DATA622_FINALPROJECT
John Mazon
5/16/2022
Homework 4 (Final project)
DATA INITIAL SUMMARY
DATA SOURCE: https://www.kaggle.com/datasets/rounakbanik/pokemon
LABELS
ARTS & Entertainment - Earth and Nature - Games - Video Games - Anime - Pop Culture
Data Source
Activity Overview activity stats Views 307518 Downloads 41644 Download per view ratio 0.14 Total unique contributors 157
Description
Context
This dataset contains information on all 802 Pokemon from all Seven Generations of Pokemon. The information contained in this dataset include Base Stats, Performance against Other Types, Height, Weight, Classification, Egg Steps, Experience Points, Abilities, etc. The information was scraped from http://serebii.net/
DATA EXPLORATION
pkm_df <- read.csv("https://raw.githubusercontent.com/johnm1990/DATA622/main/pokemon.csv")
head(pkm_df)## abilities against_bug against_dark against_dragon
## 1 ['Overgrow', 'Chlorophyll'] 1.00 1 1
## 2 ['Overgrow', 'Chlorophyll'] 1.00 1 1
## 3 ['Overgrow', 'Chlorophyll'] 1.00 1 1
## 4 ['Blaze', 'Solar Power'] 0.50 1 1
## 5 ['Blaze', 'Solar Power'] 0.50 1 1
## 6 ['Blaze', 'Solar Power'] 0.25 1 1
## against_electric against_fairy against_fight against_fire against_flying
## 1 0.5 0.5 0.5 2.0 2
## 2 0.5 0.5 0.5 2.0 2
## 3 0.5 0.5 0.5 2.0 2
## 4 1.0 0.5 1.0 0.5 1
## 5 1.0 0.5 1.0 0.5 1
## 6 2.0 0.5 0.5 0.5 1
## against_ghost against_grass against_ground against_ice against_normal
## 1 1 0.25 1 2.0 1
## 2 1 0.25 1 2.0 1
## 3 1 0.25 1 2.0 1
## 4 1 0.50 2 0.5 1
## 5 1 0.50 2 0.5 1
## 6 1 0.25 0 1.0 1
## against_poison against_psychic against_rock against_steel against_water
## 1 1 2 1 1.0 0.5
## 2 1 2 1 1.0 0.5
## 3 1 2 1 1.0 0.5
## 4 1 1 2 0.5 2.0
## 5 1 1 2 0.5 2.0
## 6 1 1 4 0.5 2.0
## attack base_egg_steps base_happiness base_total capture_rate classfication
## 1 49 5120 70 318 45 Seed Pokémon
## 2 62 5120 70 405 45 Seed Pokémon
## 3 100 5120 70 625 45 Seed Pokémon
## 4 52 5120 70 309 45 Lizard Pokémon
## 5 64 5120 70 405 45 Flame Pokémon
## 6 104 5120 70 634 45 Flame Pokémon
## defense experience_growth height_m hp japanese_name name
## 1 49 1059860 0.7 45 Fushigidaneフシギãƒ\200ãƒ\215 Bulbasaur
## 2 63 1059860 1.0 60 Fushigisouフシギソウ Ivysaur
## 3 123 1059860 2.0 80 Fushigibanaフシギãƒ\220ナVenusaur
## 4 43 1059860 0.6 39 Hitokageヒãƒ\210カゲ Charmander
## 5 58 1059860 1.1 58 Lizardoリザード Charmeleon
## 6 78 1059860 1.7 78 Lizardonリザードン Charizard
## percentage_male pokedex_number sp_attack sp_defense speed type1 type2
## 1 88.1 1 65 65 45 grass poison
## 2 88.1 2 80 80 60 grass poison
## 3 88.1 3 122 120 80 grass poison
## 4 88.1 4 60 50 65 fire
## 5 88.1 5 80 65 80 fire
## 6 88.1 6 159 115 100 fire flying
## weight_kg generation is_legendary
## 1 6.9 1 0
## 2 13.0 1 0
## 3 100.0 1 0
## 4 8.5 1 0
## 5 19.0 1 0
## 6 90.5 1 0DATA PREPARATION
glimpse(pkm_df)## Rows: 801
## Columns: 41
## $ abilities <chr> "['Overgrow', 'Chlorophyll']", "['Overgrow', 'Chloro~
## $ against_bug <dbl> 1.00, 1.00, 1.00, 0.50, 0.50, 0.25, 1.00, 1.00, 1.00~
## $ against_dark <dbl> 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1~
## $ against_dragon <dbl> 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1~
## $ against_electric <dbl> 0.5, 0.5, 0.5, 1.0, 1.0, 2.0, 2.0, 2.0, 2.0, 1.0, 1.~
## $ against_fairy <dbl> 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1.0, 1.0, 1.0, 1.0, 1.~
## $ against_fight <dbl> 0.50, 0.50, 0.50, 1.00, 1.00, 0.50, 1.00, 1.00, 1.00~
## $ against_fire <dbl> 2.0, 2.0, 2.0, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 2.0, 2.~
## $ against_flying <dbl> 2.0, 2.0, 2.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 2.0, 2.~
## $ against_ghost <dbl> 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0~
## $ against_grass <dbl> 0.25, 0.25, 0.25, 0.50, 0.50, 0.25, 2.00, 2.00, 2.00~
## $ against_ground <dbl> 1.0, 1.0, 1.0, 2.0, 2.0, 0.0, 1.0, 1.0, 1.0, 0.5, 0.~
## $ against_ice <dbl> 2.0, 2.0, 2.0, 0.5, 0.5, 1.0, 0.5, 0.5, 0.5, 1.0, 1.~
## $ against_normal <dbl> 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1~
## $ against_poison <dbl> 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.~
## $ against_psychic <dbl> 2, 2, 2, 1, 1, 1, 1, 1, 1, 1, 1, 1, 2, 2, 2, 1, 1, 1~
## $ against_rock <dbl> 1, 1, 1, 2, 2, 4, 1, 1, 1, 2, 2, 4, 2, 2, 2, 2, 2, 2~
## $ against_steel <dbl> 1.0, 1.0, 1.0, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1.0, 1.~
## $ against_water <dbl> 0.5, 0.5, 0.5, 2.0, 2.0, 2.0, 0.5, 0.5, 0.5, 1.0, 1.~
## $ attack <int> 49, 62, 100, 52, 64, 104, 48, 63, 103, 30, 20, 45, 3~
## $ base_egg_steps <int> 5120, 5120, 5120, 5120, 5120, 5120, 5120, 5120, 5120~
## $ base_happiness <int> 70, 70, 70, 70, 70, 70, 70, 70, 70, 70, 70, 70, 70, ~
## $ base_total <int> 318, 405, 625, 309, 405, 634, 314, 405, 630, 195, 20~
## $ capture_rate <chr> "45", "45", "45", "45", "45", "45", "45", "45", "45"~
## $ classfication <chr> "Seed Pokémon", "Seed Pokémon", "Seed Pokémon", "~
## $ defense <int> 49, 63, 123, 43, 58, 78, 65, 80, 120, 35, 55, 50, 30~
## $ experience_growth <int> 1059860, 1059860, 1059860, 1059860, 1059860, 1059860~
## $ height_m <dbl> 0.7, 1.0, 2.0, 0.6, 1.1, 1.7, 0.5, 1.0, 1.6, 0.3, 0.~
## $ hp <int> 45, 60, 80, 39, 58, 78, 44, 59, 79, 45, 50, 60, 40, ~
## $ japanese_name <chr> "Fushigidaneフシギãƒ\200ãƒ\215", "Fushigisouフã‚~
## $ name <chr> "Bulbasaur", "Ivysaur", "Venusaur", "Charmander", "C~
## $ percentage_male <dbl> 88.1, 88.1, 88.1, 88.1, 88.1, 88.1, 88.1, 88.1, 88.1~
## $ pokedex_number <int> 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 1~
## $ sp_attack <int> 65, 80, 122, 60, 80, 159, 50, 65, 135, 20, 25, 90, 2~
## $ sp_defense <int> 65, 80, 120, 50, 65, 115, 64, 80, 115, 20, 25, 80, 2~
## $ speed <int> 45, 60, 80, 65, 80, 100, 43, 58, 78, 45, 30, 70, 50,~
## $ type1 <chr> "grass", "grass", "grass", "fire", "fire", "fire", "~
## $ type2 <chr> "poison", "poison", "poison", "", "", "flying", "", ~
## $ weight_kg <dbl> 6.9, 13.0, 100.0, 8.5, 19.0, 90.5, 9.0, 22.5, 85.5, ~
## $ generation <int> 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1~
## $ is_legendary <int> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0~Pre-processing to identify legendary by logical
pkm_df <- pkm_df %>% mutate(is_legendary = as.factor(if_else(is_legendary == 1,
"yes", "no")))We can now check the levels as needed We check for NA
levels(pkm_df$capture_rate)## NULLpkm_df <- pkm_df %>% mutate(capture_rate = if_else(capture_rate == "30 (Meteorite)255 (Core)",
30, as.numeric(capture_rate)), generation = as.factor(generation))## Warning in replace_with(out, !condition, false, fmt_args(~false), glue("length
## of {fmt_args(~condition)}")): NAs introduced by coercioncolSums(is.na(pkm_df))## abilities against_bug against_dark against_dragon
## 0 0 0 0
## against_electric against_fairy against_fight against_fire
## 0 0 0 0
## against_flying against_ghost against_grass against_ground
## 0 0 0 0
## against_ice against_normal against_poison against_psychic
## 0 0 0 0
## against_rock against_steel against_water attack
## 0 0 0 0
## base_egg_steps base_happiness base_total capture_rate
## 0 0 0 0
## classfication defense experience_growth height_m
## 0 0 0 20
## hp japanese_name name percentage_male
## 0 0 0 98
## pokedex_number sp_attack sp_defense speed
## 0 0 0 0
## type1 type2 weight_kg generation
## 0 0 20 0
## is_legendary
## 0Since we see perce_male variable has a few missing value, we will remove them in order to conserver data.
pkm_df2 <- pkm_df %>% select_if(~is.numeric(.)) %>% select(-c(pokedex_number, percentage_male)) %>%
mutate(legendary = pkm_df$is_legendary, name = pkm_df$name) %>% na.omit()
pkm_df1 <- pkm_df2 %>% select(-c(name, legendary))ggplot(pkm_df, aes(base_egg_steps, base_total, color = pkm_df$legendary, size = capture_rate)) +
geom_point(alpha = 0.5) + theme_minimal()## Warning: Use of `pkm_df$legendary` is discouraged. Use `legendary` instead.
pkm_df %>% filter(is_legendary == "no") %>% group_by(type1, type2) %>% summarise(base = mean(base_total)) %>%
ggplot(aes(type1, type2, fill = base)) + scale_fill_viridis_c(option = "B") +
geom_tile(color = "yellow") + theme_minimal()## `summarise()` has grouped output by 'type1'. You can override using the `.groups` argument.
p1 <- ggplot(pkm_df, aes(is_legendary, height_m, fill = is_legendary)) + geom_boxplot(show.legend = F) +
theme_minimal() + labs(title = "Height")
p2 <- ggplot(pkm_df, aes(is_legendary, weight_kg, fill = is_legendary)) + geom_boxplot(show.legend = F) +
theme_minimal() + labs(title = "Weight")
p3 <- ggplot(pkm_df, aes(is_legendary, speed, fill = is_legendary)) + geom_boxplot(show.legend = F) +
theme_minimal() + labs(title = "Speed")
p4 <- ggplot(pkm_df, aes(is_legendary, hp, fill = is_legendary)) + geom_boxplot() +
theme_minimal() + theme(legend.position = "bottom") + labs(title = "Health Point (HP)")
plot_grid(p1, p2, p3, p4)## Warning: Removed 20 rows containing non-finite values (stat_boxplot).
## Warning: Removed 20 rows containing non-finite values (stat_boxplot).
K-MEANS CLUSTERING
using KMEANS method
set.seed(111)
km <- kmeans(pkm_df1, centers = 4)
head(km)## $cluster
## 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 21 22
## 1 1 1 1 1 1 1 1 1 3 3 3 3 3 3 1 1 1 3 3
## 23 24 25 29 30 31 32 33 34 35 36 39 40 41 42 43 44 45 46 47
## 3 3 3 1 1 1 1 1 1 2 2 2 2 3 3 1 1 1 3 3
## 48 49 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71
## 3 3 3 3 3 3 4 4 1 1 1 1 1 1 1 1 1 1 1 1
## 72 73 77 78 79 80 81 82 83 84 85 86 87 90 91 92 93 94 95 96
## 4 4 3 3 3 3 3 3 3 3 3 3 3 4 4 1 1 1 3 3
## 97 98 99 100 101 102 104 106 107 108 109 110 111 112 113 114 115 116 117 118
## 3 3 3 3 3 4 3 3 3 3 3 3 4 4 2 3 3 3 3 3
## 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138
## 3 4 4 3 3 3 3 3 4 4 4 4 4 3 3 3 3 3 3 3
## 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158
## 3 3 3 4 4 4 4 4 4 4 4 4 1 1 1 1 1 1 1 1
## 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178
## 1 1 3 3 3 3 2 2 2 2 3 4 4 3 2 2 2 2 3 3
## 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198
## 1 1 1 1 2 2 3 1 1 1 1 2 1 1 3 3 3 3 3 1
## 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218
## 3 2 3 3 3 3 3 3 1 3 2 2 3 3 1 4 1 3 3 3
## 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238
## 3 4 4 2 3 3 2 4 4 4 4 3 3 3 3 4 2 3 3 3
## 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258
## 3 3 4 2 4 4 4 4 4 4 4 4 1 1 1 1 1 1 1 1
## 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278
## 1 1 3 3 3 3 3 3 3 3 3 1 1 1 1 1 1 1 1 3
## 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298
## 3 4 4 4 3 3 4 4 4 4 4 2 2 2 1 1 1 4 4 2
## 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318
## 3 2 2 1 2 4 4 4 3 3 4 4 3 3 2 4 1 4 4 4
## 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338
## 4 4 4 3 3 3 2 2 2 1 1 1 1 1 2 2 2 4 2 2
## 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358
## 3 3 4 4 3 3 2 2 2 2 2 2 3 1 2 2 2 2 4 2
## 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378
## 1 3 3 3 1 1 1 2 2 2 4 2 4 4 4 4 4 4 4 4
## 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398
## 4 4 4 4 4 4 4 4 1 1 1 1 1 1 1 1 1 1 1 1
## 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418
## 3 3 1 1 1 1 1 1 1 2 2 2 2 3 3 3 1 1 3 3
## 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438
## 3 3 3 3 3 2 4 4 3 3 2 1 2 2 2 3 3 3 3 3
## 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458
## 3 2 1 3 4 4 4 4 1 1 4 4 4 4 3 3 4 2 2 4
## 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478
## 4 4 1 3 3 4 3 3 3 2 3 3 3 1 4 3 4 3 2 3
## 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498
## 3 4 4 4 4 4 4 4 4 4 4 4 4 1 4 4 1 1 1 1
## 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518
## 1 1 1 1 1 3 3 1 1 1 3 3 3 3 3 3 3 3 2 2
## 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538
## 1 1 1 3 3 1 1 1 3 3 3 3 2 1 1 1 1 1 1 3
## 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558
## 3 1 1 1 1 1 1 3 3 3 3 3 1 1 1 1 1 3 3 3
## 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578
## 3 3 3 3 3 3 3 3 3 3 3 1 1 2 2 1 1 1 1 1
## 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598
## 1 3 3 4 4 4 3 3 3 3 3 3 3 3 3 2 3 3 3 3
## 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618
## 1 1 1 4 4 4 3 3 1 1 1 4 4 4 3 3 3 3 3 3
## 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638
## 1 1 3 3 3 3 3 3 4 4 4 4 3 3 4 4 4 4 4 4
## 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658
## 4 4 4 4 4 4 4 4 4 4 4 1 1 1 1 1 1 1 1 1
## 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678
## 3 3 1 1 1 3 3 3 1 1 3 3 3 3 3 3 3 3 3 3
## 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698
## 3 3 3 3 3 3 3 3 3 3 3 3 3 4 4 3 3 3 3 3
## 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718
## 3 3 3 3 4 4 4 4 2 3 3 3 3 3 3 3 3 4 4 4
## 719 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739
## 4 4 1 1 1 1 1 1 1 1 1 3 3 3 3 3 3 3 3 3
## 740 741 742 743 744 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760
## 3 3 3 3 3 2 3 3 3 3 3 3 3 3 3 3 3 3 3 3
## 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780
## 1 1 1 2 4 4 3 3 3 3 2 4 4 1 4 3 3 3 3 3
## 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800
## 3 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4
## 801
## 4
##
## $centers
## against_bug against_dark against_dragon against_electric against_fairy
## 1 1.0954774 1.010050 0.9924623 1.042714 1.012563
## 2 0.8910256 1.096154 0.7820513 1.243590 0.974359
## 3 0.9601563 1.067969 0.9406250 1.092188 1.035937
## 4 0.9904891 1.057065 1.0679348 1.061141 1.245924
## against_fight against_fire against_flying against_ghost against_grass
## 1 1.011307 1.183417 1.381910 0.9472362 0.9120603
## 2 1.048077 1.016026 1.038462 0.9487179 1.1474359
## 3 1.035937 1.216406 1.197656 0.9875000 1.0445312
## 4 1.160326 1.019022 1.074728 1.0353261 1.0353261
## against_ground against_ice against_normal against_poison against_psychic
## 1 1.013819 1.331658 0.9346734 1.0816583 1.0854271
## 2 1.044872 1.038462 0.8076923 1.0256410 0.9487179
## 3 1.110156 1.132031 0.8757812 0.9523438 1.0203125
## 4 1.154891 1.258152 0.8926630 0.9076087 0.9116848
## against_rock against_steel against_water attack base_egg_steps
## 1 1.282663 0.8580402 1.016332 74.82412 5274.372
## 2 1.256410 1.2115385 1.025641 63.43590 5120.000
## 3 1.281250 0.9812500 1.044531 73.19375 5196.000
## 4 1.197011 1.0108696 1.058424 94.66848 13753.043
## base_happiness base_total capture_rate defense experience_growth height_m
## 1 69.02010 410.1558 95.10050 65.90955 1059860.0 0.9442211
## 2 72.62821 393.9487 110.38462 67.87179 743589.7 0.9269231
## 3 69.53125 404.4094 116.79063 70.97500 1000000.0 1.0165625
## 4 50.40761 506.0489 62.58696 86.37500 1279673.9 1.7581522
## hp sp_attack sp_defense speed weight_kg
## 1 64.41709 72.97487 66.00503 66.02513 34.36985
## 2 69.60256 60.84615 74.33333 57.85897 29.45769
## 3 64.50000 66.01875 66.92500 62.79688 48.14000
## 4 82.15761 84.51630 82.15217 76.17935 127.14239
##
## $totss
## [1] 2.045757e+13
##
## $withinss
## [1] 2.051105e+09 6.320885e+11 4.603243e+08 1.988054e+12
##
## $tot.withinss
## [1] 2.622654e+12
##
## $betweenss
## [1] 1.783492e+13PCA
poke_pca <- PCA(pkm_df2 %>% select(-name), scale.unit = T, ncp = 31, graph = F,
quali.sup = 32)
summary(poke_pca)##
## Call:
## PCA(X = pkm_df2 %>% select(-name), scale.unit = T, ncp = 31,
## quali.sup = 32, graph = F)
##
##
## Eigenvalues
## Dim.1 Dim.2 Dim.3 Dim.4 Dim.5 Dim.6 Dim.7
## Variance 5.747 3.540 2.572 2.179 1.921 1.765 1.385
## % of var. 18.538 11.419 8.296 7.028 6.198 5.692 4.469
## Cumulative % of var. 18.538 29.957 38.254 45.282 51.480 57.172 61.641
## Dim.8 Dim.9 Dim.10 Dim.11 Dim.12 Dim.13 Dim.14
## Variance 1.324 1.249 1.103 0.998 0.793 0.756 0.666
## % of var. 4.270 4.028 3.557 3.220 2.557 2.438 2.149
## Cumulative % of var. 65.911 69.939 73.496 76.716 79.273 81.711 83.860
## Dim.15 Dim.16 Dim.17 Dim.18 Dim.19 Dim.20 Dim.21
## Variance 0.634 0.586 0.522 0.456 0.427 0.397 0.326
## % of var. 2.045 1.890 1.683 1.470 1.377 1.281 1.052
## Cumulative % of var. 85.905 87.795 89.479 90.949 92.326 93.607 94.659
## Dim.22 Dim.23 Dim.24 Dim.25 Dim.26 Dim.27 Dim.28
## Variance 0.321 0.305 0.257 0.224 0.189 0.145 0.088
## % of var. 1.035 0.983 0.829 0.723 0.608 0.467 0.283
## Cumulative % of var. 95.695 96.678 97.507 98.230 98.839 99.305 99.589
## Dim.29 Dim.30 Dim.31
## Variance 0.069 0.058 0.000
## % of var. 0.223 0.188 0.000
## Cumulative % of var. 99.812 100.000 100.000
##
## Individuals (the 10 first)
## Dist Dim.1 ctr cos2 Dim.2 ctr cos2
## 1 | 4.247 | -2.048 0.093 0.233 | 1.493 0.081 0.124 |
## 2 | 3.850 | -0.926 0.019 0.058 | 1.735 0.109 0.203 |
## 3 | 5.132 | 2.180 0.106 0.181 | 2.173 0.171 0.179 |
## 4 | 4.058 | -1.563 0.054 0.148 | -1.664 0.100 0.168 |
## 5 | 3.538 | -0.268 0.002 0.006 | -1.385 0.069 0.153 |
## 6 | 6.684 | 2.348 0.123 0.123 | 1.093 0.043 0.027 |
## 7 | 3.573 | -1.558 0.054 0.190 | -0.994 0.036 0.077 |
## 8 | 3.013 | -0.316 0.002 0.011 | -0.736 0.020 0.060 |
## 9 | 4.572 | 2.680 0.160 0.343 | -0.193 0.001 0.002 |
## 10 | 5.183 | -4.493 0.450 0.751 | 0.813 0.024 0.025 |
## Dim.3 ctr cos2
## 1 -1.005 0.050 0.056 |
## 2 -1.088 0.059 0.080 |
## 3 -1.318 0.087 0.066 |
## 4 -0.401 0.008 0.010 |
## 5 -0.488 0.012 0.019 |
## 6 -2.080 0.215 0.097 |
## 7 0.228 0.003 0.004 |
## 8 0.158 0.001 0.003 |
## 9 -0.186 0.002 0.002 |
## 10 -0.516 0.013 0.010 |
##
## Variables (the 10 first)
## Dim.1 ctr cos2 Dim.2 ctr cos2 Dim.3 ctr
## against_bug | -0.021 0.008 0.000 | 0.309 2.699 0.096 | 0.068 0.179
## against_dark | 0.123 0.262 0.015 | -0.181 0.928 0.033 | -0.727 20.578
## against_dragon | 0.170 0.500 0.029 | 0.247 1.717 0.061 | 0.200 1.558
## against_electric | -0.074 0.097 0.006 | -0.025 0.017 0.001 | -0.118 0.541
## against_fairy | 0.147 0.376 0.022 | 0.382 4.129 0.146 | 0.509 10.062
## against_fight | 0.146 0.369 0.021 | -0.329 3.049 0.108 | 0.712 19.731
## against_fire | -0.161 0.449 0.026 | 0.390 4.300 0.152 | -0.268 2.797
## against_flying | -0.251 1.094 0.063 | 0.702 13.934 0.493 | -0.080 0.250
## against_ghost | 0.152 0.403 0.023 | -0.116 0.381 0.013 | -0.755 22.185
## against_grass | 0.078 0.106 0.006 | -0.491 6.821 0.241 | 0.291 3.302
## cos2
## against_bug 0.005 |
## against_dark 0.529 |
## against_dragon 0.040 |
## against_electric 0.014 |
## against_fairy 0.259 |
## against_fight 0.507 |
## against_fire 0.072 |
## against_flying 0.006 |
## against_ghost 0.571 |
## against_grass 0.085 |
##
## Supplementary categories
## Dist Dim.1 cos2 v.test Dim.2 cos2 v.test
## no | 0.479 | -0.432 0.813 -16.157 | -0.086 0.033 -4.120
## yes | 4.941 | 4.455 0.813 16.157 | 0.892 0.033 4.120
## Dim.3 cos2 v.test
## no | 0.054 0.013 3.005 |
## yes | -0.554 0.013 -3.005 |# FIT KMEANS FOR PKM
fit <- kmeans(pkm_df1[,-1], 3, iter.max=1000)
#capture rate barplot
barplot(table(pkm_df1$capture_rate), col="#336699") #plot
#pca <- prcomp(pkm_df1[,-1], scale=TRUE) #principle component analysis
pca_data <- mutate(fortify(pkm_df1), col=fit$cluster)
#We want to examine the cluster memberships for each #observation - see last column
ggplot(pca_data) + geom_point(aes(x=speed, y=height_m, fill=factor(col)),
size=3, col="#7f7f7f", shape=21) + theme_bw(base_family="Helvetica")## Warning in grid.Call(C_stringMetric, as.graphicsAnnot(x$label)): font family not
## found in Windows font database
## Warning in grid.Call(C_stringMetric, as.graphicsAnnot(x$label)): font family not
## found in Windows font database## Warning in grid.Call(C_textBounds, as.graphicsAnnot(x$label), x$x, x$y, : font
## family not found in Windows font database
## Warning in grid.Call(C_textBounds, as.graphicsAnnot(x$label), x$x, x$y, : font
## family not found in Windows font database
## Warning in grid.Call(C_textBounds, as.graphicsAnnot(x$label), x$x, x$y, : font
## family not found in Windows font database
## Warning in grid.Call(C_textBounds, as.graphicsAnnot(x$label), x$x, x$y, : font
## family not found in Windows font database
## Warning in grid.Call(C_textBounds, as.graphicsAnnot(x$label), x$x, x$y, : font
## family not found in Windows font database
## Warning in grid.Call(C_textBounds, as.graphicsAnnot(x$label), x$x, x$y, : font
## family not found in Windows font database
## Warning in grid.Call(C_textBounds, as.graphicsAnnot(x$label), x$x, x$y, : font
## family not found in Windows font database
## Warning in grid.Call(C_textBounds, as.graphicsAnnot(x$label), x$x, x$y, : font
## family not found in Windows font database## Warning in grid.Call.graphics(C_text, as.graphicsAnnot(x$label), x$x, x$y, :
## font family not found in Windows font database## Warning in grid.Call(C_textBounds, as.graphicsAnnot(x$label), x$x, x$y, : font
## family not found in Windows font database
## Warning in grid.Call(C_textBounds, as.graphicsAnnot(x$label), x$x, x$y, : font
## family not found in Windows font database
NICE CLUSTER VISUALIZATION OF X AXIS OF SPEED AND Y-AXIS OF HEIGHT_M
PCA Visualize variance
fviz_eig(poke_pca, ncp = 15, addlabels = T, main = "Variance explained by each dimensions")
This is so you can see that we can segment/extr. the values of PC1 to PC13 for new data frame. If needed can be used to demonstrate supervised learning
df_pca <- data.frame(poke_pca$ind$coord[, 1:13]) %>% bind_cols(cluster = as.factor(km$cluster)) %>%
select(cluster, 1:13)
head(df_pca)## cluster Dim.1 Dim.2 Dim.3 Dim.4 Dim.5 Dim.6
## 1 1 -2.0482689 1.492719 -1.0045448 0.286136546 1.26207290 -1.4101871
## 2 1 -0.9261837 1.735385 -1.0879066 0.004112326 1.49529970 -1.0978834
## 3 1 2.1803303 2.173474 -1.3182468 -0.435886223 2.32994924 -0.4853144
## 4 1 -1.5633020 -1.663909 -0.4007239 -1.503710041 -0.26792880 -0.6871526
## 5 1 -0.2678436 -1.385088 -0.4884444 -1.814505168 -0.02738300 -0.3548355
## 6 1 2.3480258 1.093030 -2.0803618 -4.421165007 -0.09279685 0.3653839
## Dim.7 Dim.8 Dim.9 Dim.10 Dim.11 Dim.12
## 1 1.2486080 -0.65081332 -0.4836803 0.07307885 0.3195961 -0.5758634
## 2 1.4996984 -0.49281827 -0.5863074 -0.10586181 0.3463365 -0.5161645
## 3 2.0748878 -0.31191269 -0.2724118 -0.80905749 0.4415624 -0.7678341
## 4 -0.5432244 -0.06761517 -1.7412878 0.58487637 0.5462090 -0.5795146
## 5 -0.2712232 0.09403477 -1.8069230 0.43192314 0.7010062 -0.5202674
## 6 -1.5763563 1.60696746 -0.7618889 -0.34817371 0.8695344 -0.4785768
## Dim.13
## 1 -0.02173397
## 2 -0.10239078
## 3 0.09489559
## 4 0.73142011
## 5 0.57696354
## 6 1.01798043theme_set(theme_bw())
h.pcaScores <- data.frame(df_pca[, 1:3]) # we only need the first two principal components
ggplot(h.pcaScores, aes(y = Dim.1, x = Dim.2)) + geom_point(col = 'tomato2')
From a set of p=7 features, we have now plotted our pkm data into a low-dimensional scatter plot where essentially p=2. You can see some clusters within this scatter plot, although they are not too apparent.
TREES
CLASSIFICATION
pkm_df_x = pkm_df[3:8]
class.tree <- rpart(against_dark ~ ., data = pkm_df_x,
control = rpart.control(maxdepth = 2, minsplit = 10), method = "class")
class.tree## n= 801
##
## node), split, n, loss, yval, (yprob)
## * denotes terminal node
##
## 1) root 801 236 1 (0.0037 0.16 0.71 0.13 0.0025)
## 2) against_fairy>=1.5 112 44 0.5 (0.027 0.61 0.34 0.027 0)
## 4) against_dragon< 1.5 72 10 0.5 (0.042 0.86 0.097 0 0) *
## 5) against_dragon>=1.5 40 9 1 (0 0.15 0.78 0.075 0) *
## 3) against_fairy< 1.5 689 162 1 (0 0.084 0.76 0.15 0.0029)
## 6) against_dragon< 0.25 47 7 0.5 (0 0.85 0.15 0 0) *
## 7) against_dragon>=0.25 642 122 1 (0 0.028 0.81 0.16 0.0031) *prp(class.tree, type = 1, extra = 1, split.font = 1, varlen = -10) 
pkm_df_x$against_dark = factor(pkm_df_x$against_dark, levels = c(0, 1))library(caTools)
set.seed(123)
split = sample.split(pkm_df_x$against_dark, SplitRatio = 0.75)
training_set = subset(pkm_df_x, split == TRUE)
test_set = subset(pkm_df_x, split == FALSE)library(rpart)
classifier = rpart(formula = against_dragon ~ .,
data = training_set)plot(classifier)
text(classifier)
CONCLUSION
We can pull some conclusions regarding our dataset based on the previous cluster and principle component analysis. For example, we can separate our data into at least 4 clusters based on all of the numerical features, with more than 87% of the total sum of squares come from the distance of observations between clusters. Also note Cluster 2 has the unique traits that it has the most (if not all) of the legendary Pokemon, which make it the best overall in base_total battle stats. We can reduce our dimensions from 31 features into just 13 dimensions and still retain more than 80% of the variances using PCA. The dimensionality reduction can be useful if we apply the new PCA for machine learning applications. Moreover, However, as we have seen, the dimensionality reduction is not enough for us to visualize the clustering of our data, indicated by overlapping of clusters if we only use the first 2 dimensions. Perhaps the result from the gap statistic method is true, that there is only 1 big cluster