Association Rules Project
2025-06-18
library(mlbench)
library(readr)
library(arules)## Loading required package: Matrix##
## Attaching package: 'arules'## The following objects are masked from 'package:base':
##
## abbreviate, writelibrary(arulesViz)
library("knitr")
Data01 = read.csv("C:\\Users\\huiwu\\OneDrive\\Desktop\\CAU\\Spring2025\\R_DataScience\\Data_250626.csv")
summary(Data01)## paper pens pencils X
## Length:9 Length:9 Length:9 Length:9
## Class :character Class :character Class :character Class :character
## Mode :character Mode :character Mode :character Mode :characteritemsets1<-apriori(Data01,parameter=list(minlen=1,maxlen=1,support=0.25,confidence=0.6,target="frequent itemsets"))## Warning: Column(s) 1, 2, 3, 4 not logical or factor. Applying default
## discretization (see '? discretizeDF').## Apriori
##
## Parameter specification:
## confidence minval smax arem aval originalSupport maxtime support minlen
## NA 0.1 1 none FALSE TRUE 5 0.25 1
## maxlen target ext
## 1 frequent itemsets TRUE
##
## Algorithmic control:
## filter tree heap memopt load sort verbose
## 0.1 TRUE TRUE FALSE TRUE 2 TRUE
##
## Absolute minimum support count: 2
##
## set item appearances ...[0 item(s)] done [0.00s].
## set transactions ...[15 item(s), 9 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## Warning in apriori(Data01, parameter = list(minlen = 1, maxlen = 1, support =
## 0.25, : Mining stopped (maxlen reached). Only patterns up to a length of 1
## returned!## done [0.00s].
## sorting transactions ... done [0.00s].
## writing ... [7 set(s)] done [0.00s].
## creating S4 object ... done [0.00s].summary(itemsets1) ## set of 7 itemsets
##
## most frequent items:
## paper=paper paper=pens pens=cards pens=ruler pencils= (Other)
## 1 1 1 1 1 2
##
## element (itemset/transaction) length distribution:sizes
## 1
## 7
##
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 1 1 1 1 1 1
##
## summary of quality measures:
## support count
## Min. :0.3333 Min. :3.000
## 1st Qu.:0.3333 1st Qu.:3.000
## Median :0.3333 Median :3.000
## Mean :0.4127 Mean :3.714
## 3rd Qu.:0.3889 3rd Qu.:3.500
## Max. :0.7778 Max. :7.000
##
## includes transaction ID lists: FALSE
##
## mining info:
## data ntransactions support confidence
## Data01 9 0.25 1
## call
## apriori(data = Data01, parameter = list(minlen = 1, maxlen = 1, support = 0.25, confidence = 0.6, target = "frequent itemsets"))inspect(head(sort(itemsets1,by="support"),10)) ## items support count
## [1] {X=} 0.7777778 7
## [2] {paper=paper} 0.4444444 4
## [3] {paper=pens} 0.3333333 3
## [4] {pens=ruler} 0.3333333 3
## [5] {pencils=} 0.3333333 3
## [6] {pens=cards} 0.3333333 3
## [7] {pencils=cards} 0.3333333 3itemsets2<-apriori(Data01,parameter=list(minlen=2,maxlen=2,support=0.25,confidence=0.6,target="frequent itemsets"))## Warning: Column(s) 1, 2, 3, 4 not logical or factor. Applying default
## discretization (see '? discretizeDF').## Apriori
##
## Parameter specification:
## confidence minval smax arem aval originalSupport maxtime support minlen
## NA 0.1 1 none FALSE TRUE 5 0.25 2
## maxlen target ext
## 2 frequent itemsets TRUE
##
## Algorithmic control:
## filter tree heap memopt load sort verbose
## 0.1 TRUE TRUE FALSE TRUE 2 TRUE
##
## Absolute minimum support count: 2
##
## set item appearances ...[0 item(s)] done [0.00s].
## set transactions ...[15 item(s), 9 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## Warning in apriori(Data01, parameter = list(minlen = 2, maxlen = 2, support =
## 0.25, : Mining stopped (maxlen reached). Only patterns up to a length of 2
## returned!## done [0.00s].
## sorting transactions ... done [0.00s].
## writing ... [4 set(s)] done [0.00s].
## creating S4 object ... done [0.00s].inspect(head(sort(itemsets2,by="support"),10)) ## items support count
## [1] {paper=pens, X=} 0.3333333 3
## [2] {pens=ruler, X=} 0.3333333 3
## [3] {pencils=, X=} 0.3333333 3
## [4] {pens=cards, X=} 0.3333333 3summary(itemsets2) ## set of 4 itemsets
##
## most frequent items:
## X= paper=pens pens=cards pens=ruler pencils= (Other)
## 4 1 1 1 1 0
##
## element (itemset/transaction) length distribution:sizes
## 2
## 4
##
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 2 2 2 2 2 2
##
## summary of quality measures:
## support count
## Min. :0.3333 Min. :3
## 1st Qu.:0.3333 1st Qu.:3
## Median :0.3333 Median :3
## Mean :0.3333 Mean :3
## 3rd Qu.:0.3333 3rd Qu.:3
## Max. :0.3333 Max. :3
##
## includes transaction ID lists: FALSE
##
## mining info:
## data ntransactions support confidence
## Data01 9 0.25 1
## call
## apriori(data = Data01, parameter = list(minlen = 2, maxlen = 2, support = 0.25, confidence = 0.6, target = "frequent itemsets"))rules <- apriori(Data01,parameter=list(support=0.25,confidence=0.6,target="rules"))## Warning: Column(s) 1, 2, 3, 4 not logical or factor. Applying default
## discretization (see '? discretizeDF').## Apriori
##
## Parameter specification:
## confidence minval smax arem aval originalSupport maxtime support minlen
## 0.6 0.1 1 none FALSE TRUE 5 0.25 1
## maxlen target ext
## 10 rules TRUE
##
## Algorithmic control:
## filter tree heap memopt load sort verbose
## 0.1 TRUE TRUE FALSE TRUE 2 TRUE
##
## Absolute minimum support count: 2
##
## set item appearances ...[0 item(s)] done [0.00s].
## set transactions ...[15 item(s), 9 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 done [0.00s].
## writing ... [5 rule(s)] done [0.00s].
## creating S4 object ... done [0.00s].rules## set of 5 rulesstr(rules)## Formal class 'rules' [package "arules"] with 4 slots
## ..@ lhs :Formal class 'itemMatrix' [package "arules"] with 3 slots
## .. .. ..@ data :Formal class 'ngCMatrix' [package "Matrix"] with 5 slots
## .. .. .. .. ..@ i : int [1:4] 2 6 7 3
## .. .. .. .. ..@ p : int [1:6] 0 0 1 2 3 4
## .. .. .. .. ..@ Dim : int [1:2] 15 5
## .. .. .. .. ..@ Dimnames:List of 2
## .. .. .. .. .. ..$ : NULL
## .. .. .. .. .. ..$ : NULL
## .. .. .. .. ..@ factors : list()
## .. .. ..@ itemInfo :'data.frame': 15 obs. of 3 variables:
## .. .. .. ..$ labels : chr [1:15] "paper=paper" "paper=pencils" "paper=pens" "pens=cards" ...
## .. .. .. ..$ variables: Factor w/ 4 levels "paper","pencils",..: 1 1 1 3 3 3 3 2 2 2 ...
## .. .. .. ..$ levels : Factor w/ 8 levels "","calculator",..: 5 6 7 3 6 7 8 1 2 3 ...
## .. .. ..@ itemsetInfo:'data.frame': 0 obs. of 0 variables
## ..@ rhs :Formal class 'itemMatrix' [package "arules"] with 3 slots
## .. .. ..@ data :Formal class 'ngCMatrix' [package "Matrix"] with 5 slots
## .. .. .. .. ..@ i : int [1:5] 12 12 12 12 12
## .. .. .. .. ..@ p : int [1:6] 0 1 2 3 4 5
## .. .. .. .. ..@ Dim : int [1:2] 15 5
## .. .. .. .. ..@ Dimnames:List of 2
## .. .. .. .. .. ..$ : NULL
## .. .. .. .. .. ..$ : NULL
## .. .. .. .. ..@ factors : list()
## .. .. ..@ itemInfo :'data.frame': 15 obs. of 3 variables:
## .. .. .. ..$ labels : chr [1:15] "paper=paper" "paper=pencils" "paper=pens" "pens=cards" ...
## .. .. .. ..$ variables: Factor w/ 4 levels "paper","pencils",..: 1 1 1 3 3 3 3 2 2 2 ...
## .. .. .. ..$ levels : Factor w/ 8 levels "","calculator",..: 5 6 7 3 6 7 8 1 2 3 ...
## .. .. ..@ itemsetInfo:'data.frame': 0 obs. of 0 variables
## ..@ quality:'data.frame': 5 obs. of 5 variables:
## .. ..$ support : num [1:5] 0.778 0.333 0.333 0.333 0.333
## .. ..$ confidence: num [1:5] 0.778 1 1 1 1
## .. ..$ coverage : num [1:5] 1 0.333 0.333 0.333 0.333
## .. ..$ lift : num [1:5] 1 1.29 1.29 1.29 1.29
## .. ..$ count : int [1:5] 7 3 3 3 3
## ..@ info :List of 5
## .. ..$ data : symbol Data01
## .. ..$ ntransactions: int 9
## .. ..$ support : num 0.25
## .. ..$ confidence : num 0.6
## .. ..$ call : chr "apriori(data = Data01, parameter = list(support = 0.25, confidence = 0.6, target = \"rules\"))"summary(rules) ## set of 5 rules
##
## rule length distribution (lhs + rhs):sizes
## 1 2
## 1 4
##
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 1.0 2.0 2.0 1.8 2.0 2.0
##
## summary of quality measures:
## support confidence coverage lift
## Min. :0.3333 Min. :0.7778 Min. :0.3333 Min. :1.000
## 1st Qu.:0.3333 1st Qu.:1.0000 1st Qu.:0.3333 1st Qu.:1.286
## Median :0.3333 Median :1.0000 Median :0.3333 Median :1.286
## Mean :0.4222 Mean :0.9556 Mean :0.4667 Mean :1.229
## 3rd Qu.:0.3333 3rd Qu.:1.0000 3rd Qu.:0.3333 3rd Qu.:1.286
## Max. :0.7778 Max. :1.0000 Max. :1.0000 Max. :1.286
## count
## Min. :3.0
## 1st Qu.:3.0
## Median :3.0
## Mean :3.8
## 3rd Qu.:3.0
## Max. :7.0
##
## mining info:
## data ntransactions support confidence
## Data01 9 0.25 0.6
## call
## apriori(data = Data01, parameter = list(support = 0.25, confidence = 0.6, target = "rules"))plot(rules) ## To reduce overplotting, jitter is added! Use jitter = 0 to prevent jitter.
inspect(head(sort(rules,by="lift"),10))## lhs rhs support confidence coverage lift count
## [1] {paper=pens} => {X=} 0.3333333 1.0000000 0.3333333 1.285714 3
## [2] {pens=ruler} => {X=} 0.3333333 1.0000000 0.3333333 1.285714 3
## [3] {pencils=} => {X=} 0.3333333 1.0000000 0.3333333 1.285714 3
## [4] {pens=cards} => {X=} 0.3333333 1.0000000 0.3333333 1.285714 3
## [5] {} => {X=} 0.7777778 0.7777778 1.0000000 1.000000 7inspect( head( sort (rules, by = "lift")))## lhs rhs support confidence coverage lift count
## [1] {paper=pens} => {X=} 0.3333333 1.0000000 0.3333333 1.285714 3
## [2] {pens=ruler} => {X=} 0.3333333 1.0000000 0.3333333 1.285714 3
## [3] {pencils=} => {X=} 0.3333333 1.0000000 0.3333333 1.285714 3
## [4] {pens=cards} => {X=} 0.3333333 1.0000000 0.3333333 1.285714 3
## [5] {} => {X=} 0.7777778 0.7777778 1.0000000 1.000000 7inspect( head( sort (rules, by = "confidence")))## lhs rhs support confidence coverage lift count
## [1] {paper=pens} => {X=} 0.3333333 1.0000000 0.3333333 1.285714 3
## [2] {pens=ruler} => {X=} 0.3333333 1.0000000 0.3333333 1.285714 3
## [3] {pencils=} => {X=} 0.3333333 1.0000000 0.3333333 1.285714 3
## [4] {pens=cards} => {X=} 0.3333333 1.0000000 0.3333333 1.285714 3
## [5] {} => {X=} 0.7777778 0.7777778 1.0000000 1.000000 7
## R Markdown
This is an R Markdown document. Markdown is a simple formatting syntax for authoring HTML, PDF, and MS Word documents. For more details on using R Markdown see <http://rmarkdown.rstudio.com>.
When you click the **Knit** button a document will be generated that includes both content as well as the output of any embedded R code chunks within the document. You can embed an R code chunk like this:
```