第100+15步 ChatGPT学习：R实现Ababoost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Ababoost分类

（1）导入数据

我习惯用RStudio自带的导入功能：

（2）建立Ababoost模型（默认参数）

# Load necessary libraries
library(caret)
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, ]
 
# Convert the target variable to a factor for classification
trainData$X <- as.factor(trainData$X)
validData$X <- as.factor(validData$X)
 
# Define control method for training with cross-validation
trainControl <- trainControl(method = "cv", number = 10)
 
# Fit Random Forest model on the training set
model <- train(X ~ ., data = trainData, method = "ada", trControl = trainControl)
 
# Print the best parameters found by the model
best_params <- model$bestTune
cat("The best parameters found are:\n")
print(best_params)
 
# Predict on the training and validation sets
trainPredict <- predict(model, trainData, type = "prob")[,2]
validPredict <- predict(model, validData, type = "prob")[,2]
 
# Calculate ROC curves and AUC values
trainRoc <- roc(response = trainData$X, predictor = trainPredict)
validRoc <- roc(response = validData$X, predictor = validPredict)
 
# Plot ROC curves with AUC values
ggplot(data = data.frame(fpr = trainRoc$specificities, tpr = trainRoc$sensitivities), aes(x = 1 - fpr, y = tpr)) +
  geom_line(color = "blue") +
  geom_area(alpha = 0.2, fill = "blue") +
  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")
 
ggplot(data = data.frame(fpr = validRoc$specificities, tpr = validRoc$sensitivities), aes(x = 1 - fpr, y = tpr)) +
  geom_line(color = "red") +
  geom_area(alpha = 0.2, fill = "red") +
  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")
 
# 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")
 
# Extract values for calculations
a_train <- confMatTrain[1, 1]
b_train <- confMatTrain[1, 2]
c_train <- confMatTrain[2, 1]
d_train <- confMatTrain[2, 2]
 
a_valid <- confMatValid[1, 1]
b_valid <- confMatValid[1, 2]
c_valid <- confMatValid[2, 1]
d_valid <- confMatValid[2, 2]
 
# Training Set Metrics
acc_train <- (a_train + d_train) / sum(confMatTrain)
error_rate_train <- 1 - acc_train
sen_train <- d_train / (d_train + c_train)
sep_train <- a_train / (a_train + b_train)
precision_train <- d_train / (b_train + d_train)
F1_train <- (2 * precision_train * sen_train) / (precision_train + sen_train)
MCC_train <- (d_train * a_train - b_train * c_train) / sqrt((d_train + b_train) * (d_train + c_train) * (a_train + b_train) * (a_train + c_train))
auc_train <- roc(response = trainData$X, predictor = trainPredict)$auc
 
# Validation Set Metrics
acc_valid <- (a_valid + d_valid) / sum(confMatValid)
error_rate_valid <- 1 - acc_valid
sen_valid <- d_valid / (d_valid + c_valid)
sep_valid <- a_valid / (a_valid + b_valid)
precision_valid <- d_valid / (b_valid + d_valid)
F1_valid <- (2 * precision_valid * sen_valid) / (precision_valid + sen_valid)
MCC_valid <- (d_valid * a_valid - b_valid * c_valid) / sqrt((d_valid + b_valid) * (d_valid + c_valid) * (a_valid + b_valid) * (a_valid + c_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")

在R语言中，使用 caret 包训练Ababoost模型时，最关键的可调参数不多，下面是一些可以调整的关键参数：

①Iter: 这是最重要的参数之一，代表弱学习器的数量，即AdaBoost算法中的迭代次数。较大的nIter值通常可以提高模型的复杂度和拟合能力，但也可能导致过拟合。

②maxdepth: 这是决策树的最大深度。AdaBoost通常使用决策树作为其弱学习器。通过调整maxdepth可以控制单个决策树的复杂度，从而影响整个集成模型的复杂度。

③nu: 这个参数是学习率（也称为收缩参数或步长）。它用于更新每次迭代中模型权重。较小的nu值可以使模型学习得更加谨慎，通常可以减少过拟合的风险，但可能需要更多的迭代次数来收敛。

结果输出（默认参数）：

在默认参数中，caret包已经默默帮我们吧上面三个参数进行测试和寻优。

从AUC来看，Ababoost随便一跑，就跑出个不错的结果。不过有些过拟合了，验证集的性能稍微差些。

三、Ababoost手动调参方法（3个值）

设置iter值取值50、100、200、400、600；maxdepth取值1、2、5、7和9；nu取值0.01、0.1、0.5：

# Load necessary libraries
library(caret)
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, ]
 
# Convert the target variable to a factor for classification
trainData$X <- as.factor(trainData$X)
validData$X <- as.factor(validData$X)
 
# Define control method for training with cross-validation
trainControl <- trainControl(method = "cv", number = 10)
 
# Define the tuning grid with correct parameter names
tuneGrid <- expand.grid(iter = c(50, 100, 200, 400, 600),
                        maxdepth = c(1, 2, 5, 7, 9),
                        nu = c(0.01, 0.1, 0.5))
 
# Train the model using the ada method and the corrected tuning grid
model <- train(X ~ ., data = trainData, method = "ada", trControl = trainControl, tuneGrid = tuneGrid)
 
 
# Print the best parameters found by the model
best_params <- model$bestTune
cat("The best parameters found are:\n")
print(best_params)
 
# Predict on the training and validation sets
trainPredict <- predict(model, trainData, type = "prob")[,2]
validPredict <- predict(model, validData, type = "prob")[,2]
 
# Calculate ROC curves and AUC values
trainRoc <- roc(response = trainData$X, predictor = trainPredict)
validRoc <- roc(response = validData$X, predictor = validPredict)
 
# Plot ROC curves with AUC values
ggplot(data = data.frame(fpr = trainRoc$specificities, tpr = trainRoc$sensitivities), aes(x = 1 - fpr, y = tpr)) +
  geom_line(color = "blue") +
  geom_area(alpha = 0.2, fill = "blue") +
  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")
 
ggplot(data = data.frame(fpr = validRoc$specificities, tpr = validRoc$sensitivities), aes(x = 1 - fpr, y = tpr)) +
  geom_line(color = "red") +
  geom_area(alpha = 0.2, fill = "red") +
  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")
 
# 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")
 
# Extract values for calculations
a_train <- confMatTrain[1, 1]
b_train <- confMatTrain[1, 2]
c_train <- confMatTrain[2, 1]
d_train <- confMatTrain[2, 2]
 
a_valid <- confMatValid[1, 1]
b_valid <- confMatValid[1, 2]
c_valid <- confMatValid[2, 1]
d_valid <- confMatValid[2, 2]
 
# Training Set Metrics
acc_train <- (a_train + d_train) / sum(confMatTrain)
error_rate_train <- 1 - acc_train
sen_train <- d_train / (d_train + c_train)
sep_train <- a_train / (a_train + b_train)
precision_train <- d_train / (b_train + d_train)
F1_train <- (2 * precision_train * sen_train) / (precision_train + sen_train)
MCC_train <- (d_train * a_train - b_train * c_train) / sqrt((d_train + b_train) * (d_train + c_train) * (a_train + b_train) * (a_train + c_train))
auc_train <- roc(response = trainData$X, predictor = trainPredict)$auc
 
# Validation Set Metrics
acc_valid <- (a_valid + d_valid) / sum(confMatValid)
error_rate_valid <- 1 - acc_valid
sen_valid <- d_valid / (d_valid + c_valid)
sep_valid <- a_valid / (a_valid + b_valid)
precision_valid <- d_valid / (b_valid + d_valid)
F1_valid <- (2 * precision_valid * sen_valid) / (precision_valid + sen_valid)
MCC_valid <- (d_valid * a_valid - b_valid * c_valid) / sqrt((d_valid + b_valid) * (d_valid + c_valid) * (a_valid + b_valid) * (a_valid + c_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：

以上是找到的相对最优参数组合，看看具体性能：

还不让入默认的性能好呢。

看看GPT给的参数的取值建议，祝各位调得开心：

iter (迭代次数): 这个参数通常设置在10到1000之间。较小的数据集可能需要较少的迭代，而较大或较复杂的数据集可能需要更多的迭代。通常开始可以尝试50, 100, 200等值，然后根据模型的性能来调整。

maxdepth (树的最大深度): 这个参数一般设置在1到10之间。深度为1意味着使用决策树桩（仅一个决策点），这有助于防止过拟合，是AdaBoost中常用的设置。但对于更复杂的数据模式，可能需要更深的树。可以尝试的值包括1, 2, 3, 5等。

nu (学习率): 学习率的典型取值范围是0.01到1。较小的学习率（如0.01, 0.1）可以使模型学习得更稳健，但收敛速度可能较慢，需要更多的迭代次数。较高的学习率可以加快学习速度，但可能导致模型在训练过程中不稳定。

四、最后

数据嘛：

链接：https://pan.baidu.com/s/1rEf6JZyzA1ia5exoq5OF7g?pwd=x8xm

提取码：x8xm