install.packages("flexclust")
## Installing package into '/cloud/lib/x86_64-pc-linux-gnu-library/4.5'
## (as 'lib' is unspecified)
install.packages("dbscan")
## Installing package into '/cloud/lib/x86_64-pc-linux-gnu-library/4.5'
## (as 'lib' is unspecified)
install.packages("meanShiftR")
## Installing package into '/cloud/lib/x86_64-pc-linux-gnu-library/4.5'
## (as 'lib' is unspecified)
install.packages("e1071")
## Installing package into '/cloud/lib/x86_64-pc-linux-gnu-library/4.5'
## (as 'lib' is unspecified)
install.packages("cluster")
## Installing package into '/cloud/lib/x86_64-pc-linux-gnu-library/4.5'
## (as 'lib' is unspecified)
install.packages("fpc")
## Installing package into '/cloud/lib/x86_64-pc-linux-gnu-library/4.5'
## (as 'lib' is unspecified)
install.packages("mclust")
## Installing package into '/cloud/lib/x86_64-pc-linux-gnu-library/4.5'
## (as 'lib' is unspecified)
install.packages("dplyr")
## Installing package into '/cloud/lib/x86_64-pc-linux-gnu-library/4.5'
## (as 'lib' is unspecified)
install.packages("psych")
## Installing package into '/cloud/lib/x86_64-pc-linux-gnu-library/4.5'
## (as 'lib' is unspecified)
install.packages("factoextra")
## Installing package into '/cloud/lib/x86_64-pc-linux-gnu-library/4.5'
## (as 'lib' is unspecified)
library(flexclust)
library(dbscan)
##
## Attaching package: 'dbscan'
## The following object is masked from 'package:stats':
##
## as.dendrogram
library(meanShiftR)
library(e1071)
##
## Attaching package: 'e1071'
## The following object is masked from 'package:flexclust':
##
## bclust
library(cluster)
library(fpc)
##
## Attaching package: 'fpc'
## The following object is masked from 'package:dbscan':
##
## dbscan
library(mclust)
## Package 'mclust' version 6.1.2
## Type 'citation("mclust")' for citing this R package in publications.
library(dplyr)
##
## Attaching package: 'dplyr'
## The following object is masked from 'package:mclust':
##
## count
## The following objects are masked from 'package:stats':
##
## filter, lag
## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, union
library(psych)
##
## Attaching package: 'psych'
## The following object is masked from 'package:mclust':
##
## sim
library(factoextra)
## Loading required package: ggplot2
##
## Attaching package: 'ggplot2'
## The following objects are masked from 'package:psych':
##
## %+%, alpha
## The following object is masked from 'package:e1071':
##
## element
## Welcome to factoextra!
## Want to learn more? See two factoextra-related books at https://www.datanovia.com/en/product/practical-guide-to-principal-component-methods-in-r/
data <- read.csv("parkinsons.csv")
str(data)
## 'data.frame': 195 obs. of 24 variables:
## $ name : chr "phon_R01_S01_1" "phon_R01_S01_2" "phon_R01_S01_3" "phon_R01_S01_4" ...
## $ MDVP.Fo.Hz. : num 120 122 117 117 116 ...
## $ MDVP.Fhi.Hz. : num 157 149 131 138 142 ...
## $ MDVP.Flo.Hz. : num 75 114 112 111 111 ...
## $ MDVP.Jitter... : num 0.00784 0.00968 0.0105 0.00997 0.01284 ...
## $ MDVP.Jitter.Abs.: num 0.00007 0.00008 0.00009 0.00009 0.00011 0.00008 0.00003 0.00003 0.00006 0.00006 ...
## $ MDVP.RAP : num 0.0037 0.00465 0.00544 0.00502 0.00655 0.00463 0.00155 0.00144 0.00293 0.00268 ...
## $ MDVP.PPQ : num 0.00554 0.00696 0.00781 0.00698 0.00908 0.0075 0.00202 0.00182 0.00332 0.00332 ...
## $ Jitter.DDP : num 0.0111 0.0139 0.0163 0.015 0.0197 ...
## $ MDVP.Shimmer : num 0.0437 0.0613 0.0523 0.0549 0.0643 ...
## $ MDVP.Shimmer.dB.: num 0.426 0.626 0.482 0.517 0.584 0.456 0.14 0.134 0.191 0.255 ...
## $ Shimmer.APQ3 : num 0.0218 0.0313 0.0276 0.0292 0.0349 ...
## $ Shimmer.APQ5 : num 0.0313 0.0452 0.0386 0.0401 0.0483 ...
## $ MDVP.APQ : num 0.0297 0.0437 0.0359 0.0377 0.0447 ...
## $ Shimmer.DDA : num 0.0654 0.094 0.0827 0.0877 0.1047 ...
## $ NHR : num 0.0221 0.0193 0.0131 0.0135 0.0177 ...
## $ HNR : num 21 19.1 20.7 20.6 19.6 ...
## $ status : int 1 1 1 1 1 1 1 1 1 1 ...
## $ RPDE : num 0.415 0.458 0.43 0.435 0.417 ...
## $ DFA : num 0.815 0.82 0.825 0.819 0.823 ...
## $ spread1 : num -4.81 -4.08 -4.44 -4.12 -3.75 ...
## $ spread2 : num 0.266 0.336 0.311 0.334 0.235 ...
## $ D2 : num 2.3 2.49 2.34 2.41 2.33 ...
## $ PPE : num 0.285 0.369 0.333 0.369 0.41 ...
data_numeric <- data[sapply(data, is.numeric)]
label <- data_numeric$status
data_clustering <- data_numeric[, colnames(data_numeric) != "status"]
colSums(is.na(data_numeric))
## MDVP.Fo.Hz. MDVP.Fhi.Hz. MDVP.Flo.Hz. MDVP.Jitter...
## 0 0 0 0
## MDVP.Jitter.Abs. MDVP.RAP MDVP.PPQ Jitter.DDP
## 0 0 0 0
## MDVP.Shimmer MDVP.Shimmer.dB. Shimmer.APQ3 Shimmer.APQ5
## 0 0 0 0
## MDVP.APQ Shimmer.DDA NHR HNR
## 0 0 0 0
## status RPDE DFA spread1
## 0 0 0 0
## spread2 D2 PPE
## 0 0 0
sum(duplicated(data_numeric))
## [1] 0
describe(data_clustering)
## vars n mean sd median trimmed mad min max
## MDVP.Fo.Hz. 1 195 154.23 41.39 148.79 150.80 47.13 88.33 260.10
## MDVP.Fhi.Hz. 2 195 197.10 91.49 175.83 180.97 62.99 102.14 592.03
## MDVP.Flo.Hz. 3 195 116.32 43.52 104.32 109.94 35.11 65.48 239.17
## MDVP.Jitter... 4 195 0.01 0.00 0.00 0.01 0.00 0.00 0.03
## MDVP.Jitter.Abs. 5 195 0.00 0.00 0.00 0.00 0.00 0.00 0.00
## MDVP.RAP 6 195 0.00 0.00 0.00 0.00 0.00 0.00 0.02
## MDVP.PPQ 7 195 0.00 0.00 0.00 0.00 0.00 0.00 0.02
## Jitter.DDP 8 195 0.01 0.01 0.01 0.01 0.00 0.00 0.06
## MDVP.Shimmer 9 195 0.03 0.02 0.02 0.03 0.01 0.01 0.12
## MDVP.Shimmer.dB. 10 195 0.28 0.19 0.22 0.25 0.13 0.09 1.30
## Shimmer.APQ3 11 195 0.02 0.01 0.01 0.01 0.01 0.00 0.06
## Shimmer.APQ5 12 195 0.02 0.01 0.01 0.02 0.01 0.01 0.08
## MDVP.APQ 13 195 0.02 0.02 0.02 0.02 0.01 0.01 0.14
## Shimmer.DDA 14 195 0.05 0.03 0.04 0.04 0.02 0.01 0.17
## NHR 15 195 0.02 0.04 0.01 0.02 0.01 0.00 0.31
## HNR 16 195 21.89 4.43 22.09 22.17 4.37 8.44 33.05
## RPDE 17 195 0.50 0.10 0.50 0.50 0.12 0.26 0.69
## DFA 18 195 0.72 0.06 0.72 0.72 0.06 0.57 0.83
## spread1 19 195 -5.68 1.09 -5.72 -5.74 1.07 -7.96 -2.43
## spread2 20 195 0.23 0.08 0.22 0.23 0.07 0.01 0.45
## D2 21 195 2.38 0.38 2.36 2.36 0.40 1.42 3.67
## PPE 22 195 0.21 0.09 0.19 0.20 0.09 0.04 0.53
## range skew kurtosis se
## MDVP.Fo.Hz. 171.77 0.58 -0.67 2.96
## MDVP.Fhi.Hz. 489.88 2.50 7.30 6.55
## MDVP.Flo.Hz. 173.69 1.20 0.57 3.12
## MDVP.Jitter... 0.03 3.04 11.54 0.00
## MDVP.Jitter.Abs. 0.00 2.61 10.42 0.00
## MDVP.RAP 0.02 3.31 13.65 0.00
## MDVP.PPQ 0.02 3.03 11.48 0.00
## Jitter.DDP 0.06 3.31 13.66 0.00
## MDVP.Shimmer 0.11 1.64 3.06 0.00
## MDVP.Shimmer.dB. 1.22 1.97 4.89 0.01
## Shimmer.APQ3 0.05 1.56 2.56 0.00
## Shimmer.APQ5 0.07 1.77 3.68 0.00
## MDVP.APQ 0.13 2.58 10.71 0.00
## Shimmer.DDA 0.16 1.56 2.56 0.00
## NHR 0.31 4.16 21.15 0.00
## HNR 24.61 -0.51 0.53 0.32
## RPDE 0.43 -0.14 -0.95 0.01
## DFA 0.25 -0.03 -0.72 0.00
## spread1 5.53 0.43 -0.11 0.08
## spread2 0.44 0.14 -0.14 0.01
## D2 2.25 0.42 0.15 0.03
## PPE 0.48 0.79 0.45 0.01
cor(data_clustering)
## MDVP.Fo.Hz. MDVP.Fhi.Hz. MDVP.Flo.Hz. MDVP.Jitter...
## MDVP.Fo.Hz. 1.00000000 0.400984676 0.59654552 -0.11800263
## MDVP.Fhi.Hz. 0.40098468 1.000000000 0.08495125 0.10208635
## MDVP.Flo.Hz. 0.59654552 0.084951251 1.00000000 -0.13991889
## MDVP.Jitter... -0.11800263 0.102086349 -0.13991889 1.00000000
## MDVP.Jitter.Abs. -0.38202665 -0.029198333 -0.27781524 0.93571398
## MDVP.RAP -0.07619381 0.097176619 -0.10051932 0.99027559
## MDVP.PPQ -0.11216543 0.091126194 -0.09582837 0.97425639
## Jitter.DDP -0.07621269 0.097149867 -0.10048768 0.99027622
## MDVP.Shimmer -0.09837375 0.002281231 -0.14454332 0.76906323
## MDVP.Shimmer.dB. -0.07374246 0.043465164 -0.11908865 0.80428928
## Shimmer.APQ3 -0.09471706 -0.003743251 -0.15074650 0.74662520
## Shimmer.APQ5 -0.07068178 -0.009996776 -0.10109462 0.72556100
## MDVP.APQ -0.07777382 0.004936985 -0.10729342 0.75825526
## Shimmer.DDA -0.09473157 -0.003732893 -0.15073674 0.74663517
## NHR -0.02198078 0.163766404 -0.10867045 0.90695860
## HNR 0.05914439 -0.024893140 0.21085090 -0.72816507
## RPDE -0.38389390 -0.112403513 -0.40014307 0.36067348
## DFA -0.44601329 -0.343096724 -0.05040631 0.09857244
## spread1 -0.41373817 -0.076657801 -0.39485736 0.69357671
## spread2 -0.24945005 -0.002953614 -0.24382940 0.38512347
## D2 0.17797951 0.176322818 -0.10062909 0.43343402
## PPE -0.37235638 -0.069543002 -0.34007134 0.72154293
## MDVP.Jitter.Abs. MDVP.RAP MDVP.PPQ Jitter.DDP
## MDVP.Fo.Hz. -0.38202665 -0.07619381 -0.11216543 -0.07621269
## MDVP.Fhi.Hz. -0.02919833 0.09717662 0.09112619 0.09714987
## MDVP.Flo.Hz. -0.27781524 -0.10051932 -0.09582837 -0.10048768
## MDVP.Jitter... 0.93571398 0.99027559 0.97425639 0.99027622
## MDVP.Jitter.Abs. 1.00000000 0.92291097 0.89777790 0.92291303
## MDVP.RAP 0.92291097 1.00000000 0.95731689 0.99999960
## MDVP.PPQ 0.89777790 0.95731689 1.00000000 0.95731916
## Jitter.DDP 0.92291303 0.99999960 0.95731916 1.00000000
## MDVP.Shimmer 0.70332237 0.75958052 0.79782603 0.75955470
## MDVP.Shimmer.dB. 0.71660128 0.79065155 0.83923894 0.79062060
## Shimmer.APQ3 0.69715303 0.74491236 0.76357992 0.74489376
## Shimmer.APQ5 0.64896070 0.70992682 0.78678047 0.70990709
## MDVP.APQ 0.64879344 0.73745467 0.80413930 0.73743867
## Shimmer.DDA 0.69716971 0.74491923 0.76359216 0.74490062
## NHR 0.83497218 0.91952071 0.84460353 0.91954818
## HNR -0.65680959 -0.72154316 -0.73151047 -0.72149437
## RPDE 0.44183856 0.34213980 0.33327415 0.34207948
## DFA 0.17503599 0.06408302 0.19630142 0.06402640
## spread1 0.73577923 0.64832777 0.71648864 0.64832755
## spread2 0.38854284 0.32440718 0.40760548 0.32437685
## D2 0.31069445 0.42660538 0.41252368 0.42655576
## PPE 0.74816165 0.67099905 0.76964729 0.67100525
## MDVP.Shimmer MDVP.Shimmer.dB. Shimmer.APQ3 Shimmer.APQ5
## MDVP.Fo.Hz. -0.098373748 -0.07374246 -0.094717062 -0.070681785
## MDVP.Fhi.Hz. 0.002281231 0.04346516 -0.003743251 -0.009996776
## MDVP.Flo.Hz. -0.144543324 -0.11908865 -0.150746503 -0.101094616
## MDVP.Jitter... 0.769063235 0.80428928 0.746625201 0.725561003
## MDVP.Jitter.Abs. 0.703322372 0.71660128 0.697153027 0.648960696
## MDVP.RAP 0.759580521 0.79065155 0.744912357 0.709926823
## MDVP.PPQ 0.797826025 0.83923894 0.763579916 0.786780474
## Jitter.DDP 0.759554700 0.79062060 0.744893765 0.709907085
## MDVP.Shimmer 1.000000000 0.98725781 0.987625052 0.982835448
## MDVP.Shimmer.dB. 0.987257815 1.00000000 0.963198085 0.973750561
## Shimmer.APQ3 0.987625052 0.96319809 1.000000000 0.960069764
## Shimmer.APQ5 0.982835448 0.97375056 0.960069764 1.000000000
## MDVP.APQ 0.950082893 0.96097672 0.896644519 0.949146111
## Shimmer.DDA 0.987625653 0.96320170 0.999999964 0.960071593
## NHR 0.722194454 0.74447728 0.716206735 0.658079759
## HNR -0.835270676 -0.82780535 -0.827123311 -0.813752789
## RPDE 0.447423645 0.41068380 0.435242425 0.399902849
## DFA 0.159953618 0.16515658 0.151124464 0.213873102
## spread1 0.654734300 0.65254666 0.610967362 0.646808933
## spread2 0.452024826 0.45431437 0.402242954 0.457194945
## D2 0.507088281 0.51223317 0.467265430 0.502174433
## PPE 0.693770720 0.69505813 0.645376686 0.702455664
## MDVP.APQ Shimmer.DDA NHR HNR RPDE
## MDVP.Fo.Hz. -0.077773819 -0.094731567 -0.02198078 0.059144387 -0.3838939
## MDVP.Fhi.Hz. 0.004936985 -0.003732893 0.16376640 -0.024893140 -0.1124035
## MDVP.Flo.Hz. -0.107293423 -0.150736736 -0.10867045 0.210850898 -0.4001431
## MDVP.Jitter... 0.758255255 0.746635172 0.90695860 -0.728165074 0.3606735
## MDVP.Jitter.Abs. 0.648793442 0.697169706 0.83497218 -0.656809593 0.4418386
## MDVP.RAP 0.737454666 0.744919228 0.91952071 -0.721543160 0.3421398
## MDVP.PPQ 0.804139303 0.763592161 0.84460353 -0.731510466 0.3332741
## Jitter.DDP 0.737438675 0.744900620 0.91954818 -0.721494370 0.3420795
## MDVP.Shimmer 0.950082893 0.987625653 0.72219445 -0.835270676 0.4474236
## MDVP.Shimmer.dB. 0.960976723 0.963201704 0.74447728 -0.827805346 0.4106838
## Shimmer.APQ3 0.896644519 0.999999964 0.71620674 -0.827123311 0.4352424
## Shimmer.APQ5 0.949146111 0.960071593 0.65807976 -0.813752789 0.3999028
## MDVP.APQ 1.000000000 0.896646766 0.69401905 -0.800406561 0.4513791
## Shimmer.DDA 0.896646766 1.000000000 0.71621454 -0.827130202 0.4352373
## NHR 0.694019049 0.716214539 1.00000000 -0.714072430 0.3708905
## HNR -0.800406561 -0.827130202 -0.71407243 1.000000000 -0.5987363
## RPDE 0.451379050 0.435237302 0.37089049 -0.598736337 1.0000000
## DFA 0.157275784 0.151132394 -0.13188174 -0.008664939 -0.1109500
## spread1 0.673158141 0.610971213 0.54086514 -0.673209818 0.5911170
## spread2 0.502187886 0.402223092 0.31809896 -0.431563748 0.4799045
## D2 0.536869028 0.467261374 0.47094876 -0.601401006 0.2369314
## PPE 0.721693953 0.645388954 0.55259127 -0.692875853 0.5458857
## DFA spread1 spread2 D2 PPE
## MDVP.Fo.Hz. -0.446013292 -0.4137382 -0.249450046 0.1779795 -0.3723564
## MDVP.Fhi.Hz. -0.343096724 -0.0766578 -0.002953614 0.1763228 -0.0695430
## MDVP.Flo.Hz. -0.050406307 -0.3948574 -0.243829403 -0.1006291 -0.3400713
## MDVP.Jitter... 0.098572442 0.6935767 0.385123473 0.4334340 0.7215429
## MDVP.Jitter.Abs. 0.175035992 0.7357792 0.388542835 0.3106944 0.7481617
## MDVP.RAP 0.064083019 0.6483278 0.324407179 0.4266054 0.6709990
## MDVP.PPQ 0.196301424 0.7164886 0.407605477 0.4125237 0.7696473
## Jitter.DDP 0.064026401 0.6483276 0.324376852 0.4265558 0.6710053
## MDVP.Shimmer 0.159953618 0.6547343 0.452024826 0.5070883 0.6937707
## MDVP.Shimmer.dB. 0.165156580 0.6525467 0.454314373 0.5122332 0.6950581
## Shimmer.APQ3 0.151124464 0.6109674 0.402242954 0.4672654 0.6453767
## Shimmer.APQ5 0.213873102 0.6468089 0.457194945 0.5021744 0.7024557
## MDVP.APQ 0.157275784 0.6731581 0.502187886 0.5368690 0.7216940
## Shimmer.DDA 0.151132394 0.6109712 0.402223092 0.4672614 0.6453890
## NHR -0.131881743 0.5408651 0.318098962 0.4709488 0.5525913
## HNR -0.008664939 -0.6732098 -0.431563748 -0.6014010 -0.6928759
## RPDE -0.110949960 0.5911170 0.479904528 0.2369314 0.5458857
## DFA 1.000000000 0.1956684 0.166548111 -0.1653810 0.2704447
## spread1 0.195668403 1.0000000 0.652357812 0.4951227 0.9624353
## spread2 0.166548111 0.6523578 1.000000000 0.5235317 0.6447110
## D2 -0.165381035 0.4951227 0.523531735 1.0000000 0.4805845
## PPE 0.270444747 0.9624353 0.644710959 0.4805845 1.0000000
corrplot::corrplot(cor(data_numeric),tl.col = "black",type= "full",tl.srt=40,tl.cex = 0.5)
r <- cor(data_clustering)
KMO(r)
## Kaiser-Meyer-Olkin factor adequacy
## Call: KMO(r = r)
## Overall MSA = 0.89
## MSA for each item =
## MDVP.Fo.Hz. MDVP.Fhi.Hz. MDVP.Flo.Hz. MDVP.Jitter...
## 0.53 0.65 0.68 0.91
## MDVP.Jitter.Abs. MDVP.RAP MDVP.PPQ Jitter.DDP
## 0.88 0.90 0.88 0.90
## MDVP.Shimmer MDVP.Shimmer.dB. Shimmer.APQ3 Shimmer.APQ5
## 0.89 0.95 0.90 0.90
## MDVP.APQ Shimmer.DDA NHR HNR
## 0.91 0.90 0.96 0.93
## RPDE DFA spread1 spread2
## 0.81 0.49 0.89 0.87
## D2 PPE
## 0.85 0.87
bartlett.test(data_clustering)
##
## Bartlett test of homogeneity of variances
##
## data: data_clustering
## Bartlett's K-squared = 48089, df = 21, p-value < 2.2e-16
df <- scale(data_clustering)
set.seed(123)
wss <- sapply(1:10, function(k){
kmeans(df, centers = k, nstart = 20)$tot.withinss
})
plot(1:10, wss, type="b", pch=19,
xlab="Jumlah Cluster (K)",
ylab="Total Within Sum of Squares",
main="Elbow Method")
avg_sil <- function(k){
km <- kmeans(df, centers = k, nstart = 25)
ss <- silhouette(km$cluster, dist(df))
mean(ss[,3])
}
k_values <- 2:10
avg_sil_values <- sapply(k_values, avg_sil)
plot(k_values, avg_sil_values, type="b", pch=19,
xlab="Jumlah Cluster",
ylab="Average Silhouette Width",
main="Silhouette Analysis")
kmeans <- kmeans(df, centers = 2)
kmedian <- pam(df, k = 2)
dbscan <- dbscan(df, eps = 0.7, MinPts = 5)
ms <- meanShift(df)
fcm <- cmeans(df, centers = 2, m = 2)
plot(df, col = kmeans$cluster, main = "K-Means")
plot(df, col = kmedian$clustering, main = "K-Median (PAM)")
plot(df, col = dbscan$cluster + 1, main = "DBSCAN (0 = Noise)")
plot(df, col = ms$assignment, main = "Mean Shift")
plot(df, col = fcm$cluster, main = "Fuzzy C-Means")
plot(df, col = label + 1, main = "Status")
fviz_cluster(list(data = df, cluster = kmeans$cluster), main="K-Means")
fviz_cluster(list(data = df, cluster = kmedian$clustering), main="K-Median")
fviz_cluster(list(data = df, cluster = dbscan$cluster), main="DBSCAN")
fviz_cluster(list(data = df, cluster = fcm$cluster), main="Fuzzy C-Means")
