sessionInfo()
## R version 3.2.2 (2015-08-14)
## Platform: i386-w64-mingw32/i386 (32-bit)
## Running under: Windows 7 (build 7601) Service Pack 1
##
## locale:
## [1] LC_COLLATE=English_United States.1252
## [2] LC_CTYPE=English_United States.1252
## [3] LC_MONETARY=English_United States.1252
## [4] LC_NUMERIC=C
## [5] LC_TIME=English_United States.1252
##
## attached base packages:
## [1] stats graphics grDevices utils datasets methods base
##
## loaded via a namespace (and not attached):
## [1] magrittr_1.5 tools_3.2.2 htmltools_0.3 stringi_1.0-1 rmarkdown_0.7
## [6] knitr_1.10.5 stringr_1.0.0 digest_0.6.8 evaluate_0.7
library(arules)
## Loading required package: Matrix
##
## Attaching package: 'arules'
##
## The following objects are masked from 'package:base':
##
## %in%, write
library(arulesViz)
## Loading required package: grid
##
## Attaching package: 'arulesViz'
##
## The following object is masked from 'package:base':
##
## abbreviate
data("Groceries")
Groceries
## transactions in sparse format with
## 9835 transactions (rows) and
## 169 items (columns)
head(Groceries)
## transactions in sparse format with
## 6 transactions (rows) and
## 169 items (columns)
Groceries[1:6]
## transactions in sparse format with
## 6 transactions (rows) and
## 169 items (columns)
inspect(Groceries[1:6])
## items
## 1 {citrus fruit,
## semi-finished bread,
## margarine,
## ready soups}
## 2 {tropical fruit,
## yogurt,
## coffee}
## 3 {whole milk}
## 4 {pip fruit,
## yogurt,
## cream cheese ,
## meat spreads}
## 5 {other vegetables,
## whole milk,
## condensed milk,
## long life bakery product}
## 6 {whole milk,
## butter,
## yogurt,
## rice,
## abrasive cleaner}
itemFrequencyPlot(Groceries,topN=20,type="absolute")
#apriori
rules.all=apriori(Groceries,
parameter = list(supp = 0.001, conf = 0.8))
##
## Parameter specification:
## confidence minval smax arem aval originalSupport support minlen maxlen
## 0.8 0.1 1 none FALSE TRUE 0.001 1 10
## target ext
## rules FALSE
##
## Algorithmic control:
## filter tree heap memopt load sort verbose
## 0.1 TRUE TRUE FALSE TRUE 2 TRUE
##
## apriori - find association rules with the apriori algorithm
## version 4.21 (2004.05.09) (c) 1996-2004 Christian Borgelt
## set item appearances ...[0 item(s)] done [0.00s].
## set transactions ...[169 item(s), 9835 transaction(s)] done [0.00s].
## sorting and recoding items ... [157 item(s)] done [0.00s].
## creating transaction tree ... done [0.01s].
## checking subsets of size 1 2 3 4 5 6 done [0.02s].
## writing ... [410 rule(s)] done [0.00s].
## creating S4 object ... done [0.00s].
rules.all
## set of 410 rules
inspect(rules.all[1:5])
## lhs rhs support confidence lift
## 1 {liquor,
## red/blush wine} => {bottled beer} 0.001931876 0.9047619 11.235269
## 2 {curd,
## cereals} => {whole milk} 0.001016777 0.9090909 3.557863
## 3 {yogurt,
## cereals} => {whole milk} 0.001728521 0.8095238 3.168192
## 4 {butter,
## jam} => {whole milk} 0.001016777 0.8333333 3.261374
## 5 {soups,
## bottled beer} => {whole milk} 0.001118454 0.9166667 3.587512
plot(rules.all[1:5])
plot(rules.all[1:5],method="graph",interactive = F)
plot(rules.all[1:15],method="graph",interactive = T)
subrules2 <- head(sort(rules.all, by="lift"), 10)
plot(subrules2, method="graph")
plot(subrules2, method="grouped")
plot(subrules2, method="matrix")
## Itemsets in Antecedent (LHS)
## [1] "{liquor,red/blush wine}"
## [2] "{citrus fruit,other vegetables,soda,fruit/vegetable juice}"
## [3] "{tropical fruit,other vegetables,whole milk,yogurt,oil}"
## [4] "{citrus fruit,grapes,fruit/vegetable juice}"
## [5] "{other vegetables,whole milk,yogurt,rice}"
## [6] "{tropical fruit,other vegetables,whole milk,oil}"
## [7] "{ham,pip fruit,other vegetables,yogurt}"
## [8] "{beef,citrus fruit,tropical fruit,other vegetables}"
## [9] "{root vegetables,butter,cream cheese }"
## [10] "{tropical fruit,whole milk,butter,sliced cheese}"
## Itemsets in Consequent (RHS)
## [1] "{bottled beer}" "{root vegetables}" "{tropical fruit}"
## [4] "{yogurt}"
plot(rules.all[1:15], method="matrix3D")
## Itemsets in Antecedent (LHS)
## [1] "{liquor,red/blush wine}"
## [2] "{curd,cereals}"
## [3] "{yogurt,cereals}"
## [4] "{butter,jam}"
## [5] "{soups,bottled beer}"
## [6] "{napkins,house keeping products}"
## [7] "{whipped/sour cream,house keeping products}"
## [8] "{pastry,sweet spreads}"
## [9] "{turkey,curd}"
## [10] "{rice,sugar}"
## [11] "{butter,rice}"
## [12] "{domestic eggs,rice}"
## [13] "{rice,bottled water}"
## [14] "{yogurt,rice}"
## [15] "{oil,mustard}"
## Itemsets in Consequent (RHS)
## [1] "{bottled beer}" "{whole milk}" "{other vegetables}"
plot(rules.all[1:15], method="matrix3D",measure="lift")
## Itemsets in Antecedent (LHS)
## [1] "{liquor,red/blush wine}"
## [2] "{curd,cereals}"
## [3] "{yogurt,cereals}"
## [4] "{butter,jam}"
## [5] "{soups,bottled beer}"
## [6] "{napkins,house keeping products}"
## [7] "{whipped/sour cream,house keeping products}"
## [8] "{pastry,sweet spreads}"
## [9] "{turkey,curd}"
## [10] "{rice,sugar}"
## [11] "{butter,rice}"
## [12] "{domestic eggs,rice}"
## [13] "{rice,bottled water}"
## [14] "{yogurt,rice}"
## [15] "{oil,mustard}"
## Itemsets in Consequent (RHS)
## [1] "{bottled beer}" "{whole milk}" "{other vegetables}"
plot(rules.all, measure=c("support", "lift"), shading="confidence")
plot(subrules2, method="paracoord")
#Example from
#http://datamining.togaware.com/survivor/Video_Marketing.html
getwd()
## [1] "C:/Users/dell/Desktop/Teaching"
dvd.transactions <- read.transactions("DVD.csv", sep=",")
## Warning in readLines(file, encoding = encoding): incomplete final line
## found on 'DVD.csv'
dvd.transactions
## transactions in sparse format with
## 10 transactions (rows) and
## 11 items (columns)
summary(dvd.transactions)
## transactions as itemMatrix in sparse format with
## 10 rows (elements/itemsets/transactions) and
## 11 columns (items) and a density of 0.2727273
##
## most frequent items:
## Gladiator Patriot Sixth Sense Green Mile Harry Potter1
## 6 6 6 2 2
## (Other)
## 8
##
## element (itemset/transaction) length distribution:
## sizes
## 2 3 4 5
## 3 5 1 1
##
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 2.00 2.25 3.00 3.00 3.00 5.00
##
## includes extended item information - examples:
## labels
## 1 Braveheart
## 2 Galdiator
## 3 Gladiator
dvdrules.all=apriori(dvd.transactions,
parameter = list(supp = 0.2, conf = 0.7))
##
## Parameter specification:
## confidence minval smax arem aval originalSupport support minlen maxlen
## 0.7 0.1 1 none FALSE TRUE 0.2 1 10
## target ext
## rules FALSE
##
## Algorithmic control:
## filter tree heap memopt load sort verbose
## 0.1 TRUE TRUE FALSE TRUE 2 TRUE
##
## apriori - find association rules with the apriori algorithm
## version 4.21 (2004.05.09) (c) 1996-2004 Christian Borgelt
## set item appearances ...[0 item(s)] done [0.00s].
## set transactions ...[11 item(s), 10 transaction(s)] done [0.00s].
## sorting and recoding items ... [7 item(s)] done [0.00s].
## creating transaction tree ... done [0.00s].
## checking subsets of size 1 2 3 done [0.00s].
## writing ... [7 rule(s)] done [0.00s].
## creating S4 object ... done [0.00s].
dvdrules.all
## set of 7 rules
inspect(dvdrules.all)
## lhs rhs support confidence lift
## 1 {LOTR1} => {LOTR2} 0.2 1 5.000000
## 2 {LOTR2} => {LOTR1} 0.2 1 5.000000
## 3 {Green Mile} => {Sixth Sense} 0.2 1 1.666667
## 4 {Gladiator} => {Patriot} 0.6 1 1.666667
## 5 {Patriot} => {Gladiator} 0.6 1 1.666667
## 6 {Gladiator,
## Sixth Sense} => {Patriot} 0.4 1 1.666667
## 7 {Patriot,
## Sixth Sense} => {Gladiator} 0.4 1 1.666667
plot(dvdrules.all,method="graph",interactive = F)
