generated from github/welcome-to-github-and-desktop
-
Notifications
You must be signed in to change notification settings - Fork 0
/
tb data mining.R
70 lines (38 loc) · 1.13 KB
/
tb data mining.R
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
setwd("C:/TB-DATA MINING (001,004,037)")
getwd()
install.packages("tidyverse")
install.packages("cluster")
install.packages("factoextra")
library(tidyverse)
library(cluster) # Algoritma klastering
library(factoextra) # Algoritma klastering dan visualisasi
dataset <- read.csv("USArrest.csv", sep = ";")
str(dataset)
dataclus <- USArrests
str(dataclus)
head(dataclus)
dataclus1 <- na.omit(dataclus) #untuk menghilangkan data missing
summary(dataclus1)
datafix <- scale(dataclus1) #standarisasi data
fviz_nbclust(datafix, kmeans, method = "wss") # metode elbow
fviz_nbclust(datafix, kmeans, method = "silhouette") # metode silhouette
set.seed(123)
gap_stat <- clusGap(datafix, FUN = kmeans, nstart = 25,
K.max = 10, B = 50) # metode gap statistic
fviz_gap_stat(gap_stat)
final <- kmeans(datafix, 4, nstart = 25)
print(final)
fviz_cluster(final, data = datafix)
USArrests %>%
mutate(Cluster = final$cluster) %>%
group_by(Cluster) %>%
summarise_all("mean")
?fviz
?nbclust
?datafix
?set.seed
?gap_stat
?mutate
?group_by
?fun
?summari