Project_250617
2025-06-18
library(mlbench)## Warning: package 'mlbench' was built under R version 4.4.3library(readr)## Warning: package 'readr' was built under R version 4.4.3library(data.table)## Warning: package 'data.table' was built under R version 4.4.3library(stats)
library(arules)## Loading required package: Matrix## Warning: package 'Matrix' was built under R version 4.4.3##
## Attaching package: 'arules'## The following objects are masked from 'package:base':
##
## abbreviate, writelibrary(arulesViz)## Warning: package 'arulesViz' was built under R version 4.4.3library(kernlab)##
## Attaching package: 'kernlab'## The following object is masked from 'package:arules':
##
## sizelibrary(Matrix)
##Take a little bit look at the data, the following is the top ##5 rows of the data set
bank_full_1 = read.csv("C:\\Users\\shann\\Downloads\\bank-full.csv")
bank_full=bank_full_1[,c(1,2,3,4,6,7,8,11,12)]
##extract the most important 8 (out of 17) columns from this ##data set to analyze
str(bank_full)## 'data.frame': 45211 obs. of 9 variables:
## $ age : int 58 44 33 47 33 35 28 42 58 43 ...
## $ job : chr "management" "technician" "entrepreneur" "blue-collar" ...
## $ marital : chr "married" "single" "married" "married" ...
## $ education: chr "tertiary" "secondary" "secondary" "unknown" ...
## $ balance : int 2143 29 2 1506 1 231 447 2 121 593 ...
## $ housing : chr "yes" "yes" "yes" "yes" ...
## $ loan : chr "no" "no" "yes" "no" ...
## $ month : chr "may" "may" "may" "may" ...
## $ duration : int 261 151 76 92 198 139 217 380 50 55 ...##More in depth information
require(lattice)## Loading required package: lattice## Warning: package 'lattice' was built under R version 4.4.3require(ggplot2)## Loading required package: ggplot2## Warning: package 'ggplot2' was built under R version 4.4.3##
## Attaching package: 'ggplot2'## The following object is masked from 'package:kernlab':
##
## alphaggplot(bank_full, aes(x=age)) + geom_bar()
ggplot(bank_full, aes(x=job)) + geom_bar() + theme(axis.text.x = element_text(angle = 45, vjust = 1, hjust = 1))
ggplot(bank_full, aes(x=marital)) + geom_bar()
ggplot(bank_full, aes(x=education)) + geom_bar() + theme(axis.text.x = element_text(angle = 45, vjust = 1, hjust = 1))
ggplot(bank_full, aes(x=housing)) + geom_bar()
ggplot(bank_full, aes(x=loan)) + geom_bar()
bank_full$month <- factor(bank_full$month, levels = c("jan", "feb", "mar","apr", "may","jun","jul","aug","sep","oct","nov","dec"))
ggplot(bank_full, aes(x=month)) + geom_bar()
ggplot(bank_full, aes(age)) + geom_bar(fill="skyblue") + facet_wrap(~job)
ggplot(bank_full, aes(education)) + geom_bar(fill="skyblue") + facet_wrap(~job) + theme(axis.text.x = element_text(angle = 45, vjust = 1, hjust = 1))
ggplot(bank_full, aes(marital)) + geom_bar(fill="skyblue") + facet_wrap(~job)
ggplot(bank_full, aes(housing)) + geom_bar(fill="skyblue") + facet_wrap(~loan)
ggplot(bank_full, aes(marital)) + geom_bar(fill="skyblue") + facet_wrap(~loan)
ggplot(bank_full, aes(job)) + geom_bar(fill="skyblue") + facet_wrap(~loan) + theme(axis.text.x = element_text(angle = 45, vjust = 1, hjust = 1))
ggplot(bank_full, aes(education)) + geom_bar(fill="skyblue") + facet_wrap(~loan) + theme(axis.text.x = element_text(angle = 45, vjust = 1, hjust = 1))
balance <- ggplot(bank_full, aes(factor(job), balance))
balance + geom_boxplot() + theme(axis.text.x = element_text(angle = 45, vjust = 1, hjust = 1))
##Visualizing of balance with outliers
balance + geom_boxplot(outlier.shape = NA) + scale_y_continuous(limits = quantile(bank_full$balance, c(0.1, 0.9))) + theme(axis.text.x = element_text(angle = 45, vjust = 1, hjust = 1))## Warning: Removed 8287 rows containing non-finite outside the scale range
## (`stat_boxplot()`).
##Visualizing of balance without outliers
bankrules <- apriori(bank_full, parameter=list(support=0.025, confidence=0.75,minlen = 2))## Warning: Column(s) 1, 2, 3, 4, 5, 6, 7, 9 not logical or factor. Applying
## default discretization (see '? discretizeDF').## Apriori
##
## Parameter specification:
## confidence minval smax arem aval originalSupport maxtime support minlen
## 0.75 0.1 1 none FALSE TRUE 5 0.025 2
## 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: 1130
##
## set item appearances ...[0 item(s)] done [0.00s].
## set transactions ...[44 item(s), 45211 transaction(s)] done [0.01s].
## sorting and recoding items ... [38 item(s)] done [0.00s].
## creating transaction tree ... done [0.01s].
## checking subsets of size 1 2 3 4 5 6 done [0.02s].
## writing ... [1502 rule(s)] done [0.00s].
## creating S4 object ... done [0.00s].bankrules## set of 1502 rules## Items/itemsets must appear in at least 2.5% of transactions
## Rules must have at least 75% confidence (strong rules)
## Rules must have at least 2 items
inspect(bankrules[1:10])## lhs rhs support confidence coverage
## [1] {job=unemployed} => {loan=no} 0.02640950 0.9163469 0.02882042
## [2] {month=jan} => {loan=no} 0.02634315 0.8488952 0.03103227
## [3] {job=entrepreneur} => {loan=no} 0.02501604 0.7605918 0.03289023
## [4] {job=self-employed} => {loan=no} 0.02985999 0.8549715 0.03492513
## [5] {education=unknown} => {loan=no} 0.03813231 0.9283791 0.04107407
## [6] {job=retired} => {age=[45,95]} 0.04859437 0.9704064 0.05007631
## [7] {job=retired} => {housing=no} 0.03921612 0.7831272 0.05007631
## [8] {job=retired} => {marital=married} 0.03828714 0.7645760 0.05007631
## [9] {job=retired} => {loan=no} 0.04324169 0.8635159 0.05007631
## [10] {month=feb} => {loan=no} 0.04996572 0.8527746 0.05859194
## lift count
## [1] 1.0911834 1194
## [2] 1.0108621 1191
## [3] 0.9057106 1131
## [4] 1.0180977 1350
## [5] 1.1055113 1724
## [6] 2.8008837 2197
## [7] 1.7631574 1773
## [8] 1.2702008 1731
## [9] 1.0282724 1955
## [10] 1.0154817 2259##Display the first 10 association rules from bankrules
bankrules <- apriori(bank_full, parameter=list(support=0.025, confidence=0.75,minlen = 3))## Warning: Column(s) 1, 2, 3, 4, 5, 6, 7, 9 not logical or factor. Applying
## default discretization (see '? discretizeDF').## Apriori
##
## Parameter specification:
## confidence minval smax arem aval originalSupport maxtime support minlen
## 0.75 0.1 1 none FALSE TRUE 5 0.025 3
## 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: 1130
##
## set item appearances ...[0 item(s)] done [0.00s].
## set transactions ...[44 item(s), 45211 transaction(s)] done [0.01s].
## sorting and recoding items ... [38 item(s)] done [0.00s].
## creating transaction tree ... done [0.01s].
## checking subsets of size 1 2 3 4 5 6 done [0.02s].
## writing ... [1459 rule(s)] done [0.00s].
## creating S4 object ... done [0.00s].bankrules## set of 1459 rulesinspect(bankrules[1:10])## lhs rhs support confidence
## [1] {age=[45,95], job=retired} => {housing=no} 0.03826502 0.7874374
## [2] {job=retired, housing=no} => {age=[45,95]} 0.03826502 0.9757473
## [3] {age=[45,95], job=retired} => {marital=married} 0.03742452 0.7701411
## [4] {job=retired, marital=married} => {age=[45,95]} 0.03742452 0.9774697
## [5] {age=[45,95], job=retired} => {loan=no} 0.04200305 0.8643605
## [6] {job=retired, loan=no} => {age=[45,95]} 0.04200305 0.9713555
## [7] {job=retired, housing=no} => {marital=married} 0.03043507 0.7760857
## [8] {job=retired, marital=married} => {housing=no} 0.03043507 0.7949162
## [9] {job=retired, housing=no} => {loan=no} 0.03461547 0.8826847
## [10] {job=retired, loan=no} => {housing=no} 0.03461547 0.8005115
## coverage lift count
## [1] 0.04859437 1.772862 1730
## [2] 0.03921612 2.816299 1730
## [3] 0.04859437 1.279446 1692
## [4] 0.03828714 2.821271 1692
## [5] 0.04859437 1.029278 1899
## [6] 0.04324169 2.803623 1899
## [7] 0.03921612 1.289322 1376
## [8] 0.03828714 1.789700 1376
## [9] 0.03921612 1.051099 1565
## [10] 0.04324169 1.802297 1565bankrules <- sort(bankrules, by = "confidence", decreasing = TRUE)
##This command sorts your association rules by confidence in ##descending order, so the rules with the highest confidence ##(strongest predictive power) will appear first
bankrules.sorted = sort(bankrules, by = "lift")
##Sorts rules by lift in ascending order (lowest lift first)
subset.matrix = is.subset(bankrules.sorted, bankrules.sorted)
##Creates a matrix showing which rules are subsets of others
subset.matrix[lower.tri(subset.matrix, diag = TRUE)] = NA## Warning in `[<-`(`*tmp*`, as.vector(i), value = NA): x[.] <- val: x is
## "ngTMatrix", val not in {TRUE, FALSE} is coerced; NA |--> TRUE.##Sets the lower triangle and diagonal to NA
##Keeps only the upper triangle to avoid duplicate ##comparisons
redundant = colSums(subset.matrix, na.rm = TRUE) >= 100
##Counts how many rules are subsets of each rule (column-wise)
##Marks rules as redundant if they have 100+ subset rules
##This is a very high threshold - these would be extremely ##general rules
##which(redundant)
##Shows the positions/indices of the redundant rules
##If this returns an empty result, no rules had 100+ subsets
bankrules.pruned = bankrules.sorted[!redundant]
bankrules.pruned## set of 95 rules##Keeps only the non-redundant rules (using the negation !)
##Creates a cleaner, more focused rule set
inspect(bankrules.pruned[1:10])## lhs rhs support confidence coverage lift count
## [1] {age=[45,95],
## job=admin.} => {loan=no} 0.02722789 0.7952196 0.03423945 0.9469454 1231
## [2] {job=blue-collar,
## housing=no} => {loan=no} 0.04717878 0.7947094 0.05936608 0.9463378 2133
## [3] {marital=married,
## education=secondary,
## duration=[126,258)} => {loan=no} 0.08409458 0.7945664 0.10583708 0.9461674 3802
## [4] {age=[18,35),
## marital=married,
## duration=[126,258)} => {loan=no} 0.03729181 0.7941592 0.04695760 0.9456826 1686
## [5] {balance=[-8.02e+03,175),
## housing=no} => {loan=no} 0.11293712 0.7937199 0.14228838 0.9451595 5106
## [6] {marital=married,
## balance=[-8.02e+03,175),
## housing=no} => {loan=no} 0.06403309 0.7935855 0.08068833 0.9449995 2895
## [7] {age=[35,45),
## balance=[-8.02e+03,175),
## duration=[0,126)} => {loan=no} 0.03065626 0.7933600 0.03864104 0.9447310 1386
## [8] {age=[18,35),
## job=blue-collar,
## education=secondary} => {loan=no} 0.03724757 0.7924706 0.04700184 0.9436718 1684
## [9] {age=[45,95],
## education=secondary,
## duration=[0,126)} => {loan=no} 0.04352923 0.7919517 0.05496450 0.9430539 1968
## [10] {age=[45,95],
## marital=married,
## balance=[-8.02e+03,175),
## housing=no} => {loan=no} 0.03275751 0.7915553 0.04138373 0.9425819 1481##Displays 1st 10 remaining rules after pruning
bankrules.pruned <- sort(bankrules.pruned, by = "lift", decreasing = TRUE)
inspect(bankrules.pruned[1:6])## lhs rhs support confidence coverage lift count
## [1] {age=[45,95],
## job=admin.} => {loan=no} 0.02722789 0.7952196 0.03423945 0.9469454 1231
## [2] {job=blue-collar,
## housing=no} => {loan=no} 0.04717878 0.7947094 0.05936608 0.9463378 2133
## [3] {marital=married,
## education=secondary,
## duration=[126,258)} => {loan=no} 0.08409458 0.7945664 0.10583708 0.9461674 3802
## [4] {age=[18,35),
## marital=married,
## duration=[126,258)} => {loan=no} 0.03729181 0.7941592 0.04695760 0.9456826 1686
## [5] {balance=[-8.02e+03,175),
## housing=no} => {loan=no} 0.11293712 0.7937199 0.14228838 0.9451595 5106
## [6] {marital=married,
## balance=[-8.02e+03,175),
## housing=no} => {loan=no} 0.06403309 0.7935855 0.08068833 0.9449995 2895##sorts the association rules by lift in descending order
## and displays the top 6 rules with the highest lift values
summary(bankrules.pruned)## set of 95 rules
##
## rule length distribution (lhs + rhs):sizes
## 3 4 5 6
## 20 50 24 1
##
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 3.000 4.000 4.000 4.063 5.000 6.000
##
## summary of quality measures:
## support confidence coverage lift
## Min. :0.02508 Min. :0.7507 Min. :0.03218 Min. :0.8939
## 1st Qu.:0.02982 1st Qu.:0.7737 1st Qu.:0.03863 1st Qu.:0.9213
## Median :0.03729 Median :0.7790 Median :0.04725 Median :0.9276
## Mean :0.04783 Mean :0.7786 Mean :0.06137 Mean :0.9271
## 3rd Qu.:0.05391 3rd Qu.:0.7871 3rd Qu.:0.06953 3rd Qu.:0.9373
## Max. :0.15120 Max. :0.7952 Max. :0.19497 Max. :0.9469
## count
## Min. :1134
## 1st Qu.:1348
## Median :1686
## Mean :2162
## 3rd Qu.:2438
## Max. :6836
##
## mining info:
## data ntransactions support confidence
## bank_full 45211 0.025 0.75
## call
## apriori(data = bank_full, parameter = list(support = 0.025, confidence = 0.75, minlen = 3))## provides overview statistics:
##Total number of rules found
##Distribution of rule lengths (how many items in antecedent ##+ consequent)
##Summary statistics for support, confidence, coverage, lift, ##and count
##Quartiles and mean values for each metric
inspect(sort(bankrules.pruned, by = "confidence")[1:5])## lhs rhs support confidence coverage lift count
## [1] {age=[45,95],
## job=admin.} => {loan=no} 0.02722789 0.7952196 0.03423945 0.9469454 1231
## [2] {job=blue-collar,
## housing=no} => {loan=no} 0.04717878 0.7947094 0.05936608 0.9463378 2133
## [3] {marital=married,
## education=secondary,
## duration=[126,258)} => {loan=no} 0.08409458 0.7945664 0.10583708 0.9461674 3802
## [4] {age=[18,35),
## marital=married,
## duration=[126,258)} => {loan=no} 0.03729181 0.7941592 0.04695760 0.9456826 1686
## [5] {balance=[-8.02e+03,175),
## housing=no} => {loan=no} 0.11293712 0.7937199 0.14228838 0.9451595 5106##shows the 5 rules with the lowest confidence
inspect(sort(bankrules.pruned, by = "lift", decreasing = TRUE) [1:5])## lhs rhs support confidence coverage lift count
## [1] {age=[45,95],
## job=admin.} => {loan=no} 0.02722789 0.7952196 0.03423945 0.9469454 1231
## [2] {job=blue-collar,
## housing=no} => {loan=no} 0.04717878 0.7947094 0.05936608 0.9463378 2133
## [3] {marital=married,
## education=secondary,
## duration=[126,258)} => {loan=no} 0.08409458 0.7945664 0.10583708 0.9461674 3802
## [4] {age=[18,35),
## marital=married,
## duration=[126,258)} => {loan=no} 0.03729181 0.7941592 0.04695760 0.9456826 1686
## [5] {balance=[-8.02e+03,175),
## housing=no} => {loan=no} 0.11293712 0.7937199 0.14228838 0.9451595 5106##This command shows the 5 association rules with the ##highest lift values - these are your strongest, most ##surprising patterns in the banking data.
plot(bankrules, measure = c("support", "lift"), shading = "confidence")## To reduce overplotting, jitter is added! Use jitter = 0 to prevent jitter.
plot(bankrules.pruned, measure = c("support", "lift"), shading = "confidence")
##This creates a scatter plot visualization of your ##association rules using the arulesViz package. Here's what ##this plot shows:
##Plot Elements:
##X-axis: Support (how frequently the rule appears in your ##data)
##Y-axis: Lift (how much stronger the association is compared ##to random)
##Color/Shading: Confidence (how reliable each rule is)
##Each point: Represents one association rulebankrules <- apriori(bank_full, parameter=list(support=0.025, confidence=0.75,minlen = 2)) bankrules
Items/itemsets must appear in at least 2.5% of transactions
Rules must have at least 75% confidence (strong rules)
Rules must have at least 2 items
inspect(bankrules[1:10])
##Display the first 10 association rules from bankrules
bankrules <- apriori(bank_full, parameter=list(support=0.025, confidence=0.75,minlen = 3)) bankrules
inspect(bankrules[1:10])
bankrules <- sort(bankrules, by = “confidence”, decreasing = TRUE)
##This command sorts your association rules by confidence in ##descending order, so the rules with the highest confidence ##(strongest predictive power) will appear first
bankrules.sorted = sort(bankrules, by = “lift”)
##Sorts rules by lift in ascending order (lowest lift first)
subset.matrix = is.subset(bankrules.sorted, bankrules.sorted)
##Creates a matrix showing which rules are subsets of others
subset.matrix[lower.tri(subset.matrix, diag = TRUE)] = NA
##Sets the lower triangle and diagonal to NA ##Keeps only the upper triangle to avoid duplicate ##comparisons
redundant = colSums(subset.matrix, na.rm = TRUE) >= 100
##Counts how many rules are subsets of each rule (column-wise) ##Marks rules as redundant if they have 100+ subset rules ##This is a very high threshold - these would be extremely ##general rules
which(redundant)
##Shows the positions/indices of the redundant rules ##If this returns an empty result, no rules had 100+ subsets
bankrules.pruned = bankrules.sorted[!redundant]
##Keeps only the non-redundant rules (using the negation !) ##Creates a cleaner, more focused rule set
inspect(bankrules.pruned)
##Displays all the remaining rules after pruning
bankrules <- sort(bankrules, by = “lift”, decreasing = TRUE) inspect(bankrules[1:6])
##sorts the association rules by lift in descending order ## and displays the top 6 rules with the highest lift values
summary(bankrules)
provides overview statistics:
##Total number of rules found ##Distribution of rule lengths (how many items in antecedent ##+ consequent) ##Summary statistics for support, confidence, coverage, lift, ##and count ##Quartiles and mean values for each metric
inspect(sort(bankrules, by = “confidence”)[1:5])
##shows the 5 rules with the lowest confidence
inspect(sort(bankrules, by = “lift”, decreasing = TRUE) [1:5])
##This command shows the 5 association rules with the ##highest lift values - these are your strongest, most ##surprising patterns in the banking data.
plot(bankrules, measure = c(“support”, “lift”), shading = “confidence”)
plot(bankrules.pruned, measure = c(“support”, “lift”), shading = “confidence”)
##This creates a scatter plot visualization of your ##association rules using the arulesViz package. Here’s what ##this plot shows: ##Plot Elements:
##X-axis: Support (how frequently the rule appears in your ##data) ##Y-axis: Lift (how much stronger the association is compared ##to random) ##Color/Shading: Confidence (how reliable each rule is) ##Each point: Represents one association rule
## 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:
library(mlbench) library(readr) library(data.table) library(stats) library(arules) library(arulesViz) library(kernlab) library(Matrix)
bank_full_1 = read.csv(“/Users/maxineharlemon/AIOpt/bank_full_2.csv”) summary(bank_full) head(bank_full, n=5)
##Take a little bit look at the data, the following is the top ##5 rows of the data set
bank_full=bank_full_1[,c(1,2,3,4,6,7,8,11)] bank_full=bank_full[,c(1,2,3,4,6,7,8,11)]
##extract the most important 8 (out of 17) columns from this ##data set to analyze
str(bank_full)
##More in depth information
require(lattice) require(ggplot2)
ggplot(bank_full, aes(x=age)) + geom_bar()
ggplot(bank_full, aes(x=job)) + geom_bar()
ggplot(bank_full, aes(x=marital)) + geom_bar()
ggplot(bank_full, aes(x=education)) + geom_bar()
ggplot(bank_full, aes(x=housing)) + geom_bar()
ggplot(bank_full, aes(x=loan)) + geom_bar()
ggplot(bank_full, aes(x=month)) + geom_bar()
ggplot(bank_full, aes(age)) + geom_bar(fill=“skyblue”) + facet_wrap(~job)
ggplot(bank_full, aes(education)) + geom_bar(fill=“skyblue”) + facet_wrap(~job)
ggplot(bank_full, aes(marital)) + geom_bar(fill=“skyblue”) + facet_wrap(~job)
ggplot(bank_full, aes(housing)) + geom_bar(fill=“skyblue”) + facet_wrap(~loan)
ggplot(bank_full, aes(marital)) + geom_bar(fill=“skyblue”) + facet_wrap(~loan)
ggplot(bank_full, aes(job)) + geom_bar(fill=“skyblue”) + facet_wrap(~loan)
ggplot(bank_full, aes(education)) + geom_bar(fill=“skyblue”) + facet_wrap(~loan)
balance <- ggplot(bank_full, aes(factor(job), balance)) balance + geom_boxplot()
##Visualizing of balance with outliers
balance + geom_boxplot(outlier.shape = NA) + scale_y_continuous(limits = quantile(bank_full$balance, c(0.1, 0.9)))
##Visualizing of balance without outliers
bankrules <- apriori(bank_full, parameter=list(support=0.025, confidence=0.75,minlen = 2))
bankrules
## Items/itemsets must appear in at least 2.5% of transactions
## Rules must have at least 75% confidence (strong rules)
## Rules must have at least 2 items
inspect(bankrules[1:10])
##Display the first 10 association rules from bankrules
bankrules <- apriori(bank_full, parameter=list(support=0.025, confidence=0.75,minlen = 3))
bankrules
inspect(bankrules[1:10])
bankrules <- sort(bankrules, by = "confidence", decreasing = TRUE)
##This command sorts your association rules by confidence in ##descending order, so the rules with the highest confidence ##(strongest predictive power) will appear first
bankrules.sorted = sort(bankrules, by = "lift")
##Sorts rules by lift in ascending order (lowest lift first)
subset.matrix = is.subset(bankrules.sorted, bankrules.sorted)
##Creates a matrix showing which rules are subsets of others
subset.matrix[lower.tri(subset.matrix, diag = TRUE)] = NA
##Sets the lower triangle and diagonal to NA
##Keeps only the upper triangle to avoid duplicate ##comparisons
redundant = colSums(subset.matrix, na.rm = TRUE) >= 100
##Counts how many rules are subsets of each rule (column-wise)
##Marks rules as redundant if they have 100+ subset rules
##This is a very high threshold - these would be extremely ##general rules
which(redundant)
##Shows the positions/indices of the redundant rules
##If this returns an empty result, no rules had 100+ subsets
bankrules.pruned = bankrules.sorted[!redundant]
##Keeps only the non-redundant rules (using the negation !)
##Creates a cleaner, more focused rule set
inspect(bankrules.pruned)
##Displays all the remaining rules after pruning
bankrules <- sort(bankrules, by = "lift", decreasing = TRUE)
inspect(bankrules[1:6])
##sorts the association rules by lift in descending order
## and displays the top 6 rules with the highest lift values
summary(bankrules)
## provides overview statistics:
##Total number of rules found
##Distribution of rule lengths (how many items in antecedent ##+ consequent)
##Summary statistics for support, confidence, coverage, lift, ##and count
##Quartiles and mean values for each metric
inspect(sort(bankrules, by = "confidence")[1:5])
##shows the 5 rules with the lowest confidence
inspect(sort(bankrules, by = "lift", decreasing = TRUE) [1:5])
##This command shows the 5 association rules with the ##highest lift values - these are your strongest, most ##surprising patterns in the banking data.
plot(bankrules, measure = c("support", "lift"), shading = "confidence")
plot(bankrules.pruned, measure = c("support", "lift"), shading = "confidence")
##This creates a scatter plot visualization of your ##association rules using the arulesViz package. Here's what ##this plot shows:
##Plot Elements:
##X-axis: Support (how frequently the rule appears in your ##data)
##Y-axis: Lift (how much stronger the association is compared ##to random)
##Color/Shading: Confidence (how reliable each rule is)
##Each point: Represents one association rule