Spaces:
Sleeping
Sleeping
File size: 30,561 Bytes
45a5c11 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 |
{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
"#! pip install -r ../requirements.txt"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
"import pandas as pd"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [],
"source": [
"movies_path = '../data/standard/movies_m10_rich'"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [],
"source": [
"links = pd.read_csv('../data/standard/links.csv', index_col='movieId') # ids do filme y nas plataformas imdb e tmdb, util para enriquecer os dados\n",
"movies = pd.read_csv(movies_path+'.csv', index_col='movieId') # dados do filme y\n",
"ratings = pd.read_csv('../data/reduced/ratings_m10.csv', index_col='movieId') # avaliacao do usuario x pro filme y\n",
"tags = pd.read_csv('../data/standard/tags.csv', index_col='movieId') # n parece mto relevante"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## separação do ano de lançamento"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [],
"source": [
"movies[['title', 'year']] = movies['title'].str.extract('(.+)+\\((\\d+)', expand=True)\n",
"\n",
"movies.head()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [
{
"data": {
"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>tmdbId</th>\n",
" <th>imdbId</th>\n",
" <th>cast</th>\n",
" <th>director</th>\n",
" <th>keywords</th>\n",
" <th>overview</th>\n",
" <th>title</th>\n",
" <th>genres</th>\n",
" <th>year</th>\n",
" </tr>\n",
" <tr>\n",
" <th>movieId</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>117529</th>\n",
" <td>135397</td>\n",
" <td>369610</td>\n",
" <td>Chris Pratt|Bryce Dallas Howard|Irrfan Khan|Vi...</td>\n",
" <td>Colin Trevorrow</td>\n",
" <td>monster|dna|tyrannosaurus rex|velociraptor|island</td>\n",
" <td>Twenty-two years after the events of Jurassic ...</td>\n",
" <td>Jurassic World</td>\n",
" <td>Action|Adventure|Drama|Sci-Fi|Thriller</td>\n",
" <td>2015</td>\n",
" </tr>\n",
" <tr>\n",
" <th>122882</th>\n",
" <td>76341</td>\n",
" <td>1392190</td>\n",
" <td>Tom Hardy|Charlize Theron|Hugh Keays-Byrne|Nic...</td>\n",
" <td>George Miller</td>\n",
" <td>future|chase|post-apocalyptic|dystopia|australia</td>\n",
" <td>An apocalyptic story set in the furthest reach...</td>\n",
" <td>Mad Max: Fury Road</td>\n",
" <td>Action|Adventure|Sci-Fi|Thriller</td>\n",
" <td>2015</td>\n",
" </tr>\n",
" <tr>\n",
" <th>122886</th>\n",
" <td>140607</td>\n",
" <td>2488496</td>\n",
" <td>Harrison Ford|Mark Hamill|Carrie Fisher|Adam D...</td>\n",
" <td>J.J. Abrams</td>\n",
" <td>android|spaceship|jedi|space opera|3d</td>\n",
" <td>Thirty years after defeating the Galactic Empi...</td>\n",
" <td>Star Wars: Episode VII - The Force Awakens</td>\n",
" <td>Action|Adventure|Fantasy|Sci-Fi|IMAX</td>\n",
" <td>2015</td>\n",
" </tr>\n",
" <tr>\n",
" <th>139385</th>\n",
" <td>281957</td>\n",
" <td>1663202</td>\n",
" <td>Leonardo DiCaprio|Tom Hardy|Will Poulter|Domhn...</td>\n",
" <td>Alejandro González Iñárritu</td>\n",
" <td>father-son relationship|rape|based on novel|mo...</td>\n",
" <td>In the 1820s, a frontiersman, Hugh Glass, sets...</td>\n",
" <td>The Revenant</td>\n",
" <td>Adventure|Drama</td>\n",
" <td>2015</td>\n",
" </tr>\n",
" <tr>\n",
" <th>134130</th>\n",
" <td>286217</td>\n",
" <td>3659388</td>\n",
" <td>Matt Damon|Jessica Chastain|Kristen Wiig|Jeff ...</td>\n",
" <td>Ridley Scott</td>\n",
" <td>based on novel|mars|nasa|isolation|botanist</td>\n",
" <td>During a manned mission to Mars, Astronaut Mar...</td>\n",
" <td>The Martian</td>\n",
" <td>Adventure|Drama|Sci-Fi</td>\n",
" <td>2015</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" tmdbId imdbId cast \\\n",
"movieId \n",
"117529 135397 369610 Chris Pratt|Bryce Dallas Howard|Irrfan Khan|Vi... \n",
"122882 76341 1392190 Tom Hardy|Charlize Theron|Hugh Keays-Byrne|Nic... \n",
"122886 140607 2488496 Harrison Ford|Mark Hamill|Carrie Fisher|Adam D... \n",
"139385 281957 1663202 Leonardo DiCaprio|Tom Hardy|Will Poulter|Domhn... \n",
"134130 286217 3659388 Matt Damon|Jessica Chastain|Kristen Wiig|Jeff ... \n",
"\n",
" director \\\n",
"movieId \n",
"117529 Colin Trevorrow \n",
"122882 George Miller \n",
"122886 J.J. Abrams \n",
"139385 Alejandro González Iñárritu \n",
"134130 Ridley Scott \n",
"\n",
" keywords \\\n",
"movieId \n",
"117529 monster|dna|tyrannosaurus rex|velociraptor|island \n",
"122882 future|chase|post-apocalyptic|dystopia|australia \n",
"122886 android|spaceship|jedi|space opera|3d \n",
"139385 father-son relationship|rape|based on novel|mo... \n",
"134130 based on novel|mars|nasa|isolation|botanist \n",
"\n",
" overview \\\n",
"movieId \n",
"117529 Twenty-two years after the events of Jurassic ... \n",
"122882 An apocalyptic story set in the furthest reach... \n",
"122886 Thirty years after defeating the Galactic Empi... \n",
"139385 In the 1820s, a frontiersman, Hugh Glass, sets... \n",
"134130 During a manned mission to Mars, Astronaut Mar... \n",
"\n",
" title \\\n",
"movieId \n",
"117529 Jurassic World \n",
"122882 Mad Max: Fury Road \n",
"122886 Star Wars: Episode VII - The Force Awakens \n",
"139385 The Revenant \n",
"134130 The Martian \n",
"\n",
" genres year \n",
"movieId \n",
"117529 Action|Adventure|Drama|Sci-Fi|Thriller 2015 \n",
"122882 Action|Adventure|Sci-Fi|Thriller 2015 \n",
"122886 Action|Adventure|Fantasy|Sci-Fi|IMAX 2015 \n",
"139385 Adventure|Drama 2015 \n",
"134130 Adventure|Drama|Sci-Fi 2015 "
]
},
"execution_count": 7,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"movies.head()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"genres = movies['genres']\n",
"cast = movies['cast']\n",
"keywords = movies['keywords']\n",
"\n",
"def split_into_list(series):\n",
" return str(series).split('|') \n",
"\n",
"genres = genres.apply(split_into_list)\n",
"cast = cast.apply(split_into_list)\n",
"keywords = keywords.apply(split_into_list)\n",
"\n",
"\n",
"movies['genres'] = genres\n",
"movies['cast'] = cast\n",
"movies['keywords'] = keywords"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [
{
"data": {
"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>tmdbId</th>\n",
" <th>imdbId</th>\n",
" <th>cast</th>\n",
" <th>director</th>\n",
" <th>keywords</th>\n",
" <th>overview</th>\n",
" <th>title</th>\n",
" <th>genres</th>\n",
" <th>year</th>\n",
" </tr>\n",
" <tr>\n",
" <th>movieId</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>117529</th>\n",
" <td>135397</td>\n",
" <td>369610</td>\n",
" <td>[Chris Pratt, Bryce Dallas Howard, Irrfan Khan...</td>\n",
" <td>Colin Trevorrow</td>\n",
" <td>[monster, dna, tyrannosaurus rex, velociraptor...</td>\n",
" <td>Twenty-two years after the events of Jurassic ...</td>\n",
" <td>Jurassic World</td>\n",
" <td>[Action, Adventure, Drama, Sci-Fi, Thriller]</td>\n",
" <td>2015</td>\n",
" </tr>\n",
" <tr>\n",
" <th>122882</th>\n",
" <td>76341</td>\n",
" <td>1392190</td>\n",
" <td>[Tom Hardy, Charlize Theron, Hugh Keays-Byrne,...</td>\n",
" <td>George Miller</td>\n",
" <td>[future, chase, post-apocalyptic, dystopia, au...</td>\n",
" <td>An apocalyptic story set in the furthest reach...</td>\n",
" <td>Mad Max: Fury Road</td>\n",
" <td>[Action, Adventure, Sci-Fi, Thriller]</td>\n",
" <td>2015</td>\n",
" </tr>\n",
" <tr>\n",
" <th>122886</th>\n",
" <td>140607</td>\n",
" <td>2488496</td>\n",
" <td>[Harrison Ford, Mark Hamill, Carrie Fisher, Ad...</td>\n",
" <td>J.J. Abrams</td>\n",
" <td>[android, spaceship, jedi, space opera, 3d]</td>\n",
" <td>Thirty years after defeating the Galactic Empi...</td>\n",
" <td>Star Wars: Episode VII - The Force Awakens</td>\n",
" <td>[Action, Adventure, Fantasy, Sci-Fi, IMAX]</td>\n",
" <td>2015</td>\n",
" </tr>\n",
" <tr>\n",
" <th>139385</th>\n",
" <td>281957</td>\n",
" <td>1663202</td>\n",
" <td>[Leonardo DiCaprio, Tom Hardy, Will Poulter, D...</td>\n",
" <td>Alejandro González Iñárritu</td>\n",
" <td>[father-son relationship, rape, based on novel...</td>\n",
" <td>In the 1820s, a frontiersman, Hugh Glass, sets...</td>\n",
" <td>The Revenant</td>\n",
" <td>[Adventure, Drama]</td>\n",
" <td>2015</td>\n",
" </tr>\n",
" <tr>\n",
" <th>134130</th>\n",
" <td>286217</td>\n",
" <td>3659388</td>\n",
" <td>[Matt Damon, Jessica Chastain, Kristen Wiig, J...</td>\n",
" <td>Ridley Scott</td>\n",
" <td>[based on novel, mars, nasa, isolation, botanist]</td>\n",
" <td>During a manned mission to Mars, Astronaut Mar...</td>\n",
" <td>The Martian</td>\n",
" <td>[Adventure, Drama, Sci-Fi]</td>\n",
" <td>2015</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" tmdbId imdbId cast \\\n",
"movieId \n",
"117529 135397 369610 [Chris Pratt, Bryce Dallas Howard, Irrfan Khan... \n",
"122882 76341 1392190 [Tom Hardy, Charlize Theron, Hugh Keays-Byrne,... \n",
"122886 140607 2488496 [Harrison Ford, Mark Hamill, Carrie Fisher, Ad... \n",
"139385 281957 1663202 [Leonardo DiCaprio, Tom Hardy, Will Poulter, D... \n",
"134130 286217 3659388 [Matt Damon, Jessica Chastain, Kristen Wiig, J... \n",
"\n",
" director \\\n",
"movieId \n",
"117529 Colin Trevorrow \n",
"122882 George Miller \n",
"122886 J.J. Abrams \n",
"139385 Alejandro González Iñárritu \n",
"134130 Ridley Scott \n",
"\n",
" keywords \\\n",
"movieId \n",
"117529 [monster, dna, tyrannosaurus rex, velociraptor... \n",
"122882 [future, chase, post-apocalyptic, dystopia, au... \n",
"122886 [android, spaceship, jedi, space opera, 3d] \n",
"139385 [father-son relationship, rape, based on novel... \n",
"134130 [based on novel, mars, nasa, isolation, botanist] \n",
"\n",
" overview \\\n",
"movieId \n",
"117529 Twenty-two years after the events of Jurassic ... \n",
"122882 An apocalyptic story set in the furthest reach... \n",
"122886 Thirty years after defeating the Galactic Empi... \n",
"139385 In the 1820s, a frontiersman, Hugh Glass, sets... \n",
"134130 During a manned mission to Mars, Astronaut Mar... \n",
"\n",
" title \\\n",
"movieId \n",
"117529 Jurassic World \n",
"122882 Mad Max: Fury Road \n",
"122886 Star Wars: Episode VII - The Force Awakens \n",
"139385 The Revenant \n",
"134130 The Martian \n",
"\n",
" genres year \n",
"movieId \n",
"117529 [Action, Adventure, Drama, Sci-Fi, Thriller] 2015 \n",
"122882 [Action, Adventure, Sci-Fi, Thriller] 2015 \n",
"122886 [Action, Adventure, Fantasy, Sci-Fi, IMAX] 2015 \n",
"139385 [Adventure, Drama] 2015 \n",
"134130 [Adventure, Drama, Sci-Fi] 2015 "
]
},
"execution_count": 9,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"movies.head()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"movies = movies.sort_index()\n",
"movies.index = [i+1 for i in range(len(movies.index.values))]"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"movies['movieId'] = movies.index"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [
{
"data": {
"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>tmdbId</th>\n",
" <th>imdbId</th>\n",
" <th>cast</th>\n",
" <th>director</th>\n",
" <th>keywords</th>\n",
" <th>overview</th>\n",
" <th>title</th>\n",
" <th>genres</th>\n",
" <th>year</th>\n",
" <th>movieId</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>862</td>\n",
" <td>114709</td>\n",
" <td>[Tom Hanks, Tim Allen, Don Rickles, Jim Varney...</td>\n",
" <td>John Lasseter</td>\n",
" <td>[jealousy, toy, boy, friendship, friends]</td>\n",
" <td>Woody the cowboy is young Andy’s favorite to...</td>\n",
" <td>Toy Story</td>\n",
" <td>[Adventure, Animation, Children, Comedy, Fantasy]</td>\n",
" <td>1995</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>8844</td>\n",
" <td>113497</td>\n",
" <td>[Robin Williams, Jonathan Hyde, Kirsten Dunst,...</td>\n",
" <td>Joe Johnston</td>\n",
" <td>[board game, disappearance, based on a childre...</td>\n",
" <td>When siblings Judy and Peter discover an encha...</td>\n",
" <td>Jumanji</td>\n",
" <td>[Adventure, Children, Fantasy]</td>\n",
" <td>1995</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>15602</td>\n",
" <td>113228</td>\n",
" <td>[Walter Matthau, Jack Lemmon, Ann-Margret, Sop...</td>\n",
" <td>Howard Deutch</td>\n",
" <td>[fishing, best friend, duringcreditsstinger, o...</td>\n",
" <td>A family wedding reignites the ancient feud be...</td>\n",
" <td>Grumpier Old Men</td>\n",
" <td>[Comedy, Romance]</td>\n",
" <td>1995</td>\n",
" <td>3</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>11862</td>\n",
" <td>113041</td>\n",
" <td>[Steve Martin, Diane Keaton, Martin Short, Kim...</td>\n",
" <td>Charles Shyer</td>\n",
" <td>[baby, midlife crisis, confidence, aging, daug...</td>\n",
" <td>Just when George Banks has recovered from his ...</td>\n",
" <td>Father of the Bride Part II</td>\n",
" <td>[Comedy]</td>\n",
" <td>1995</td>\n",
" <td>4</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>949</td>\n",
" <td>113277</td>\n",
" <td>[Al Pacino, Robert De Niro, Val Kilmer, Jon Vo...</td>\n",
" <td>Michael Mann</td>\n",
" <td>[gambling, suicide attempt, burglar, booties, ...</td>\n",
" <td>Obsessive master thief, Neil McCauley leads a ...</td>\n",
" <td>Heat</td>\n",
" <td>[Action, Crime, Thriller]</td>\n",
" <td>1995</td>\n",
" <td>5</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2022</th>\n",
" <td>281957</td>\n",
" <td>1663202</td>\n",
" <td>[Leonardo DiCaprio, Tom Hardy, Will Poulter, D...</td>\n",
" <td>Alejandro González Iñárritu</td>\n",
" <td>[father-son relationship, rape, based on novel...</td>\n",
" <td>In the 1820s, a frontiersman, Hugh Glass, sets...</td>\n",
" <td>The Revenant</td>\n",
" <td>[Adventure, Drama]</td>\n",
" <td>2015</td>\n",
" <td>2022</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2023</th>\n",
" <td>273481</td>\n",
" <td>3397884</td>\n",
" <td>[Emily Blunt, Benicio del Toro, Josh Brolin, V...</td>\n",
" <td>Denis Villeneuve</td>\n",
" <td>[mexico, cia, smoking, texas, fbi]</td>\n",
" <td>A young female FBI agent joins a secret CIA op...</td>\n",
" <td>Sicario</td>\n",
" <td>[Crime, Drama, Mystery]</td>\n",
" <td>2015</td>\n",
" <td>2023</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2024</th>\n",
" <td>257211</td>\n",
" <td>2361509</td>\n",
" <td>[Robert De Niro, Anne Hathaway, Rene Russo, An...</td>\n",
" <td>Nancy Meyers</td>\n",
" <td>[intern, woman director]</td>\n",
" <td>70-year-old widower Ben Whittaker has discover...</td>\n",
" <td>The Intern</td>\n",
" <td>[Comedy]</td>\n",
" <td>2015</td>\n",
" <td>2024</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2025</th>\n",
" <td>314365</td>\n",
" <td>1895587</td>\n",
" <td>[Mark Ruffalo, Michael Keaton, Rachel McAdams,...</td>\n",
" <td>Tom McCarthy</td>\n",
" <td>[child abuse, journalism, judge, florida, boston]</td>\n",
" <td>The true story of how The Boston Globe uncover...</td>\n",
" <td>Spotlight</td>\n",
" <td>[Thriller]</td>\n",
" <td>2015</td>\n",
" <td>2025</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2026</th>\n",
" <td>318846</td>\n",
" <td>1596363</td>\n",
" <td>[Christian Bale, Steve Carell, Ryan Gosling, B...</td>\n",
" <td>Adam McKay</td>\n",
" <td>[bank, fraud, biography, wall street, finances]</td>\n",
" <td>The men who made millions from a global econom...</td>\n",
" <td>Big Short, The</td>\n",
" <td>[Drama]</td>\n",
" <td>2015</td>\n",
" <td>2026</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>2026 rows × 10 columns</p>\n",
"</div>"
],
"text/plain": [
" tmdbId imdbId cast \\\n",
"1 862 114709 [Tom Hanks, Tim Allen, Don Rickles, Jim Varney... \n",
"2 8844 113497 [Robin Williams, Jonathan Hyde, Kirsten Dunst,... \n",
"3 15602 113228 [Walter Matthau, Jack Lemmon, Ann-Margret, Sop... \n",
"4 11862 113041 [Steve Martin, Diane Keaton, Martin Short, Kim... \n",
"5 949 113277 [Al Pacino, Robert De Niro, Val Kilmer, Jon Vo... \n",
"... ... ... ... \n",
"2022 281957 1663202 [Leonardo DiCaprio, Tom Hardy, Will Poulter, D... \n",
"2023 273481 3397884 [Emily Blunt, Benicio del Toro, Josh Brolin, V... \n",
"2024 257211 2361509 [Robert De Niro, Anne Hathaway, Rene Russo, An... \n",
"2025 314365 1895587 [Mark Ruffalo, Michael Keaton, Rachel McAdams,... \n",
"2026 318846 1596363 [Christian Bale, Steve Carell, Ryan Gosling, B... \n",
"\n",
" director \\\n",
"1 John Lasseter \n",
"2 Joe Johnston \n",
"3 Howard Deutch \n",
"4 Charles Shyer \n",
"5 Michael Mann \n",
"... ... \n",
"2022 Alejandro González Iñárritu \n",
"2023 Denis Villeneuve \n",
"2024 Nancy Meyers \n",
"2025 Tom McCarthy \n",
"2026 Adam McKay \n",
"\n",
" keywords \\\n",
"1 [jealousy, toy, boy, friendship, friends] \n",
"2 [board game, disappearance, based on a childre... \n",
"3 [fishing, best friend, duringcreditsstinger, o... \n",
"4 [baby, midlife crisis, confidence, aging, daug... \n",
"5 [gambling, suicide attempt, burglar, booties, ... \n",
"... ... \n",
"2022 [father-son relationship, rape, based on novel... \n",
"2023 [mexico, cia, smoking, texas, fbi] \n",
"2024 [intern, woman director] \n",
"2025 [child abuse, journalism, judge, florida, boston] \n",
"2026 [bank, fraud, biography, wall street, finances] \n",
"\n",
" overview \\\n",
"1 Woody the cowboy is young Andy’s favorite to... \n",
"2 When siblings Judy and Peter discover an encha... \n",
"3 A family wedding reignites the ancient feud be... \n",
"4 Just when George Banks has recovered from his ... \n",
"5 Obsessive master thief, Neil McCauley leads a ... \n",
"... ... \n",
"2022 In the 1820s, a frontiersman, Hugh Glass, sets... \n",
"2023 A young female FBI agent joins a secret CIA op... \n",
"2024 70-year-old widower Ben Whittaker has discover... \n",
"2025 The true story of how The Boston Globe uncover... \n",
"2026 The men who made millions from a global econom... \n",
"\n",
" title \\\n",
"1 Toy Story \n",
"2 Jumanji \n",
"3 Grumpier Old Men \n",
"4 Father of the Bride Part II \n",
"5 Heat \n",
"... ... \n",
"2022 The Revenant \n",
"2023 Sicario \n",
"2024 The Intern \n",
"2025 Spotlight \n",
"2026 Big Short, The \n",
"\n",
" genres year movieId \n",
"1 [Adventure, Animation, Children, Comedy, Fantasy] 1995 1 \n",
"2 [Adventure, Children, Fantasy] 1995 2 \n",
"3 [Comedy, Romance] 1995 3 \n",
"4 [Comedy] 1995 4 \n",
"5 [Action, Crime, Thriller] 1995 5 \n",
"... ... ... ... \n",
"2022 [Adventure, Drama] 2015 2022 \n",
"2023 [Crime, Drama, Mystery] 2015 2023 \n",
"2024 [Comedy] 2015 2024 \n",
"2025 [Thriller] 2015 2025 \n",
"2026 [Drama] 2015 2026 \n",
"\n",
"[2026 rows x 10 columns]"
]
},
"execution_count": 17,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"movies"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"movies.to_csv(movies_path+'_pre.csv')"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"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": "3.11.4"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
|