关联规则demo

library(arules) # association rules library(arulesViz) # data visualization of association rules library(RColorBrewer) groceries <- read.transactions("groceries.csv", format="basket", sep=",") summary(groceries) #########进一步查看数据集的信息 class(groceries) groceries dim(groceries) colnames(groceries)[1:5] rownames(groceries)[1:5] basketSize<-size(groceries) summary(basketSize) sum(basketSize) #count of all 1s in the sparse matrix itemFreq <- itemFrequency(groceries) sum(itemFreq) #本质上代表"平均一个transaction购买的item个数" itemCount <- (itemFreq/sum(itemFreq))*sum(basketSize)#####itemCount表示每个item出现的次数。Support(X) = Xs / N, N是总的交易数，Xs就是Item X###的count。itemXCount = N * itemXFreq = (ItemXFreq / sum(itemFreq)) * sum(basketSize) ## summary(itemCount) orderedItem <- sort(itemCount, decreasing = ) orderedItem[1:10] orderedItemFreq <- sort(itemFrequency(groceries), decreasing=) orderedItemFreq[1:10] itemFrequencyPlot(groceries, support=0.1) itemFrequencyPlot(groceries, topN=10, horiz=T) inspect(groceries[1:5]) image(groceries[1:10]) image(sample(groceries,100)) ############# groceryrules <- apriori(groceries, parameter = list(support = 0.006, confidence = 0.25, minlen = 2)) ######inspect查看规则记录 inspect(groceryrules[1:10]) ##########评估 ordered_groceryrules <- sort(groceryrules, by="lift") inspect(ordered_groceryrules[1:5]) ####### 搜索规则 yogurtrules <- subset(groceryrules, items %in% c("yogurt")) inspect(yogurtrules) ########### qualityMeasures<-interestMeasure(groceryrules,c(“coverage”,”fishersExactTest”,”conviction”, “chiSquared”), transactions=groceries) summary(qualityMeasures) ######## write(groceryrules, file=”groceryrules.csv”, sep=”,”, quote=TRUE, row.names=FALSE) 转化data.frame分析： groceryrules_df <- as(groceryrules, “data.frame”)? str(groceryrules_df) ########### 可视化 plot(groceryrules, method=”scatterplot”,control=list(jitter=2, col = rev(brewer.pal(9, “Greens”))), shading = “lift”) plot(groceryrules, control=list(jitter=2, col = rev(brewer.pal(9, “Greens”))), shading = “lift”,method = ‘grouped’)