Clustering and Association Rules
Puneet Bhatia
Clustering-European Employment Data
Summary
Data
Percentage of population employed in different industries in Europian countries during 1979. The purpose of examining this data is to get insights into patterns of employment (if any) amongst European countries in 1970s.
Variable Names
- Country: Name of country
- Agr: Percentage employed in agriculture
- Min: Percentage employed in mining
- Man: Percentage employed in manufacturing
- PS: Percentage employed in power supply industries
- Con: Percentage employed in construction
- SI: Percentage employed in service industries
- Fin: Percentage employed in finance
- SPS: Percentage employed in social and personal services
- TC: Percentage employed in transport and communications
K-Means Clustering
Loading Libraries
library(data.table)
library(gridExtra)
library(factoextra)
library(tidyverse)
library(fpc)
library(knitr)Input Data and test-train split
data <- fread("europeanJobs.txt")
set.seed(13433518)
# randomly select 80% of the data
index <- sample(nrow(data), size = 0.8*nrow(data))
subset <- data[index,]Clustering
Visualizing clusters with different
k2 <- kmeans(subset[,-1], centers = 2, nstart = 25)
k3 <- kmeans(subset[,-1], centers = 3, nstart = 25)
k4 <- kmeans(subset[,-1], centers = 4, nstart = 25)
k5 <- kmeans(subset[,-1], centers = 5, nstart = 25)
# plots to compare
p1 <- fviz_cluster(k2, geom = "point", data = subset[,-1]) + ggtitle("k = 2")
p2 <- fviz_cluster(k3, geom = "point", data = subset[,-1]) + ggtitle("k = 3")
p3 <- fviz_cluster(k4, geom = "point", data = subset[,-1]) + ggtitle("k = 4")
p4 <- fviz_cluster(k5, geom = "point", data = subset[,-1]) + ggtitle("k = 5")
grid.arrange(p1, p2, p3, p4, nrow = 2)
plotcluster(subset[,-1], k2$cluster)
plotcluster(subset[,-1], k3$cluster)
plotcluster(subset[,-1], k4$cluster)
plotcluster(subset[,-1], k5$cluster)
Determining number of clusters
Plotting Within Cluster Sum of Squares vs Cluster Size. Cluster size = 3 seems to be appropriate.
#within group sum of squares method
wss <- (nrow(subset[,-1])-1)*sum(apply(subset[,-1],2,var))
for (i in 2:12) wss[i] <- sum(kmeans(subset[,-1],
centers=i)$withinss)
plot(1:12, wss, type="b", xlab="Number of Clusters",ylab="Within groups sum of squares")
Plotting R-Square vs Cluster Size. Cluster size = 3 seems to be appropriate.
# r-square
r_square <- c()
for (i in 1:12)
{
# calculating total between sum square for each cluster size
bss <- sum(kmeans(subset[,-1], centers=i, nstart = 25)$betweenss)
# calculating total sum square for each cluster size
tss <- sum(kmeans(subset[,-1], centers=i, nstart = 25)$totss)
r_square[i] <- bss/tss
}
# plotting wss vs number of clusters
plot(1:12, r_square, type="b", xlab="Number of Clusters",ylab="R-Square")
Silhouette width and dunn index. Cluster size = 3 seems to be appropriate.
d = dist(subset[,-1], method = "euclidean")
result = matrix(nrow = 14, ncol = 3)
for (i in 2:15){
cluster_result = kmeans(subset[,-1], i)
clusterstat=cluster.stats(d, cluster_result$cluster)
result[i-1,1]=i
result[i-1,2]=clusterstat$avg.silwidth
result[i-1,3]=clusterstat$dunn
}
plot(result[,c(1,2)], type="l", ylab = 'silhouette width', xlab = 'number of clusters')
plot(result[,c(1,3)], type="l", ylab = 'dunn index', xlab = 'number of clusters')
Interpretting Clusters
centers_df <- round(as.data.frame(k3$centers))
centers_df$cluster <- rownames(centers_df)
centers_df <- select(centers_df, cluster, everything())
kable(centers_df)| cluster | Agr | Min | Man | PS | Con | SI | Fin | SPS | TC |
|---|---|---|---|---|---|---|---|---|---|
| 1 | 52 | 1 | 14 | 1 | 5 | 8 | 5 | 9 | 5 |
| 2 | 25 | 1 | 28 | 1 | 9 | 10 | 2 | 17 | 6 |
| 3 | 9 | 1 | 28 | 1 | 8 | 16 | 5 | 24 | 7 |
subset$cluster <- k3$cluster
kable(arrange(subset, cluster))| Country | Agr | Min | Man | PS | Con | SI | Fin | SPS | TC | cluster |
|---|---|---|---|---|---|---|---|---|---|---|
| Greece | 41.4 | 0.6 | 17.6 | 0.6 | 8.1 | 11.5 | 2.4 | 11.0 | 6.7 | 1 |
| Turkey | 66.8 | 0.7 | 7.9 | 0.1 | 2.8 | 5.2 | 1.1 | 11.9 | 3.2 | 1 |
| Yugoslavia | 48.7 | 1.5 | 16.8 | 1.1 | 4.9 | 6.4 | 11.3 | 5.3 | 4.0 | 1 |
| Spain | 22.9 | 0.8 | 28.5 | 0.7 | 11.5 | 9.7 | 8.5 | 11.8 | 5.5 | 2 |
| Bulgaria | 23.6 | 1.9 | 32.3 | 0.6 | 7.9 | 8.0 | 0.7 | 18.2 | 6.7 | 2 |
| Czechoslovakia | 16.5 | 2.9 | 35.5 | 1.2 | 8.7 | 9.2 | 0.9 | 17.9 | 7.0 | 2 |
| Ireland | 23.2 | 1.0 | 20.7 | 1.3 | 7.5 | 16.8 | 2.8 | 20.8 | 6.1 | 2 |
| Portugal | 27.8 | 0.3 | 24.5 | 0.6 | 8.4 | 13.3 | 2.7 | 16.7 | 5.7 | 2 |
| USSR | 23.7 | 1.4 | 25.8 | 0.6 | 9.2 | 6.1 | 0.5 | 23.6 | 9.3 | 2 |
| Rumania | 34.7 | 2.1 | 30.1 | 0.6 | 8.7 | 5.9 | 1.3 | 11.7 | 5.0 | 2 |
| Denmark | 9.2 | 0.1 | 21.8 | 0.6 | 8.3 | 14.6 | 6.5 | 32.2 | 7.1 | 3 |
| Belgium | 3.3 | 0.9 | 27.6 | 0.9 | 8.2 | 19.1 | 6.2 | 26.6 | 7.2 | 3 |
| WGermany | 6.7 | 1.3 | 35.8 | 0.9 | 7.3 | 14.4 | 5.0 | 22.3 | 6.1 | 3 |
| Austria | 12.7 | 1.1 | 30.2 | 1.4 | 9.0 | 16.8 | 4.9 | 16.8 | 7.0 | 3 |
| Sweden | 6.1 | 0.4 | 25.9 | 0.8 | 7.2 | 14.4 | 6.0 | 32.4 | 6.8 | 3 |
| UK | 2.7 | 1.4 | 30.2 | 1.4 | 6.9 | 16.9 | 5.7 | 28.3 | 6.4 | 3 |
| Finland | 13.0 | 0.4 | 25.9 | 1.3 | 7.4 | 14.7 | 5.5 | 24.3 | 7.6 | 3 |
| France | 10.8 | 0.8 | 27.5 | 0.9 | 8.9 | 16.8 | 6.0 | 22.6 | 5.7 | 3 |
| Luxembourg | 7.7 | 3.1 | 30.8 | 0.8 | 9.2 | 18.5 | 4.6 | 19.2 | 6.2 | 3 |
| Italy | 15.9 | 0.6 | 27.6 | 0.5 | 10.0 | 18.1 | 1.6 | 20.1 | 5.7 | 3 |
Cluster 1: Countries with more blue collar jobs - High percentage of the population is employed in agriculture or manufacturing industry.
Cluster 2: Countries with balance of blue collar and white collar jobs - Blue collar and white collar jobs are in similar percentages.
Cluster 3: Countries with more white collar jobs - High percentage of the population is either employed in service industry, social/personal services.
Hierarchical Clustering
Hierarchical Clustering/Ward’s Method
# Calculate the distance matrix
distance <- dist(subset[,-1])
#Obtain clusters using the Wards method
hierarchical_clustering <- hclust(distance, method="ward.D")
plot(hierarchical_clustering)
#Cut dendrogram at the 3 clusters level and obtain cluster membership
hierarchical_clustering_3_clusters = cutree(hierarchical_clustering,k=3)
subset$cluster <- hierarchical_clustering_3_clusters
subset[,-1] %>%
group_by(cluster) %>%
summarise_all(funs(mean)) %>%
round() %>%
kable()## Warning: funs() is soft deprecated as of dplyr 0.8.0
## Please use a list of either functions or lambdas:
##
## # Simple named list:
## list(mean = mean, median = median)
##
## # Auto named with `tibble::lst()`:
## tibble::lst(mean, median)
##
## # Using lambdas
## list(~ mean(., trim = .2), ~ median(., na.rm = TRUE))
## This warning is displayed once per session.| cluster | Agr | Min | Man | PS | Con | SI | Fin | SPS | TC |
|---|---|---|---|---|---|---|---|---|---|
| 1 | 9 | 1 | 28 | 1 | 8 | 16 | 5 | 24 | 7 |
| 2 | 25 | 1 | 28 | 1 | 9 | 10 | 2 | 17 | 6 |
| 3 | 52 | 1 | 14 | 1 | 5 | 8 | 5 | 9 | 5 |
# Same cluster representation as K-means clusteringAssociation Rule Mining
About Cincinnati Zoo:
- Cincinnati Zoo was founded in 1873. Officially opened in 1875. Second oldest in the Nation after Pennsylvania Zoo.
- Zoo houses over 300 animal and over 3,000 plant species.
- Reptile house is the oldest Zoo building in the country, dating from 1875.
- Zoo serves over a million visitors each year.
Goal of Project:
To Study association of the items Zoo members buy.
Data:
Food Table-Over 14,000 records of [Demographics + Email, Food items purchased, Dates of purchase(July,2010 through March,2011), Price of food item purchased]
Loading Libraries
library(data.table)
library(tidyverse)
library(knitr)
library(arules)
library(arulesViz)Loading Data
TransFood <- read.csv('https://xiaoruizhu.github.io/Data-Mining-R/data/food_4_association.csv')
TransFood <- TransFood[, -1]
# Find out elements that are not equal to 0 or 1 and change them to 1.
Others <- which(!(as.matrix(TransFood) ==1 | as.matrix(TransFood) ==0), arr.ind=T )
TransFood[Others] <- 1
# converting to spare format
TransFood <- as(as.matrix(TransFood), "transactions")Exploring Data
Summary of Data
summary(TransFood)## transactions as itemMatrix in sparse format with
## 19076 rows (elements/itemsets/transactions) and
## 118 columns (items) and a density of 0.02230729
##
## most frequent items:
## Bottled.WaterFood Slice.of.CheeseFood Medium.DrinkFood Small.DrinkFood
## 3166 3072 2871 2769
## Slice.of.PeppFood (Other)
## 2354 35981
##
## element (itemset/transaction) length distribution:
## sizes
## 0 1 2 3 4 5 6 7 8 9 10 11 12 13 15
## 197 5675 5178 3253 2129 1293 655 351 178 95 42 14 8 7 1
##
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.000 1.000 2.000 2.632 4.000 15.000
##
## includes extended item information - examples:
## labels
## 1 Add.CheeseFood
## 2 BeerFood
## 3 Bottled.WaterFoodFrequently bought items
itemFrequencyPlot(TransFood, support = 0.1, cex.names=0.8)
Basket containing more than 10 items
x = TransFood[size(TransFood) > 10]
inspect(x)## items
## [1] {Cheese.Fries.BasketFood,
## Cheeseburger.BasketFood,
## CookieFood,
## French.Fries.BasketFood,
## Hot.DogFood,
## PopcornFood,
## Rice.Krispie.TreatFood,
## Slice.of.CheeseFood,
## Slice.of.PeppFood,
## Small.DrinkFood,
## Soft.Pretzel..3_39Food,
## Souvenir.DrinkFood,
## Souvenir.RefillFood}
## [2] {Bottled.WaterFood,
## Cheeseburger.BasketFood,
## Chicken.Tender.BasketFood,
## ChipsFood,
## GatoradeFood,
## Gourmet.CupFood,
## Krazy.KritterFood,
## Medium.DrinkFood,
## Rice.Krispie.TreatFood,
## Sandwich.BasketFood,
## Slice.of.CheeseFood,
## Souvenir.DrinkFood,
## Souvenir.RefillFood}
## [3] {Cheeseburger.BasketFood,
## CheeseburgerFood,
## ChipsFood,
## CoffeeFood,
## CookieFood,
## French.Fries.BasketFood,
## GatoradeFood,
## Hot.ChocolateFood,
## Krazy.KritterFood,
## Medium.DrinkFood,
## Slice.of.CheeseFood,
## Slice.of.PeppFood}
## [4] {Bottled.WaterFood,
## Chicken.Tender.BasketFood,
## Chicken.TendersFood,
## CoffeeFood,
## CookieFood,
## French.Fries.BasketFood,
## GatoradeFood,
## Gourmet.CupFood,
## Krazy.KritterFood,
## SandwichFood,
## Veggie.Burger.BasketFood,
## Veggie.BurgerFood}
## [5] {Cheeseburger.BasketFood,
## Chicken.Tender.BasketFood,
## French.Fries.BasketFood,
## GatoradeFood,
## Gourmet.CupFood,
## Krazy.KritterFood,
## Medium.DrinkFood,
## PopcornFood,
## SandwichFood,
## Slice.of.CheeseFood,
## Slice.of.PeppFood,
## Small.DrinkFood}
## [6] {Cheese.Fries.BasketFood,
## CheeseburgerFood,
## ChipsFood,
## French.Fries.BasketFood,
## Grilled.Chicken.SandwichFood,
## Hot.ChocolateFood,
## Hot.Dog.BasketFood,
## Hot.DogFood,
## Krazy.KritterFood,
## Sandwich.BasketFood,
## Small.DrinkFood}
## [7] {Burger.BasketFood,
## Cheese.Fries.BasketFood,
## Chicken.Tender.BasketFood,
## GatoradeFood,
## Gourmet.CupFood,
## Ice.Cream.ConeFood,
## IceeFood,
## Krazy.KritterFood,
## Medium.DrinkFood,
## Rice.Krispie.TreatFood,
## Slice.of.PeppFood}
## [8] {Bottled.WaterFood,
## Cheeseburger.BasketFood,
## Chicken.Nugget.BasketFood,
## Grilled.Chicken.Sandwich.BasketFood,
## Hot.Dog.BasketFood,
## Medium.DrinkFood,
## Medium.Iced.TeaFood,
## NachoFood,
## PopcornFood,
## Small.Diet.PepsiFood,
## Small.Sierra.MistFood,
## Souvenir.Diet.PepsiFood,
## Souvenir.RefillFood}
## [9] {Bottled.WaterFood,
## Cheese.ConeyFood,
## Chicken.Tender.BasketFood,
## ChipsFood,
## FloatFood,
## French.Fries.BasketFood,
## Ice.Cream.ConeFood,
## Krazy.KritterFood,
## Medium.DrinkFood,
## SaladFood,
## Slice.of.PeppFood}
## [10] {BeerFood,
## Cheeseburger.BasketFood,
## Hot.Dog.BasketFood,
## Ice.Cream.ConeFood,
## Medium.DrinkFood,
## PopcornFood,
## Sandwich.BasketFood,
## SandwichFood,
## Slice.of.CheeseFood,
## Slice.of.PeppFood,
## Soft.Pretzel..3_39Food,
## Souvenir.DrinkFood,
## ToppingFood}
## [11] {Bottled.WaterFood,
## CheeseburgerFood,
## Chicken.TendersFood,
## ChipsFood,
## French.Fries.BasketFood,
## GatoradeFood,
## Gourmet.CupFood,
## Medium.DrinkFood,
## Rice.Krispie.TreatFood,
## Slice.of.CheeseFood,
## Slice.of.PeppFood,
## Small.DrinkFood}
## [12] {Add.CheeseFood,
## Bottled.WaterFood,
## GatoradeFood,
## Grilled.Chicken.Sandwich.BasketFood,
## Hot.Dog.BasketFood,
## Krazy.KritterFood,
## Large.FryFood,
## NachoFood,
## PopcornFood,
## Sandwich.BasketFood,
## Souvenir.DrinkFood,
## Souvenir.RefillFood}
## [13] {Bottled.WaterFood,
## Cheeseburger.BasketFood,
## Chicken.Tender.BasketFood,
## French.Fries.BasketFood,
## Gourmet.CupFood,
## Hot.ChocolateFood,
## Hot.DogFood,
## Medium.DrinkFood,
## Slice.of.CheeseFood,
## Small.DrinkFood,
## Veggie.BurgerFood}
## [14] {Bud.LightFood,
## Cheeseburger.BasketFood,
## Chicken.Nugget.BasketFood,
## Fish.BasketFood,
## GatoradeFood,
## Hot.Dog.BasketFood,
## Land.SharkFood,
## Medium.Dr.PepperFood,
## Medium.Pink.LemonadeFood,
## October.FestFood,
## Soft.Pretzel..3_39Food,
## Souvenir.PepsiFood}
## [15] {Cheese.ConeyFood,
## Chicken.Nugget.BasketFood,
## ChipsFood,
## French.Fries.BasketFood,
## GatoradeFood,
## Rice.Krispie.TreatFood,
## Slice.of.CheeseFood,
## Small.DrinkFood,
## Small.PepsiFood,
## Souvenir.Diet.PepsiFood,
## Souvenir.DrinkFood}
## [16] {BeerFood,
## Bottled.WaterFood,
## Cheese.ConeyFood,
## Chicken.Nugget.BasketFood,
## French.Fries.BasketFood,
## GatoradeFood,
## Hot.DogFood,
## Ice.Cream.ConeFood,
## IceeFood,
## Medium.DrinkFood,
## Slice.of.CheeseFood,
## Slice.of.PeppFood,
## ToppingFood}
## [17] {Cheese.Fries.BasketFood,
## CheeseburgerFood,
## Chicken.TendersFood,
## French.Fries.BasketFood,
## Hot.Chocolate.SouvenirFood,
## Kettle.ChipsFood,
## Krazy.KritterFood,
## Sandwich.BasketFood,
## Slice.of.CheeseFood,
## Slice.of.PeppFood,
## Souvenir.DrinkFood}
## [18] {Cheese.Fries.BasketFood,
## Gourmet.CupFood,
## Ice.Cream.ConeFood,
## Krazy.KritterFood,
## Medium.DrinkFood,
## Rice.Krispie.TreatFood,
## Sandwich.BasketFood,
## Siberian.ChillFood,
## Slice.of.CheeseFood,
## Slice.of.PeppFood,
## ToppingFood}
## [19] {Cheeseburger.BasketFood,
## Chicken.Nugget.BasketFood,
## CookieFood,
## Grilled.Chicken.Sandwich.BasketFood,
## Hot.Dog.BasketFood,
## Krazy.KritterFood,
## Rice.Krispie.TreatFood,
## Souvenir.Dr.PepperFood,
## Souvenir.PepsiFood,
## Souvenir.RefillFood,
## Souvenir.Sierra.MistFood}
## [20] {Bottled.WaterFood,
## BurgerFood,
## CheeseburgerFood,
## Chicken.TendersFood,
## ChiliFood,
## CoffeeFood,
## French.Fries.BasketFood,
## Kettle.ChipsFood,
## Slice.of.PeppFood,
## Small.DrinkFood,
## Souvenir.RefillFood}
## [21] {Bottled.WaterFood,
## CheeseburgerFood,
## ChipsFood,
## French.Fries.BasketFood,
## GatoradeFood,
## Gourmet.CupFood,
## Ice.Cream.ConeFood,
## Krazy.KritterFood,
## Medium.DrinkFood,
## SandwichFood,
## Slice.of.CheeseFood,
## Slice.of.PeppFood,
## Small.DrinkFood,
## Soft.Pretzel..3_39Food,
## Souvenir.DrinkFood}
## [22] {Bottled.WaterFood,
## CheeseburgerFood,
## French.Fries.BasketFood,
## Krazy.KritterFood,
## Medium.DrinkFood,
## Rice.Krispie.TreatFood,
## SaladFood,
## Sandwich.BasketFood,
## SandwichFood,
## Slice.of.CheeseFood,
## Souvenir.DrinkFood}
## [23] {Bottled.WaterFood,
## Cheese.Fries.BasketFood,
## Chicken.Tender.BasketFood,
## CoffeeFood,
## GatoradeFood,
## Gourmet.CupFood,
## Grilled.Chicken.Sandwich.BasketFood,
## Hot.Dog.BasketFood,
## Medium.DrinkFood,
## MilkFood,
## Slice.of.CheeseFood,
## Slice.of.PeppFood,
## Small.DrinkFood}
## [24] {Burger.BasketFood,
## BurgerFood,
## ChiliFood,
## French.Fries.BasketFood,
## GatoradeFood,
## Hot.DogFood,
## Kettle.ChipsFood,
## SaladFood,
## Slice.of.CheeseFood,
## Slice.of.PeppFood,
## Small.DrinkFood,
## Souvenir.RefillFood}
## [25] {Bottled.WaterFood,
## CheeseburgerFood,
## French.Fries.BasketFood,
## Grilled.Chicken.SandwichFood,
## Hot.DogFood,
## Krazy.KritterFood,
## Rice.Krispie.TreatFood,
## Slice.of.CheeseFood,
## Slice.of.PeppFood,
## Souvenir.DrinkFood,
## Souvenir.RefillFood}
## [26] {Cheeseburger.BasketFood,
## Chicken.Nugget.BasketFood,
## Grilled.Chicken.Sandwich.BasketFood,
## Hot.Dog.BasketFood,
## Souvenir.Diet.Pepsi.RefillFood,
## Souvenir.Dr.Pepper.RefillFood,
## Souvenir.PepsiFood,
## Souvenir.Pink.LemonadeFood,
## Souvenir.RefillFood,
## Souvenir.Sierra.Mist.RefillFood,
## Souvenir.Sierra.MistFood}
## [27] {Bottled.WaterFood,
## CheeseburgerFood,
## Chicken.TendersFood,
## French.Fries.BasketFood,
## Grilled.Chicken.SandwichFood,
## Ice.Cream.ConeFood,
## MilkFood,
## Slice.of.CheeseFood,
## Souvenir.DrinkFood,
## Souvenir.RefillFood,
## ToppingFood}
## [28] {Cheese.ConeyFood,
## Chicken.Tender.BasketFood,
## Chili.Cheese.SandwichFood,
## ChipsFood,
## GatoradeFood,
## Hot.DogFood,
## Medium.DrinkFood,
## Siberian.ChillFood,
## Side.of.CheeseFood,
## Slice.of.PeppFood,
## Small.DrinkFood,
## Souvenir.DrinkFood,
## Souvenir.RefillFood}
## [29] {Chicken.Tender.BasketFood,
## CookieFood,
## Krazy.KritterFood,
## Medium.DrinkFood,
## PopcornFood,
## SaladFood,
## Sandwich.BasketFood,
## Slice.of.CheeseFood,
## Small.DrinkFood,
## Souvenir.DrinkFood,
## Souvenir.RefillFood,
## Veggie.Burger.BasketFood}
## [30] {Cheese.ConeyFood,
## Cheeseburger.BasketFood,
## Chicken.Nugget.BasketFood,
## French.Fries.BasketFood,
## Hot.DogFood,
## Medium.Diet.PepsiFood,
## Side.of.CheeseFood,
## Small.Diet.PepsiFood,
## Small.DrinkFood,
## Small.PepsiFood,
## Small.Pink.LemonadeFood}Running Apriori Algorithm to determine association rules
Using apriori() algorithm to find all rules (the default association type for apriori()) with a minimum support of 0.3% and a confidence of 0.5.
# Run the apriori algorithm
basket_rules <- apriori(TransFood,parameter = list(sup = 0.003, conf = 0.5,target="rules"))## Apriori
##
## Parameter specification:
## confidence minval smax arem aval originalSupport maxtime support minlen
## 0.5 0.1 1 none FALSE TRUE 5 0.003 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: 57
##
## set item appearances ...[0 item(s)] done [0.00s].
## set transactions ...[115 item(s), 19076 transaction(s)] done [0.00s].
## sorting and recoding items ... [74 item(s)] done [0.00s].
## creating transaction tree ... done [0.00s].
## checking subsets of size 1 2 3 4 done [0.00s].
## writing ... [42 rule(s)] done [0.00s].
## creating S4 object ... done [0.00s].Summary of the algorithm
summary(basket_rules)## set of 42 rules
##
## rule length distribution (lhs + rhs):sizes
## 2 3 4
## 12 27 3
##
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 2.000 2.000 3.000 2.786 3.000 4.000
##
## summary of quality measures:
## support confidence lift count
## Min. :0.003093 Min. :0.5032 Min. : 3.125 Min. : 59.00
## 1st Qu.:0.003683 1st Qu.:0.5944 1st Qu.: 6.307 1st Qu.: 70.25
## Median :0.004561 Median :0.7586 Median : 8.235 Median : 87.00
## Mean :0.006836 Mean :0.7404 Mean : 8.929 Mean :130.40
## 3rd Qu.:0.007496 3rd Qu.:0.8721 3rd Qu.: 9.016 3rd Qu.:143.00
## Max. :0.028570 Max. :1.0000 Max. :26.179 Max. :545.00
##
## mining info:
## data ntransactions support confidence
## TransFood 19076 0.003 0.5Checking the generated rules
inspect(basket_rules)## lhs rhs support confidence lift count
## [1] {Small.Pink.LemonadeFood} => {Chicken.Nugget.BasketFood} 0.003355001 0.5925926 16.034463 64
## [2] {Grilled.Chicken.SandwichFood} => {French.Fries.BasketFood} 0.003721954 0.6698113 6.862149 71
## [3] {FloatFood} => {Ice.Cream.ConeFood} 0.007024533 0.7089947 6.355631 134
## [4] {Side.of.CheeseFood} => {Cheese.ConeyFood} 0.004665548 0.6846154 25.912149 89
## [5] {Side.of.CheeseFood} => {Hot.DogFood} 0.006290627 0.9230769 21.605663 120
## [6] {BurgerFood} => {French.Fries.BasketFood} 0.004613126 0.6616541 6.778579 88
## [7] {SandwichFood} => {French.Fries.BasketFood} 0.007653596 0.6822430 6.989510 146
## [8] {Hot.Chocolate.Souvenir.RefillFood} => {Hot.Chocolate.SouvenirFood} 0.014992661 0.5596869 13.180972 286
## [9] {ToppingFood} => {Ice.Cream.ConeFood} 0.028569931 0.9981685 8.947868 545
## [10] {Add.CheeseFood} => {Soft.Pretzel..3_39Food} 0.019133990 0.6965649 7.601643 365
## [11] {Chicken.TendersFood} => {French.Fries.BasketFood} 0.017299224 0.7586207 7.771992 330
## [12] {CheeseburgerFood} => {French.Fries.BasketFood} 0.016879849 0.7931034 8.125264 322
## [13] {Cheese.ConeyFood,
## Side.of.CheeseFood} => {Hot.DogFood} 0.004351017 0.9325843 21.828193 83
## [14] {Hot.DogFood,
## Side.of.CheeseFood} => {Cheese.ConeyFood} 0.004351017 0.6916667 26.179034 83
## [15] {Bottled.WaterFood,
## ToppingFood} => {Ice.Cream.ConeFood} 0.004036486 1.0000000 8.964286 77
## [16] {Add.CheeseFood,
## Bottled.WaterFood} => {Soft.Pretzel..3_39Food} 0.003826798 0.8021978 8.754419 73
## [17] {CheeseburgerFood,
## Chicken.TendersFood} => {French.Fries.BasketFood} 0.003931642 0.9615385 9.850863 75
## [18] {Chicken.TendersFood,
## Souvenir.DrinkFood} => {French.Fries.BasketFood} 0.003197735 0.7922078 8.116088 61
## [19] {Chicken.TendersFood,
## Krazy.KritterFood} => {French.Fries.BasketFood} 0.005661564 0.9557522 9.791584 108
## [20] {Chicken.TendersFood,
## Slice.of.PeppFood} => {French.Fries.BasketFood} 0.003669532 0.9210526 9.436090 70
## [21] {Chicken.TendersFood,
## Small.DrinkFood} => {French.Fries.BasketFood} 0.004822814 0.8214286 8.415452 92
## [22] {Chicken.TendersFood,
## Medium.DrinkFood} => {French.Fries.BasketFood} 0.004141329 0.8144330 8.343783 79
## [23] {Bottled.WaterFood,
## Chicken.TendersFood} => {French.Fries.BasketFood} 0.003459845 0.7586207 7.771992 66
## [24] {Chicken.TendersFood,
## Slice.of.CheeseFood} => {French.Fries.BasketFood} 0.005399455 0.8728814 8.942580 103
## [25] {CheeseburgerFood,
## Souvenir.DrinkFood} => {French.Fries.BasketFood} 0.003250157 0.9117647 9.340936 62
## [26] {CheeseburgerFood,
## Krazy.KritterFood} => {French.Fries.BasketFood} 0.005451877 0.8813559 9.029402 104
## [27] {CheeseburgerFood,
## Slice.of.PeppFood} => {French.Fries.BasketFood} 0.003721954 0.8658537 8.870582 71
## [28] {CheeseburgerFood,
## Small.DrinkFood} => {French.Fries.BasketFood} 0.004141329 0.8315789 8.519441 79
## [29] {CheeseburgerFood,
## Medium.DrinkFood} => {French.Fries.BasketFood} 0.005189767 0.8761062 8.975619 99
## [30] {Bottled.WaterFood,
## CheeseburgerFood} => {French.Fries.BasketFood} 0.003092892 0.7662338 7.849987 59
## [31] {CheeseburgerFood,
## Slice.of.CheeseFood} => {French.Fries.BasketFood} 0.005242189 0.8695652 8.908607 100
## [32] {ChipsFood,
## Slice.of.PeppFood} => {Slice.of.CheeseFood} 0.008282659 0.5808824 3.607068 158
## [33] {CookieFood,
## Slice.of.PeppFood} => {Slice.of.CheeseFood} 0.004508283 0.5243902 3.256272 86
## [34] {Hot.DogFood,
## Krazy.KritterFood} => {French.Fries.BasketFood} 0.003669532 0.6140351 6.290727 70
## [35] {Ice.Cream.ConeFood,
## Slice.of.PeppFood} => {Slice.of.CheeseFood} 0.003407423 0.5200000 3.229010 65
## [36] {GatoradeFood,
## Slice.of.PeppFood} => {Slice.of.CheeseFood} 0.010117425 0.5830816 3.620724 193
## [37] {Slice.of.PeppFood,
## Souvenir.DrinkFood} => {Slice.of.CheeseFood} 0.008125393 0.5032468 3.124979 155
## [38] {Medium.DrinkFood,
## Slice.of.PeppFood} => {Slice.of.CheeseFood} 0.013629692 0.5273834 3.274858 260
## [39] {Bottled.WaterFood,
## Slice.of.PeppFood} => {Slice.of.CheeseFood} 0.010694066 0.5151515 3.198903 204
## [40] {Krazy.KritterFood,
## Medium.DrinkFood,
## Slice.of.PeppFood} => {Slice.of.CheeseFood} 0.003250157 0.5535714 3.437477 62
## [41] {Medium.DrinkFood,
## Slice.of.PeppFood,
## Small.DrinkFood} => {Slice.of.CheeseFood} 0.003145313 0.6000000 3.725781 60
## [42] {Medium.DrinkFood,
## Slice.of.CheeseFood,
## Small.DrinkFood} => {Slice.of.PeppFood} 0.003145313 0.5172414 4.191545 60Basket rules of size greater than 2
inspect(subset(basket_rules, size(basket_rules)>2))## lhs rhs support confidence lift count
## [1] {Cheese.ConeyFood,
## Side.of.CheeseFood} => {Hot.DogFood} 0.004351017 0.9325843 21.828193 83
## [2] {Hot.DogFood,
## Side.of.CheeseFood} => {Cheese.ConeyFood} 0.004351017 0.6916667 26.179034 83
## [3] {Bottled.WaterFood,
## ToppingFood} => {Ice.Cream.ConeFood} 0.004036486 1.0000000 8.964286 77
## [4] {Add.CheeseFood,
## Bottled.WaterFood} => {Soft.Pretzel..3_39Food} 0.003826798 0.8021978 8.754419 73
## [5] {CheeseburgerFood,
## Chicken.TendersFood} => {French.Fries.BasketFood} 0.003931642 0.9615385 9.850863 75
## [6] {Chicken.TendersFood,
## Souvenir.DrinkFood} => {French.Fries.BasketFood} 0.003197735 0.7922078 8.116088 61
## [7] {Chicken.TendersFood,
## Krazy.KritterFood} => {French.Fries.BasketFood} 0.005661564 0.9557522 9.791584 108
## [8] {Chicken.TendersFood,
## Slice.of.PeppFood} => {French.Fries.BasketFood} 0.003669532 0.9210526 9.436090 70
## [9] {Chicken.TendersFood,
## Small.DrinkFood} => {French.Fries.BasketFood} 0.004822814 0.8214286 8.415452 92
## [10] {Chicken.TendersFood,
## Medium.DrinkFood} => {French.Fries.BasketFood} 0.004141329 0.8144330 8.343783 79
## [11] {Bottled.WaterFood,
## Chicken.TendersFood} => {French.Fries.BasketFood} 0.003459845 0.7586207 7.771992 66
## [12] {Chicken.TendersFood,
## Slice.of.CheeseFood} => {French.Fries.BasketFood} 0.005399455 0.8728814 8.942580 103
## [13] {CheeseburgerFood,
## Souvenir.DrinkFood} => {French.Fries.BasketFood} 0.003250157 0.9117647 9.340936 62
## [14] {CheeseburgerFood,
## Krazy.KritterFood} => {French.Fries.BasketFood} 0.005451877 0.8813559 9.029402 104
## [15] {CheeseburgerFood,
## Slice.of.PeppFood} => {French.Fries.BasketFood} 0.003721954 0.8658537 8.870582 71
## [16] {CheeseburgerFood,
## Small.DrinkFood} => {French.Fries.BasketFood} 0.004141329 0.8315789 8.519441 79
## [17] {CheeseburgerFood,
## Medium.DrinkFood} => {French.Fries.BasketFood} 0.005189767 0.8761062 8.975619 99
## [18] {Bottled.WaterFood,
## CheeseburgerFood} => {French.Fries.BasketFood} 0.003092892 0.7662338 7.849987 59
## [19] {CheeseburgerFood,
## Slice.of.CheeseFood} => {French.Fries.BasketFood} 0.005242189 0.8695652 8.908607 100
## [20] {ChipsFood,
## Slice.of.PeppFood} => {Slice.of.CheeseFood} 0.008282659 0.5808824 3.607068 158
## [21] {CookieFood,
## Slice.of.PeppFood} => {Slice.of.CheeseFood} 0.004508283 0.5243902 3.256272 86
## [22] {Hot.DogFood,
## Krazy.KritterFood} => {French.Fries.BasketFood} 0.003669532 0.6140351 6.290727 70
## [23] {Ice.Cream.ConeFood,
## Slice.of.PeppFood} => {Slice.of.CheeseFood} 0.003407423 0.5200000 3.229010 65
## [24] {GatoradeFood,
## Slice.of.PeppFood} => {Slice.of.CheeseFood} 0.010117425 0.5830816 3.620724 193
## [25] {Slice.of.PeppFood,
## Souvenir.DrinkFood} => {Slice.of.CheeseFood} 0.008125393 0.5032468 3.124979 155
## [26] {Medium.DrinkFood,
## Slice.of.PeppFood} => {Slice.of.CheeseFood} 0.013629692 0.5273834 3.274858 260
## [27] {Bottled.WaterFood,
## Slice.of.PeppFood} => {Slice.of.CheeseFood} 0.010694066 0.5151515 3.198903 204
## [28] {Krazy.KritterFood,
## Medium.DrinkFood,
## Slice.of.PeppFood} => {Slice.of.CheeseFood} 0.003250157 0.5535714 3.437477 62
## [29] {Medium.DrinkFood,
## Slice.of.PeppFood,
## Small.DrinkFood} => {Slice.of.CheeseFood} 0.003145313 0.6000000 3.725781 60
## [30] {Medium.DrinkFood,
## Slice.of.CheeseFood,
## Small.DrinkFood} => {Slice.of.PeppFood} 0.003145313 0.5172414 4.191545 60Basket rules of size lift greater than 10
inspect(subset(basket_rules, lift>10))## lhs rhs support confidence lift count
## [1] {Small.Pink.LemonadeFood} => {Chicken.Nugget.BasketFood} 0.003355001 0.5925926 16.03446 64
## [2] {Side.of.CheeseFood} => {Cheese.ConeyFood} 0.004665548 0.6846154 25.91215 89
## [3] {Side.of.CheeseFood} => {Hot.DogFood} 0.006290627 0.9230769 21.60566 120
## [4] {Hot.Chocolate.Souvenir.RefillFood} => {Hot.Chocolate.SouvenirFood} 0.014992661 0.5596869 13.18097 286
## [5] {Cheese.ConeyFood,
## Side.of.CheeseFood} => {Hot.DogFood} 0.004351017 0.9325843 21.82819 83
## [6] {Hot.DogFood,
## Side.of.CheeseFood} => {Cheese.ConeyFood} 0.004351017 0.6916667 26.17903 83Basket rules containing Cheese.ConeyFood on rhs and lift greater than 5
Cheese.ConeyFood.rhs <- subset(basket_rules, subset = rhs %in% "Cheese.ConeyFood" & lift>5)
inspect(Cheese.ConeyFood.rhs)## lhs rhs support
## [1] {Side.of.CheeseFood} => {Cheese.ConeyFood} 0.004665548
## [2] {Hot.DogFood,Side.of.CheeseFood} => {Cheese.ConeyFood} 0.004351017
## confidence lift count
## [1] 0.6846154 25.91215 89
## [2] 0.6916667 26.17903 83Visualizing Association Rules
Plotting confidence vs support of all rules
plot(basket_rules)
Plot selected rules with their corresponding support and lift
plot(basket_rules, method="grouped")
Graph Plot of 5 rules with highest lift
plot(head(sort(basket_rules, by="lift"), 5), method = "graph")