RF

Setting

rm(list=ls(all=TRUE))
setwd('C:/Users/sitdo/Documents/GitHub/IBD-EDA/paper1/')

Loading Data

library(dplyr)

载入程辑包：‘dplyr’

The following objects are masked from ‘package:stats’:

    filter, lag

The following objects are masked from ‘package:base’:

    intersect, setdiff, setequal, union

data <- read.csv("./data_preprocessed/data.csv") %>% select(-1)

Installing Packages

library(randomForest)

randomForest 4.7-1.1
Type rfNews() to see new features/changes/bug fixes.

载入程辑包：‘randomForest’

The following object is masked from ‘package:dplyr’:

    combine

library(pROC)

Type 'citation("pROC")' for a citation.

载入程辑包：‘pROC’

The following objects are masked from ‘package:stats’:

    cov, smooth, var

Method I: Splitting Data

set.seed(123)
splitting_ratio <- 0.7

indices <- 1:nrow(data)
shuffled_indices <- sample(indices) 
train_size <- floor(splitting_ratio * length(indices))

train_indices <- shuffled_indices[1:train_size]
test_indices <- shuffled_indices[(train_size + 1):length(indices)]

train_data <- data[train_indices, ]
test_data <- data[test_indices, ]

train_X <- as.matrix(train_data[, -1])
train_y <- train_data[, 1]

test_X <- as.matrix(test_data[, -1])
test_y <- test_data[, 1]

Building Model

rf_model <- randomForest(train_X, train_y)

Warning: The response has five or fewer unique values.  Are you sure you want to do regression?

predictions <- predict(rf_model, test_X)

Performance

Confusion Matrix

confusion_matrix <- table(
  as.numeric(test_data$dod), as.numeric(ifelse(predictions > 0.5, 1, 0))
)

TP <- confusion_matrix[1, 1]
TN <- confusion_matrix[2, 2]
FP <- confusion_matrix[2, 1]
FN <- confusion_matrix[1, 2]

## Calculate Accuracy
accuracy <- (TP + TN) / (TP + FP + TN + FN)
cat("Accuracy:", accuracy, "\n")

Accuracy: 0.8677686 

## Calculate Recall
recall <- TP / (TP + FN)
cat("Recall:", recall, "\n")

Recall: 0.9495114 

## Calculate Precision
precision <- TP / (TP + FP)
cat("Precision:", precision, "\n")

Precision: 0.8996914 

## Calculate Specificity
specificity <- TN / (TN + FP)
cat("Specificity:", specificity, "\n")

Specificity: 0.4196429 

## Calculate F1 Score
f1_score <- 2 * (precision * recall) / (precision + recall)
cat("F1 Score:", f1_score, "\n")

F1 Score: 0.9239303 

ROC Curve

# Calculate ROC curve using the actual values and predictions
roc_obj <- roc(
  as.numeric(test_data$dod), predictions
)

Setting levels: control = 0, case = 1
Setting direction: controls < cases

# Plot the ROC curve
plot(
  roc_obj,
  col = "blue",
  main = "ROC Curve - Random Forest",
  legacy.axes = TRUE,
  print.auc = TRUE,
  print.thres = TRUE,
  grid = c(0.2, 0.2),
  grid.col = c("green", "orange")
)

Method II: Cross Validation

# Perform 10-fold cross-validation
num_folds <- 10
folds <- cut(seq(1, nrow(data)), breaks = num_folds, labels = FALSE)

# Create empty vectors to store the predictions and actual values
all_predictions <- vector()
all_actuals <- vector()

for (i in 1:num_folds) {
  # Split the data into training and test sets for the current fold
  train_data <- data[folds != i, ]
  test_data <- data[folds == i, ]
  
  # Convert training data to matrix format
  train_X <- as.matrix(train_data[, -1])
  train_y <- train_data[, 1]
  
  # Train the random forest model
  rf_model <- randomForest(train_X, train_y)
  
  # Convert test data to matrix format
  test_X <- as.matrix(test_data[, -1])
  test_y <- test_data[, 1]
  
  # Make predictions on the test set
  predictions <- predict(rf_model, test_X)
  
  # Append the predictions and actual values to the vectors
  all_predictions <- c(all_predictions, predictions)
  all_actuals <- c(all_actuals, test_y)
}

Warning: The response has five or fewer unique values.  Are you sure you want to do regression?Warning: The response has five or fewer unique values.  Are you sure you want to do regression?Warning: The response has five or fewer unique values.  Are you sure you want to do regression?Warning: The response has five or fewer unique values.  Are you sure you want to do regression?Warning: The response has five or fewer unique values.  Are you sure you want to do regression?Warning: The response has five or fewer unique values.  Are you sure you want to do regression?Warning: The response has five or fewer unique values.  Are you sure you want to do regression?Warning: The response has five or fewer unique values.  Are you sure you want to do regression?Warning: The response has five or fewer unique values.  Are you sure you want to do regression?Warning: The response has five or fewer unique values.  Are you sure you want to do regression?

Performance

Confusion Matrix

confusion_matrix <- table(
  as.numeric(all_actuals), 
  as.numeric(ifelse(all_predictions > 0.5, 1, 0))
)

TP <- confusion_matrix[1, 1]
TN <- confusion_matrix[2, 2]
FP <- confusion_matrix[2, 1]
FN <- confusion_matrix[1, 2]

## Calculate Accuracy
accuracy <- (TP + TN) / (TP + FP + TN + FN)
cat("Accuracy:", accuracy, "\n")

Accuracy: 0.8709144 

## Calculate Recall
recall <- TP / (TP + FN)
cat("Recall:", recall, "\n")

Recall: 0.9543446 

## Calculate Precision
precision <- TP / (TP + FP)
cat("Precision:", precision, "\n")

Precision: 0.8987517 

## Calculate Specificity
specificity <- TN / (TN + FP)
cat("Specificity:", specificity, "\n")

Specificity: 0.4236842 

## Calculate F1 Score
f1_score <- 2 * (precision * recall) / (precision + recall)
cat("F1 Score:", f1_score, "\n")

F1 Score: 0.9257143 

ROC Curve

# Calculate ROC curve using the actual values and predictions
roc_obj <- roc(
  as.numeric(all_actuals), all_predictions
)

Setting levels: control = 0, case = 1
Setting direction: controls < cases

# Plot the ROC curve
plot(
  roc_obj,
  col = "blue",
  main = "ROC Curve - Random Forest (Cross Validation)",
  legacy.axes = TRUE,
  print.auc = TRUE,
  print.thres = TRUE,
  grid = c(0.2, 0.2),
  grid.col = c("green", "orange")
)