Also Observe the change in number of rules for different support,confidence values
install.packages("rmarkdown",repos = "http://cran.us.r-project.org")
## Installing package into 'C:/Users/tswaminathan/Documents/R/win-library/3.5'
## (as 'lib' is unspecified)
## package 'rmarkdown' successfully unpacked and MD5 sums checked
##
## The downloaded binary packages are in
## C:\Users\tswaminathan\AppData\Local\Temp\RtmpGkj4Ij\downloaded_packages
install.packages("arules",repos = "http://cran.us.r-project.org")
## Installing package into 'C:/Users/tswaminathan/Documents/R/win-library/3.5'
## (as 'lib' is unspecified)
## package 'arules' successfully unpacked and MD5 sums checked
##
## The downloaded binary packages are in
## C:\Users\tswaminathan\AppData\Local\Temp\RtmpGkj4Ij\downloaded_packages
install.packages("arulesViz",repos = "http://cran.us.r-project.org")
## Installing package into 'C:/Users/tswaminathan/Documents/R/win-library/3.5'
## (as 'lib' is unspecified)
## package 'arulesViz' successfully unpacked and MD5 sums checked
##
## The downloaded binary packages are in
## C:\Users\tswaminathan\AppData\Local\Temp\RtmpGkj4Ij\downloaded_packages
library(arules)
## Loading required package: Matrix
##
## Attaching package: 'arules'
## The following objects are masked from 'package:base':
##
## abbreviate, write
library(arulesViz)
## Loading required package: grid
TransRetail <- read.csv(file.choose())
View(TransRetail)
rules <- apriori(TransRetail,parameter=list(support=0.003, confidence = 0.8,minlen=5))
## Apriori
##
## Parameter specification:
## confidence minval smax arem aval originalSupport maxtime support minlen
## 0.8 0.1 1 none FALSE TRUE 5 0.003 5
## maxlen target ext
## 10 rules FALSE
##
## Algorithmic control:
## filter tree heap memopt load sort verbose
## 0.1 TRUE TRUE FALSE TRUE 2 TRUE
##
## Absolute minimum support count: 1671
##
## set item appearances ...[0 item(s)] done [0.00s].
## set transactions ...[4754 item(s), 557040 transaction(s)] done [1.04s].
## sorting and recoding items ... [307 item(s)] done [0.02s].
## creating transaction tree ... done [0.41s].
## checking subsets of size 1 2 3 4 5 done [0.00s].
## writing ... [8 rule(s)] done [0.00s].
## creating S4 object ... done [0.06s].
# Provided the rules with 0.3% Support, 80 % Confidence and Purchased a minimum of 3 items
rules
## set of 8 rules
summary(rules)
## set of 8 rules
##
## rule length distribution (lhs + rhs):sizes
## 5
## 8
##
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 5 5 5 5 5 5
##
## summary of quality measures:
## support confidence lift count
## Min. :0.003704 Min. :1 Min. :26.93 Min. :2063
## 1st Qu.:0.003704 1st Qu.:1 1st Qu.:37.11 1st Qu.:2063
## Median :0.003977 Median :1 Median :62.95 Median :2216
## Mean :0.003977 Mean :1 Mean :57.92 Mean :2216
## 3rd Qu.:0.004251 3rd Qu.:1 3rd Qu.:78.42 3rd Qu.:2368
## Max. :0.004251 Max. :1 Max. :80.56 Max. :2368
##
## mining info:
## data ntransactions support confidence
## TransRetail 557040 0.003 0.8
inspect(head(sort(rules, by = "lift")))
## lhs rhs support confidence lift count
## [1] {X.HEART.='HEART',
## X.HOLDER.='HOLDER',
## X.T.LIGHT.='T-LIGHT',
## X.WHITE.='WHITE'} => {X.HANGING.='HANGING'} 0.004251041 1 80.55531 2368
## [2] {X.HANGING.='HANGING',
## X.HEART.='HEART',
## X.HOLDER.='HOLDER',
## X.WHITE.='WHITE'} => {X.T.LIGHT.='T-LIGHT'} 0.004251041 1 79.53170 2368
## [3] {X.HANGING.='72',
## X.HEART.='CAKE',
## X.HOLDER.='CASES',
## X.T.LIGHT.='OF'} => {X.WHITE.='PACK'} 0.003703504 1 78.04960 2063
## [4] {X.HANGING.='HANGING',
## X.HEART.='HEART',
## X.T.LIGHT.='T-LIGHT',
## X.WHITE.='WHITE'} => {X.HOLDER.='HOLDER'} 0.004251041 1 71.77426 2368
## [5] {X.HANGING.='72',
## X.HEART.='CAKE',
## X.T.LIGHT.='OF',
## X.WHITE.='PACK'} => {X.HOLDER.='CASES'} 0.003703504 1 54.12885 2063
## [6] {X.HANGING.='72',
## X.HOLDER.='CASES',
## X.T.LIGHT.='OF',
## X.WHITE.='PACK'} => {X.HEART.='CAKE'} 0.003703504 1 38.00764 2063
head(quality(rules))
## support confidence lift count
## 1 0.003703504 1 26.93226 2063
## 2 0.003703504 1 38.00764 2063
## 3 0.003703504 1 54.12885 2063
## 4 0.003703504 1 78.04960 2063
## 5 0.004251041 1 34.41493 2368
## 6 0.004251041 1 71.77426 2368
plot(rules,method = "scatterplot",jitter =0)
plot(rules, method = "grouped")
# It looks like people who purchase Heart, Holder, T-Light and White would definitely purchase Hanging.
# People who purchase 72, Cake,Of,Pack would purchase Cases.
plot(rules,method = "graph")
