_user"):
            print(f"โญ๏ธ {user_id}: local_user๋กœ ์‹œ์ž‘ํ•˜๋Š” ์‚ฌ์šฉ์ž๋Š” ์ œ์™ธ")
            continue
        try:
            user_data = existing[user_id]
            if len(user_data) > 0:
                valid_users[user_id] = user_data
            else:
                print(f"โš ๏ธ {user_id}: ๋นˆ ๋ฐ์ดํ„ฐ์…‹, ๊ฑด๋„ˆ๋œ€")
        except Exception as e:
            print(f"โš ๏ธ {user_id}: ๋ฐ์ดํ„ฐ ์ ‘๊ทผ ์‹คํŒจ ({e}), ๊ฑด๋„ˆ๋œ€")
            continue
    
    if len(valid_users) == 0:
        print("โŒ ์œ ํšจํ•œ ์‚ฌ์šฉ์ž ๋ฐ์ดํ„ฐ๊ฐ€ ์—†์Šต๋‹ˆ๋‹ค.")
        return
    
    print(f"โœ… ์œ ํšจํ•œ ์‚ฌ์šฉ์ž ์ˆ˜: {len(valid_users)}๋ช…")
    
    # ํ˜„์žฌ ์ด ๋ ˆ์ฝ”๋“œ ์ˆ˜ ๊ณ„์‚ฐ
    current_total = sum(len(valid_users[user_id]) for user_id in valid_users)
    print(f"๐Ÿ“Š ํ˜„์žฌ ์ด ๋ ˆ์ฝ”๋“œ ์ˆ˜: {current_total}")
    
    # ๊ธฐ์กด ์‚ฌ์šฉ์ž ๋ชฉ๋ก ๊ฐ€์ ธ์˜ค๊ธฐ (์ƒ˜ํ”Œ๋ง์šฉ)
    all_users = list(valid_users.keys())
    
    if len(all_users) == 0:
        print("โŒ ์ฆํญํ•  ์ฐธ์กฐ ๋ฐ์ดํ„ฐ๊ฐ€ ์—†์Šต๋‹ˆ๋‹ค.")
        return
    
    # ์ƒˆ๋กœ์šด ์‚ฌ์šฉ์ž 20๋ช… ์ƒ์„ฑ (๊ธฐ์กด ์‚ฌ์šฉ์ž ๋ฐ์ดํ„ฐ๋ฅผ ์ฐธ์กฐํ•˜์—ฌ ์ฆํญ)
    print(f"๐ŸŽฏ ์ƒˆ๋กœ์šด ์‚ฌ์šฉ์ž {TARGET_USERS}๋ช… ์ƒ์„ฑ ์ค‘...")
    print(f"๐Ÿ“‹ ์ฐธ์กฐ ์‚ฌ์šฉ์ž: {len(all_users)}๋ช…")
    print(f"๐ŸŽฏ ์‚ฌ์šฉ์ž๋‹น ๋ชฉํ‘œ ๋ ˆ์ฝ”๋“œ ์ˆ˜: {RECORDS_PER_USER}")
    
    # ์ƒˆ๋กœ์šด ์‚ฌ์šฉ์ž ๋ฐ์ดํ„ฐ์…‹ ์ƒ์„ฑ
    new_user_datasets = {}
    for i in range(1, TARGET_USERS + 1):
        # ์ƒˆ๋กœ์šด ์‚ฌ์šฉ์ž ID ์ƒ์„ฑ
        new_user_id = f"augmented_user_{i:03d}"
        
        # ๊ธฐ์กด ์‚ฌ์šฉ์ž ์ค‘ ๋žœ๋ค ์„ ํƒ (์ฐธ์กฐ์šฉ)
        reference_user_id = random.choice(all_users)
        reference_df = valid_users[reference_user_id].to_pandas()
        
        if len(reference_df) == 0:
            print(f"โš ๏ธ ์ฐธ์กฐ ์‚ฌ์šฉ์ž {reference_user_id}์˜ ๋ฐ์ดํ„ฐ๊ฐ€ ๋น„์–ด์žˆ์–ด ๊ฑด๋„ˆ๋œ€")
            continue
        
        try:
            # ์ฐธ์กฐ ๋ฐ์ดํ„ฐ๋ฅผ ์ฆํญํ•˜์—ฌ ์ƒˆ๋กœ์šด ์‚ฌ์šฉ์ž ๋ฐ์ดํ„ฐ ์ƒ์„ฑ (์ƒˆ ์‚ฌ์šฉ์ž ID ์ „๋‹ฌ)
            new_user_df = augment_user_data(reference_df, RECORDS_PER_USER, new_user_id=new_user_id)
            # user_id ์ปฌ๋Ÿผ์ด ์—†์œผ๋ฉด ์ถ”๊ฐ€
            if "user_id" not in new_user_df.columns:
                new_user_df["user_id"] = new_user_id
            else:
                new_user_df["user_id"] = new_user_id
            new_user_datasets[new_user_id] = Dataset.from_pandas(new_user_df, preserve_index=False)
            actual_count = len(new_user_df)
            print(f"๐Ÿ“ˆ {new_user_id}: {actual_count} ๋ ˆ์ฝ”๋“œ ์ƒ์„ฑ (์ฐธ์กฐ: {reference_user_id}, ๋ชฉํ‘œ: {RECORDS_PER_USER})")
            if actual_count != RECORDS_PER_USER:
                print(f"   โš ๏ธ ๊ฒฝ๊ณ : ์ƒ์„ฑ๋œ ๋ ˆ์ฝ”๋“œ ์ˆ˜({actual_count})๊ฐ€ ๋ชฉํ‘œ({RECORDS_PER_USER})์™€ ๋‹ค๋ฆ…๋‹ˆ๋‹ค!")
        except Exception as e:
            print(f"โŒ {new_user_id}: ์ƒ์„ฑ ์‹คํŒจ ({e}), ๊ฑด๋„ˆ๋œ€")
            continue
    
    if len(new_user_datasets) == 0:
        print("โŒ ์ƒˆ๋กœ์šด ์‚ฌ์šฉ์ž ๋ฐ์ดํ„ฐ๊ฐ€ ์ƒ์„ฑ๋˜์ง€ ์•Š์•˜์Šต๋‹ˆ๋‹ค.")
        return
    
    # ๊ธฐ์กด ๋ฐ์ดํ„ฐ์˜ ์Šคํ‚ค๋งˆ ํ™•์ธ (์ฒซ ๋ฒˆ์งธ ์‚ฌ์šฉ์ž ๋ฐ์ดํ„ฐ ๊ธฐ์ค€)
    print("๐Ÿ”ง ๊ธฐ์กด ๋ฐ์ดํ„ฐ ์Šคํ‚ค๋งˆ ํ™•์ธ ์ค‘...")
    reference_user_id = list(valid_users.keys())[0]
    reference_df = valid_users[reference_user_id].to_pandas()
    existing_columns = set(reference_df.columns)
    print(f"  ๐Ÿ“‹ ๊ธฐ์กด ๋ฐ์ดํ„ฐ ์ปฌ๋Ÿผ ์ˆ˜: {len(existing_columns)}")
    print(f"  ๐Ÿ“‹ ๊ธฐ์กด ๋ฐ์ดํ„ฐ ์ปฌ๋Ÿผ: {sorted(existing_columns)}")
    
    # ์ƒˆ๋กœ์šด ์‚ฌ์šฉ์ž ๋ฐ์ดํ„ฐ๋ฅผ ๊ธฐ์กด ์Šคํ‚ค๋งˆ์— ๋งž์ถค
    print("๐Ÿ”ง ์ƒˆ๋กœ์šด ์‚ฌ์šฉ์ž ๋ฐ์ดํ„ฐ๋ฅผ ๊ธฐ์กด ์Šคํ‚ค๋งˆ์— ๋งž์ถ”๋Š” ์ค‘...")
    for user_id in new_user_datasets.keys():
        df = new_user_datasets[user_id].to_pandas()
        
        # ๊ธฐ์กด์— ์—†๋Š” ์ปฌ๋Ÿผ ์ œ๊ฑฐ
        columns_to_remove = set(df.columns) - existing_columns
        if columns_to_remove:
            df = df.drop(columns=list(columns_to_remove))
            print(f"  โš ๏ธ {user_id}: ๋ถˆํ•„์š”ํ•œ ์ปฌ๋Ÿผ ์ œ๊ฑฐ: {columns_to_remove}")
        
        # ๊ธฐ์กด์— ์žˆ๋Š”๋ฐ ์—†๋Š” ์ปฌ๋Ÿผ ์ถ”๊ฐ€ (None์œผ๋กœ)
        columns_to_add = existing_columns - set(df.columns)
        if columns_to_add:
            for col in columns_to_add:
                df[col] = None
            print(f"  โž• {user_id}: ๋ˆ„๋ฝ๋œ ์ปฌ๋Ÿผ ์ถ”๊ฐ€: {columns_to_add}")
        
        # ์ปฌ๋Ÿผ ์ˆœ์„œ๋ฅผ ๊ธฐ์กด ๋ฐ์ดํ„ฐ์™€ ๋™์ผํ•˜๊ฒŒ ๋งž์ถค
        df = df[list(reference_df.columns)]
        
        new_user_datasets[user_id] = Dataset.from_pandas(df, preserve_index=False)
        print(f"  โœ… {user_id}: ์Šคํ‚ค๋งˆ ์ •๊ทœํ™” ์™„๋ฃŒ")
    
    # ๊ธฐ์กด ๋ฐ์ดํ„ฐ์…‹์— ์ƒˆ๋กœ์šด ์‚ฌ์šฉ์ž ๋ฐ์ดํ„ฐ ์ถ”๊ฐ€
    final_datasets = {}
    # ๊ธฐ์กด ์‚ฌ์šฉ์ž ๋ฐ์ดํ„ฐ ์œ ์ง€
    for user_id in valid_users.keys():
        final_datasets[user_id] = valid_users[user_id]
    # ์ƒˆ๋กœ์šด ์‚ฌ์šฉ์ž ๋ฐ์ดํ„ฐ ์ถ”๊ฐ€
    for user_id in new_user_datasets.keys():
        final_datasets[user_id] = new_user_datasets[user_id]
    
    final_dict = DatasetDict(final_datasets)
    new_users_total = sum(len(new_user_datasets[user_id]) for user_id in new_user_datasets)
    total_records = sum(len(final_dict[user_id]) for user_id in final_dict)
    print(f"๐Ÿ“Š ์ƒˆ๋กœ์šด ์‚ฌ์šฉ์ž๋“ค์˜ ์ด ๋ ˆ์ฝ”๋“œ ์ˆ˜: {new_users_total}")
    print(f"๐Ÿ“Š ์ „์ฒด ๋ฐ์ดํ„ฐ์…‹ ์ด ๋ ˆ์ฝ”๋“œ ์ˆ˜: {total_records}")
    print(f"๐Ÿ“Š ์ƒˆ๋กœ์šด parquet ํŒŒ์ผ ์ˆ˜: {len(new_user_datasets)}๊ฐœ")
    
    # local_user๋กœ ์‹œ์ž‘ํ•˜๋Š” ํŒŒ์ผ ์‚ญ์ œ
    print("๐Ÿ—‘๏ธ local_user๋กœ ์‹œ์ž‘ํ•˜๋Š” ํŒŒ์ผ ์‚ญ์ œ ์ค‘...")
    try:
        files_to_delete = []
        for file_path in parquet_files:
            filename = file_path.split("/")[-1] if "/" in file_path else file_path
            filename_no_ext = filename.replace(".parquet", "")
            # -00000-of-00001 ๋ถ€๋ถ„์ด ์žˆ์œผ๋ฉด ์ œ๊ฑฐ
            if "-" in filename_no_ext:
                user_id = filename_no_ext.split("-")[0]
            else:
                user_id = filename_no_ext
            
            if user_id.startswith("local_user"):
                files_to_delete.append(file_path)
        
        for file_path in files_to_delete:
            try:
                api.delete_file(path_in_repo=file_path, repo_id=repo_id, repo_type="dataset", token=token)
                print(f"  โœ… ์‚ญ์ œ: {file_path}")
            except Exception as e:
                print(f"  โš ๏ธ ์‚ญ์ œ ์‹คํŒจ ({file_path}): {str(e)[:100]}")
        
        if files_to_delete:
            print(f"๐Ÿ—‘๏ธ {len(files_to_delete)}๊ฐœ ํŒŒ์ผ ์‚ญ์ œ ์™„๋ฃŒ")
        else:
            print("โ„น๏ธ ์‚ญ์ œํ•  local_user ํŒŒ์ผ์ด ์—†์Šต๋‹ˆ๋‹ค")
    except Exception as e:
        print(f"โš ๏ธ ํŒŒ์ผ ์‚ญ์ œ ์ค‘ ์˜ค๋ฅ˜ ๋ฐœ์ƒ: {str(e)[:100]}")
    
    print(f"๐Ÿ“ค Hugging Face Hub์— ์—…๋กœ๋“œ ์ค‘: {repo_id}")
    final_dict.push_to_hub(repo_id, token=token, private=True)
    print("โœ… ์—…๋กœ๋“œ ์™„๋ฃŒ")


if __name__ == "__main__":
    main()