Groceries Dataset
library(arules)
## Warning: package 'arules' was built under R version 3.4.4
## Loading required package: Matrix
##
## Attaching package: 'arules'
## The following objects are masked from 'package:base':
##
## abbreviate, write
library(arulesViz)
## Warning: package 'arulesViz' was built under R version 3.4.4
## Loading required package: grid
library(grid)
data("Groceries")
#data()
class(Groceries)
## [1] "transactions"
## attr(,"package")
## [1] "arules"
# Item Frequency plot
windows()
itemFrequencyPlot(Groceries,topN=15)
# topN = top frequent items
class(Groceries) # transactions type
## [1] "transactions"
## attr(,"package")
## [1] "arules"
rules <-
apriori(Groceries,parameter=list(supp=0.002, confidence=0.60,minlen = 2, maxlen=4))
## Apriori
##
## Parameter specification:
## confidence minval smax arem aval originalSupport maxtime support minlen
## 0.6 0.1 1 none FALSE TRUE 5 0.002 2
## maxlen target ext
## 4 rules FALSE
##
## Algorithmic control:
## filter tree heap memopt load sort verbose
## 0.1 TRUE TRUE FALSE TRUE 2 TRUE
##
## Absolute minimum support count: 19
##
## set item appearances ...[0 item(s)] done [0.00s].
## set transactions ...[169 item(s), 9835 transaction(s)] done [0.00s].
## sorting and recoding items ... [147 item(s)] done [0.00s].
## creating transaction tree ... done [0.00s].
## checking subsets of size 1 2 3 4
## Warning in apriori(Groceries, parameter = list(supp = 0.002, confidence =
## 0.6, : Mining stopped (maxlen reached). Only patterns up to a length of 4
## returned!
## done [0.01s].
## writing ... [349 rule(s)] done [0.00s].
## creating S4 object ... done [0.00s].
inspect(head(sort(rules), n=10))
## lhs rhs support confidence lift count
## [1] {butter,
## yogurt} => {whole milk} 0.009354347 0.6388889 2.500387 92
## [2] {root vegetables,
## butter} => {whole milk} 0.008235892 0.6377953 2.496107 81
## [3] {root vegetables,
## other vegetables,
## yogurt} => {whole milk} 0.007829181 0.6062992 2.372842 77
## [4] {tropical fruit,
## other vegetables,
## yogurt} => {whole milk} 0.007625826 0.6198347 2.425816 75
## [5] {tropical fruit,
## domestic eggs} => {whole milk} 0.006914082 0.6071429 2.376144 68
## [6] {butter,
## whipped/sour cream} => {whole milk} 0.006710727 0.6600000 2.583008 66
## [7] {tropical fruit,
## curd} => {whole milk} 0.006507372 0.6336634 2.479936 64
## [8] {tropical fruit,
## butter} => {whole milk} 0.006202339 0.6224490 2.436047 61
## [9] {butter,
## domestic eggs} => {whole milk} 0.005998983 0.6210526 2.430582 59
## [10] {pip fruit,
## whipped/sour cream} => {whole milk} 0.005998983 0.6483516 2.537421 59
# Plotting rules as graphs
plot(head(sort(rules, by = "lift"), n=10), method = "graph") #, control=list(cex=1.9))
# Default plot of Rules
plot(rules)
## To reduce overplotting, jitter is added! Use jitter = 0 to prevent jitter.
# Dark red spots are interesting as they represent high lift values
plot(head(sort(rules, by = "lift"), n=10),method="grouped")
