K Means Clustering
Big Datamatica
16 August 2016
K-Means Clustering
Set data path as per your data file location
getwd()## [1] "E:/R ALGORITHM/UBCF(User-based collaborative filtering)"setwd("E:/R ALGORITHM/UBCF(User-based collaborative filtering)")Read the file along with header
Age_income<-read.csv("Age_income.csv",header=TRUE)
print(Age_income)## Age Income
## 1 50 1273
## 2 24 1591
## 3 39 1680
## 4 46 1179
## 5 38 1107
## 6 42 1286
## 7 23 1328
## 8 36 1526
## 9 34 1188
## 10 28 1227
## 11 29 1738
## 12 45 1194
## 13 30 1834
## 14 28 1321
## 15 26 1263
## 16 31 1935
## 17 48 1287
## 18 42 1276
## 19 33 1228
## 20 40 1445
## 21 29 1468
## 22 25 1498
## 23 36 1211
## 24 27 1257
## 25 42 1477
## 26 33 1466
## 27 24 1922
## 28 34 1722
## 29 26 1957
## 30 48 1701
## 31 25 1586
## 32 37 1354
## 33 27 1994
## 34 40 1255
## 35 48 1930
## 36 33 1741
## 37 40 1569
## 38 29 1638
## 39 29 1425
## 40 44 1871
## 41 42 1006
## 42 24 1922
## 43 35 1594
## 44 44 1904
## 45 29 1529
## 46 29 1819
## 47 37 1203
## 48 48 1822
## 49 28 1623
## 50 29 1853
## 51 42 1365
## 52 34 1840
## 53 41 1003
## 54 39 1800
## 55 37 1490
## 56 38 1531
## 57 48 1697
## 58 45 1127
## 59 39 1434
## 60 44 1515
## 61 36 1650
## 62 36 1219
## 63 39 1723
## 64 44 1459
## 65 25 1424
## 66 30 1900
## 67 40 1125
## 68 46 1145
## 69 35 1387
## 70 41 1346
## 71 23 1403
## 72 24 1631
## 73 28 1938
## 74 26 1059
## 75 46 1204
## 76 30 1349
## 77 44 1978
## 78 32 1491
## 79 28 1605
## 80 39 1842
## 81 30 1891
## 82 38 1952
## 83 40 1934
## 84 33 1829
## 85 41 1066
## 86 24 1712
## 87 41 1909
## 88 48 1586
## 89 29 1315
## 90 45 2000
## 91 33 1241
## 92 50 1092
## 93 39 1159
## 94 50 1537
## 95 33 1959
## 96 49 1625
## 97 44 1716
## 98 38 1551
## 99 42 1233
## 100 23 1452AP<-read.csv("Amazon_products.csv",header=TRUE)
print(AP)## user Product Date City Age Gender
## 1 101 Iphone 13-04-2016 London 25 1
## 2 102 Nokia 10-04-2016 USA 26 0
## 3 103 Samsung 01-04-2016 CHINA 27 1
## 4 104 HTC 04-04-2016 Singapore 28 0
## 5 105 MI 08-04-2016 China 29 1
## 6 106 Lenovo 07-04-2016 Dubai 22 0
## 7 107 blackberry 13-04-2016 Europe 23 1
## 8 108 Micromax 14-04-2016 INDIA 24 0
## 9 109 Celkon 15-04-2016 Srilanka 21 1
## 10 110 Intex 16-04-2016 Austrailla 20 0
## 11 101 Iphone 14-04-2016 London 25 1
## 12 102 Nokia 10-04-2016 USA 26 0
## 13 103 Samsung 02-04-2016 CHINA 27 1
## 14 104 HTC 05-04-2016 Singapore 28 0
## 15 105 MI 09-04-2016 China 29 1
## 16 106 Lenovo 08-04-2016 Dubai 22 0
## 17 102 Nokia 10-04-2016 USA 26 0
## 18 108 Micromax 15-04-2016 INDIA 24 0
## 19 109 Celkon 16-04-2016 Srilanka 21 1
## 20 102 Nokia 10-04-2016 USA 26 0
## URL Revene
## 1 https://www.Flipkart.com 1689
## 2 https://www.amazon.com 1341
## 3 https://www.snapdeal.com 4395
## 4 https://www.shopclues.com 3818
## 5 https://www.Slickdeals.net 1425
## 6 https://www.ebay.com 4893
## 7 https://www.google.co.in/chromecast/get-offers/ 4284
## 8 http://www.newegg.com/global/in 4783
## 9 https://www.paytm.com/ 4677
## 10 https://www.yahoo.com 2861
## 11 https://www.Flipkart.com 3515
## 12 https://www.amazon.com 4537
## 13 https://www.snapdeal.com 4804
## 14 https://www.shopclues.com 2057
## 15 https://www.Slickdeals.net 1055
## 16 https://www.ebay.com 3519
## 17 https://www.amazon.com 4383
## 18 http://www.newegg.com 1891
## 19 https://www.paytm.com/ 3175
## 20 https://www.amazon.com 1904AP1<-AP[,-c(2,4,7)]
AP1<-AP1[,-c(2)]dim(AP1)## [1] 20 4APclust<-kmeans(AP1,3)
APclust1<-cbind(AP1,APclust$cluster)
plot(AP1,col=APclust$cluster)
The data given by x are clustered by the k-means method, which aims to partition the points into k groups such that the sum of squares from points to the assigned cluster centres is minimized. At the minimum, all cluster centres are at the mean of their Voronoi sets (the set of data points which are nearest to the cluster centre).
Value
kmeans returns an object of class “kmeans” which has a print and a fitted method. It
is a list with at least the following components:
cluster A vector of integers (from 1:k) indicating the cluster to which each point is
centers A matrix of cluster centres.
totss The total sum of squares.
withinss Vector of within-cluster sum of squares, one component per cluster.
tot.withinss Total within-cluster sum of squares, i.e. sum(withinss).
betweenss The between-cluster sum of squares, i.e. totss-tot.withinss.
size The number of points in each cluster.
iter The number of (outer) iterations.
ifault integer: indicator of a possible algorithm problem - for experts.
Implementing K_means clustering Model
clust<-kmeans(Age_income,3)
summary(clust)## Length Class Mode
## cluster 100 -none- numeric
## centers 6 -none- numeric
## totss 1 -none- numeric
## withinss 3 -none- numeric
## tot.withinss 1 -none- numeric
## betweenss 1 -none- numeric
## size 3 -none- numeric
## iter 1 -none- numeric
## ifault 1 -none- numericAge_income1<-cbind(Age_income,clust$cluster)
plot(Age_income,col=clust$cluster)
points(clust$centers,col=1:2,pch=8,cex=2)