Data <- read.csv("D:\\DataScience\\Assignments\\AssociationRules\\book.csv")
colnames(Data)
## [1] "ChildBks" "YouthBks" "CookBks" "DoItYBks" "RefBks"
## [6] "ArtBks" "GeogBks" "ItalCook" "ItalAtlas" "ItalArt"
## [11] "Florence"
Data$ChildBks <- factor(Data$ChildBks,levels = c("1","0"),labels = c("ChildBks",""))
Data$YouthBks <- factor(Data$YouthBks,levels = c("1","0"),labels = c("YouthBks",""))
Data$CookBks <- factor(Data$CookBks,levels = c("1","0"),labels = c("CookBks",""))
Data$DoItYBks <- factor(Data$DoItYBks,levels = c("1","0"),labels = c("DoItYBks",""))
Data$RefBks <- factor(Data$RefBks,levels = c("1","0"),labels = c("RefBks",""))
Data$ArtBks <- factor(Data$ArtBks,levels = c("1","0"),labels = c("ArtBks",""))
Data$GeogBks <- factor(Data$GeogBks,levels = c("1","0"),labels = c("GeogBks",""))
Data$ItalCook <- factor(Data$ItalCook,levels = c("1","0"),labels = c("ItalCook",""))
Data$ItalAtlas <- factor(Data$ItalAtlas,levels = c("1","0"),labels = c("ItalAtlas",""))
Data$ItalArt <- factor(Data$ItalArt,levels = c("1","0"),labels = c("ItalArt",""))
Data$Florence <- factor(Data$Florence,levels = c("1","0"),labels = c("Florence",""))
library(car)
## Warning: package 'car' was built under R version 3.5.1
## Loading required package: carData
library(carData)
library(arules)
## Warning: package 'arules' was built under R version 3.5.1
## Loading required package: Matrix
##
## Attaching package: 'arules'
## The following object is masked from 'package:car':
##
## recode
## The following objects are masked from 'package:base':
##
## abbreviate, write
library(arulesViz)
## Warning: package 'arulesViz' was built under R version 3.5.1
## Loading required package: grid
library(mvinfluence)
## Warning: package 'mvinfluence' was built under R version 3.5.1
## Loading required package: heplots
## Warning: package 'heplots' was built under R version 3.5.1
Data1 <- as(Data,"transactions")
# Item Frequency plot
itemFrequencyPlot(Data1,topN=25)
Book_apriori <- apriori(Data1, parameter = list(supp=0.005, conf=0.45, minlen=2, maxlen=4))
## Apriori
##
## Parameter specification:
## confidence minval smax arem aval originalSupport maxtime support minlen
## 0.45 0.1 1 none FALSE TRUE 5 0.005 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: 10
##
## set item appearances ...[0 item(s)] done [0.00s].
## set transactions ...[22 item(s), 2000 transaction(s)] done [0.00s].
## sorting and recoding items ... [22 item(s)] done [0.00s].
## creating transaction tree ... done [0.00s].
## checking subsets of size 1 2 3 4
## Warning in apriori(Data1, parameter = list(supp = 0.005, conf = 0.45,
## minlen = 2, : Mining stopped (maxlen reached). Only patterns up to a length
## of 4 returned!
## done [0.01s].
## writing ... [12822 rule(s)] done [0.00s].
## creating S4 object ... done [0.02s].
Book_apriori
## set of 12822 rules
inspect(head(sort(Book_apriori),n=20))
## lhs rhs support confidence lift
## [1] {ItalArt=} => {ItalAtlas=} 0.9310 0.9784551 1.016049
## [2] {ItalAtlas=} => {ItalArt=} 0.9310 0.9667705 1.016049
## [3] {ItalCook=} => {ItalArt=} 0.8755 0.9875917 1.037931
## [4] {ItalArt=} => {ItalCook=} 0.8755 0.9201261 1.037931
## [5] {ItalCook=} => {ItalAtlas=} 0.8725 0.9842076 1.022022
## [6] {ItalAtlas=} => {ItalCook=} 0.8725 0.9060228 1.022022
## [7] {ItalCook=,ItalArt=} => {ItalAtlas=} 0.8655 0.9885780 1.026561
## [8] {ItalCook=,ItalAtlas=} => {ItalArt=} 0.8655 0.9919771 1.042540
## [9] {ItalAtlas=,ItalArt=} => {ItalCook=} 0.8655 0.9296455 1.048670
## [10] {Florence=} => {ItalAtlas=} 0.8610 0.9657880 1.002895
## [11] {ItalAtlas=} => {Florence=} 0.8610 0.8940810 1.002895
## [12] {Florence=} => {ItalArt=} 0.8555 0.9596186 1.008532
## [13] {ItalArt=} => {Florence=} 0.8555 0.8991067 1.008532
## [14] {ItalArt=,Florence=} => {ItalAtlas=} 0.8375 0.9789597 1.016573
## [15] {ItalAtlas=,Florence=} => {ItalArt=} 0.8375 0.9727062 1.022287
## [16] {ItalAtlas=,ItalArt=} => {Florence=} 0.8375 0.8995704 1.009053
## [17] {ItalCook=} => {Florence=} 0.7955 0.8973491 1.006561
## [18] {Florence=} => {ItalCook=} 0.7955 0.8923163 1.006561
## [19] {ItalCook=,Florence=} => {ItalArt=} 0.7875 0.9899434 1.040403
## [20] {ItalCook=,ItalArt=} => {Florence=} 0.7875 0.8994860 1.008958
## count
## [1] 1862
## [2] 1862
## [3] 1751
## [4] 1751
## [5] 1745
## [6] 1745
## [7] 1731
## [8] 1731
## [9] 1731
## [10] 1722
## [11] 1722
## [12] 1711
## [13] 1711
## [14] 1675
## [15] 1675
## [16] 1675
## [17] 1591
## [18] 1591
## [19] 1575
## [20] 1575
inspect(tail(sort(Book_apriori),n=20))
## lhs rhs support confidence lift count
## [1] {YouthBks=YouthBks,
## ItalCook=ItalCook,
## Florence=Florence} => {ItalAtlas=} 0.005 0.6666667 0.6922811 10
## [2] {DoItYBks=DoItYBks,
## ItalCook=ItalCook,
## Florence=Florence} => {RefBks=} 0.005 0.5555556 0.7072636 10
## [3] {RefBks=,
## ItalCook=ItalCook,
## Florence=Florence} => {DoItYBks=DoItYBks} 0.005 0.5000000 1.7730496 10
## [4] {DoItYBks=,
## ItalCook=ItalCook,
## Florence=Florence} => {RefBks=} 0.005 0.5882353 0.7488673 10
## [5] {RefBks=,
## ItalCook=ItalCook,
## Florence=Florence} => {DoItYBks=} 0.005 0.5000000 0.6963788 10
## [6] {YouthBks=,
## ItalCook=ItalCook,
## Florence=Florence} => {ItalArt=} 0.005 0.5000000 0.5254861 10
## [7] {ItalCook=ItalCook,
## ItalArt=,
## Florence=Florence} => {YouthBks=} 0.005 0.6250000 0.8305648 10
## [8] {RefBks=RefBks,
## ArtBks=,
## Florence=Florence} => {GeogBks=GeogBks} 0.005 0.4545455 1.6469038 10
## [9] {ChildBks=,
## YouthBks=YouthBks,
## Florence=Florence} => {ArtBks=ArtBks} 0.005 0.5882353 2.4408103 10
## [10] {ChildBks=,
## YouthBks=YouthBks,
## Florence=Florence} => {CookBks=CookBks} 0.005 0.5882353 1.3648151 10
## [11] {YouthBks=YouthBks,
## ArtBks=,
## Florence=Florence} => {CookBks=CookBks} 0.005 0.7692308 1.7847582 10
## [12] {ChildBks=,
## YouthBks=YouthBks,
## Florence=Florence} => {GeogBks=} 0.005 0.5882353 0.8124797 10
## [13] {YouthBks=YouthBks,
## GeogBks=,
## Florence=Florence} => {ChildBks=} 0.005 0.5555556 0.9628346 10
## [14] {CookBks=,
## DoItYBks=DoItYBks,
## Florence=Florence} => {GeogBks=GeogBks} 0.005 0.6250000 2.2644928 10
## [15] {CookBks=,
## DoItYBks=DoItYBks,
## Florence=Florence} => {ChildBks=ChildBks} 0.005 0.6250000 1.4775414 10
## [16] {DoItYBks=DoItYBks,
## ArtBks=,
## Florence=Florence} => {CookBks=CookBks} 0.005 0.7142857 1.6572754 10
## [17] {DoItYBks=DoItYBks,
## ArtBks=,
## Florence=Florence} => {ItalCook=} 0.005 0.7142857 0.8057368 10
## [18] {ChildBks=,
## RefBks=RefBks,
## ItalCook=ItalCook} => {CookBks=CookBks} 0.005 1.0000000 2.3201856 10
## [19] {ChildBks=,
## ArtBks=ArtBks,
## ItalCook=ItalCook} => {YouthBks=YouthBks} 0.005 0.4545455 1.8365473 10
## [20] {ChildBks=,
## ArtBks=ArtBks,
## ItalCook=ItalCook} => {GeogBks=} 0.005 0.4545455 0.6278252 10
plot(head(sort(Book_apriori),n=20), method="graph", control=list(cex=0.70))
plot(Book_apriori)
## To reduce overplotting, jitter is added! Use jitter = 0 to prevent jitter.
plot(head(sort(Book_apriori),n=10), method="grouped", control=list(cex=0.2))
## Warning: Unknown control parameters: cex
## Available control parameters (with default values):
## main = Grouped Matrix for 10 Rules
## k = 20
## rhs_max = 10
## lhs_items = 2
## aggr.fun = function (x, ...) UseMethod("mean")
## col = c("#EE0000FF", "#EE0303FF", "#EE0606FF", "#EE0909FF", "#EE0C0CFF", "#EE0F0FFF", "#EE1212FF", "#EE1515FF", "#EE1818FF", "#EE1B1BFF", "#EE1E1EFF", "#EE2222FF", "#EE2525FF", "#EE2828FF", "#EE2B2BFF", "#EE2E2EFF", "#EE3131FF", "#EE3434FF", "#EE3737FF", "#EE3A3AFF", "#EE3D3DFF", "#EE4040FF", "#EE4444FF", "#EE4747FF", "#EE4A4AFF", "#EE4D4DFF", "#EE5050FF", "#EE5353FF", "#EE5656FF", "#EE5959FF", "#EE5C5CFF", "#EE5F5FFF", "#EE6262FF", "#EE6666FF", "#EE6969FF", "#EE6C6CFF", "#EE6F6FFF", "#EE7272FF", "#EE7575FF", "#EE7878FF", "#EE7B7BFF", "#EE7E7EFF", "#EE8181FF", "#EE8484FF", "#EE8888FF", "#EE8B8BFF", "#EE8E8EFF", "#EE9191FF", "#EE9494FF", "#EE9797FF", "#EE9999FF", "#EE9B9BFF", "#EE9D9DFF", "#EE9F9FFF", "#EEA0A0FF", "#EEA2A2FF", "#EEA4A4FF", "#EEA5A5FF", "#EEA7A7FF", "#EEA9A9FF", "#EEABABFF", "#EEACACFF", "#EEAEAEFF", "#EEB0B0FF", "#EEB1B1FF", "#EEB3B3FF", "#EEB5B5FF", "#EEB7B7FF", "#EEB8B8FF", "#EEBABAFF", "#EEBCBCFF", "#EEBDBDFF", "#EEBFBFFF", "#EEC1C1FF", "#EEC3C3FF", "#EEC4C4FF", "#EEC6C6FF", "#EEC8C8FF", "#EEC9C9FF", "#EECBCBFF", "#EECDCDFF", "#EECFCFFF", "#EED0D0FF", "#EED2D2FF", "#EED4D4FF", "#EED5D5FF", "#EED7D7FF", "#EED9D9FF", "#EEDBDBFF", "#EEDCDCFF", "#EEDEDEFF", "#EEE0E0FF", "#EEE1E1FF", "#EEE3E3FF", "#EEE5E5FF", "#EEE7E7FF", "#EEE8E8FF", "#EEEAEAFF", "#EEECECFF", "#EEEEEEFF")
## reverse = TRUE
## xlab = NULL
## ylab = NULL
## legend = Size: support Color: lift
## spacing = -1
## panel.function = function (row, size, shading, spacing) { size[size == 0] <- NA shading[is.na(shading)] <- 1 grid.circle(x = c(1:length(size)), y = row, r = size/2 * (1 - spacing), default.units = "native", gp = gpar(fill = shading, col = shading, alpha = 0.9)) }
## gp_main = list(cex = 1.2, fontface = "bold", font = c(bold = 2))
## gp_labels = list(cex = 0.8)
## gp_labs = list(cex = 1.2, fontface = "bold", font = c(bold = 2))
## gp_lines = list(col = "gray", lty = 3)
## newpage = TRUE
## max.shading = NA
## engine = default
## verbose = FALSE
