第100+18步 ChatGPT学习：R实现SVM分类

基于R 4.2.2版本演示

一、写在前面

有不少大佬问做机器学习分类能不能用R语言，不想学Python咯。

答曰：可！用GPT或者Kimi转一下就得了呗。

加上最近也没啥内容写了，就帮各位搬运一下吧。

二、R代码实现SVM分类

（1）导入数据

我习惯用RStudio自带的导入功能：

（2）建立SVM模型（默认参数）

# Load necessary libraries
library(caret)
library(kernlab) 
library(pROC)
library(ggplot2)

# Assume 'data' is your dataframe containing the data
# Set seed to ensure reproducibility
set.seed(123)

# Split data into training and validation sets (80% training, 20% validation)
trainIndex <- createDataPartition(data$X, p = 0.8, list = FALSE)
trainData <- data[trainIndex, ]
validData <- data[-trainIndex, ]

# Train the SVM model
svmModel <- ksvm(X ~ ., data = trainData, type = "C-svc", kernel = "rbfdot", prob.model = TRUE)

# Predict on the training and validation sets
trainPredict <- predict(svmModel, trainData, type = "probabilities")[,1] 
validPredict <- predict(svmModel, validData, type = "probabilities")[,1]

# Convert predictions to binary using 0.5 as threshold
trainPredictBinary <- ifelse(trainPredict > 0.5, 1, 0)
validPredictBinary <- ifelse(validPredict > 0.5, 1, 0)

# Compute ROC objects
trainRoc <- roc(response = as.numeric(trainData$X) - 1, predictor = trainPredict)
validRoc <- roc(response = as.numeric(validData$X) - 1, predictor = validPredict)

# Plot ROC curves using ggplot2
trainRocPlot <- ggplot(data = data.frame(fpr = 1 - trainRoc$specificities, tpr = trainRoc$sensitivities), aes(x = fpr, y = tpr)) +
  geom_line(color = "blue") +
  geom_area(aes(ifelse(fpr <= 1, fpr, NA)), fill = "blue", alpha = 0.2) +
  geom_abline(slope = 1, intercept = 0, linetype = "dashed", color = "black") +
  ggtitle("Training ROC Curve") +
  xlab("False Positive Rate") +
  ylab("True Positive Rate") +
  annotate("text", x = 0.5, y = 0.1, label = paste("Training AUC =", round(auc(trainRoc), 2)), hjust = 0.5, color = "blue")

validRocPlot <- ggplot(data = data.frame(fpr = 1 - validRoc$specificities, tpr = validRoc$sensitivities), aes(x = fpr, y = tpr)) +
  geom_line(color = "red") +
  geom_area(aes(ifelse(fpr <= 1, fpr, NA)), fill = "red", alpha = 0.2) +
  geom_abline(slope = 1, intercept = 0, linetype = "dashed", color = "black") +
  ggtitle("Validation ROC Curve") +
  xlab("False Positive Rate") +
  ylab("True Positive Rate") +
  annotate("text", x = 0.5, y = 0.2, label = paste("Validation AUC =", round(auc(validRoc), 2)), hjust = 0.5, color = "red")

# Display plots
print(trainRocPlot)
print(validRocPlot)

# Calculate confusion matrices based on 0.5 cutoff for probability
confMatTrain <- table(trainData$X, trainPredict >= 0.5)
confMatValid <- table(validData$X, validPredict >= 0.5)

# Function to plot confusion matrix using ggplot2
plot_confusion_matrix <- function(conf_mat, dataset_name) {
  conf_mat_df <- as.data.frame(as.table(conf_mat))
  colnames(conf_mat_df) <- c("Actual", "Predicted", "Freq")
  
  p <- ggplot(data = conf_mat_df, aes(x = Predicted, y = Actual, fill = Freq)) +
    geom_tile(color = "white") +
    geom_text(aes(label = Freq), vjust = 1.5, color = "black", size = 5) +
    scale_fill_gradient(low = "white", high = "steelblue") +
    labs(title = paste("Confusion Matrix -", dataset_name, "Set"), x = "Predicted Class", y = "Actual Class") +
    theme_minimal() +
    theme(axis.text.x = element_text(angle = 45, hjust = 1), plot.title = element_text(hjust = 0.5))
  
  print(p)
}

# Now call the function to plot and display the confusion matrices
plot_confusion_matrix(confMatTrain, "Training")
plot_confusion_matrix(confMatValid, "Validation")

# 提取混淆矩阵的值，确保它们的命名与你的混淆矩阵布局一致
fp_train <- confMatTrain[1, 1]
tn_train <- confMatTrain[1, 2]
tp_train <- confMatTrain[2, 1]
fn_train <- confMatTrain[2, 2]

fp_valid <- confMatValid[1, 1]
tn_valid <- confMatValid[1, 2]
tp_valid <- confMatValid[2, 1]
fn_valid <- confMatValid[2, 2]

# 训练集指标
acc_train <- (tp_train + tn_train) / sum(confMatTrain)
error_rate_train <- 1 - acc_train
sen_train <- tp_train / (tp_train + fn_train)  # 灵敏度
sep_train <- tn_train / (tn_train + fp_train)  # 特异度
precision_train <- tp_train / (tp_train + fp_train)  # 精确度
F1_train <- 2 * (precision_train * sen_train) / (precision_train + sen_train)
MCC_train <- (tp_train * tn_train - fp_train * fn_train) / sqrt((tp_train + fp_train) * (tp_train + fn_train) * (tn_train + fp_train) * (tn_train + fn_train))
auc_train <- roc(response = trainData$X, predictor = trainPredict)$auc

# 验证集指标
acc_valid <- (tp_valid + tn_valid) / sum(confMatValid)
error_rate_valid <- 1 - acc_valid
sen_valid <- tp_valid / (tp_valid + fn_valid)  # 灵敏度
sep_valid <- tn_valid / (tn_valid + fp_valid)  # 特异度
precision_valid <- tp_valid / (tp_valid + fp_valid)  # 精确度
F1_valid <- 2 * (precision_valid * sen_valid) / (precision_valid + sen_valid)
MCC_valid <- (tp_valid * tn_valid - fp_valid * fn_valid) / sqrt((tp_valid + fp_valid) * (tp_valid + fn_valid) * (tn_valid + fp_valid) * (tn_valid + fn_valid))
auc_valid <- roc(response = validData$X, predictor = validPredict)$auc

# Print Metrics
cat("Training Metrics\n")
cat("Accuracy:", acc_train, "\n")
cat("Error Rate:", error_rate_train, "\n")
cat("Sensitivity:", sen_train, "\n")
cat("Specificity:", sep_train, "\n")
cat("Precision:", precision_train, "\n")
cat("F1 Score:", F1_train, "\n")
cat("MCC:", MCC_train, "\n")
cat("AUC:", auc_train, "\n\n")

cat("Validation Metrics\n")
cat("Accuracy:", acc_valid, "\n")
cat("Error Rate:", error_rate_valid, "\n")
cat("Sensitivity:", sen_valid, "\n")
cat("Specificity:", sep_valid, "\n")
cat("Precision:", precision_valid, "\n")
cat("F1 Score:", F1_valid, "\n")
cat("MCC:", MCC_valid, "\n")
cat("AUC:", auc_valid, "\n")

结果输出（随便挑的）：