Class Scripts Feb20_Idris
Idris Yusuf
2024-02-21
R Markdown
This is an R Markdown document. Markdown is a simple formatting syntax for authoring HTML, PDF, and MS Word documents. For more details on using R Markdown see http://rmarkdown.rstudio.com.
When you click the Knit button a document will be generated that includes both content as well as the output of any embedded R code chunks within the document. You can embed an R code chunk like this:
Including Plots
You can also embed plots, for example:
set.seed(1234)
data('iris')
View(iris)
randDat <- matrix(rnorm(50), nrow=5)
randDat## [,1] [,2] [,3] [,4] [,5] [,6]
## [1,] -1.2070657 0.5060559 -0.47719270 -0.1102855 0.1340882 -1.4482049
## [2,] 0.2774292 -0.5747400 -0.99838644 -0.5110095 -0.4906859 0.5747557
## [3,] 1.0844412 -0.5466319 -0.77625389 -0.9111954 -0.4405479 -1.0236557
## [4,] -2.3456977 -0.5644520 0.06445882 -0.8371717 0.4595894 -0.0151383
## [5,] 0.4291247 -0.8900378 0.95949406 2.4158352 -0.6937202 -0.9359486
## [,7] [,8] [,9] [,10]
## [1,] 1.1022975 -1.1676193 1.4494963 -0.9685143
## [2,] -0.4755931 -2.1800396 -1.0686427 -1.1073182
## [3,] -0.7094400 -1.3409932 -0.8553646 -1.2519859
## [4,] -0.5012581 -0.2942939 -0.2806230 -0.5238281
## [5,] -1.6290935 -0.4658975 -0.9943401 -0.4968500dist(randDat) # Euclidean distance (default) ## 1 2 3 4
## 2 4.261667
## 3 4.038030 2.060117
## 4 3.456732 3.726399 4.037978
## 5 5.307253 4.415046 4.111230 4.814393dist(randDat, method ='manhattan') # manhattan distance## 1 2 3 4
## 2 11.382197
## 3 10.016795 4.536827
## 4 9.887932 8.845512 8.829131
## 5 14.683770 10.617871 9.091241 11.362705dist(randDat, method = 'minkowski', p= 4)## 1 2 3 4
## 2 2.899494
## 3 2.875467 1.653824
## 4 2.208297 2.814135 3.453336
## 5 3.488531 3.192217 3.398721 3.643788d <- dist(scale(iris[,-5]))
h <- hclust(d)
h##
## Call:
## hclust(d = d)
##
## Cluster method : complete
## Distance : euclidean
## Number of objects: 150plot(h)
plot(h, hang=-0.1, labels=iris[["Species"]], cex=0.5)
c <- cutree(h,3)
c## [1] 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1
## [38] 1 1 1 1 2 1 1 1 1 1 1 1 1 3 3 3 2 3 2 3 2 3 2 2 3 2 3 3 3 3 2 2 2 3 3 3 3
## [75] 3 3 3 3 3 2 2 2 2 3 3 3 3 2 3 2 2 3 2 2 2 3 3 3 2 2 3 3 3 3 3 3 2 3 3 3 3
## [112] 3 3 3 3 3 3 3 3 2 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3
## [149] 3 3(cm <- table(c, iris$Species))##
## c setosa versicolor virginica
## 1 49 0 0
## 2 1 21 2
## 3 0 29 48Error <- 100*(1-sum(diag(cm))/sum(cm))
Error## [1] 21.33333library(cluster)
silhouette(c, d)## cluster neighbor sil_width
## [1,] 1 2 0.74381061
## [2,] 1 2 0.52251215
## [3,] 1 2 0.66073019
## [4,] 1 2 0.58819251
## [5,] 1 2 0.74002653
## [6,] 1 2 0.63964608
## [7,] 1 2 0.69599504
## [8,] 1 2 0.73518521
## [9,] 1 2 0.41172906
## [10,] 1 2 0.60436547
## [11,] 1 2 0.69419410
## [12,] 1 2 0.72329651
## [13,] 1 2 0.53223683
## [14,] 1 2 0.49535416
## [15,] 1 3 0.57762368
## [16,] 1 3 0.46169664
## [17,] 1 2 0.64765800
## [18,] 1 2 0.73950603
## [19,] 1 2 0.61735113
## [20,] 1 2 0.69713933
## [21,] 1 2 0.67059935
## [22,] 1 2 0.70888740
## [23,] 1 2 0.70027595
## [24,] 1 2 0.63966308
## [25,] 1 2 0.70331638
## [26,] 1 2 0.49852786
## [27,] 1 2 0.71129988
## [28,] 1 2 0.73277924
## [29,] 1 2 0.72073892
## [30,] 1 2 0.65104081
## [31,] 1 2 0.59701883
## [32,] 1 2 0.66005618
## [33,] 1 2 0.61396099
## [34,] 1 3 0.56172259
## [35,] 1 2 0.60158592
## [36,] 1 2 0.66343730
## [37,] 1 2 0.67907313
## [38,] 1 2 0.73344514
## [39,] 1 2 0.49893006
## [40,] 1 2 0.73032162
## [41,] 1 2 0.74223204
## [42,] 2 1 0.11505796
## [43,] 1 2 0.61310051
## [44,] 1 2 0.67752577
## [45,] 1 2 0.67266764
## [46,] 1 2 0.51096571
## [47,] 1 2 0.69769140
## [48,] 1 2 0.64717198
## [49,] 1 2 0.70772044
## [50,] 1 2 0.70821522
## [51,] 3 2 0.44810916
## [52,] 3 2 0.42551507
## [53,] 3 2 0.48113585
## [54,] 2 3 0.60056798
## [55,] 3 2 0.28909599
## [56,] 2 3 0.25532064
## [57,] 3 2 0.44163580
## [58,] 2 3 0.58862119
## [59,] 3 2 0.31165524
## [60,] 2 3 0.47925063
## [61,] 2 3 0.53533494
## [62,] 3 2 0.13798259
## [63,] 2 3 0.50489380
## [64,] 3 2 0.19049376
## [65,] 3 2 -0.29889737
## [66,] 3 2 0.41447292
## [67,] 3 2 0.01586865
## [68,] 2 3 0.44246194
## [69,] 2 3 0.34101152
## [70,] 2 3 0.61849466
## [71,] 3 2 0.37763392
## [72,] 3 2 -0.13265959
## [73,] 3 2 -0.10917695
## [74,] 3 2 -0.04975816
## [75,] 3 2 0.21535096
## [76,] 3 2 0.37677150
## [77,] 3 2 0.33076400
## [78,] 3 2 0.51039252
## [79,] 3 2 0.14817057
## [80,] 2 3 0.55591487
## [81,] 2 3 0.64017720
## [82,] 2 3 0.63633810
## [83,] 2 3 0.43828812
## [84,] 3 2 0.05444339
## [85,] 3 2 -0.08567781
## [86,] 3 2 0.35396959
## [87,] 3 2 0.46838922
## [88,] 2 3 0.33877191
## [89,] 3 2 -0.13113484
## [90,] 2 3 0.60086588
## [91,] 2 3 0.54141464
## [92,] 3 2 0.25946590
## [93,] 2 3 0.51105620
## [94,] 2 3 0.59963069
## [95,] 2 3 0.45426587
## [96,] 3 2 -0.11025116
## [97,] 3 2 -0.20236125
## [98,] 3 2 0.12488131
## [99,] 2 3 0.58669598
## [100,] 2 3 0.31751136
## [101,] 3 2 0.48030393
## [102,] 3 2 0.07781886
## [103,] 3 2 0.52818285
## [104,] 3 2 0.45479299
## [105,] 3 2 0.52765484
## [106,] 3 2 0.46070084
## [107,] 2 3 0.42297967
## [108,] 3 2 0.46821593
## [109,] 3 2 0.24408754
## [110,] 3 2 0.45830809
## [111,] 3 2 0.54054151
## [112,] 3 2 0.34990684
## [113,] 3 2 0.54864397
## [114,] 3 2 -0.14954119
## [115,] 3 2 0.24982270
## [116,] 3 2 0.52152482
## [117,] 3 2 0.52530621
## [118,] 3 2 0.40527772
## [119,] 3 2 0.35156138
## [120,] 2 3 0.35090417
## [121,] 3 2 0.54433023
## [122,] 3 2 0.07700160
## [123,] 3 2 0.40831945
## [124,] 3 2 0.26315229
## [125,] 3 2 0.54408598
## [126,] 3 2 0.51663483
## [127,] 3 2 0.30994750
## [128,] 3 2 0.41268004
## [129,] 3 2 0.44434621
## [130,] 3 2 0.48294810
## [131,] 3 2 0.44165933
## [132,] 3 2 0.39458828
## [133,] 3 2 0.44191565
## [134,] 3 2 0.28181352
## [135,] 3 2 -0.02944153
## [136,] 3 2 0.45534598
## [137,] 3 2 0.48077840
## [138,] 3 2 0.52641092
## [139,] 3 2 0.36551707
## [140,] 3 2 0.55583283
## [141,] 3 2 0.53460231
## [142,] 3 2 0.53372987
## [143,] 3 2 0.07781886
## [144,] 3 2 0.54363634
## [145,] 3 2 0.51463269
## [146,] 3 2 0.52659597
## [147,] 3 2 0.08512800
## [148,] 3 2 0.53286756
## [149,] 3 2 0.47143716
## [150,] 3 2 0.34701606
## attr(,"Ordered")
## [1] FALSE
## attr(,"call")
## silhouette.default(x = c, dist = d)
## attr(,"class")
## [1] "silhouette"plot(silhouette(c, d))
d <- dist(scale(iris[,-5]))
methods <- c('complete', 'single', 'average')
avgS <- matrix( NA, ncol=3, nrow=5, dimnames=list(2:6, methods))
for (k in 2:6) {
for (m in seq_along(methods)){
h <- hclust(d, method = methods[m])
c <- cutree(h,k)
s <- silhouette(c,d)
avgS[k-1, m]=mean(s[,3])
}
}
avgS## complete single average
## 2 0.4408121 0.5817500 0.5817500
## 3 0.4496185 0.5046456 0.4802669
## 4 0.4106071 0.4067465 0.4067465
## 5 0.3520630 0.3424089 0.3746013
## 6 0.3106991 0.2018867 0.3248248d <- dist(scale(iris[,-5]))
h <- hclust(d)
h##
## Call:
## hclust(d = d)
##
## Cluster method : complete
## Distance : euclidean
## Number of objects: 150plot(h)
plot(h, hang=-0.1, labels=iris[["Species"]], cex=0.5)
Note that the echo = FALSE parameter was added to the
code chunk to prevent printing of the R code that generated the
plot.
#suppressMessages(library(compare))
# suppressWarnings( seeds_dataset <- read_delim("C:/GGTUAN/DREAMS/Yankee/TSU/MSc_TSU/Spring_2024/CS-583 Data Minning/seeds_dataset.txt", delim = "\t", escape_double = FALSE, col_names = FALSE, trim_ws =TRUE))
library(readr)
seeds_dataset <- read_table("C:/GGTUAN/DREAMS/Yankee/TSU/MSc_TSU/Spring_2024/CS-583 Data Minning/seeds_dataset.txt",
col_names = FALSE)##
## ── Column specification ────────────────────────────────────────────────────────
## cols(
## X1 = col_double(),
## X2 = col_double(),
## X3 = col_double(),
## X4 = col_double(),
## X5 = col_double(),
## X6 = col_double(),
## X7 = col_double(),
## X8 = col_double()
## )View(seeds_dataset)
seeds_dataset## # A tibble: 210 × 8
## X1 X2 X3 X4 X5 X6 X7 X8
## <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 15.3 14.8 0.871 5.76 3.31 2.22 5.22 1
## 2 14.9 14.6 0.881 5.55 3.33 1.02 4.96 1
## 3 14.3 14.1 0.905 5.29 3.34 2.70 4.82 1
## 4 13.8 13.9 0.896 5.32 3.38 2.26 4.80 1
## 5 16.1 15.0 0.903 5.66 3.56 1.36 5.18 1
## 6 14.4 14.2 0.895 5.39 3.31 2.46 4.96 1
## 7 14.7 14.5 0.880 5.56 3.26 3.59 5.22 1
## 8 14.1 14.1 0.891 5.42 3.30 2.7 5 1
## 9 16.6 15.5 0.875 6.05 3.46 2.04 5.88 1
## 10 16.4 15.2 0.888 5.88 3.50 1.97 5.53 1
## # ℹ 200 more rowsView(seeds_dataset)
sdf <- seeds_dataset[,-8]
View(sdf)
feature_name <- c('area', 'perimeter', 'compactness', 'length_of_kernel', 'width_of_kernel', 'asym_coeff', 'length_of_Kernel_groove')
colnames(sdf) <- feature_name
View(sdf)
head(sdf)## # A tibble: 6 × 7
## area perimeter compactness length_of_kernel width_of_kernel asym_coeff
## <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 15.3 14.8 0.871 5.76 3.31 2.22
## 2 14.9 14.6 0.881 5.55 3.33 1.02
## 3 14.3 14.1 0.905 5.29 3.34 2.70
## 4 13.8 13.9 0.896 5.32 3.38 2.26
## 5 16.1 15.0 0.903 5.66 3.56 1.36
## 6 14.4 14.2 0.895 5.39 3.31 2.46
## # ℹ 1 more variable: length_of_Kernel_groove <dbl>summary(sdf)## area perimeter compactness length_of_kernel
## Min. :10.59 Min. :12.41 Min. :0.8081 Min. :4.899
## 1st Qu.:12.27 1st Qu.:13.45 1st Qu.:0.8569 1st Qu.:5.262
## Median :14.36 Median :14.32 Median :0.8734 Median :5.524
## Mean :14.85 Mean :14.56 Mean :0.8710 Mean :5.629
## 3rd Qu.:17.30 3rd Qu.:15.71 3rd Qu.:0.8878 3rd Qu.:5.980
## Max. :21.18 Max. :17.25 Max. :0.9183 Max. :6.675
## width_of_kernel asym_coeff length_of_Kernel_groove
## Min. :2.630 Min. :0.7651 Min. :4.519
## 1st Qu.:2.944 1st Qu.:2.5615 1st Qu.:5.045
## Median :3.237 Median :3.5990 Median :5.223
## Mean :3.259 Mean :3.7002 Mean :5.408
## 3rd Qu.:3.562 3rd Qu.:4.7687 3rd Qu.:5.877
## Max. :4.033 Max. :8.4560 Max. :6.550is.na(sdf)## area perimeter compactness length_of_kernel width_of_kernel asym_coeff
## [1,] FALSE FALSE FALSE FALSE FALSE FALSE
## [2,] FALSE FALSE FALSE FALSE FALSE FALSE
## [3,] FALSE FALSE FALSE FALSE FALSE FALSE
## [4,] FALSE FALSE FALSE FALSE FALSE FALSE
## [5,] FALSE FALSE FALSE FALSE FALSE FALSE
## [6,] FALSE FALSE FALSE FALSE FALSE FALSE
## [7,] FALSE FALSE FALSE FALSE FALSE FALSE
## [8,] FALSE FALSE FALSE FALSE FALSE FALSE
## [9,] FALSE FALSE FALSE FALSE FALSE FALSE
## [10,] FALSE FALSE FALSE FALSE FALSE FALSE
## [11,] FALSE FALSE FALSE FALSE FALSE FALSE
## [12,] FALSE FALSE FALSE FALSE FALSE FALSE
## [13,] FALSE FALSE FALSE FALSE FALSE FALSE
## [14,] FALSE FALSE FALSE FALSE FALSE FALSE
## [15,] FALSE FALSE FALSE FALSE FALSE FALSE
## [16,] FALSE FALSE FALSE FALSE FALSE FALSE
## [17,] FALSE FALSE FALSE FALSE FALSE FALSE
## [18,] FALSE FALSE FALSE FALSE FALSE FALSE
## [19,] FALSE FALSE FALSE FALSE FALSE FALSE
## [20,] FALSE FALSE FALSE FALSE FALSE FALSE
## [21,] FALSE FALSE FALSE FALSE FALSE FALSE
## [22,] FALSE FALSE FALSE FALSE FALSE FALSE
## [23,] FALSE FALSE FALSE FALSE FALSE FALSE
## [24,] FALSE FALSE FALSE FALSE FALSE FALSE
## [25,] FALSE FALSE FALSE FALSE FALSE FALSE
## [26,] FALSE FALSE FALSE FALSE FALSE FALSE
## [27,] FALSE FALSE FALSE FALSE FALSE FALSE
## [28,] FALSE FALSE FALSE FALSE FALSE FALSE
## [29,] FALSE FALSE FALSE FALSE FALSE FALSE
## [30,] FALSE FALSE FALSE FALSE FALSE FALSE
## [31,] FALSE FALSE FALSE FALSE FALSE FALSE
## [32,] FALSE FALSE FALSE FALSE FALSE FALSE
## [33,] FALSE FALSE FALSE FALSE FALSE FALSE
## [34,] FALSE FALSE FALSE FALSE FALSE FALSE
## [35,] FALSE FALSE FALSE FALSE FALSE FALSE
## [36,] FALSE FALSE FALSE FALSE FALSE FALSE
## [37,] FALSE FALSE FALSE FALSE FALSE FALSE
## [38,] FALSE FALSE FALSE FALSE FALSE FALSE
## [39,] FALSE FALSE FALSE FALSE FALSE FALSE
## [40,] FALSE FALSE FALSE FALSE FALSE FALSE
## [41,] FALSE FALSE FALSE FALSE FALSE FALSE
## [42,] FALSE FALSE FALSE FALSE FALSE FALSE
## [43,] FALSE FALSE FALSE FALSE FALSE FALSE
## [44,] FALSE FALSE FALSE FALSE FALSE FALSE
## [45,] FALSE FALSE FALSE FALSE FALSE FALSE
## [46,] FALSE FALSE FALSE FALSE FALSE FALSE
## [47,] FALSE FALSE FALSE FALSE FALSE FALSE
## [48,] FALSE FALSE FALSE FALSE FALSE FALSE
## [49,] FALSE FALSE FALSE FALSE FALSE FALSE
## [50,] FALSE FALSE FALSE FALSE FALSE FALSE
## [51,] FALSE FALSE FALSE FALSE FALSE FALSE
## [52,] FALSE FALSE FALSE FALSE FALSE FALSE
## [53,] FALSE FALSE FALSE FALSE FALSE FALSE
## [54,] FALSE FALSE FALSE FALSE FALSE FALSE
## [55,] FALSE FALSE FALSE FALSE FALSE FALSE
## [56,] FALSE FALSE FALSE FALSE FALSE FALSE
## [57,] FALSE FALSE FALSE FALSE FALSE FALSE
## [58,] FALSE FALSE FALSE FALSE FALSE FALSE
## [59,] FALSE FALSE FALSE FALSE FALSE FALSE
## [60,] FALSE FALSE FALSE FALSE FALSE FALSE
## [61,] FALSE FALSE FALSE FALSE FALSE FALSE
## [62,] FALSE FALSE FALSE FALSE FALSE FALSE
## [63,] FALSE FALSE FALSE FALSE FALSE FALSE
## [64,] FALSE FALSE FALSE FALSE FALSE FALSE
## [65,] FALSE FALSE FALSE FALSE FALSE FALSE
## [66,] FALSE FALSE FALSE FALSE FALSE FALSE
## [67,] FALSE FALSE FALSE FALSE FALSE FALSE
## [68,] FALSE FALSE FALSE FALSE FALSE FALSE
## [69,] FALSE FALSE FALSE FALSE FALSE FALSE
## [70,] FALSE FALSE FALSE FALSE FALSE FALSE
## [71,] FALSE FALSE FALSE FALSE FALSE FALSE
## [72,] FALSE FALSE FALSE FALSE FALSE FALSE
## [73,] FALSE FALSE FALSE FALSE FALSE FALSE
## [74,] FALSE FALSE FALSE FALSE FALSE FALSE
## [75,] FALSE FALSE FALSE FALSE FALSE FALSE
## [76,] FALSE FALSE FALSE FALSE FALSE FALSE
## [77,] FALSE FALSE FALSE FALSE FALSE FALSE
## [78,] FALSE FALSE FALSE FALSE FALSE FALSE
## [79,] FALSE FALSE FALSE FALSE FALSE FALSE
## [80,] FALSE FALSE FALSE FALSE FALSE FALSE
## [81,] FALSE FALSE FALSE FALSE FALSE FALSE
## [82,] FALSE FALSE FALSE FALSE FALSE FALSE
## [83,] FALSE FALSE FALSE FALSE FALSE FALSE
## [84,] FALSE FALSE FALSE FALSE FALSE FALSE
## [85,] FALSE FALSE FALSE FALSE FALSE FALSE
## [86,] FALSE FALSE FALSE FALSE FALSE FALSE
## [87,] FALSE FALSE FALSE FALSE FALSE FALSE
## [88,] FALSE FALSE FALSE FALSE FALSE FALSE
## [89,] FALSE FALSE FALSE FALSE FALSE FALSE
## [90,] FALSE FALSE FALSE FALSE FALSE FALSE
## [91,] FALSE FALSE FALSE FALSE FALSE FALSE
## [92,] FALSE FALSE FALSE FALSE FALSE FALSE
## [93,] FALSE FALSE FALSE FALSE FALSE FALSE
## [94,] FALSE FALSE FALSE FALSE FALSE FALSE
## [95,] FALSE FALSE FALSE FALSE FALSE FALSE
## [96,] FALSE FALSE FALSE FALSE FALSE FALSE
## [97,] FALSE FALSE FALSE FALSE FALSE FALSE
## [98,] FALSE FALSE FALSE FALSE FALSE FALSE
## [99,] FALSE FALSE FALSE FALSE FALSE FALSE
## [100,] FALSE FALSE FALSE FALSE FALSE FALSE
## [101,] FALSE FALSE FALSE FALSE FALSE FALSE
## [102,] FALSE FALSE FALSE FALSE FALSE FALSE
## [103,] FALSE FALSE FALSE FALSE FALSE FALSE
## [104,] FALSE FALSE FALSE FALSE FALSE FALSE
## [105,] FALSE FALSE FALSE FALSE FALSE FALSE
## [106,] FALSE FALSE FALSE FALSE FALSE FALSE
## [107,] FALSE FALSE FALSE FALSE FALSE FALSE
## [108,] FALSE FALSE FALSE FALSE FALSE FALSE
## [109,] FALSE FALSE FALSE FALSE FALSE FALSE
## [110,] FALSE FALSE FALSE FALSE FALSE FALSE
## [111,] FALSE FALSE FALSE FALSE FALSE FALSE
## [112,] FALSE FALSE FALSE FALSE FALSE FALSE
## [113,] FALSE FALSE FALSE FALSE FALSE FALSE
## [114,] FALSE FALSE FALSE FALSE FALSE FALSE
## [115,] FALSE FALSE FALSE FALSE FALSE FALSE
## [116,] FALSE FALSE FALSE FALSE FALSE FALSE
## [117,] FALSE FALSE FALSE FALSE FALSE FALSE
## [118,] FALSE FALSE FALSE FALSE FALSE FALSE
## [119,] FALSE FALSE FALSE FALSE FALSE FALSE
## [120,] FALSE FALSE FALSE FALSE FALSE FALSE
## [121,] FALSE FALSE FALSE FALSE FALSE FALSE
## [122,] FALSE FALSE FALSE FALSE FALSE FALSE
## [123,] FALSE FALSE FALSE FALSE FALSE FALSE
## [124,] FALSE FALSE FALSE FALSE FALSE FALSE
## [125,] FALSE FALSE FALSE FALSE FALSE FALSE
## [126,] FALSE FALSE FALSE FALSE FALSE FALSE
## [127,] FALSE FALSE FALSE FALSE FALSE FALSE
## [128,] FALSE FALSE FALSE FALSE FALSE FALSE
## [129,] FALSE FALSE FALSE FALSE FALSE FALSE
## [130,] FALSE FALSE FALSE FALSE FALSE FALSE
## [131,] FALSE FALSE FALSE FALSE FALSE FALSE
## [132,] FALSE FALSE FALSE FALSE FALSE FALSE
## [133,] FALSE FALSE FALSE FALSE FALSE FALSE
## [134,] FALSE FALSE FALSE FALSE FALSE FALSE
## [135,] FALSE FALSE FALSE FALSE FALSE FALSE
## [136,] FALSE FALSE FALSE FALSE FALSE FALSE
## [137,] FALSE FALSE FALSE FALSE FALSE FALSE
## [138,] FALSE FALSE FALSE FALSE FALSE FALSE
## [139,] FALSE FALSE FALSE FALSE FALSE FALSE
## [140,] FALSE FALSE FALSE FALSE FALSE FALSE
## [141,] FALSE FALSE FALSE FALSE FALSE FALSE
## [142,] FALSE FALSE FALSE FALSE FALSE FALSE
## [143,] FALSE FALSE FALSE FALSE FALSE FALSE
## [144,] FALSE FALSE FALSE FALSE FALSE FALSE
## [145,] FALSE FALSE FALSE FALSE FALSE FALSE
## [146,] FALSE FALSE FALSE FALSE FALSE FALSE
## [147,] FALSE FALSE FALSE FALSE FALSE FALSE
## [148,] FALSE FALSE FALSE FALSE FALSE FALSE
## [149,] FALSE FALSE FALSE FALSE FALSE FALSE
## [150,] FALSE FALSE FALSE FALSE FALSE FALSE
## [151,] FALSE FALSE FALSE FALSE FALSE FALSE
## [152,] FALSE FALSE FALSE FALSE FALSE FALSE
## [153,] FALSE FALSE FALSE FALSE FALSE FALSE
## [154,] FALSE FALSE FALSE FALSE FALSE FALSE
## [155,] FALSE FALSE FALSE FALSE FALSE FALSE
## [156,] FALSE FALSE FALSE FALSE FALSE FALSE
## [157,] FALSE FALSE FALSE FALSE FALSE FALSE
## [158,] FALSE FALSE FALSE FALSE FALSE FALSE
## [159,] FALSE FALSE FALSE FALSE FALSE FALSE
## [160,] FALSE FALSE FALSE FALSE FALSE FALSE
## [161,] FALSE FALSE FALSE FALSE FALSE FALSE
## [162,] FALSE FALSE FALSE FALSE FALSE FALSE
## [163,] FALSE FALSE FALSE FALSE FALSE FALSE
## [164,] FALSE FALSE FALSE FALSE FALSE FALSE
## [165,] FALSE FALSE FALSE FALSE FALSE FALSE
## [166,] FALSE FALSE FALSE FALSE FALSE FALSE
## [167,] FALSE FALSE FALSE FALSE FALSE FALSE
## [168,] FALSE FALSE FALSE FALSE FALSE FALSE
## [169,] FALSE FALSE FALSE FALSE FALSE FALSE
## [170,] FALSE FALSE FALSE FALSE FALSE FALSE
## [171,] FALSE FALSE FALSE FALSE FALSE FALSE
## [172,] FALSE FALSE FALSE FALSE FALSE FALSE
## [173,] FALSE FALSE FALSE FALSE FALSE FALSE
## [174,] FALSE FALSE FALSE FALSE FALSE FALSE
## [175,] FALSE FALSE FALSE FALSE FALSE FALSE
## [176,] FALSE FALSE FALSE FALSE FALSE FALSE
## [177,] FALSE FALSE FALSE FALSE FALSE FALSE
## [178,] FALSE FALSE FALSE FALSE FALSE FALSE
## [179,] FALSE FALSE FALSE FALSE FALSE FALSE
## [180,] FALSE FALSE FALSE FALSE FALSE FALSE
## [181,] FALSE FALSE FALSE FALSE FALSE FALSE
## [182,] FALSE FALSE FALSE FALSE FALSE FALSE
## [183,] FALSE FALSE FALSE FALSE FALSE FALSE
## [184,] FALSE FALSE FALSE FALSE FALSE FALSE
## [185,] FALSE FALSE FALSE FALSE FALSE FALSE
## [186,] FALSE FALSE FALSE FALSE FALSE FALSE
## [187,] FALSE FALSE FALSE FALSE FALSE FALSE
## [188,] FALSE FALSE FALSE FALSE FALSE FALSE
## [189,] FALSE FALSE FALSE FALSE FALSE FALSE
## [190,] FALSE FALSE FALSE FALSE FALSE FALSE
## [191,] FALSE FALSE FALSE FALSE FALSE FALSE
## [192,] FALSE FALSE FALSE FALSE FALSE FALSE
## [193,] FALSE FALSE FALSE FALSE FALSE FALSE
## [194,] FALSE FALSE FALSE FALSE FALSE FALSE
## [195,] FALSE FALSE FALSE FALSE FALSE FALSE
## [196,] FALSE FALSE FALSE FALSE FALSE FALSE
## [197,] FALSE FALSE FALSE FALSE FALSE FALSE
## [198,] FALSE FALSE FALSE FALSE FALSE FALSE
## [199,] FALSE FALSE FALSE FALSE FALSE FALSE
## [200,] FALSE FALSE FALSE FALSE FALSE FALSE
## [201,] FALSE FALSE FALSE FALSE FALSE FALSE
## [202,] FALSE FALSE FALSE FALSE FALSE FALSE
## [203,] FALSE FALSE FALSE FALSE FALSE FALSE
## [204,] FALSE FALSE FALSE FALSE FALSE FALSE
## [205,] FALSE FALSE FALSE FALSE FALSE FALSE
## [206,] FALSE FALSE FALSE FALSE FALSE FALSE
## [207,] FALSE FALSE FALSE FALSE FALSE FALSE
## [208,] FALSE FALSE FALSE FALSE FALSE FALSE
## [209,] FALSE FALSE FALSE FALSE FALSE FALSE
## [210,] FALSE FALSE FALSE FALSE FALSE FALSE
## length_of_Kernel_groove
## [1,] FALSE
## [2,] FALSE
## [3,] FALSE
## [4,] FALSE
## [5,] FALSE
## [6,] FALSE
## [7,] FALSE
## [8,] FALSE
## [9,] FALSE
## [10,] FALSE
## [11,] FALSE
## [12,] FALSE
## [13,] FALSE
## [14,] FALSE
## [15,] FALSE
## [16,] FALSE
## [17,] FALSE
## [18,] FALSE
## [19,] FALSE
## [20,] FALSE
## [21,] FALSE
## [22,] FALSE
## [23,] FALSE
## [24,] FALSE
## [25,] FALSE
## [26,] FALSE
## [27,] FALSE
## [28,] FALSE
## [29,] FALSE
## [30,] FALSE
## [31,] FALSE
## [32,] FALSE
## [33,] FALSE
## [34,] FALSE
## [35,] FALSE
## [36,] FALSE
## [37,] FALSE
## [38,] FALSE
## [39,] FALSE
## [40,] FALSE
## [41,] FALSE
## [42,] FALSE
## [43,] FALSE
## [44,] FALSE
## [45,] FALSE
## [46,] FALSE
## [47,] FALSE
## [48,] FALSE
## [49,] FALSE
## [50,] FALSE
## [51,] FALSE
## [52,] FALSE
## [53,] FALSE
## [54,] FALSE
## [55,] FALSE
## [56,] FALSE
## [57,] FALSE
## [58,] FALSE
## [59,] FALSE
## [60,] FALSE
## [61,] FALSE
## [62,] FALSE
## [63,] FALSE
## [64,] FALSE
## [65,] FALSE
## [66,] FALSE
## [67,] FALSE
## [68,] FALSE
## [69,] FALSE
## [70,] FALSE
## [71,] FALSE
## [72,] FALSE
## [73,] FALSE
## [74,] FALSE
## [75,] FALSE
## [76,] FALSE
## [77,] FALSE
## [78,] FALSE
## [79,] FALSE
## [80,] FALSE
## [81,] FALSE
## [82,] FALSE
## [83,] FALSE
## [84,] FALSE
## [85,] FALSE
## [86,] FALSE
## [87,] FALSE
## [88,] FALSE
## [89,] FALSE
## [90,] FALSE
## [91,] FALSE
## [92,] FALSE
## [93,] FALSE
## [94,] FALSE
## [95,] FALSE
## [96,] FALSE
## [97,] FALSE
## [98,] FALSE
## [99,] FALSE
## [100,] FALSE
## [101,] FALSE
## [102,] FALSE
## [103,] FALSE
## [104,] FALSE
## [105,] FALSE
## [106,] FALSE
## [107,] FALSE
## [108,] FALSE
## [109,] FALSE
## [110,] FALSE
## [111,] FALSE
## [112,] FALSE
## [113,] FALSE
## [114,] FALSE
## [115,] FALSE
## [116,] FALSE
## [117,] FALSE
## [118,] FALSE
## [119,] FALSE
## [120,] FALSE
## [121,] FALSE
## [122,] FALSE
## [123,] FALSE
## [124,] FALSE
## [125,] FALSE
## [126,] FALSE
## [127,] FALSE
## [128,] FALSE
## [129,] FALSE
## [130,] FALSE
## [131,] FALSE
## [132,] FALSE
## [133,] FALSE
## [134,] FALSE
## [135,] FALSE
## [136,] FALSE
## [137,] FALSE
## [138,] FALSE
## [139,] FALSE
## [140,] FALSE
## [141,] FALSE
## [142,] FALSE
## [143,] FALSE
## [144,] FALSE
## [145,] FALSE
## [146,] FALSE
## [147,] FALSE
## [148,] FALSE
## [149,] FALSE
## [150,] FALSE
## [151,] FALSE
## [152,] FALSE
## [153,] FALSE
## [154,] FALSE
## [155,] FALSE
## [156,] FALSE
## [157,] FALSE
## [158,] FALSE
## [159,] FALSE
## [160,] FALSE
## [161,] FALSE
## [162,] FALSE
## [163,] FALSE
## [164,] FALSE
## [165,] FALSE
## [166,] FALSE
## [167,] FALSE
## [168,] FALSE
## [169,] FALSE
## [170,] FALSE
## [171,] FALSE
## [172,] FALSE
## [173,] FALSE
## [174,] FALSE
## [175,] FALSE
## [176,] FALSE
## [177,] FALSE
## [178,] FALSE
## [179,] FALSE
## [180,] FALSE
## [181,] FALSE
## [182,] FALSE
## [183,] FALSE
## [184,] FALSE
## [185,] FALSE
## [186,] FALSE
## [187,] FALSE
## [188,] FALSE
## [189,] FALSE
## [190,] FALSE
## [191,] FALSE
## [192,] FALSE
## [193,] FALSE
## [194,] FALSE
## [195,] FALSE
## [196,] FALSE
## [197,] FALSE
## [198,] FALSE
## [199,] FALSE
## [200,] FALSE
## [201,] FALSE
## [202,] FALSE
## [203,] FALSE
## [204,] FALSE
## [205,] FALSE
## [206,] FALSE
## [207,] FALSE
## [208,] FALSE
## [209,] FALSE
## [210,] FALSEsdf <- na.omit(sdf)
summary(sdf)## area perimeter compactness length_of_kernel
## Min. :10.59 Min. :12.41 Min. :0.8081 Min. :4.899
## 1st Qu.:12.27 1st Qu.:13.45 1st Qu.:0.8569 1st Qu.:5.262
## Median :14.36 Median :14.32 Median :0.8734 Median :5.524
## Mean :14.85 Mean :14.56 Mean :0.8710 Mean :5.629
## 3rd Qu.:17.30 3rd Qu.:15.71 3rd Qu.:0.8878 3rd Qu.:5.980
## Max. :21.18 Max. :17.25 Max. :0.9183 Max. :6.675
## width_of_kernel asym_coeff length_of_Kernel_groove
## Min. :2.630 Min. :0.7651 Min. :4.519
## 1st Qu.:2.944 1st Qu.:2.5615 1st Qu.:5.045
## Median :3.237 Median :3.5990 Median :5.223
## Mean :3.259 Mean :3.7002 Mean :5.408
## 3rd Qu.:3.562 3rd Qu.:4.7687 3rd Qu.:5.877
## Max. :4.033 Max. :8.4560 Max. :6.550sdf_scale <- scale(sdf)
View(sdf_scale)
summary(sdf_scale)## area perimeter compactness length_of_kernel
## Min. :-1.4632 Min. :-1.6458 Min. :-2.6619 Min. :-1.6466
## 1st Qu.:-0.8858 1st Qu.:-0.8494 1st Qu.:-0.5967 1st Qu.:-0.8267
## Median :-0.1693 Median :-0.1832 Median : 0.1037 Median :-0.2371
## Mean : 0.0000 Mean : 0.0000 Mean : 0.0000 Mean : 0.0000
## 3rd Qu.: 0.8446 3rd Qu.: 0.8850 3rd Qu.: 0.7100 3rd Qu.: 0.7927
## Max. : 2.1763 Max. : 2.0603 Max. : 2.0018 Max. : 2.3619
## width_of_kernel asym_coeff length_of_Kernel_groove
## Min. :-1.6642 Min. :-1.95210 Min. :-1.8090
## 1st Qu.:-0.8329 1st Qu.:-0.75734 1st Qu.:-0.7387
## Median :-0.0572 Median :-0.06731 Median :-0.3766
## Mean : 0.0000 Mean : 0.00000 Mean : 0.0000
## 3rd Qu.: 0.8026 3rd Qu.: 0.71068 3rd Qu.: 0.9541
## Max. : 2.0502 Max. : 3.16303 Max. : 2.3234sdf_scale_d <- dist(scale(sdf))
h_sdf<- hclust(sdf_scale_d)
plot(h_sdf)
plot(h_sdf, hang=-0.1, labels=sdf[["Species"]], cex=0.5)
seeds_dataset## # A tibble: 210 × 8
## X1 X2 X3 X4 X5 X6 X7 X8
## <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 15.3 14.8 0.871 5.76 3.31 2.22 5.22 1
## 2 14.9 14.6 0.881 5.55 3.33 1.02 4.96 1
## 3 14.3 14.1 0.905 5.29 3.34 2.70 4.82 1
## 4 13.8 13.9 0.896 5.32 3.38 2.26 4.80 1
## 5 16.1 15.0 0.903 5.66 3.56 1.36 5.18 1
## 6 14.4 14.2 0.895 5.39 3.31 2.46 4.96 1
## 7 14.7 14.5 0.880 5.56 3.26 3.59 5.22 1
## 8 14.1 14.1 0.891 5.42 3.30 2.7 5 1
## 9 16.6 15.5 0.875 6.05 3.46 2.04 5.88 1
## 10 16.4 15.2 0.888 5.88 3.50 1.97 5.53 1
## # ℹ 200 more rowsplot(h_sdf, hang=-0.1, labels= seeds_dataset$x8, cex=0.5) ### okay## Warning: Unknown or uninitialised column: `x8`.
plot(h_sdf, hang=-0.1, labels= seeds_dataset[["x8"]], cex=0.5) ###okay
seeds_dataset_noNa <- na.omit(seeds_dataset)
#feature_name <- c('area', 'perimeter', 'compactness', 'length_of_kernel', 'width_of_kernel', 'asym_coeff', 'length_of_Kernel_groove', 'type_of_sed')
#feature_name <- c('area', 'perimeter', 'compactness', 'length_of_kernel', 'width_of_kernel', 'asym_coeff', 'length_of_Kernel_groove')c <- cutree(h_sdf,3)
c## [1] 1 1 1 1 1 1 1 1 2 1 1 1 3 1 1 3 3 1 1 3 1 1 1 3 1 1 3 3 1 3 3 1 1 1 1 1 1
## [38] 1 1 3 1 1 3 2 1 1 1 1 1 1 1 3 1 1 1 1 1 1 1 3 3 3 3 3 3 3 1 1 1 3 2 2 2 2
## [75] 2 2 2 2 2 1 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2
## [112] 2 2 2 2 2 2 2 2 2 2 2 2 2 1 2 2 2 2 2 2 2 2 2 2 1 2 2 2 1 3 3 3 3 3 3 3 3
## [149] 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3
## [186] 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3length(c)## [1] 210dim(seeds_dataset_noNa)## [1] 210 8#(cm <- table(c, iris$Species))
(cm <- table(c, seeds_dataset_noNa$X8 ))##
## c 1 2 3
## 1 48 4 0
## 2 2 66 0
## 3 20 0 70Error <- 100*(1-sum(diag(cm))/sum(cm))
Error## [1] 12.38095library(cluster)
silhouette(c, sdf_scale_d)## cluster neighbor sil_width
## [1,] 1 2 0.5708880032
## [2,] 1 3 0.5513374299
## [3,] 1 3 0.4273358436
## [4,] 1 3 0.4476413482
## [5,] 1 2 0.4496837367
## [6,] 1 3 0.5228626070
## [7,] 1 3 0.4780097001
## [8,] 1 3 0.5117642064
## [9,] 2 1 0.0998030537
## [10,] 1 2 0.2553247601
## [11,] 1 3 0.3006419050
## [12,] 1 3 0.5037811817
## [13,] 3 1 -0.2366110187
## [14,] 1 3 0.3257994331
## [15,] 1 3 0.3045873031
## [16,] 3 1 -0.3122477498
## [17,] 3 1 -0.1295257365
## [18,] 1 2 0.5211934668
## [19,] 1 3 0.4026803962
## [20,] 3 1 0.2351776958
## [21,] 1 3 0.3124965970
## [22,] 1 3 0.4702915442
## [23,] 1 2 0.4871269382
## [24,] 3 1 -0.0043995530
## [25,] 1 3 0.5141723504
## [26,] 1 2 0.4196318430
## [27,] 3 1 0.0562098679
## [28,] 3 1 0.0463464506
## [29,] 1 3 0.5175188640
## [30,] 3 1 -0.0772613665
## [31,] 3 1 -0.2862191237
## [32,] 1 2 0.4779300777
## [33,] 1 3 0.1646250415
## [34,] 1 3 0.4753008493
## [35,] 1 2 0.5821581447
## [36,] 1 2 0.3976522347
## [37,] 1 2 0.2560816840
## [38,] 1 2 0.0489838917
## [39,] 1 3 0.5623264264
## [40,] 3 1 0.0222249087
## [41,] 1 3 0.4089719035
## [42,] 1 3 0.4269682702
## [43,] 3 1 -0.2797469693
## [44,] 2 1 -0.1615491593
## [45,] 1 2 0.5460344475
## [46,] 1 3 0.4404518575
## [47,] 1 2 0.5803837327
## [48,] 1 3 0.5927701753
## [49,] 1 3 0.5887350916
## [50,] 1 3 0.5478773169
## [51,] 1 3 0.3703040634
## [52,] 3 1 -0.2720869248
## [53,] 1 3 0.1503208973
## [54,] 1 3 0.4695352547
## [55,] 1 3 0.3949009865
## [56,] 1 3 0.5193091638
## [57,] 1 3 0.5270083716
## [58,] 1 3 0.5425860205
## [59,] 1 2 0.5938947940
## [60,] 3 1 0.1021970837
## [61,] 3 1 0.2466578948
## [62,] 3 1 0.1341520070
## [63,] 3 1 0.0221905126
## [64,] 3 1 0.0855077596
## [65,] 3 1 -0.2009863509
## [66,] 3 1 -0.1664131790
## [67,] 1 3 0.5259319254
## [68,] 1 3 0.4230410683
## [69,] 1 3 0.5159107956
## [70,] 3 1 0.2976041799
## [71,] 2 1 0.4782399534
## [72,] 2 1 0.2974514127
## [73,] 2 1 0.3446733744
## [74,] 2 1 0.4837186307
## [75,] 2 1 0.2819886843
## [76,] 2 1 0.2261411672
## [77,] 2 1 0.3210750709
## [78,] 2 1 0.5419712231
## [79,] 2 1 0.5363053405
## [80,] 1 2 -0.1176390610
## [81,] 2 1 0.2241673067
## [82,] 2 1 0.4437462363
## [83,] 2 1 0.5426936126
## [84,] 2 1 0.4674239982
## [85,] 2 1 0.5743868417
## [86,] 2 1 0.4967618856
## [87,] 2 1 0.4115980382
## [88,] 2 1 0.5142299006
## [89,] 2 1 0.4805409132
## [90,] 2 1 0.5086735154
## [91,] 2 1 0.4946807021
## [92,] 2 1 0.5322161297
## [93,] 2 1 0.5615034611
## [94,] 2 1 0.3869749975
## [95,] 2 1 0.4212735014
## [96,] 2 1 0.3438504075
## [97,] 2 1 0.5937597741
## [98,] 2 1 0.4775367774
## [99,] 2 1 0.4729201149
## [100,] 2 1 0.4954428823
## [101,] 2 1 -0.0692255063
## [102,] 2 1 0.2372055747
## [103,] 2 1 0.5316623147
## [104,] 2 1 0.5707311614
## [105,] 2 1 0.5872369759
## [106,] 2 1 0.4515703335
## [107,] 2 1 0.4983143952
## [108,] 2 1 0.4307701879
## [109,] 2 1 0.5341102823
## [110,] 2 1 0.3785986201
## [111,] 2 1 0.3886582666
## [112,] 2 1 0.5521397857
## [113,] 2 1 0.4295468267
## [114,] 2 1 0.4332311723
## [115,] 2 1 0.5336141787
## [116,] 2 1 0.5251697647
## [117,] 2 1 0.4197739388
## [118,] 2 1 0.5783066756
## [119,] 2 1 0.5276427019
## [120,] 2 1 0.5662081617
## [121,] 2 1 0.5008421893
## [122,] 2 1 0.4876610086
## [123,] 2 1 -0.0267368434
## [124,] 2 1 0.3884321721
## [125,] 1 2 0.4309253661
## [126,] 2 1 0.5155528325
## [127,] 2 1 0.5373082268
## [128,] 2 1 0.3247475559
## [129,] 2 1 0.4900463848
## [130,] 2 1 0.2317571049
## [131,] 2 1 0.3676929030
## [132,] 2 1 0.5180926895
## [133,] 2 1 -0.0754852688
## [134,] 2 1 0.0691871882
## [135,] 2 1 0.0137552131
## [136,] 1 2 0.4286063147
## [137,] 2 1 0.4423549179
## [138,] 2 1 -0.1226423362
## [139,] 2 1 -0.2235059057
## [140,] 1 2 -0.1540272750
## [141,] 3 1 0.3158453660
## [142,] 3 1 0.2467671255
## [143,] 3 1 0.2744926848
## [144,] 3 1 0.4059126422
## [145,] 3 1 0.4661186158
## [146,] 3 1 0.4514644402
## [147,] 3 1 0.3028132193
## [148,] 3 1 0.3442362359
## [149,] 3 1 0.2175771229
## [150,] 3 1 0.4471965016
## [151,] 3 1 0.4810772611
## [152,] 3 1 0.4118995970
## [153,] 3 1 0.4252937325
## [154,] 3 1 0.4202421482
## [155,] 3 1 0.4769400906
## [156,] 3 1 0.4864433718
## [157,] 3 1 0.3830792251
## [158,] 3 1 0.3920490914
## [159,] 3 1 0.3827127580
## [160,] 3 1 0.4795564798
## [161,] 3 1 0.1981658926
## [162,] 3 1 0.4265960579
## [163,] 3 1 0.4962130434
## [164,] 3 1 0.3669196759
## [165,] 3 1 0.4724656500
## [166,] 3 1 -0.0034370858
## [167,] 3 1 0.4411256462
## [168,] 3 1 0.3471599381
## [169,] 3 1 0.4903780696
## [170,] 3 1 0.4522132318
## [171,] 3 1 0.4422876736
## [172,] 3 1 0.4661690803
## [173,] 3 1 0.5075275367
## [174,] 3 1 0.5184285428
## [175,] 3 1 0.4466629485
## [176,] 3 1 0.4789372355
## [177,] 3 1 0.5209540594
## [178,] 3 1 0.5058041718
## [179,] 3 1 0.5077734930
## [180,] 3 1 0.0722845805
## [181,] 3 1 0.4911937030
## [182,] 3 1 0.3331614491
## [183,] 3 1 0.4485734870
## [184,] 3 1 0.4915578531
## [185,] 3 1 0.3300907114
## [186,] 3 1 0.4298523974
## [187,] 3 1 0.4322862771
## [188,] 3 1 0.4958703414
## [189,] 3 1 0.4112608115
## [190,] 3 1 0.4427003759
## [191,] 3 1 0.5194278329
## [192,] 3 1 0.4630642693
## [193,] 3 1 0.2075514297
## [194,] 3 1 0.4965669789
## [195,] 3 1 0.3616632288
## [196,] 3 1 0.1548766557
## [197,] 3 1 0.2721793689
## [198,] 3 1 -0.0008233976
## [199,] 3 1 0.2448603677
## [200,] 3 1 -0.1638794672
## [201,] 3 1 0.4241468931
## [202,] 3 1 -0.1591315217
## [203,] 3 1 0.4053643847
## [204,] 3 1 0.2376742978
## [205,] 3 1 0.3679439949
## [206,] 3 1 0.2009448064
## [207,] 3 1 0.4988773653
## [208,] 3 1 0.1918069368
## [209,] 3 1 0.4184880233
## [210,] 3 1 0.3932539376
## attr(,"Ordered")
## [1] FALSE
## attr(,"call")
## silhouette.default(x = c, dist = sdf_scale_d)
## attr(,"class")
## [1] "silhouette"plot(silhouette(c, sdf_scale_d))
set.seed(1234)d <- dist(scale(iris[,-5]))
sdf_scale_d <- dist(scale(sdf))
methods <- c('complete', 'single', 'average')
avgS <- matrix( NA, ncol=3, nrow=5, dimnames=list(2:6, methods))
for (k in 2:6) {
for (m in seq_along(methods)){
h <- hclust(sdf_scale_d, method = methods[m])
c <- cutree(h_sdf,k)
s <- silhouette(c,sdf_scale_d)
avgS[k-1, m]=mean(s[,3])
}
}
avgS## complete single average
## 2 0.4519948 0.4519948 0.4519948
## 3 0.3501985 0.3501985 0.3501985
## 4 0.3148568 0.3148568 0.3148568
## 5 0.2937202 0.2937202 0.2937202
## 6 0.2173803 0.2173803 0.2173803### Meaning 2 ranks/categories of complete single or average are the best