Spaces:
Runtime error
Runtime error
File size: 42,034 Bytes
d572f56 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 |
{
"cells": [
{
"cell_type": "code",
"execution_count": 147,
"metadata": {
"collapsed": true,
"ExecuteTime": {
"end_time": "2024-04-06T01:17:54.148969526Z",
"start_time": "2024-04-06T01:17:54.108519625Z"
}
},
"outputs": [],
"source": [
"from functools import partial\n",
"from itertools import chain\n",
"\n",
"import librosa.effects\n",
"import numpy as np\n",
"import pandas as pd\n",
"import soundfile as sf\n",
"\n",
"import os\n",
"\n",
"from ipywidgets import Audio\n",
"from matplotlib import pyplot as plt\n",
"from tqdm.contrib.concurrent import process_map\n",
"from tqdm.notebook import tqdm\n",
"\n",
"import librosa"
]
},
{
"cell_type": "code",
"execution_count": 41,
"outputs": [],
"source": [
"INFERENCE_ROOT = \"/home/kwatchar3/Documents/data/moisesdb/\"\n",
"STEM_SETUP = \"vdbgp\"\n",
"GROUND_TRUTH_ROOT = \"/home/kwatchar3/Documents/data/moisesdb\""
],
"metadata": {
"collapsed": false,
"ExecuteTime": {
"end_time": "2024-04-06T00:17:30.477964506Z",
"start_time": "2024-04-06T00:17:30.476945Z"
}
}
},
{
"cell_type": "code",
"execution_count": 42,
"outputs": [],
"source": [
"variants = [\n",
" \"vdbgp-d-pre\",\n",
" \"vdbgp-d-prefz\",\n",
" \"vdbgp-d-pre-aug\",\n",
" \"vdbgp-d-pre-bal\",\n",
" \"vdbgp-d-prefz-bal\",\n",
" \"vdbgp-d-pre-aug-bal\",\n",
"]\n",
"\n"
],
"metadata": {
"collapsed": false,
"ExecuteTime": {
"end_time": "2024-04-06T00:17:30.478032192Z",
"start_time": "2024-04-06T00:17:30.477021223Z"
}
}
},
{
"cell_type": "code",
"execution_count": 43,
"outputs": [],
"source": [
"gt_files = os.listdir(os.path.join(GROUND_TRUTH_ROOT, \"npy2\"))"
],
"metadata": {
"collapsed": false,
"ExecuteTime": {
"end_time": "2024-04-06T00:17:30.478078628Z",
"start_time": "2024-04-06T00:17:30.477041650Z"
}
}
},
{
"cell_type": "code",
"execution_count": 44,
"outputs": [],
"source": [
"def snr(gt, est):\n",
" return 10 * np.log10(np.sum(np.square(gt)) / np.sum(np.square(gt - est)))"
],
"metadata": {
"collapsed": false,
"ExecuteTime": {
"end_time": "2024-04-06T00:17:30.478120578Z",
"start_time": "2024-04-06T00:17:30.477062709Z"
}
}
},
{
"cell_type": "code",
"execution_count": 45,
"outputs": [],
"source": [
"allowed_stems = [\n",
" \"lead_female_singer\",\n",
" \"lead_male_singer\",\n",
" \"drums\",\n",
" \"bass_guitar\",\n",
" \"acoustic_guitar\",\n",
" \"clean_electric_guitar\",\n",
" \"distorted_electric_guitar\",\n",
" \"grand_piano\",\n",
" \"electric_piano\",\n",
"]"
],
"metadata": {
"collapsed": false,
"ExecuteTime": {
"end_time": "2024-04-06T00:17:30.478163141Z",
"start_time": "2024-04-06T00:17:30.477078796Z"
}
}
},
{
"cell_type": "code",
"execution_count": 46,
"outputs": [],
"source": [
"def get_results_for_song(inputs):\n",
"\n",
" song_name, inference_mode, variant = inputs\n",
"\n",
" stems = os.listdir(os.path.join(INFERENCE_ROOT, inference_mode, STEM_SETUP, variant, \"audio\", song_name))\n",
" stems = [s.replace(\".wav\", \"\") for s in stems]\n",
"\n",
" results = []\n",
"\n",
" for stem in stems:\n",
" if stem not in allowed_stems:\n",
" continue\n",
"\n",
" audio_est, sr = sf.read(os.path.join(INFERENCE_ROOT, inference_mode, STEM_SETUP, variant, \"audio\", song_name, f\"{stem}.wav\"))\n",
" audio_est = audio_est.T\n",
"\n",
" npy_path = os.path.join(GROUND_TRUTH_ROOT, \"npy2\", song_name, f\"{stem}.npy\")\n",
" if os.path.exists(npy_path):\n",
" audio = np.load(npy_path, mmap_mode=\"r\")\n",
" else:\n",
" print(\"!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!\")\n",
" print(f\"Ground truth not found for {song_name}/{stem}. Using zeros.\")\n",
" print(\"!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!\")\n",
" audio = np.zeros_like(audio_est)\n",
"\n",
" snr_full = snr(audio, audio_est)\n",
"\n",
" results.append({\n",
" \"song\": song_name,\n",
" \"stem\": stem,\n",
" \"snr\": snr_full,\n",
" \"variant\": variant,\n",
" \"inference_mode\": inference_mode,\n",
" })\n",
"\n",
" return results\n",
"\n"
],
"metadata": {
"collapsed": false,
"ExecuteTime": {
"end_time": "2024-04-06T00:17:30.478202810Z",
"start_time": "2024-04-06T00:17:30.477095928Z"
}
}
},
{
"cell_type": "code",
"execution_count": 59,
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Processing vdbgp-d-pre...\n"
]
},
{
"data": {
"text/plain": " 0%| | 0/48 [00:00<?, ?it/s]",
"application/vnd.jupyter.widget-view+json": {
"version_major": 2,
"version_minor": 0,
"model_id": "be3f2d2ef7004e8da3deb348c57ccc59"
}
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"Processing vdbgp-d-prefz...\n"
]
},
{
"data": {
"text/plain": " 0%| | 0/48 [00:00<?, ?it/s]",
"application/vnd.jupyter.widget-view+json": {
"version_major": 2,
"version_minor": 0,
"model_id": "b3d21ae2dd534643994529cbf31aadd2"
}
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"Processing vdbgp-d-pre-aug...\n"
]
},
{
"data": {
"text/plain": " 0%| | 0/48 [00:00<?, ?it/s]",
"application/vnd.jupyter.widget-view+json": {
"version_major": 2,
"version_minor": 0,
"model_id": "04f9d83a376c438ab06068514699dfeb"
}
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"Processing vdbgp-d-pre-bal...\n"
]
},
{
"data": {
"text/plain": " 0%| | 0/48 [00:00<?, ?it/s]",
"application/vnd.jupyter.widget-view+json": {
"version_major": 2,
"version_minor": 0,
"model_id": "96e08a7f38dd40e69a6d99c9c114c0bd"
}
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"Processing vdbgp-d-prefz-bal...\n"
]
},
{
"data": {
"text/plain": " 0%| | 0/48 [00:00<?, ?it/s]",
"application/vnd.jupyter.widget-view+json": {
"version_major": 2,
"version_minor": 0,
"model_id": "5e4181ab556d4c2583df627d5964457e"
}
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"Processing vdbgp-d-pre-aug-bal...\n"
]
},
{
"data": {
"text/plain": " 0%| | 0/48 [00:00<?, ?it/s]",
"application/vnd.jupyter.widget-view+json": {
"version_major": 2,
"version_minor": 0,
"model_id": "428fb352d0f74b26a73a0bb30291fc4b"
}
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"Processing vdbgp-d-pre...\n"
]
},
{
"data": {
"text/plain": " 0%| | 0/48 [00:00<?, ?it/s]",
"application/vnd.jupyter.widget-view+json": {
"version_major": 2,
"version_minor": 0,
"model_id": "7b698cb85ffa47a7887ae0b602e4d818"
}
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"Processing vdbgp-d-prefz...\n"
]
},
{
"data": {
"text/plain": " 0%| | 0/48 [00:00<?, ?it/s]",
"application/vnd.jupyter.widget-view+json": {
"version_major": 2,
"version_minor": 0,
"model_id": "44299177761e4565b77a19db3baab0d6"
}
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"Processing vdbgp-d-pre-aug...\n"
]
},
{
"data": {
"text/plain": " 0%| | 0/48 [00:00<?, ?it/s]",
"application/vnd.jupyter.widget-view+json": {
"version_major": 2,
"version_minor": 0,
"model_id": "ff6b9aabbb9a41909af4ca801f82b665"
}
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"Processing vdbgp-d-pre-bal...\n"
]
},
{
"data": {
"text/plain": " 0%| | 0/48 [00:00<?, ?it/s]",
"application/vnd.jupyter.widget-view+json": {
"version_major": 2,
"version_minor": 0,
"model_id": "4e1df82d8fd54ddc9052059f29d9e37f"
}
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"Processing vdbgp-d-prefz-bal...\n"
]
},
{
"data": {
"text/plain": " 0%| | 0/48 [00:00<?, ?it/s]",
"application/vnd.jupyter.widget-view+json": {
"version_major": 2,
"version_minor": 0,
"model_id": "1a07fe56352b40f5acd772be8035753a"
}
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"Processing vdbgp-d-pre-aug-bal...\n"
]
},
{
"data": {
"text/plain": " 0%| | 0/48 [00:00<?, ?it/s]",
"application/vnd.jupyter.widget-view+json": {
"version_major": 2,
"version_minor": 0,
"model_id": "16b4c7739ded4993a347b933ec997b49"
}
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"\n",
"df = []\n",
"\n",
"for inference_mode in [\"inference-d\", \"inference-o\"]:\n",
"\n",
" for v in variants:\n",
" print(f\"Processing {v}...\")\n",
"\n",
" test_files = os.listdir(os.path.join(INFERENCE_ROOT, inference_mode, STEM_SETUP, v, \"audio\"))\n",
"\n",
" # for song in tqdm(test_files):\n",
" # results = get_results_for_song(song, inference_mode, v)\n",
" # df.extend(results)\n",
"\n",
" inputs = [(song, inference_mode, v) for song in test_files]\n",
"\n",
" results = process_map(get_results_for_song, inputs, max_workers=16)\n",
" results = list(chain(*results))\n",
"\n",
" df.extend(results)\n",
"\n",
"\n",
"df = pd.DataFrame(df)"
],
"metadata": {
"collapsed": false,
"ExecuteTime": {
"end_time": "2024-04-06T00:45:30.138844425Z",
"start_time": "2024-04-06T00:41:31.501195560Z"
}
}
},
{
"cell_type": "markdown",
"source": [],
"metadata": {
"collapsed": false
}
},
{
"cell_type": "code",
"execution_count": 60,
"outputs": [
{
"data": {
"text/plain": " song stem \\\n0 704f1de9-1d02-4c2b-af05-107a7700a51d bass_guitar \n1 704f1de9-1d02-4c2b-af05-107a7700a51d drums \n2 704f1de9-1d02-4c2b-af05-107a7700a51d acoustic_guitar \n3 704f1de9-1d02-4c2b-af05-107a7700a51d lead_male_singer \n4 8a6c9c1f-4865-404f-a805-1949de36a33c lead_female_singer \n... ... ... \n2647 a56d9450-3a26-485c-8ac3-24b6b54e2c1d acoustic_guitar \n2648 1f98fe4d-26c7-460f-9f68-33964bc4d8d3 distorted_electric_guitar \n2649 1f98fe4d-26c7-460f-9f68-33964bc4d8d3 bass_guitar \n2650 1f98fe4d-26c7-460f-9f68-33964bc4d8d3 drums \n2651 1f98fe4d-26c7-460f-9f68-33964bc4d8d3 lead_male_singer \n\n snr variant inference_mode \n0 9.033754 vdbgp-d-pre inference-d \n1 12.501521 vdbgp-d-pre inference-d \n2 1.717476 vdbgp-d-pre inference-d \n3 7.361787 vdbgp-d-pre inference-d \n4 13.685509 vdbgp-d-pre inference-d \n... ... ... ... \n2647 10.415203 vdbgp-d-pre-aug-bal inference-o \n2648 4.498278 vdbgp-d-pre-aug-bal inference-o \n2649 8.909531 vdbgp-d-pre-aug-bal inference-o \n2650 10.670884 vdbgp-d-pre-aug-bal inference-o \n2651 1.847866 vdbgp-d-pre-aug-bal inference-o \n\n[2652 rows x 5 columns]",
"text/html": "<div>\n<style scoped>\n .dataframe tbody tr th:only-of-type {\n vertical-align: middle;\n }\n\n .dataframe tbody tr th {\n vertical-align: top;\n }\n\n .dataframe thead th {\n text-align: right;\n }\n</style>\n<table border=\"1\" class=\"dataframe\">\n <thead>\n <tr style=\"text-align: right;\">\n <th></th>\n <th>song</th>\n <th>stem</th>\n <th>snr</th>\n <th>variant</th>\n <th>inference_mode</th>\n </tr>\n </thead>\n <tbody>\n <tr>\n <th>0</th>\n <td>704f1de9-1d02-4c2b-af05-107a7700a51d</td>\n <td>bass_guitar</td>\n <td>9.033754</td>\n <td>vdbgp-d-pre</td>\n <td>inference-d</td>\n </tr>\n <tr>\n <th>1</th>\n <td>704f1de9-1d02-4c2b-af05-107a7700a51d</td>\n <td>drums</td>\n <td>12.501521</td>\n <td>vdbgp-d-pre</td>\n <td>inference-d</td>\n </tr>\n <tr>\n <th>2</th>\n <td>704f1de9-1d02-4c2b-af05-107a7700a51d</td>\n <td>acoustic_guitar</td>\n <td>1.717476</td>\n <td>vdbgp-d-pre</td>\n <td>inference-d</td>\n </tr>\n <tr>\n <th>3</th>\n <td>704f1de9-1d02-4c2b-af05-107a7700a51d</td>\n <td>lead_male_singer</td>\n <td>7.361787</td>\n <td>vdbgp-d-pre</td>\n <td>inference-d</td>\n </tr>\n <tr>\n <th>4</th>\n <td>8a6c9c1f-4865-404f-a805-1949de36a33c</td>\n <td>lead_female_singer</td>\n <td>13.685509</td>\n <td>vdbgp-d-pre</td>\n <td>inference-d</td>\n </tr>\n <tr>\n <th>...</th>\n <td>...</td>\n <td>...</td>\n <td>...</td>\n <td>...</td>\n <td>...</td>\n </tr>\n <tr>\n <th>2647</th>\n <td>a56d9450-3a26-485c-8ac3-24b6b54e2c1d</td>\n <td>acoustic_guitar</td>\n <td>10.415203</td>\n <td>vdbgp-d-pre-aug-bal</td>\n <td>inference-o</td>\n </tr>\n <tr>\n <th>2648</th>\n <td>1f98fe4d-26c7-460f-9f68-33964bc4d8d3</td>\n <td>distorted_electric_guitar</td>\n <td>4.498278</td>\n <td>vdbgp-d-pre-aug-bal</td>\n <td>inference-o</td>\n </tr>\n <tr>\n <th>2649</th>\n <td>1f98fe4d-26c7-460f-9f68-33964bc4d8d3</td>\n <td>bass_guitar</td>\n <td>8.909531</td>\n <td>vdbgp-d-pre-aug-bal</td>\n <td>inference-o</td>\n </tr>\n <tr>\n <th>2650</th>\n <td>1f98fe4d-26c7-460f-9f68-33964bc4d8d3</td>\n <td>drums</td>\n <td>10.670884</td>\n <td>vdbgp-d-pre-aug-bal</td>\n <td>inference-o</td>\n </tr>\n <tr>\n <th>2651</th>\n <td>1f98fe4d-26c7-460f-9f68-33964bc4d8d3</td>\n <td>lead_male_singer</td>\n <td>1.847866</td>\n <td>vdbgp-d-pre-aug-bal</td>\n <td>inference-o</td>\n </tr>\n </tbody>\n</table>\n<p>2652 rows × 5 columns</p>\n</div>"
},
"execution_count": 60,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df"
],
"metadata": {
"collapsed": false,
"ExecuteTime": {
"end_time": "2024-04-06T00:45:30.158479994Z",
"start_time": "2024-04-06T00:45:30.147710710Z"
}
}
},
{
"cell_type": "code",
"execution_count": 61,
"outputs": [],
"source": [
"df[\"snr\"] = df[\"snr\"].replace(-np.inf, np.nan)"
],
"metadata": {
"collapsed": false,
"ExecuteTime": {
"end_time": "2024-04-06T00:45:30.187430478Z",
"start_time": "2024-04-06T00:45:30.159339419Z"
}
}
},
{
"cell_type": "code",
"execution_count": 62,
"outputs": [],
"source": [
"df.to_csv(os.path.join(INFERENCE_ROOT, \"bandit_vdbgp.csv\"), index=False)"
],
"metadata": {
"collapsed": false,
"ExecuteTime": {
"end_time": "2024-04-06T00:45:30.190577704Z",
"start_time": "2024-04-06T00:45:30.171662355Z"
}
}
},
{
"cell_type": "code",
"execution_count": 194,
"outputs": [],
"source": [
"df = pd.read_csv(os.path.join(INFERENCE_ROOT, \"bandit_vdbgp.csv\"))\n",
"\n",
"stem_dtype = pd.CategoricalDtype(categories=allowed_stems, ordered=True)\n",
"df[\"stem\"] = df[\"stem\"].astype(stem_dtype)\n",
"\n",
"bool_dtype = pd.CategoricalDtype(categories=[\"Y\", \"N\"], ordered=True)\n",
"ibool_dtype = pd.CategoricalDtype(categories=[\"N\", \"Y\"], ordered=True)\n",
"\n",
"df[\"is_frozen\"] = df[\"variant\"].str.contains(\"prefz\").apply(lambda x: \"Y\" if x else \"N\").astype(bool_dtype)\n",
"df[\"is_balanced\"] = df[\"variant\"].str.contains(\"bal\").apply(lambda x: \"Y\" if x else \"N\").astype(ibool_dtype)\n",
"df[\"is_augmented\"] = df[\"variant\"].str.contains(\"aug\").apply(lambda x: \"Y\" if x else \"N\").astype(ibool_dtype)\n",
"df[\"query_same\"] = df[\"inference_mode\"].str.contains(\"-o\").apply(lambda x: \"same\" if x else \"diff.\")"
],
"metadata": {
"collapsed": false,
"ExecuteTime": {
"end_time": "2024-04-08T02:49:07.480294174Z",
"start_time": "2024-04-08T02:49:07.174661559Z"
}
}
},
{
"cell_type": "code",
"execution_count": 195,
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"/tmp/ipykernel_1039573/4175560588.py:10: FutureWarning: The default of observed=False is deprecated and will be changed to True in a future version of pandas. Pass observed=False to retain current behavior or observed=True to adopt the future default and silence this warning.\n",
" dfagg = df.groupby([\n"
]
}
],
"source": [
"def q25(x):\n",
" return x.quantile(0.25)\n",
"\n",
"def q75(x):\n",
" return x.quantile(0.75)\n",
"\n",
"def q50(x):\n",
" return x.quantile(0.5)\n",
"\n",
"dfagg = df.groupby([\n",
" \"is_frozen\",\n",
" \"is_augmented\",\n",
" \"is_balanced\",\n",
" \"query_same\",\n",
" \"stem\"\n",
"]).agg({\"snr\": [q25, q50, q75]})\n",
"dfagg.columns = [\"q25\", \"q50\", \"q75\"]\n",
"dfagg = dfagg.reset_index()\n",
"dfagg = dfagg.reset_index().pivot_table(\n",
" index=[\"is_frozen\", \"is_augmented\", \"is_balanced\", \"query_same\"],\n",
" columns=\"stem\",\n",
" values=[\"q25\", \"q50\", \"q75\"]\n",
")\n"
],
"metadata": {
"collapsed": false,
"ExecuteTime": {
"end_time": "2024-04-08T02:49:09.322104050Z",
"start_time": "2024-04-08T02:49:09.283623798Z"
}
}
},
{
"cell_type": "code",
"execution_count": 196,
"outputs": [
{
"data": {
"text/plain": "stem lead_female_singer \\\n q25 q50 \nis_frozen is_augmented is_balanced query_same \nY N N diff. 7.198664 9.723279 \n same 7.369198 9.691747 \n Y diff. 6.161379 9.097359 \n same 6.250170 9.161142 \nN N N diff. 5.952838 9.630895 \n same 6.257276 9.636968 \n Y N diff. 5.008355 9.851802 \n same 5.147925 9.868163 \n\nstem lead_male_singer \\\n q75 q25 \nis_frozen is_augmented is_balanced query_same \nY N N diff. 12.798156 6.314435 \n same 12.805657 6.613824 \n Y diff. 12.302063 6.114836 \n same 12.315944 5.442377 \nN N N diff. 12.874142 6.463644 \n same 12.874389 6.461676 \n Y N diff. 13.350157 6.362659 \n same 13.350220 6.323971 \n\nstem drums \\\n q50 q75 q25 \nis_frozen is_augmented is_balanced query_same \nY N N diff. 7.357547 9.797291 8.157859 \n same 7.426128 9.785307 8.153814 \n Y diff. 6.884451 8.748042 7.779492 \n same 7.065612 8.892028 7.777564 \nN N N diff. 7.947806 9.908751 7.881636 \n same 7.945579 9.902304 7.845629 \n Y N diff. 8.032614 10.098088 8.560939 \n same 8.017485 10.071638 8.559176 \n\nstem \\\n q50 q75 \nis_frozen is_augmented is_balanced query_same \nY N N diff. 9.804378 11.801135 \n same 9.805333 11.800478 \n Y diff. 8.966419 11.010345 \n same 8.954748 11.022204 \nN N N diff. 9.339234 11.766748 \n same 9.343800 11.762347 \n Y N diff. 9.983489 12.399178 \n same 9.985436 12.399270 \n\nstem bass_guitar ... \\\n q25 ... \nis_frozen is_augmented is_balanced query_same ... \nY N N diff. 8.015215 ... \n same 8.012354 ... \n Y diff. 7.595034 ... \n same 7.557049 ... \nN N N diff. 7.897048 ... \n same 7.902327 ... \n Y N diff. 8.709943 ... \n same 8.710634 ... \n\nstem clean_electric_guitar \\\n q75 \nis_frozen is_augmented is_balanced query_same \nY N N diff. 1.722306 \n same 1.812555 \n Y diff. 1.463174 \n same 1.567352 \nN N N diff. 2.941832 \n same 2.423461 \n Y N diff. 2.095459 \n same 1.868485 \n\nstem distorted_electric_guitar \\\n q25 \nis_frozen is_augmented is_balanced query_same \nY N N diff. 0.604794 \n same 0.503696 \n Y diff. 0.322619 \n same 0.384457 \nN N N diff. 0.903565 \n same 0.653814 \n Y N diff. 0.543903 \n same 0.555051 \n\nstem grand_piano \\\n q50 q75 q25 \nis_frozen is_augmented is_balanced query_same \nY N N diff. 2.584025 4.775978 0.095643 \n same 2.538738 4.548766 -0.103905 \n Y diff. 2.324578 4.031529 -1.498889 \n same 2.235533 4.021377 -1.435887 \nN N N diff. 2.742352 5.189143 0.740644 \n same 2.747163 4.717952 0.744294 \n Y N diff. 2.276117 4.393632 0.479100 \n same 2.258218 4.542683 0.463992 \n\nstem \\\n q50 q75 \nis_frozen is_augmented is_balanced query_same \nY N N diff. 0.943940 2.099960 \n same 0.947414 2.103304 \n Y diff. 0.780164 1.989419 \n same 0.767682 1.977984 \nN N N diff. 2.365721 3.059876 \n same 2.370211 3.079071 \n Y N diff. 1.570971 2.857273 \n same 1.423379 2.961855 \n\nstem electric_piano \\\n q25 q50 \nis_frozen is_augmented is_balanced query_same \nY N N diff. -0.005586 0.215652 \n same 0.247375 0.391507 \n Y diff. -0.054843 0.401561 \n same 0.312920 0.480738 \nN N N diff. 0.136738 0.631473 \n same -0.778946 0.823196 \n Y N diff. 0.000027 0.000667 \n same 0.021866 0.107850 \n\nstem \n q75 \nis_frozen is_augmented is_balanced query_same \nY N N diff. 0.590281 \n same 0.559184 \n Y diff. 0.757468 \n same 0.698899 \nN N N diff. 0.744000 \n same 1.677319 \n Y N diff. 0.202467 \n same 0.135602 \n\n[8 rows x 27 columns]",
"text/html": "<div>\n<style scoped>\n .dataframe tbody tr th:only-of-type {\n vertical-align: middle;\n }\n\n .dataframe tbody tr th {\n vertical-align: top;\n }\n\n .dataframe thead tr th {\n text-align: left;\n }\n\n .dataframe thead tr:last-of-type th {\n text-align: right;\n }\n</style>\n<table border=\"1\" class=\"dataframe\">\n <thead>\n <tr>\n <th></th>\n <th></th>\n <th></th>\n <th>stem</th>\n <th colspan=\"3\" halign=\"left\">lead_female_singer</th>\n <th colspan=\"3\" halign=\"left\">lead_male_singer</th>\n <th colspan=\"3\" halign=\"left\">drums</th>\n <th>bass_guitar</th>\n <th>...</th>\n <th>clean_electric_guitar</th>\n <th colspan=\"3\" halign=\"left\">distorted_electric_guitar</th>\n <th colspan=\"3\" halign=\"left\">grand_piano</th>\n <th colspan=\"3\" halign=\"left\">electric_piano</th>\n </tr>\n <tr>\n <th></th>\n <th></th>\n <th></th>\n <th></th>\n <th>q25</th>\n <th>q50</th>\n <th>q75</th>\n <th>q25</th>\n <th>q50</th>\n <th>q75</th>\n <th>q25</th>\n <th>q50</th>\n <th>q75</th>\n <th>q25</th>\n <th>...</th>\n <th>q75</th>\n <th>q25</th>\n <th>q50</th>\n <th>q75</th>\n <th>q25</th>\n <th>q50</th>\n <th>q75</th>\n <th>q25</th>\n <th>q50</th>\n <th>q75</th>\n </tr>\n <tr>\n <th>is_frozen</th>\n <th>is_augmented</th>\n <th>is_balanced</th>\n <th>query_same</th>\n <th></th>\n <th></th>\n <th></th>\n <th></th>\n <th></th>\n <th></th>\n <th></th>\n <th></th>\n <th></th>\n <th></th>\n <th></th>\n <th></th>\n <th></th>\n <th></th>\n <th></th>\n <th></th>\n <th></th>\n <th></th>\n <th></th>\n <th></th>\n <th></th>\n </tr>\n </thead>\n <tbody>\n <tr>\n <th rowspan=\"4\" valign=\"top\">Y</th>\n <th rowspan=\"4\" valign=\"top\">N</th>\n <th rowspan=\"2\" valign=\"top\">N</th>\n <th>diff.</th>\n <td>7.198664</td>\n <td>9.723279</td>\n <td>12.798156</td>\n <td>6.314435</td>\n <td>7.357547</td>\n <td>9.797291</td>\n <td>8.157859</td>\n <td>9.804378</td>\n <td>11.801135</td>\n <td>8.015215</td>\n <td>...</td>\n <td>1.722306</td>\n <td>0.604794</td>\n <td>2.584025</td>\n <td>4.775978</td>\n <td>0.095643</td>\n <td>0.943940</td>\n <td>2.099960</td>\n <td>-0.005586</td>\n <td>0.215652</td>\n <td>0.590281</td>\n </tr>\n <tr>\n <th>same</th>\n <td>7.369198</td>\n <td>9.691747</td>\n <td>12.805657</td>\n <td>6.613824</td>\n <td>7.426128</td>\n <td>9.785307</td>\n <td>8.153814</td>\n <td>9.805333</td>\n <td>11.800478</td>\n <td>8.012354</td>\n <td>...</td>\n <td>1.812555</td>\n <td>0.503696</td>\n <td>2.538738</td>\n <td>4.548766</td>\n <td>-0.103905</td>\n <td>0.947414</td>\n <td>2.103304</td>\n <td>0.247375</td>\n <td>0.391507</td>\n <td>0.559184</td>\n </tr>\n <tr>\n <th rowspan=\"2\" valign=\"top\">Y</th>\n <th>diff.</th>\n <td>6.161379</td>\n <td>9.097359</td>\n <td>12.302063</td>\n <td>6.114836</td>\n <td>6.884451</td>\n <td>8.748042</td>\n <td>7.779492</td>\n <td>8.966419</td>\n <td>11.010345</td>\n <td>7.595034</td>\n <td>...</td>\n <td>1.463174</td>\n <td>0.322619</td>\n <td>2.324578</td>\n <td>4.031529</td>\n <td>-1.498889</td>\n <td>0.780164</td>\n <td>1.989419</td>\n <td>-0.054843</td>\n <td>0.401561</td>\n <td>0.757468</td>\n </tr>\n <tr>\n <th>same</th>\n <td>6.250170</td>\n <td>9.161142</td>\n <td>12.315944</td>\n <td>5.442377</td>\n <td>7.065612</td>\n <td>8.892028</td>\n <td>7.777564</td>\n <td>8.954748</td>\n <td>11.022204</td>\n <td>7.557049</td>\n <td>...</td>\n <td>1.567352</td>\n <td>0.384457</td>\n <td>2.235533</td>\n <td>4.021377</td>\n <td>-1.435887</td>\n <td>0.767682</td>\n <td>1.977984</td>\n <td>0.312920</td>\n <td>0.480738</td>\n <td>0.698899</td>\n </tr>\n <tr>\n <th rowspan=\"4\" valign=\"top\">N</th>\n <th rowspan=\"2\" valign=\"top\">N</th>\n <th rowspan=\"2\" valign=\"top\">N</th>\n <th>diff.</th>\n <td>5.952838</td>\n <td>9.630895</td>\n <td>12.874142</td>\n <td>6.463644</td>\n <td>7.947806</td>\n <td>9.908751</td>\n <td>7.881636</td>\n <td>9.339234</td>\n <td>11.766748</td>\n <td>7.897048</td>\n <td>...</td>\n <td>2.941832</td>\n <td>0.903565</td>\n <td>2.742352</td>\n <td>5.189143</td>\n <td>0.740644</td>\n <td>2.365721</td>\n <td>3.059876</td>\n <td>0.136738</td>\n <td>0.631473</td>\n <td>0.744000</td>\n </tr>\n <tr>\n <th>same</th>\n <td>6.257276</td>\n <td>9.636968</td>\n <td>12.874389</td>\n <td>6.461676</td>\n <td>7.945579</td>\n <td>9.902304</td>\n <td>7.845629</td>\n <td>9.343800</td>\n <td>11.762347</td>\n <td>7.902327</td>\n <td>...</td>\n <td>2.423461</td>\n <td>0.653814</td>\n <td>2.747163</td>\n <td>4.717952</td>\n <td>0.744294</td>\n <td>2.370211</td>\n <td>3.079071</td>\n <td>-0.778946</td>\n <td>0.823196</td>\n <td>1.677319</td>\n </tr>\n <tr>\n <th rowspan=\"2\" valign=\"top\">Y</th>\n <th rowspan=\"2\" valign=\"top\">N</th>\n <th>diff.</th>\n <td>5.008355</td>\n <td>9.851802</td>\n <td>13.350157</td>\n <td>6.362659</td>\n <td>8.032614</td>\n <td>10.098088</td>\n <td>8.560939</td>\n <td>9.983489</td>\n <td>12.399178</td>\n <td>8.709943</td>\n <td>...</td>\n <td>2.095459</td>\n <td>0.543903</td>\n <td>2.276117</td>\n <td>4.393632</td>\n <td>0.479100</td>\n <td>1.570971</td>\n <td>2.857273</td>\n <td>0.000027</td>\n <td>0.000667</td>\n <td>0.202467</td>\n </tr>\n <tr>\n <th>same</th>\n <td>5.147925</td>\n <td>9.868163</td>\n <td>13.350220</td>\n <td>6.323971</td>\n <td>8.017485</td>\n <td>10.071638</td>\n <td>8.559176</td>\n <td>9.985436</td>\n <td>12.399270</td>\n <td>8.710634</td>\n <td>...</td>\n <td>1.868485</td>\n <td>0.555051</td>\n <td>2.258218</td>\n <td>4.542683</td>\n <td>0.463992</td>\n <td>1.423379</td>\n <td>2.961855</td>\n <td>0.021866</td>\n <td>0.107850</td>\n <td>0.135602</td>\n </tr>\n </tbody>\n</table>\n<p>8 rows × 27 columns</p>\n</div>"
},
"execution_count": 196,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"dfagg = dfagg.swaplevel(axis=1).sort_index(axis=1)\n",
"\n",
"dfagg\n",
"\n"
],
"metadata": {
"collapsed": false,
"ExecuteTime": {
"end_time": "2024-04-08T02:49:12.457737959Z",
"start_time": "2024-04-08T02:49:12.443099451Z"
}
}
},
{
"cell_type": "code",
"execution_count": 191,
"outputs": [],
"source": [
"dfagg_max = dfagg.max(axis=0)"
],
"metadata": {
"collapsed": false,
"ExecuteTime": {
"end_time": "2024-04-06T01:26:04.949522820Z",
"start_time": "2024-04-06T01:26:04.947355962Z"
}
}
},
{
"cell_type": "code",
"execution_count": 192,
"outputs": [],
"source": [
"\n",
"def bold_formatter(x, val):\n",
" if round(x, 1) == round(val, 1):\n",
" return r\"\\bfseries \" + f\"{x:.1f}\"\n",
" return f\"{x:.1f}\"\n",
"\n",
"formatters = {\n",
" (c, d): partial(bold_formatter, val=dfagg_max.loc[c, d])\n",
" for c, d in dfagg.columns\n",
"}"
],
"metadata": {
"collapsed": false,
"ExecuteTime": {
"end_time": "2024-04-06T01:26:05.770492667Z",
"start_time": "2024-04-06T01:26:05.767276008Z"
}
}
},
{
"cell_type": "code",
"execution_count": 193,
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\\begin{tabular}{llllrrrrrrrrrrrrrrrrrrrrrrrrrrr}\n",
"\\toprule\n",
" & & & stem & \\multicolumn{3}{r}{lead_female_singer} & \\multicolumn{3}{r}{lead_male_singer} & \\multicolumn{3}{r}{drums} & \\multicolumn{3}{r}{bass_guitar} & \\multicolumn{3}{r}{acoustic_guitar} & \\multicolumn{3}{r}{clean_electric_guitar} & \\multicolumn{3}{r}{distorted_electric_guitar} & \\multicolumn{3}{r}{grand_piano} & \\multicolumn{3}{r}{electric_piano} \\\\\n",
" & & & & q25 & q50 & q75 & q25 & q50 & q75 & q25 & q50 & q75 & q25 & q50 & q75 & q25 & q50 & q75 & q25 & q50 & q75 & q25 & q50 & q75 & q25 & q50 & q75 & q25 & q50 & q75 \\\\\n",
"is_frozen & is_augmented & is_balanced & query_same & & & & & & & & & & & & & & & & & & & & & & & & & & & \\\\\n",
"\\midrule\n",
"Y & N & N & diff. & 7.2 & 9.6 & 12.8 & 6.4 & 7.6 & 9.9 & 8.2 & 9.8 & 11.8 & 8.1 & 10.1 & 12.1 & 0.4 & 1.5 & 2.4 & 0.1 & 0.5 & 1.6 & 0.6 & 2.7 & 4.9 & -0.3 & 0.8 & 2.4 & 0.2 & 0.5 & 0.9 \\\\\n",
" & & & same & \\bfseries 7.3 & 9.7 & 12.8 & 6.7 & 7.6 & 9.9 & 8.2 & 9.8 & 11.8 & 8.0 & 10.1 & 12.1 & 0.4 & 1.5 & 2.4 & 0.2 & 0.6 & 1.6 & 0.6 & 2.6 & 4.8 & -0.3 & 0.8 & 2.4 & 0.3 & 0.5 & 0.7 \\\\\n",
" & & Y & diff. & 7.0 & 9.4 & 12.2 & 6.5 & 7.4 & 9.8 & 8.1 & 9.6 & 11.5 & 7.9 & 10.2 & 11.9 & 0.3 & 1.5 & 2.5 & 0.1 & 0.5 & 1.7 & 0.5 & 2.7 & 4.9 & -0.2 & 1.0 & 2.2 & 0.1 & 0.5 & 0.8 \\\\\n",
" & & & same & 6.9 & 9.5 & 12.3 & 6.7 & 7.4 & 9.8 & 8.1 & 9.6 & 11.5 & 7.7 & 10.3 & 11.9 & 0.3 & 1.5 & 2.5 & 0.1 & 0.5 & 1.8 & 0.5 & 2.7 & 4.9 & -0.2 & 0.9 & 2.2 & 0.3 & 0.5 & 0.9 \\\\\n",
"N & N & N & diff. & 5.5 & 9.6 & 13.2 & 6.7 & \\bfseries 7.9 & 10.0 & 8.0 & 9.6 & 11.6 & 7.9 & 9.9 & 12.0 & 0.9 & \\bfseries 1.8 & 3.6 & 0.2 & 0.7 & 2.4 & 0.9 & 2.4 & 5.3 & 0.7 & 2.3 & 2.9 & 0.0 & 0.6 & 0.7 \\\\\n",
" & & & same & 5.6 & 9.6 & 13.2 & 6.7 & \\bfseries 7.9 & 10.0 & 8.0 & 9.6 & 11.6 & 7.9 & 9.9 & 12.0 & 0.9 & \\bfseries 1.8 & 3.7 & 0.2 & 0.9 & 2.6 & 0.9 & 2.4 & 5.3 & 0.7 & 2.2 & 3.0 & 0.0 & 0.8 & 1.5 \\\\\n",
" & & Y & diff. & 6.1 & 9.6 & 13.1 & 6.8 & 7.7 & 9.7 & 7.8 & 9.3 & 11.3 & 7.6 & 10.0 & 11.5 & 0.8 & \\bfseries 1.8 & 3.6 & 0.2 & 0.8 & 2.5 & 1.0 & 2.5 & \\bfseries 5.4 & \\bfseries 0.8 & 2.5 & 3.1 & -0.1 & 0.7 & 0.8 \\\\\n",
" & & & same & 6.1 & 9.6 & 13.1 & 6.8 & 7.7 & 9.7 & 7.8 & 9.3 & 11.3 & 7.6 & 10.0 & 11.5 & 0.8 & \\bfseries 1.8 & 3.7 & -0.0 & 0.9 & 2.7 & \\bfseries 1.2 & 2.5 & \\bfseries 5.4 & \\bfseries 0.8 & 2.5 & 3.1 & -0.6 & 0.8 & 1.8 \\\\\n",
" & Y & N & diff. & 5.5 & \\bfseries 10.1 & 13.0 & \\bfseries 6.9 & \\bfseries 7.9 & \\bfseries 10.2 & \\bfseries 8.5 & \\bfseries 10.1 & \\bfseries 12.3 & \\bfseries 8.4 & \\bfseries 10.7 & \\bfseries 13.2 & \\bfseries 1.2 & 1.7 & 4.5 & 0.2 & 0.9 & \\bfseries 3.0 & 0.9 & 2.8 & 4.7 & \\bfseries 0.8 & \\bfseries 2.8 & \\bfseries 3.2 & 0.1 & 0.5 & 0.9 \\\\\n",
" & & & same & 5.5 & \\bfseries 10.1 & 13.1 & \\bfseries 6.9 & \\bfseries 7.9 & \\bfseries 10.2 & \\bfseries 8.5 & \\bfseries 10.1 & \\bfseries 12.3 & \\bfseries 8.4 & \\bfseries 10.7 & \\bfseries 13.2 & \\bfseries 1.2 & 1.7 & \\bfseries 4.6 & 0.2 & \\bfseries 1.1 & 2.7 & 0.9 & 2.8 & 4.7 & \\bfseries 0.8 & 2.4 & 3.1 & -0.1 & 0.6 & 0.9 \\\\\n",
" & & Y & diff. & 5.5 & \\bfseries 10.1 & \\bfseries 13.5 & 6.5 & 7.8 & 10.0 & 8.3 & 9.5 & 11.8 & \\bfseries 8.4 & 10.3 & 12.1 & 1.1 & 1.7 & 3.9 & 0.0 & 0.4 & 2.7 & 0.9 & \\bfseries 3.0 & 4.9 & \\bfseries 0.8 & 2.6 & \\bfseries 3.2 & 0.2 & 0.5 & 0.9 \\\\\n",
" & & & same & 5.5 & \\bfseries 10.1 & \\bfseries 13.5 & 6.5 & 7.8 & 10.0 & 8.3 & 9.5 & 11.8 & 7.8 & 10.3 & 12.1 & 1.0 & 1.7 & 3.9 & \\bfseries 0.3 & 0.6 & 2.7 & 0.6 & \\bfseries 3.0 & 4.8 & \\bfseries 0.8 & 2.5 & \\bfseries 3.2 & \\bfseries 0.6 & \\bfseries 0.9 & \\bfseries 2.1 \\\\\n",
"\\bottomrule\n",
"\\end{tabular}\n",
"\n"
]
}
],
"source": [
"str_ = dfagg.to_latex(\n",
" formatters=formatters,\n",
" sparsify=True,\n",
" multirow=False,\n",
")\n",
"\n",
"print(str_)"
],
"metadata": {
"collapsed": false,
"ExecuteTime": {
"end_time": "2024-04-06T01:26:08.716247171Z",
"start_time": "2024-04-06T01:26:08.716050409Z"
}
}
},
{
"cell_type": "code",
"execution_count": null,
"outputs": [],
"source": [],
"metadata": {
"collapsed": false
}
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 2
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython2",
"version": "2.7.6"
}
},
"nbformat": 4,
"nbformat_minor": 0
}
|