File size: 22,202 Bytes
9b068d0 fe7005f 9b068d0 fe7005f 9b068d0 fe7005f 9b068d0 fe7005f 9b068d0 fe7005f 9b068d0 fe7005f 9b068d0 fe7005f 9b068d0 fe7005f 9b068d0 fe7005f 9b068d0 fe7005f 9b068d0 fe7005f 9b068d0 fe7005f 9b068d0 fe7005f 9b068d0 fe7005f 9b068d0 fe7005f 9b068d0 fe7005f 9b068d0 fe7005f 9b068d0 fe7005f 9b068d0 fe7005f 9b068d0 fe7005f 9b068d0 fe7005f 9b068d0 fe7005f 9b068d0 fe7005f 9b068d0 fe7005f 9b068d0 fe7005f 9b068d0 fe7005f 9b068d0 fe7005f 9b068d0 fe7005f 9b068d0 fe7005f 9b068d0 fe7005f 9b068d0 fe7005f 9b068d0 fe7005f 9b068d0 fe7005f 9b068d0 fe7005f 9b068d0 fe7005f 9b068d0 fe7005f 9b068d0 fe7005f 9b068d0 fe7005f 9b068d0 fe7005f 9b068d0 fe7005f 9b068d0 fe7005f 9b068d0 fe7005f 9b068d0 fe7005f 9b068d0 fe7005f 9b068d0 fe7005f 9b068d0 fe7005f 9b068d0 fe7005f 9b068d0 fe7005f 9b068d0 fe7005f 9b068d0 fe7005f 9b068d0 |
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 |
{
"cells": [
{
"cell_type": "code",
"execution_count": 7,
"id": "ae9bc87a",
"metadata": {},
"outputs": [],
"source": [
"from datasets import load_dataset\n",
"import datasets\n",
"from tqdm.notebook import tqdm"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "d5bc67fe",
"metadata": {},
"outputs": [],
"source": [
"ds = load_dataset(\"chainyo/rvl-cdip\")"
]
},
{
"cell_type": "markdown",
"id": "85f49eeb",
"metadata": {},
"source": [
"## Creates the \"rvl_cdip_data\" dir"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "936deafa",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"🚀 Starting RVL-CDIP Downloader (Disk Optimized)\n",
" Target Folder: /Users/arpit-zstch1557/Projects/document-classification/rvl_cdip_data\n",
" Workers: 12\n",
" Loading dataset structure from Hugging Face...\n"
]
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "0a79c4079dd44915af9193231077adc9",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"Resolving data files: 0%| | 0/119 [00:00<?, ?it/s]"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "105602455af94c04a85e8dd5eed8e1bb",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"Loading dataset shards: 0%| | 0/64 [00:00<?, ?it/s]"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
" Found 16 categories.\n",
" Configuring dataset for safe raw access...\n",
"\n",
"📦 Processing SPLIT: TRAIN\n"
]
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "59511ab60fd047758ad0d5671f5f6789",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"Saving train (num_proc=12): 0%| | 0/319999 [00:00<?, ? examples/s]"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"📦 Processing SPLIT: VAL\n"
]
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "19ac18978db046e0aea0cbf7da2748ba",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"Saving val (num_proc=12): 0%| | 0/40000 [00:00<?, ? examples/s]"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"📦 Processing SPLIT: TEST\n"
]
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "890739f28bd2495bacc55ea33099c2f2",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"Saving test (num_proc=12): 0%| | 0/40000 [00:00<?, ? examples/s]"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"/Users/arpit-zstch1557/miniconda3/envs/lab_env/lib/python3.13/site-packages/PIL/TiffImagePlugin.py:949: UserWarning: Corrupt EXIF data. Expecting to read 2 bytes but only got 0. \n",
" warnings.warn(str(msg))\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"[Worker] Skipping corrupt image ID 34965 in test: cannot identify image file <_io.BytesIO object at 0x371a331a0>\n",
"\n",
"✅ Download and Extraction Complete!\n",
" You can now load this in PyTorch using:\n",
" datasets.ImageFolder(root='rvl_cdip_data/train')\n"
]
}
],
"source": [
"import os\n",
"import io\n",
"from datasets import load_dataset, Image as HFImage\n",
"from PIL import Image, UnidentifiedImageError\n",
"\n",
"OUTPUT_DIR = \"rvl_cdip_data\" # Where data will be saved\n",
"NUM_PROC = os.cpu_count() # Use all available CPU cores\n",
"SPLITS = ['train', 'val', 'test'] # Splits to process\n",
"\n",
"def save_image_worker(batch, indices, split_name, output_root, idx_to_class):\n",
" # Unpack batch\n",
" images_data = batch['image'] \n",
" labels = batch['label']\n",
" \n",
" for i, (img_data, label_idx, original_idx) in enumerate(zip(images_data, labels, indices)):\n",
" try:\n",
" # Determine Paths\n",
" class_name = idx_to_class[label_idx]\n",
" target_folder = os.path.join(output_root, split_name, class_name)\n",
" filename = f\"{original_idx}.png\"\n",
" file_path = os.path.join(target_folder, filename)\n",
" \n",
" if os.path.exists(file_path) and os.path.getsize(file_path) > 0:\n",
" continue\n",
" \n",
" # Create Directory\n",
" os.makedirs(target_folder, exist_ok=True)\n",
" \n",
" # 5. Decode Image Safely\n",
" image_bytes = img_data['bytes']\n",
" with Image.open(io.BytesIO(image_bytes)) as img:\n",
" if img.mode != 'RGB':\n",
" img = img.convert('RGB')\n",
" img.save(file_path)\n",
"\n",
" except (UnidentifiedImageError, OSError, ValueError) as e:\n",
" print(f\"[Worker] Skipping corrupt image ID {original_idx} in {split_name}: {e}\")\n",
" \n",
" return {}\n",
"\n",
"def main():\n",
" print(f\"🚀 Starting RVL-CDIP Downloader (Disk Optimized)\")\n",
" print(f\" Target Folder: {os.path.abspath(OUTPUT_DIR)}\")\n",
" print(f\" Workers: {NUM_PROC}\")\n",
" \n",
" # Load Dataset\n",
" print(\" Loading dataset structure from Hugging Face...\")\n",
" dataset = load_dataset(\"chainyo/rvl-cdip\") \n",
"\n",
" # Setup Class Mapping\n",
" labels_feature = dataset['train'].features['label']\n",
" idx_to_class = {idx: name for idx, name in enumerate(labels_feature.names)}\n",
" print(f\" Found {len(idx_to_class)} categories.\")\n",
"\n",
" # Disable Auto-Decoding (Prevents crashes on corrupt files)\n",
" print(\" Configuring dataset for safe raw access...\")\n",
" for split in SPLITS:\n",
" dataset[split] = dataset[split].cast_column(\"image\", HFImage(decode=False))\n",
"\n",
" # Execute Parallel Processing\n",
" for split in SPLITS:\n",
" print(f\"\\n📦 Processing SPLIT: {split.upper()}\")\n",
" \n",
" # We use remove_columns to ensure the output dataset is empty\n",
" # This prevents the 50GB duplicate cache file.\n",
" dataset[split].map(\n",
" save_image_worker,\n",
" batched=True,\n",
" batch_size=100,\n",
" with_indices=True,\n",
" num_proc=NUM_PROC,\n",
" remove_columns=dataset[split].column_names, \n",
" fn_kwargs={\n",
" 'split_name': split,\n",
" 'output_root': OUTPUT_DIR,\n",
" 'idx_to_class': idx_to_class\n",
" },\n",
" desc=f\"Saving {split}\"\n",
" )\n",
"\n",
" print(f\"\\n✅ Download and Extraction Complete!\")\n",
" print(f\" You can now load this in PyTorch using:\")\n",
" print(f\" datasets.ImageFolder(root='{OUTPUT_DIR}/train')\")\n",
"\n",
"if __name__ == \"__main__\":\n",
" main()"
]
},
{
"cell_type": "markdown",
"id": "c8530c8e",
"metadata": {},
"source": [
"## Checking the Data Imbalance in ds (from HF)"
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "2785360c",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"SPLIT CLASS NAME COUNT STATUS\n",
"------------------------------------------------------------\n",
"TRAIN advertisement 19963 ❌ MISMATCH (Exp: 20000)\n",
"TRAIN budget 20010 ❌ MISMATCH (Exp: 20000)\n",
"TRAIN email 19954 ❌ MISMATCH (Exp: 20000)\n",
"TRAIN file folder 20022 ❌ MISMATCH (Exp: 20000)\n",
"TRAIN form 19957 ❌ MISMATCH (Exp: 20000)\n",
"TRAIN handwritten 20034 ❌ MISMATCH (Exp: 20000)\n",
"TRAIN invoice 19947 ❌ MISMATCH (Exp: 20000)\n",
"TRAIN letter 20106 ❌ MISMATCH (Exp: 20000)\n",
"TRAIN memo 19975 ❌ MISMATCH (Exp: 20000)\n",
"TRAIN news article 20011 ❌ MISMATCH (Exp: 20000)\n",
"TRAIN presentation 20043 ❌ MISMATCH (Exp: 20000)\n",
"TRAIN questionnaire 20048 ❌ MISMATCH (Exp: 20000)\n",
"TRAIN resume 20036 ❌ MISMATCH (Exp: 20000)\n",
"TRAIN scientific publication 19902 ❌ MISMATCH (Exp: 20000)\n",
"TRAIN scientific report 19994 ❌ MISMATCH (Exp: 20000)\n",
"TRAIN specification 19997 ❌ MISMATCH (Exp: 20000)\n",
"------------------------------------------------------------\n",
"VAL advertisement 2522 ❌ MISMATCH (Exp: 2500)\n",
"VAL budget 2485 ❌ MISMATCH (Exp: 2500)\n",
"VAL email 2530 ❌ MISMATCH (Exp: 2500)\n",
"VAL file folder 2451 ❌ MISMATCH (Exp: 2500)\n",
"VAL form 2537 ❌ MISMATCH (Exp: 2500)\n",
"VAL handwritten 2434 ❌ MISMATCH (Exp: 2500)\n",
"VAL invoice 2576 ❌ MISMATCH (Exp: 2500)\n",
"VAL letter 2430 ❌ MISMATCH (Exp: 2500)\n",
"VAL memo 2533 ❌ MISMATCH (Exp: 2500)\n",
"VAL news article 2526 ❌ MISMATCH (Exp: 2500)\n",
"VAL presentation 2468 ❌ MISMATCH (Exp: 2500)\n",
"VAL questionnaire 2517 ❌ MISMATCH (Exp: 2500)\n",
"VAL resume 2426 ❌ MISMATCH (Exp: 2500)\n",
"VAL scientific publication 2526 ❌ MISMATCH (Exp: 2500)\n",
"VAL scientific report 2508 ❌ MISMATCH (Exp: 2500)\n",
"VAL specification 2531 ❌ MISMATCH (Exp: 2500)\n",
"------------------------------------------------------------\n",
"TEST advertisement 2515 ❌ MISMATCH (Exp: 2500)\n",
"TEST budget 2505 ❌ MISMATCH (Exp: 2500)\n",
"TEST email 2516 ❌ MISMATCH (Exp: 2500)\n",
"TEST file folder 2527 ❌ MISMATCH (Exp: 2500)\n",
"TEST form 2506 ❌ MISMATCH (Exp: 2500)\n",
"TEST handwritten 2532 ❌ MISMATCH (Exp: 2500)\n",
"TEST invoice 2477 ❌ MISMATCH (Exp: 2500)\n",
"TEST letter 2464 ❌ MISMATCH (Exp: 2500)\n",
"TEST memo 2492 ❌ MISMATCH (Exp: 2500)\n",
"TEST news article 2463 ❌ MISMATCH (Exp: 2500)\n",
"TEST presentation 2489 ❌ MISMATCH (Exp: 2500)\n",
"TEST questionnaire 2435 ❌ MISMATCH (Exp: 2500)\n",
"TEST resume 2537 ❌ MISMATCH (Exp: 2500)\n",
"TEST scientific publication 2572 ❌ MISMATCH (Exp: 2500)\n",
"TEST scientific report 2498 ❌ MISMATCH (Exp: 2500)\n",
"TEST specification 2472 ❌ MISMATCH (Exp: 2500)\n",
"------------------------------------------------------------\n"
]
}
],
"source": [
"from collections import Counter\n",
"import pandas as pd\n",
"\n",
"#Setup\n",
"splits = ['train', 'val', 'test']\n",
"label_feature = ds['train'].features['label']\n",
"int2str = label_feature.int2str \n",
"\n",
"print(f\"{'SPLIT':<10} {'CLASS NAME':<25} {'COUNT':<10} {'STATUS'}\")\n",
"print(\"-\" * 60)\n",
"\n",
"for split in splits:\n",
" # Get all labels (Load only the label column into memory)\n",
" # This is instant compared to loading images\n",
" labels = ds[split]['label']\n",
" \n",
" # Count frequencies\n",
" counts = Counter(labels)\n",
" \n",
" # Analyze each class\n",
" # We sort by class ID to keep it organized\n",
" for label_id in sorted(counts.keys()):\n",
" count = counts[label_id]\n",
" class_name = int2str(label_id)\n",
" \n",
" # Define Expected Counts based on the Paper\n",
" # Train: 320k / 16 = 20,000\n",
" # Test/Val: 40k / 16 = 2,500\n",
" if split == 'train':\n",
" expected = 20000\n",
" else:\n",
" expected = 2500\n",
" \n",
" status = \"✅ OK\" if count == expected else f\"❌ MISMATCH (Exp: {expected})\"\n",
" \n",
" print(f\"{split.upper():<10} {class_name:<25} {count:<10} {status}\")\n",
" \n",
" print(\"-\" * 60) "
]
},
{
"cell_type": "markdown",
"id": "5f7b75a2",
"metadata": {},
"source": [
"## Checking the data imbalance in \"rvl_cdip_data\" dir"
]
},
{
"cell_type": "code",
"execution_count": 9,
"id": "059bfaa5",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"📂 Scanning directory: /Users/arpit-zstch1557/Projects/document-classification/rvl_cdip_data\n",
"SPLIT CLASS NAME FILES STATUS\n",
"-----------------------------------------------------------------\n",
"TRAIN advertisement 19963 ❌ MISMATCH (Exp: 20000)\n",
"TRAIN budget 20010 ❌ MISMATCH (Exp: 20000)\n",
"TRAIN email 19954 ❌ MISMATCH (Exp: 20000)\n",
"TRAIN file folder 20022 ❌ MISMATCH (Exp: 20000)\n",
"TRAIN form 19957 ❌ MISMATCH (Exp: 20000)\n",
"TRAIN handwritten 20034 ❌ MISMATCH (Exp: 20000)\n",
"TRAIN invoice 19947 ❌ MISMATCH (Exp: 20000)\n",
"TRAIN letter 20106 ❌ MISMATCH (Exp: 20000)\n",
"TRAIN memo 19975 ❌ MISMATCH (Exp: 20000)\n",
"TRAIN news article 20011 ❌ MISMATCH (Exp: 20000)\n",
"TRAIN presentation 20043 ❌ MISMATCH (Exp: 20000)\n",
"TRAIN questionnaire 20048 ❌ MISMATCH (Exp: 20000)\n",
"TRAIN resume 20036 ❌ MISMATCH (Exp: 20000)\n",
"TRAIN scientific publication 19902 ❌ MISMATCH (Exp: 20000)\n",
"TRAIN scientific report 19994 ❌ MISMATCH (Exp: 20000)\n",
"TRAIN specification 19997 ⚠️ OK (Off by 3)\n",
"-----------------------------------------------------------------\n",
"VAL advertisement 2522 ❌ MISMATCH (Exp: 2500)\n",
"VAL budget 2485 ❌ MISMATCH (Exp: 2500)\n",
"VAL email 2530 ❌ MISMATCH (Exp: 2500)\n",
"VAL file folder 2451 ❌ MISMATCH (Exp: 2500)\n",
"VAL form 2537 ❌ MISMATCH (Exp: 2500)\n",
"VAL handwritten 2434 ❌ MISMATCH (Exp: 2500)\n",
"VAL invoice 2576 ❌ MISMATCH (Exp: 2500)\n",
"VAL letter 2430 ❌ MISMATCH (Exp: 2500)\n",
"VAL memo 2533 ❌ MISMATCH (Exp: 2500)\n",
"VAL news article 2526 ❌ MISMATCH (Exp: 2500)\n",
"VAL presentation 2468 ❌ MISMATCH (Exp: 2500)\n",
"VAL questionnaire 2517 ❌ MISMATCH (Exp: 2500)\n",
"VAL resume 2426 ❌ MISMATCH (Exp: 2500)\n",
"VAL scientific publication 2526 ❌ MISMATCH (Exp: 2500)\n",
"VAL scientific report 2508 ❌ MISMATCH (Exp: 2500)\n",
"VAL specification 2531 ❌ MISMATCH (Exp: 2500)\n",
"-----------------------------------------------------------------\n",
"TEST advertisement 2515 ❌ MISMATCH (Exp: 2500)\n",
"TEST budget 2505 ❌ MISMATCH (Exp: 2500)\n",
"TEST email 2516 ❌ MISMATCH (Exp: 2500)\n",
"TEST file folder 2527 ❌ MISMATCH (Exp: 2500)\n",
"TEST form 2506 ❌ MISMATCH (Exp: 2500)\n",
"TEST handwritten 2532 ❌ MISMATCH (Exp: 2500)\n",
"TEST invoice 2477 ❌ MISMATCH (Exp: 2500)\n",
"TEST letter 2464 ❌ MISMATCH (Exp: 2500)\n",
"TEST memo 2492 ❌ MISMATCH (Exp: 2500)\n",
"TEST news article 2463 ❌ MISMATCH (Exp: 2500)\n",
"TEST presentation 2489 ❌ MISMATCH (Exp: 2500)\n",
"TEST questionnaire 2435 ❌ MISMATCH (Exp: 2500)\n",
"TEST resume 2537 ❌ MISMATCH (Exp: 2500)\n",
"TEST scientific publication 2571 ❌ MISMATCH (Exp: 2500)\n",
"TEST scientific report 2498 ⚠️ OK (Off by 2)\n",
"TEST specification 2472 ❌ MISMATCH (Exp: 2500)\n",
"-----------------------------------------------------------------\n",
"\n",
"Analysis Complete.\n"
]
}
],
"source": [
"import os\n",
"import pandas as pd\n",
"\n",
"# Configuration\n",
"DATA_DIR = \"rvl_cdip_data\" # Your directory name\n",
"splits = ['train', 'val', 'test']\n",
"\n",
"print(f\"📂 Scanning directory: {os.path.abspath(DATA_DIR)}\")\n",
"print(f\"{'SPLIT':<10} {'CLASS NAME':<25} {'FILES':<10} {'STATUS'}\")\n",
"print(\"-\" * 65)\n",
"\n",
"stats = []\n",
"\n",
"for split in splits:\n",
" split_dir = os.path.join(DATA_DIR, split)\n",
" \n",
" # Check if split folder exists\n",
" if not os.path.exists(split_dir):\n",
" print(f\"❌ Missing folder: {split}\")\n",
" continue\n",
" \n",
" # Get all class folders (sorted for consistency)\n",
" try:\n",
" classes = sorted([d for d in os.listdir(split_dir) if os.path.isdir(os.path.join(split_dir, d))])\n",
" except OSError:\n",
" print(f\"❌ Error reading {split} directory.\")\n",
" continue\n",
"\n",
" for cls in classes:\n",
" cls_path = os.path.join(split_dir, cls)\n",
" \n",
" # Count actual files (ignoring hidden files like .DS_Store)\n",
" file_count = len([\n",
" name for name in os.listdir(cls_path) \n",
" if os.path.isfile(os.path.join(cls_path, name)) \n",
" and not name.startswith('.')\n",
" ])\n",
" \n",
" # Determine Expected Count based on the paper\n",
" if split == 'train':\n",
" expected = 20000 \n",
" else:\n",
" expected = 2500\n",
"\n",
" # Status Check\n",
" if file_count == expected:\n",
" status = \"✅ OK\"\n",
" elif abs(file_count - expected) < 5: \n",
" # If off by 1-4 files (like the corrupt one we skipped), it's acceptable\n",
" status = f\"⚠️ OK (Off by {expected - file_count})\"\n",
" else:\n",
" status = f\"❌ MISMATCH (Exp: {expected})\"\n",
" \n",
" print(f\"{split.upper():<10} {cls:<25} {file_count:<10} {status}\")\n",
" \n",
" print(\"-\" * 65)\n",
"\n",
"print(\"\\nAnalysis Complete.\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "4ef697a2",
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "lab_env",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.13.11"
}
},
"nbformat": 4,
"nbformat_minor": 5
}
|