DATA 622 -Exploratory Data Analysis

bank <- bank %>%
  mutate(age_group = case_when(
    age < 25 ~ "Young",
    age >= 25 & age < 50 ~ "Middle-aged",
    age >= 50 ~ "Senior"
  ))

bank <- bank %>%
  mutate(credit_risk = case_when(
    balance < 0 | loan == "yes" ~ "High Risk",
    balance >= 0 & balance < 5000 & loan == "no" ~ "Medium Risk",
    balance >= 5000 & loan == "no" ~ "Low Risk"
  ))

# Remove specific columns ('pdays', 'poutcome', 'duration') from the 'bank' dataset
bank.new <- bank[ , !(names(bank) %in% c("pdays", "poutcome", "duration"))]

# Convert 'day', 'campaign', and 'previous' columns to factors
bank.new[c("day", "campaign", "previous")] <- lapply(bank.new[c("day", "campaign", "previous")], factor)

# Print the columns of the 'bank.new' dataset
print("Bank Columns:")

[1] "Bank Columns:"

print(names(bank.new))

 [1] "age"                  "job"                  "marital"             
 [4] "education"            "default"              "balance"             
 [7] "housing"              "loan"                 "contact"             
[10] "day"                  "month"                "campaign"            
[13] "previous"             "Subscription"         "contact_success_rate"
[16] "age_group"            "credit_risk"         

sapply(bank, class)

                 age                  job              marital 
           "integer"          "character"          "character" 
           education              default              balance 
         "character"          "character"            "integer" 
             housing                 loan              contact 
         "character"          "character"          "character" 
                 day                month             duration 
           "integer"          "character"            "integer" 
            campaign                pdays             previous 
           "integer"            "integer"            "integer" 
            poutcome         Subscription contact_success_rate 
         "character"          "character"            "numeric" 
           age_group          credit_risk 
         "character"          "character" 

# Convert categorical columns to factor
bank[c("job", "marital", "education", "default", "housing", "loan", "contact", "month", "campaign", "previous", "Subscription")] <- 
  lapply(bank[c("job", "marital", "education", "default", "housing", "loan", "contact", "month", "campaign", "previous", "Subscription")], factor)

# Verify the class of each column
sapply(bank, class)

                 age                  job              marital 
           "integer"             "factor"             "factor" 
           education              default              balance 
            "factor"             "factor"            "integer" 
             housing                 loan              contact 
            "factor"             "factor"             "factor" 
                 day                month             duration 
           "integer"             "factor"            "integer" 
            campaign                pdays             previous 
            "factor"            "integer"             "factor" 
            poutcome         Subscription contact_success_rate 
         "character"             "factor"            "numeric" 
           age_group          credit_risk 
         "character"          "character" 

The bank dataset is updated by adding new columns for age_group and credit_risk based on age, balance, and loan status. Irrelevant columns (pdays, poutcome, and duration) are removed, while columns such as day, campaign, and previous, along with several categorical variables, are converted to factors. The final dataset structure is displayed to show the class of each column after these transformations.

Next, we perform a train-test split on the data. This simulates predicting unseen data and allows us to evaluate the model’s performance.

library(caret)
set.seed(7) 
partition <- caret::createDataPartition(y=bank$Subscription, p=.75, list=FALSE) 
data_train <- bank[partition,]
data_test <- bank[-partition,]
print(nrow(data_train)/(nrow(data_test)+nrow(data_train)))

[1] 0.7501343

The data is split into training and testing sets using caret::createDataPartition, with 75% allocated to the training set (data_train) and 25% to the testing set (data_test). The split ratio is confirmed by the printed proportion.

# Normalizing data

# A function that normalizes numeric data
data_norm <- function(x){return((x - min(x))/(max(x) - min(x)))}

train.train.norm <- data_train
train.test.norm <- data_test

for(col in colnames(train.train.norm)){
  if(is.numeric(train.train.norm[[col]])){
    train.train.norm[[col]] <- data_norm(train.train.norm[[col]])
  }
}

for(col in colnames(train.test.norm)){
  if(is.numeric(train.test.norm[[col]])){
    train.test.norm[[col]] <- data_norm(train.test.norm[[col]])
  }
}

# Codifying categorical variables

train.train.new <- data.frame(model.matrix(Subscription ~ .-1, data = train.train.norm))
train.train.new <- cbind(data_train[["Subscription"]], train.train.new)
colnames(train.train.new)[1] <- c("y")

train.test.new <- data.frame(model.matrix(Subscription ~ .-1, data = train.test.norm))
train.test.new <- cbind(data_test[["Subscription"]], train.test.new)
colnames(train.test.new)[1] <- c("Subscription")

The data is normalized using a custom function, and categorical variables are codified into dummy variables for both the training and testing sets.

Building the model

start_time <- Sys.time()

set.seed(7)

# Making the model

rf.model <- randomForest(Subscription~., data = data_train)

# Predicting test set results:

pred <- predict(rf.model, newdata = data_test[, !(colnames(data_test) %in% c("Subscription"))])

end_time <- Sys.time()
time.elapse <- (end_time - start_time)
print(time.elapse)

Time difference of 2.192957 secs

# Printing the training AUC of the model
auc.predictions <- as.vector(rf.model$votes[,2])
auc.pred <- ROCR::prediction(auc.predictions, data_train$Subscription)
perf.auc <- ROCR::performance(auc.pred,"auc") 
rf.auc <- perf.auc@y.values[[1]]
print(paste("AUC:", round(rf.auc,3)))  

[1] "AUC: 0.9"

library(caret)

# Create the confusion matrix
cm <- confusionMatrix(pred, data_test$Subscription)

# Extract confusion matrix and statistics
cm_matrix <- cm$table
cm_stats <- cm$overall

# Format the confusion matrix as a table
cm_matrix_table <- as.data.frame(cm_matrix)
colnames(cm_matrix_table) <- c("Prediction", "no", "yes")

# Combine confusion matrix and statistics into a final output
cm_table <- list(
  "Confusion Matrix" = cm_matrix_table,
  "Statistics" = data.frame(
    Metric = c("Accuracy", "Kappa", "Sensitivity", "Specificity", "Pos Pred Value", "Neg Pred Value"),
    Value = c(cm_stats["Accuracy"], cm_stats["Kappa"], cm$byClass["Sensitivity"], cm$byClass["Specificity"],
              cm$byClass["Pos Pred Value"], cm$byClass["Neg Pred Value"])
  )
)

# Display confusion matrix and statistics using kable for a neat table output
for (table in cm_table) {
  print(kable(table, format = "markdown", caption = "Confusion Matrix and Statistics"))
}

Table: Confusion Matrix and Statistics

|Prediction |no  | yes|
|:----------|:---|---:|
|no         |no  | 838|
|yes        |no  |  17|
|no         |yes |  55|
|yes        |yes |  20|


Table: Confusion Matrix and Statistics

|               |Metric         |     Value|
|:--------------|:--------------|---------:|
|Accuracy       |Accuracy       | 0.9225806|
|Kappa          |Kappa          | 0.3209614|
|Sensitivity    |Sensitivity    | 0.9801170|
|Specificity    |Specificity    | 0.2666667|
|Pos Pred Value |Pos Pred Value | 0.9384099|
|Neg Pred Value |Neg Pred Value | 0.5405405|