DBSCAN Clustering
Dynasty
2022-07-21
DBSCAN Clustering
Performing DBSCAN Clustering on the given IRIS Data set.
loading library necessary
library("dbscan")## Warning: package 'dbscan' was built under R version 4.1.3Loading the data set
library(data.table)## Warning: package 'data.table' was built under R version 4.1.2m<-read.csv("http://bit.ly/IrisDataset")
head(m)## sepal_length sepal_width petal_length petal_width species
## 1 5.1 3.5 1.4 0.2 Iris-setosa
## 2 4.9 3.0 1.4 0.2 Iris-setosa
## 3 4.7 3.2 1.3 0.2 Iris-setosa
## 4 4.6 3.1 1.5 0.2 Iris-setosa
## 5 5.0 3.6 1.4 0.2 Iris-setosa
## 6 5.4 3.9 1.7 0.4 Iris-setosaRemoving class labels
m1<-m[,c(1,2,3,4)]
head(m1)## sepal_length sepal_width petal_length petal_width
## 1 5.1 3.5 1.4 0.2
## 2 4.9 3.0 1.4 0.2
## 3 4.7 3.2 1.3 0.2
## 4 4.6 3.1 1.5 0.2
## 5 5.0 3.6 1.4 0.2
## 6 5.4 3.9 1.7 0.4Applying our DBSCAN algorithm. We want minimum 4 points with in a distance of eps(0.4)
db<-dbscan(m1,eps=0.4,MinPts = 4)## Warning in dbscan(m1, eps = 0.4, MinPts = 4): converting argument MinPts (fpc)
## to minPts (dbscan)!Printing out the clustering results
print(db)## DBSCAN clustering for 150 objects.
## Parameters: eps = 0.4, minPts = 4
## The clustering contains 4 cluster(s) and 25 noise points.
##
## 0 1 2 3 4
## 25 47 38 36 4
##
## Available fields: cluster, eps, minPtsPlotting our clusters
hullplot(m1,db$cluster)
Challenge 1
Loading the data set
library(data.table)
df1 <- fread("http://bit.ly/MSDBSCANClusteringDataset")
head(df1)## Area Per Comp Len Wid As_Co Gr_Len Label
## 1: 15.26 14.84 0.8710 5.763 3.312 2.221 5.220 1
## 2: 14.88 14.57 0.8811 5.554 3.333 1.018 4.956 1
## 3: 14.29 14.09 0.9050 5.291 3.337 2.699 4.825 1
## 4: 13.84 13.94 0.8955 5.324 3.379 2.259 4.805 1
## 5: 16.14 14.99 0.9034 5.658 3.562 1.355 5.175 1
## 6: 14.38 14.21 0.8951 5.386 3.312 2.462 4.956 1anyNA(df1)## [1] FALSE- Removing class labels
df11<-df1[,c(1,2,3,4,5,6,7)]
head(df11)## Area Per Comp Len Wid As_Co Gr_Len
## 1: 15.26 14.84 0.8710 5.763 3.312 2.221 5.220
## 2: 14.88 14.57 0.8811 5.554 3.333 1.018 4.956
## 3: 14.29 14.09 0.9050 5.291 3.337 2.699 4.825
## 4: 13.84 13.94 0.8955 5.324 3.379 2.259 4.805
## 5: 16.14 14.99 0.9034 5.658 3.562 1.355 5.175
## 6: 14.38 14.21 0.8951 5.386 3.312 2.462 4.956- Applying our DBSCAN algorithm. We want minimum 4 points with in a distance of eps(0.4)
db<-dbscan(df11,eps=0.4,MinPts = 4)## Warning in dbscan(df11, eps = 0.4, MinPts = 4): converting argument MinPts (fpc)
## to minPts (dbscan)!- Printing out the clustering results
print(db)## DBSCAN clustering for 210 objects.
## Parameters: eps = 0.4, minPts = 4
## The clustering contains 10 cluster(s) and 153 noise points.
##
## 0 1 2 3 4 5 6 7 8 9 10
## 153 6 4 4 11 4 6 8 6 4 4
##
## Available fields: cluster, eps, minPts- Plotting our clusters
hullplot(df11,db$cluster)## Warning in hullplot(df11, db$cluster): Not enough colors. Some colors will be
## reused.
Challenge 2
Loading the data set
library(data.table)
df2 <- fread("http://bit.ly/MSDBSCANClusteringDataset2")
head(df2)## MMSI SOG Longitude Latitude COG
## 1: 1 0.0 -14.61289 8.368005 3.4
## 2: 1 0.0 -14.61285 8.368035 359.8
## 3: 1 0.0 -14.61285 8.368033 357.8
## 4: 2 11.5 -14.00422 8.250355 116.0
## 5: 1 0.0 -14.61284 8.368013 356.6
## 6: 2 11.6 -14.00360 8.250152 116.0anyNA(df2)## [1] FALSE- Removing class labels
df21<-df2[,c(2,3,4,5)]
head(df21)## SOG Longitude Latitude COG
## 1: 0.0 -14.61289 8.368005 3.4
## 2: 0.0 -14.61285 8.368035 359.8
## 3: 0.0 -14.61285 8.368033 357.8
## 4: 11.5 -14.00422 8.250355 116.0
## 5: 0.0 -14.61284 8.368013 356.6
## 6: 11.6 -14.00360 8.250152 116.0- Applying our DBSCAN algorithm. We want minimum 4 points with in a distance of eps(0.4)
db<-dbscan(df21,eps=0.4,MinPts = 4)## Warning in dbscan(df21, eps = 0.4, MinPts = 4): converting argument MinPts (fpc)
## to minPts (dbscan)!- Printing out the clustering results
print(db)## DBSCAN clustering for 81159 objects.
## Parameters: eps = 0.4, minPts = 4
## The clustering contains 860 cluster(s) and 5783 noise points.
##
## 0 1 2 3 4 5 6 7 8 9 10 11 12
## 5783 3743 2644 20748 2205 81 1573 21856 18 16 28 10 41
## 13 14 15 16 17 18 19 20 21 22 23 24 25
## 639 10 5998 18 43 29 4 5301 7 8 14 33 5
## 26 27 28 29 30 31 32 33 34 35 36 37 38
## 10 33 159 170 69 86 17 70 52 5 4 11 43
## 39 40 41 42 43 44 45 46 47 48 49 50 51
## 6 33 53 11 84 43 8 5 24 44 24 260 34
## 52 53 54 55 56 57 58 59 60 61 62 63 64
## 105 13 7 4 61 42 5 4 11 4 46 56 5
## 65 66 67 68 69 70 71 72 73 74 75 76 77
## 39 21 11 8 8 21 150 5 7 17 11 20 5
## 78 79 80 81 82 83 84 85 86 87 88 89 90
## 12 17 7 99 33 8 5 8 92 4 85 4 4
## 91 92 93 94 95 96 97 98 99 100 101 102 103
## 7 6 9 23 10 5 5 4 5 7 4 56 9
## 104 105 106 107 108 109 110 111 112 113 114 115 116
## 7 9 8 4 5 17 17 18 13 11 14 6 10
## 117 118 119 120 121 122 123 124 125 126 127 128 129
## 13 25 4 4 4 4 9 10 6 9 9 41 11
## 130 131 132 133 134 135 136 137 138 139 140 141 142
## 5 5 4 44 56 16 4 36 5 8 12 5 8
## 143 144 145 146 147 148 149 150 151 152 153 154 155
## 4 22 7 5 9 13 5 20 9 9 5 5 6
## 156 157 158 159 160 161 162 163 164 165 166 167 168
## 4 9 10 8 6 4 9 13 4 4 8 12 8
## 169 170 171 172 173 174 175 176 177 178 179 180 181
## 10 10 5 47 19 46 14 5 31 5 5 21 6
## 182 183 184 185 186 187 188 189 190 191 192 193 194
## 13 18 5 8 10 49 8 5 14 19 11 5 7
## 195 196 197 198 199 200 201 202 203 204 205 206 207
## 7 5 7 6 4 6 5 11 14 26 153 14 8
## 208 209 210 211 212 213 214 215 216 217 218 219 220
## 9 12 5 4 4 26 14 5 6 16 24 14 18
## 221 222 223 224 225 226 227 228 229 230 231 232 233
## 7 11 14 8 6 9 7 11 13 6 15 10 11
## 234 235 236 237 238 239 240 241 242 243 244 245 246
## 4 10 4 4 5 6 4 7 7 19 106 4 8
## 247 248 249 250 251 252 253 254 255 256 257 258 259
## 5 4 5 7 4 34 6 6 10 63 20 8 11
## 260 261 262 263 264 265 266 267 268 269 270 271 272
## 6 6 5 9 14 4 12 53 4 5 19 7 6
## 273 274 275 276 277 278 279 280 281 282 283 284 285
## 5 83 7 50 30 10 4 25 4 4 11 4 11
## 286 287 288 289 290 291 292 293 294 295 296 297 298
## 13 17 27 6 71 20 4 13 6 12 11 7 74
## 299 300 301 302 303 304 305 306 307 308 309 310 311
## 4 7 15 4 30 5 4 14 55 17 10 4 6
## 312 313 314 315 316 317 318 319 320 321 322 323 324
## 9 4 86 5 12 9 9 4 24 10 9 34 4
## 325 326 327 328 329 330 331 332 333 334 335 336 337
## 34 10 4 11 16 5 4 33 18 6 4 6 6
## 338 339 340 341 342 343 344 345 346 347 348 349 350
## 15 4 10 10 5 30 7 11 7 21 18 6 16
## 351 352 353 354 355 356 357 358 359 360 361 362 363
## 8 4 5 4 14 10 27 23 5 10 21 3 6
## 364 365 366 367 368 369 370 371 372 373 374 375 376
## 15 19 16 8 4 7 9 7 6 5 5 18 14
## 377 378 379 380 381 382 383 384 385 386 387 388 389
## 5 21 5 14 17 15 8 9 4 12 4 7 66
## 390 391 392 393 394 395 396 397 398 399 400 401 402
## 5 14 17 13 4 4 10 42 17 12 4 8 4
## 403 404 405 406 407 408 409 410 411 412 413 414 415
## 37 5 5 5 4 9 5 4 4 10 5 4 13
## 416 417 418 419 420 421 422 423 424 425 426 427 428
## 8 13 60 5 4 4 4 16 4 4 9 5 4
## 429 430 431 432 433 434 435 436 437 438 439 440 441
## 4 4 8 7 5 12 18 6 5 34 106 6 6
## 442 443 444 445 446 447 448 449 450 451 452 453 454
## 9 4 4 5 4 4 4 5 4 4 4 4 5
## 455 456 457 458 459 460 461 462 463 464 465 466 467
## 10 4 87 4 5 10 4 7 35 7 4 5 4
## 468 469 470 471 472 473 474 475 476 477 478 479 480
## 7 4 5 6 4 5 4 4 8 13 5 37 4
## 481 482 483 484 485 486 487 488 489 490 491 492 493
## 4 6 4 6 8 4 21 7 12 10 23 18 5
## 494 495 496 497 498 499 500 501 502 503 504 505 506
## 5 4 4 5 4 4 4 4 4 5 8 5 6
## 507 508 509 510 511 512 513 514 515 516 517 518 519
## 5 8 17 7 7 8 15 9 9 7 4 19 19
## 520 521 522 523 524 525 526 527 528 529 530 531 532
## 4 7 5 4 7 6 6 8 4 32 6 6 6
## 533 534 535 536 537 538 539 540 541 542 543 544 545
## 5 5 16 11 4 4 4 16 10 9 4 5 4
## 546 547 548 549 550 551 552 553 554 555 556 557 558
## 4 4 5 5 5 5 4 4 6 15 6 4 5
## 559 560 561 562 563 564 565 566 567 568 569 570 571
## 4 4 10 14 17 4 9 4 4 4 16 6 6
## 572 573 574 575 576 577 578 579 580 581 582 583 584
## 4 28 22 4 9 6 4 4 4 7 7 15 13
## 585 586 587 588 589 590 591 592 593 594 595 596 597
## 12 8 45 94 4 5 4 6 46 11 5 5 4
## 598 599 600 601 602 603 604 605 606 607 608 609 610
## 10 5 78 7 5 6 6 20 8 18 5 8 8
## 611 612 613 614 615 616 617 618 619 620 621 622 623
## 3 4 6 4 4 6 5 18 5 4 8 6 4
## 624 625 626 627 628 629 630 631 632 633 634 635 636
## 25 8 7 6 4 4 6 9 5 4 7 6 9
## 637 638 639 640 641 642 643 644 645 646 647 648 649
## 4 4 5 4 16 8 9 6 14 4 4 4 5
## 650 651 652 653 654 655 656 657 658 659 660 661 662
## 4 4 6 4 4 21 4 19 32 4 5 3 8
## 663 664 665 666 667 668 669 670 671 672 673 674 675
## 10 6 8 6 4 4 6 8 4 4 4 7 4
## 676 677 678 679 680 681 682 683 684 685 686 687 688
## 4 11 12 13 5 5 5 5 6 5 4 7 12
## 689 690 691 692 693 694 695 696 697 698 699 700 701
## 10 7 5 4 4 13 4 10 5 7 4 5 5
## 702 703 704 705 706 707 708 709 710 711 712 713 714
## 4 5 6 8 5 4 4 4 4 5 4 6 6
## 715 716 717 718 719 720 721 722 723 724 725 726 727
## 9 4 20 11 4 4 5 8 4 4 7 8 8
## 728 729 730 731 732 733 734 735 736 737 738 739 740
## 4 5 4 4 7 7 8 4 7 4 4 7 6
## 741 742 743 744 745 746 747 748 749 750 751 752 753
## 14 6 10 7 4 4 4 12 4 4 10 4 4
## 754 755 756 757 758 759 760 761 762 763 764 765 766
## 4 10 4 4 8 4 4 4 4 7 6 6 4
## 767 768 769 770 771 772 773 774 775 776 777 778 779
## 5 12 4 5 6 5 12 5 4 5 3 4 4
## 780 781 782 783 784 785 786 787 788 789 790 791 792
## 4 7 4 4 8 4 4 4 4 8 7 4 4
## 793 794 795 796 797 798 799 800 801 802 803 804 805
## 5 4 4 4 6 11 15 8 4 20 18 8 4
## 806 807 808 809 810 811 812 813 814 815 816 817 818
## 4 4 4 4 4 6 4 4 10 6 6 4 8
## 819 820 821 822 823 824 825 826 827 828 829 830 831
## 4 4 13 11 6 3 5 6 5 4 4 4 4
## 832 833 834 835 836 837 838 839 840 841 842 843 844
## 4 4 5 4 5 4 6 6 6 18 7 7 15
## 845 846 847 848 849 850 851 852 853 854 855 856 857
## 5 4 7 5 7 5 13 4 2 5 6 32 4
## 858 859 860
## 5 4 4
##
## Available fields: cluster, eps, minPts- Plotting our clusters
hullplot(df21,db$cluster)## Warning in hullplot(df21, db$cluster): Not enough colors. Some colors will be
## reused.
Challenge 3
Loading the data set
library(data.table)
df3 <- fread("http://bit.ly/MSDBSCANClusteringDataset3")
head(df3)## V1 V2
## 1: 0.000000 1.0000000
## 2: 8.622185 1.9357958
## 3: -4.736710 -7.9709577
## 4: 9.621222 0.9254231
## 5: 6.162095 -0.2732544
## 6: 8.697488 -1.0574521anyNA(df3)## [1] FALSE- Applying our DBSCAN algorithm. We want minimum 4 points with in a distance of eps(0.4)
db<-dbscan(df3,eps=0.4,MinPts = 4)## Warning in dbscan(df3, eps = 0.4, MinPts = 4): converting argument MinPts (fpc)
## to minPts (dbscan)!- Printing out the clustering results
print(db)## DBSCAN clustering for 1001 objects.
## Parameters: eps = 0.4, minPts = 4
## The clustering contains 4 cluster(s) and 66 noise points.
##
## 0 1 2 3 4
## 66 310 308 312 5
##
## Available fields: cluster, eps, minPts- Plotting our clusters
hullplot(df3,db$cluster)