library(tidyverse)
## ── Attaching packages ──────────────────────────────────────────────────────────── tidyverse 1.3.0 ──
## ✓ ggplot2 3.3.0 ✓ purrr 0.3.3
## ✓ tibble 3.0.0 ✓ dplyr 0.8.5
## ✓ tidyr 1.0.2 ✓ stringr 1.4.0
## ✓ readr 1.3.1 ✓ forcats 0.5.0
## ── Conflicts ─────────────────────────────────────────────────────────────── tidyverse_conflicts() ──
## x dplyr::filter() masks stats::filter()
## x dplyr::lag() masks stats::lag()
library(readxl)
library(knitr)
library(ggplot2)
library(lubridate)
##
## Attaching package: 'lubridate'
## The following objects are masked from 'package:dplyr':
##
## intersect, setdiff, union
## The following objects are masked from 'package:base':
##
## date, intersect, setdiff, union
library(arules)
## Loading required package: Matrix
##
## Attaching package: 'Matrix'
## The following objects are masked from 'package:tidyr':
##
## expand, pack, unpack
##
## Attaching package: 'arules'
## The following object is masked from 'package:dplyr':
##
## recode
## The following objects are masked from 'package:base':
##
## abbreviate, write
library(arulesViz)
## Loading required package: grid
## Registered S3 method overwritten by 'seriation':
## method from
## reorder.hclust gclus
library(plyr)
## ------------------------------------------------------------------------------
## You have loaded plyr after dplyr - this is likely to cause problems.
## If you need functions from both plyr and dplyr, please load plyr first, then dplyr:
## library(plyr); library(dplyr)
## ------------------------------------------------------------------------------
##
## Attaching package: 'plyr'
## The following objects are masked from 'package:dplyr':
##
## arrange, count, desc, failwith, id, mutate, rename, summarise,
## summarize
## The following object is masked from 'package:purrr':
##
## compact
library(reshape2)
##
## Attaching package: 'reshape2'
## The following object is masked from 'package:tidyr':
##
## smiths
library(DT)
library(RColorBrewer)
grocery<-read.csv("grocery.csv")
colnames(grocery)<- "items"
rownames(grocery)<-NULL
write.csv(grocery,file="g.csv",quote = FALSE,row.names = FALSE)
grocery<-read.transactions("g.csv",format="basket",sep=",")
itemFrequencyPlot(grocery, topN=20, type='absolute',col=c(brewer.pal(8,"Set1")))
rules<- apriori(grocery,parameter = list(supp=0.01,conf=0.6))
## Apriori
##
## Parameter specification:
## confidence minval smax arem aval originalSupport maxtime support minlen
## 0.6 0.1 1 none FALSE TRUE 5 0.01 1
## 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: 0
##
## set item appearances ...[0 item(s)] done [0.00s].
## set transactions ...[12 item(s), 20 transaction(s)] done [0.00s].
## sorting and recoding items ... [12 item(s)] done [0.00s].
## creating transaction tree ... done [0.00s].
## checking subsets of size 1 2 3 4 done [0.00s].
## writing ... [72 rule(s)] done [0.00s].
## creating S4 object ... done [0.00s].
rules<-sort(rules,by="confidence",decreasing = TRUE)
summary(rules)
## set of 72 rules
##
## rule length distribution (lhs + rhs):sizes
## 1 2 3 4
## 1 12 40 19
##
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 1.000 3.000 3.000 3.069 4.000 4.000
##
## summary of quality measures:
## support confidence lift count
## Min. :0.05000 Min. :0.600 Min. : 1.000 Min. : 1.000
## 1st Qu.:0.05000 1st Qu.:0.950 1st Qu.: 1.667 1st Qu.: 1.000
## Median :0.07500 Median :1.000 Median : 2.857 Median : 1.500
## Mean :0.09028 Mean :0.919 Mean : 3.105 Mean : 1.806
## 3rd Qu.:0.10000 3rd Qu.:1.000 3rd Qu.: 3.500 3rd Qu.: 2.000
## Max. :0.60000 Max. :1.000 Max. :10.000 Max. :12.000
##
## mining info:
## data ntransactions support confidence
## grocery 20 0.01 0.6
inspect(rules[1:20])
## lhs rhs support confidence lift count
## [1] {JAM} => {MAGGI} 0.10 1 4.000000 2
## [2] {JAM} => {BREAD} 0.10 1 1.666667 2
## [3] {COCK} => {COFFEE} 0.15 1 2.500000 3
## [4] {JAM,MILK} => {MAGGI} 0.05 1 4.000000 1
## [5] {MAGGI,MILK} => {JAM} 0.05 1 10.000000 1
## [6] {JAM,MILK} => {BREAD} 0.05 1 1.666667 1
## [7] {JAM,TEA} => {MAGGI} 0.05 1 4.000000 1
## [8] {JAM,MAGGI} => {BREAD} 0.10 1 1.666667 2
## [9] {BREAD,JAM} => {MAGGI} 0.10 1 4.000000 2
## [10] {JAM,TEA} => {BREAD} 0.05 1 1.666667 1
## [11] {BISCUIT,COCK} => {CORNFLAKES} 0.10 1 3.333333 2
## [12] {COCK,CORNFLAKES} => {BISCUIT} 0.10 1 3.333333 2
## [13] {BISCUIT,COCK} => {COFFEE} 0.10 1 2.500000 2
## [14] {BISCUIT,COFFEE} => {COCK} 0.10 1 6.666667 2
## [15] {COCK,CORNFLAKES} => {COFFEE} 0.10 1 2.500000 2
## [16] {BREAD,COCK} => {COFFEE} 0.05 1 2.500000 1
## [17] {BOURNVITA,COFFEE} => {SUGER} 0.05 1 3.333333 1
## [18] {BOURNVITA,TEA} => {BREAD} 0.10 1 1.666667 2
## [19] {MAGGI,MILK} => {BREAD} 0.05 1 1.666667 1
## [20] {BISCUIT,MILK} => {CORNFLAKES} 0.05 1 3.333333 1
topRules <- rules[1:10]
plot(topRules)
## To reduce overplotting, jitter is added! Use jitter = 0 to prevent jitter.
plot(topRules, method="graph")
