-
Notifications
You must be signed in to change notification settings - Fork 0
/
segmentation.r
182 lines (125 loc) · 5.37 KB
/
segmentation.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
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
require("plotrix")
customer_data = read.csv("D:/Work/customer-segmentation/customers.csv") # nolint
str(customer_data)
names(customer_data)
head(customer_data)
summary(customer_data$Age)
sd(customer_data$Age)
summary(customer_data$Annual.Income..k..)
sd(customer_data$Annual.Income..k..)
summary(customer_data$Age)
sd(customer_data$Spending.Score..1.100.)
#Customer Gender Visualization
a=table(customer_data$Gender)
barplot(a,main="Using BarPlot to display Gender Comparision",
ylab="Count",
xlab="Gender",
col=rainbow(2),
legend=rownames(a))
pct=round(a/sum(a)*100)
lbs=paste(c("Female","Male")," ",pct,"%",sep=" ")
library(plotrix)
pie3D(a,labels=lbs,
main="Pie Chart Depicting Ratio of Female and Male")
#Visualization of Age Distribution
summary(customer_data$Age)
hist(customer_data$Age,
col="blue",
main="Histogram to Show Count of Age Class",
xlab="Age Class",
ylab="Frequency",
labels=TRUE)
boxplot(customer_data$Age,
col="#ff0066",
main="Boxplot for Descriptive Analysis of Age")
#Analysis of the Annual Income of the Customers
summary(customer_data$Annual.Income..k..)
hist(customer_data$Annual.Income..k..,
col="#660033",
main="Histogram for Annual Income",
xlab="Annual Income Class",
ylab="Frequency",
labels=TRUE)
plot(density(customer_data$Annual.Income..k..),
col="yellow",
main="Density Plot for Annual Income",
xlab="Annual Income Class",
ylab="Density")
polygon(density(customer_data$Annual.Income..k..),
col="#ccff66")
boxplot(customer_data$Spending.Score..1.100.,
horizontal=TRUE,
col="#990000",
main="BoxPlot for Descriptive Analysis of Spending Score")
hist(customer_data$Spending.Score..1.100.,
main="HistoGram for Spending Score",
xlab="Spending Score Class",
ylab="Frequency",
col="#6600cc",
labels=TRUE)
#K-means Algorithm
library(purrr)
set.seed(123)
# function to calculate total intra-cluster sum of square
iss <- function(k) {
kmeans(customer_data[,3:5],k,iter.max=100,nstart=100,algorithm="Lloyd" )$tot.withinss
}
k.values <- 1:10
iss_values <- map_dbl(k.values, iss)
plot(k.values, iss_values,
type="b", pch = 19, frame = FALSE,
xlab="Number of clusters K",
ylab="Total intra-clusters sum of squares")
#Average Silhouette Method
library(cluster)
library(gridExtra)
library(grid)
k2<-kmeans(customer_data[,3:5],2,iter.max=100,nstart=50,algorithm="Lloyd")
s2<-plot(silhouette(k2$cluster,dist(customer_data[,3:5],"euclidean")))
k3<-kmeans(customer_data[,3:5],3,iter.max=100,nstart=50,algorithm="Lloyd")
s3<-plot(silhouette(k3$cluster,dist(customer_data[,3:5],"euclidean")))
k4<-kmeans(customer_data[,3:5],4,iter.max=100,nstart=50,algorithm="Lloyd")
s4<-plot(silhouette(k4$cluster,dist(customer_data[,3:5],"euclidean")))
k5<-kmeans(customer_data[,3:5],5,iter.max=100,nstart=50,algorithm="Lloyd")
s5<-plot(silhouette(k5$cluster,dist(customer_data[,3:5],"euclidean")))
k6<-kmeans(customer_data[,3:5],6,iter.max=100,nstart=50,algorithm="Lloyd")
s6<-plot(silhouette(k6$cluster,dist(customer_data[,3:5],"euclidean")))
k7<-kmeans(customer_data[,3:5],7,iter.max=100,nstart=50,algorithm="Lloyd")
s7<-plot(silhouette(k7$cluster,dist(customer_data[,3:5],"euclidean")))
k8<-kmeans(customer_data[,3:5],8,iter.max=100,nstart=50,algorithm="Lloyd")
s8<-plot(silhouette(k8$cluster,dist(customer_data[,3:5],"euclidean")))
k9<-kmeans(customer_data[,3:5],9,iter.max=100,nstart=50,algorithm="Lloyd")
s9<-plot(silhouette(k9$cluster,dist(customer_data[,3:5],"euclidean")))
k10<-kmeans(customer_data[,3:5],10,iter.max=100,nstart=50,algorithm="Lloyd")
s10<-plot(silhouette(k10$cluster,dist(customer_data[,3:5],"euclidean")))
library(NbClust)
library(factoextra)
fviz_nbclust(customer_data[,3:5], kmeans, method = "silhouette")
set.seed(125)
stat_gap <- clusGap(customer_data[,3:5], FUN = kmeans, nstart = 25,
K.max = 10, B = 50)
fviz_gap_stat(stat_gap)
k6<-kmeans(customer_data[,3:5],6,iter.max=100,nstart=50,algorithm="Lloyd")
k6
#Visualizing the Clustering Results using the First Two Principle Components
pcclust=prcomp(customer_data[,3:5],scale=FALSE) #principal component analysis
summary(pcclust)
pcclust$rotation[,1:2]
set.seed(1)
ggplot(customer_data, aes(x =Annual.Income..k.., y = Spending.Score..1.100.)) +
geom_point(stat = "identity", aes(color = as.factor(k6$cluster))) +
scale_color_discrete(name=" ",
breaks=c("1", "2", "3", "4", "5","6"),
labels=c("Cluster 1", "Cluster 2", "Cluster 3", "Cluster 4", "Cluster 5","Cluster 6")) +
ggtitle("Segments of Customers", subtitle = "Using K-means Clustering")
ggplot(customer_data, aes(x =Spending.Score..1.100., y =Age)) +
geom_point(stat = "identity", aes(color = as.factor(k6$cluster))) +
scale_color_discrete(name=" ",
breaks=c("1", "2", "3", "4", "5","6"),
labels=c("Cluster 1", "Cluster 2", "Cluster 3", "Cluster 4", "Cluster 5","Cluster 6")) +
ggtitle("Segments of Customers", subtitle = "Using K-means Clustering")
kCols=function(vec){cols=rainbow (length (unique (vec)))
return (cols[as.numeric(as.factor(vec))])}
digCluster<-k6$cluster; dignm<-as.character(digCluster); # K-means clusters
plot(pcclust$x[,1:2], col =kCols(digCluster),pch =19,xlab ="K-means",ylab="classes")
legend("bottomleft",unique(dignm),fill=unique(kCols(digCluster)))