Markert basket analysis
load the librarires
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
library(datasets)
load data
data("Groceries")
create an item frequency plot for the top 20 items
itemFrequencyPlot(Groceries, topN = 20, type = "absolute")
get the rules
rules <- apriori(Groceries, parameter = list(supp = 0.001, conf = 0.8))
## Apriori
##
## Parameter specification:
## confidence minval smax arem aval originalSupport maxtime support minlen
## 0.8 0.1 1 none FALSE TRUE 5 0.001 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: 9
##
## 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 [0.00s].
## 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].
show the top 5 rules but only 2 digits
options(digits = 2)
inspect(rules[1:5])
## lhs rhs support confidence lift
## [1] {liquor,red/blush wine} => {bottled beer} 0.0019 0.90 11.2
## [2] {curd,cereals} => {whole milk} 0.0010 0.91 3.6
## [3] {yogurt,cereals} => {whole milk} 0.0017 0.81 3.2
## [4] {butter,jam} => {whole milk} 0.0010 0.83 3.3
## [5] {soups,bottled beer} => {whole milk} 0.0011 0.92 3.6
## count
## [1] 19
## [2] 10
## [3] 17
## [4] 10
## [5] 11
summary(rules)
## set of 410 rules
##
## rule length distribution (lhs + rhs):sizes
## 3 4 5 6
## 29 229 140 12
##
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 3.0 4.0 4.0 4.3 5.0 6.0
##
## summary of quality measures:
## support confidence lift count
## Min. :0.00102 Min. :0.80 Min. : 3.1 Min. :10.0
## 1st Qu.:0.00102 1st Qu.:0.83 1st Qu.: 3.3 1st Qu.:10.0
## Median :0.00122 Median :0.85 Median : 3.6 Median :12.0
## Mean :0.00125 Mean :0.87 Mean : 4.0 Mean :12.3
## 3rd Qu.:0.00132 3rd Qu.:0.91 3rd Qu.: 4.3 3rd Qu.:13.0
## Max. :0.00315 Max. :1.00 Max. :11.2 Max. :31.0
##
## mining info:
## data ntransactions support confidence
## Groceries 9835 0.001 0.8
Sorting stuff out
rules <- sort(rules, by = "confidence", decreasing = T)
rules[1:5]
## set of 5 rules
rules
## set of 410 rules
inspect(rules[1:20])
## lhs rhs support confidence lift count
## [1] {rice,
## sugar} => {whole milk} 0.0012 1 3.9 12
## [2] {canned fish,
## hygiene articles} => {whole milk} 0.0011 1 3.9 11
## [3] {root vegetables,
## butter,
## rice} => {whole milk} 0.0010 1 3.9 10
## [4] {root vegetables,
## whipped/sour cream,
## flour} => {whole milk} 0.0017 1 3.9 17
## [5] {butter,
## soft cheese,
## domestic eggs} => {whole milk} 0.0010 1 3.9 10
## [6] {citrus fruit,
## root vegetables,
## soft cheese} => {other vegetables} 0.0010 1 5.2 10
## [7] {pip fruit,
## butter,
## hygiene articles} => {whole milk} 0.0010 1 3.9 10
## [8] {root vegetables,
## whipped/sour cream,
## hygiene articles} => {whole milk} 0.0010 1 3.9 10
## [9] {pip fruit,
## root vegetables,
## hygiene articles} => {whole milk} 0.0010 1 3.9 10
## [10] {cream cheese ,
## domestic eggs,
## sugar} => {whole milk} 0.0011 1 3.9 11
## [11] {curd,
## domestic eggs,
## sugar} => {whole milk} 0.0010 1 3.9 10
## [12] {cream cheese ,
## domestic eggs,
## napkins} => {whole milk} 0.0011 1 3.9 11
## [13] {pip fruit,
## whipped/sour cream,
## brown bread} => {other vegetables} 0.0011 1 5.2 11
## [14] {tropical fruit,
## grapes,
## whole milk,
## yogurt} => {other vegetables} 0.0010 1 5.2 10
## [15] {ham,
## tropical fruit,
## pip fruit,
## yogurt} => {other vegetables} 0.0010 1 5.2 10
## [16] {ham,
## tropical fruit,
## pip fruit,
## whole milk} => {other vegetables} 0.0011 1 5.2 11
## [17] {tropical fruit,
## root vegetables,
## yogurt,
## oil} => {whole milk} 0.0011 1 3.9 11
## [18] {root vegetables,
## other vegetables,
## yogurt,
## oil} => {whole milk} 0.0014 1 3.9 14
## [19] {root vegetables,
## other vegetables,
## butter,
## white bread} => {whole milk} 0.0010 1 3.9 10
## [20] {pork,
## other vegetables,
## butter,
## whipped/sour cream} => {whole milk} 0.0010 1 3.9 10
Targeting Items
rules <- apriori(data = Groceries, parameter = list(supp = 0.001, conf = 0.08),
appearance = list(default = "lhs", rhs = "whole milk"),
control = list(verbose = F))
rules <- sort(rules, by = "confidence", decreasing = T)
inspect(rules[1:20])
## lhs rhs support confidence lift count
## [1] {rice,
## sugar} => {whole milk} 0.0012 1 3.9 12
## [2] {canned fish,
## hygiene articles} => {whole milk} 0.0011 1 3.9 11
## [3] {root vegetables,
## butter,
## rice} => {whole milk} 0.0010 1 3.9 10
## [4] {root vegetables,
## whipped/sour cream,
## flour} => {whole milk} 0.0017 1 3.9 17
## [5] {butter,
## soft cheese,
## domestic eggs} => {whole milk} 0.0010 1 3.9 10
## [6] {pip fruit,
## butter,
## hygiene articles} => {whole milk} 0.0010 1 3.9 10
## [7] {root vegetables,
## whipped/sour cream,
## hygiene articles} => {whole milk} 0.0010 1 3.9 10
## [8] {pip fruit,
## root vegetables,
## hygiene articles} => {whole milk} 0.0010 1 3.9 10
## [9] {cream cheese ,
## domestic eggs,
## sugar} => {whole milk} 0.0011 1 3.9 11
## [10] {curd,
## domestic eggs,
## sugar} => {whole milk} 0.0010 1 3.9 10
## [11] {cream cheese ,
## domestic eggs,
## napkins} => {whole milk} 0.0011 1 3.9 11
## [12] {tropical fruit,
## root vegetables,
## yogurt,
## oil} => {whole milk} 0.0011 1 3.9 11
## [13] {root vegetables,
## other vegetables,
## yogurt,
## oil} => {whole milk} 0.0014 1 3.9 14
## [14] {root vegetables,
## other vegetables,
## butter,
## white bread} => {whole milk} 0.0010 1 3.9 10
## [15] {pork,
## other vegetables,
## butter,
## whipped/sour cream} => {whole milk} 0.0010 1 3.9 10
## [16] {other vegetables,
## butter,
## whipped/sour cream,
## domestic eggs} => {whole milk} 0.0012 1 3.9 12
## [17] {citrus fruit,
## whipped/sour cream,
## rolls/buns,
## pastry} => {whole milk} 0.0010 1 3.9 10
## [18] {pip fruit,
## root vegetables,
## other vegetables,
## bottled water} => {whole milk} 0.0011 1 3.9 11
## [19] {sausage,
## tropical fruit,
## root vegetables,
## rolls/buns} => {whole milk} 0.0010 1 3.9 10
## [20] {tropical fruit,
## root vegetables,
## other vegetables,
## yogurt,
## oil} => {whole milk} 0.0010 1 3.9 10
Whole milk in lhs
rules <- apriori(data = Groceries,
parameter = list(supp = 0.001, conf = 0.08),
appearance = list(default = "rhs", lhs = "whole milk"),
control = list(verbose = F)
)
rules <- sort(rules, by = "confidence", decreasing = T)
inspect(rules[1:20])
## lhs rhs support confidence lift count
## [1] {whole milk} => {other vegetables} 0.075 0.29 1.5 736
## [2] {whole milk} => {rolls/buns} 0.057 0.22 1.2 557
## [3] {whole milk} => {yogurt} 0.056 0.22 1.6 551
## [4] {} => {other vegetables} 0.193 0.19 1.0 1903
## [5] {whole milk} => {root vegetables} 0.049 0.19 1.8 481
## [6] {} => {rolls/buns} 0.184 0.18 1.0 1809
## [7] {} => {soda} 0.174 0.17 1.0 1715
## [8] {whole milk} => {tropical fruit} 0.042 0.17 1.6 416
## [9] {whole milk} => {soda} 0.040 0.16 0.9 394
## [10] {} => {yogurt} 0.140 0.14 1.0 1372
## [11] {whole milk} => {bottled water} 0.034 0.13 1.2 338
## [12] {whole milk} => {pastry} 0.033 0.13 1.5 327
## [13] {whole milk} => {whipped/sour cream} 0.032 0.13 1.8 317
## [14] {whole milk} => {citrus fruit} 0.031 0.12 1.4 300
## [15] {whole milk} => {pip fruit} 0.030 0.12 1.6 296
## [16] {whole milk} => {domestic eggs} 0.030 0.12 1.9 295
## [17] {whole milk} => {sausage} 0.030 0.12 1.2 294
## [18] {} => {bottled water} 0.111 0.11 1.0 1087
## [19] {} => {root vegetables} 0.109 0.11 1.0 1072
## [20] {whole milk} => {butter} 0.028 0.11 1.9 271
vizualization
library(arulesViz)
plot(rules[1:10], method = "graph", interactive = TRUE, shading = NA)
## Warning in plot.rules(rules[1:10], method = "graph", interactive = TRUE, :
## The parameter interactive is deprecated. Use engine='interactive' instead.