基于R 4.2.2版本演示

一、寫在前面

有不少大佬問做機器學習分類能不能用R語言，不想學Python咯。

答曰：可！用GPT或者Kimi轉一下就得了唄。

加上最近也沒啥內容寫了，就幫各位搬運一下吧。

二、R代碼實現決策樹分類

（1）導入數據

我習慣用RStudio自帶的導入功能：

（2）建立決策樹模型（默認參數）

# 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$X)# Define control method for training with cross-validation
trainControl <- trainControl(method = "cv", number = 10)
# Fit Decision Tree model on the training set
model <- train(X ~ ., data = trainData, method = "rpart", trControl = trainControl)# Print the best parameters found by the model
best_params <- model$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]# Convert true values to factor for ROC analysis
trainData$X <- as.factor(trainData$X)
validData$X <- as.factor(validData$X)# 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語言中，還是使用caret包來訓練決策樹模型，可以調整多種參數來優化模型的性能：

①cp (Complexity Parameter): 用來控制樹的生長。cp 值越大，生成的模型越簡單。如果 cp 設置得太高，可能導致模型欠擬合。

②maxdepth:?決定了樹的最大深度。較深的樹可以更好地捕捉數據中的復雜關系，但也可能導致過擬合。

③minsplit:?定義了節點在嘗試分裂之前所需的最小樣本數。增加這個值可以讓樹更加穩健，但也可能導致欠擬合。

④minbucket: 葉節點最少包含的樣本數。這個參數可以幫助防止模型過于復雜，從而避免過擬合。

結果輸出（默認參數）：

在默認參數中，caret包只會默默幫我們找幾個合適的cp值進行測試。其他三個參數就一個默認值。

三、決策樹調參方法（僅cp值）

如前所述，決策樹的關鍵參數就是有4個，但是caret包做網格搜索的話，只能提供對于cp值的遍歷，其余三個不提供。

比如我設置cp值從0.001到0.1，步長是0.001；而maxdepth = 20, minsplit = 10, minbucket = 10：

# Load necessary libraries
library(caret)
library(pROC)
library(ggplot2)
library(rpart)# 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$X)# 定義交叉驗證控制方法
trainControl <- trainControl(method = "cv", number = 10)# 定義參數網格，只包括 cp
tuneGrid <- expand.grid(cp = seq(0.001, 0.1, by = 0.001))# 定義 rpart.control，固定其他參數
rpartControl <- rpart.control(maxdepth = 20, minsplit = 10, minbucket = 10)# 使用 rpart 方法訓練決策樹模型
model <- train(X ~ ., data = trainData, method = "rpart", trControl = trainControl, tuneGrid = tuneGrid,control = rpartControl)# 打印找到的最佳參數
best_params <- model$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]# Convert true values to factor for ROC analysis
trainData$X <- as.factor(trainData$X)
validData$X <- as.factor(validData$X)# 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")

結果輸出：

似乎好了一點了，那么，如果我先把其余三個參數也納入遍歷呢？那只能用循環語句了。

四、決策樹調參方法（4個值）

設置cp值從0.001到0.1，步長是0.001；maxdepth從10到30，步長是5；minsplit取值10、20、30、40；minbucket取值5、10、15、20：

# Load necessary libraries
library(caret)
library(pROC)
library(ggplot2)
library(rpart)# 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$X)# 參數網格定義
cp_values <- seq(0.001, 0.01, by = 0.001)
maxdepth_values <- seq(10, 30, by = 5)
minsplit_values <- c(10, 20, 30, 40)
minbucket_values <- c(5, 10, 15, 20)# 用于存儲結果的列表
results <- list()# 網格搜索實現
for (cp in cp_values) {for (maxdepth in maxdepth_values) {for (minsplit in minsplit_values) {for (minbucket in minbucket_values) {# 訓練模型model <- rpart(X ~ ., data = trainData, control = rpart.control(cp = cp, maxdepth = maxdepth,minsplit = minsplit, minbucket = minbucket))# 預測驗證集predictions <- predict(model, validData, type = "class")# 計算性能指標，這里使用準確度accuracy <- sum(predictions == validData$X) / nrow(validData)# 存儲結果results[[length(results) + 1]] <- list(cp = cp, maxdepth = maxdepth, minsplit = minsplit, minbucket = minbucket,accuracy = accuracy)}}}
}# 找到最高準確度的模型參數
best_model <- results[[which.max(sapply(results, function(x) x$accuracy))]]
print(best_model)# Predict on the training and validation sets
trainPredict <- predict(model, trainData, type = "prob")[,2]
validPredict <- predict(model, validData, type = "prob")[,2]# Convert true values to factor for ROC analysis
trainData$X <- as.factor(trainData$X)
validData$X <- as.factor(validData$X)# Calculate ROC curves and AUC values
trainRoc <- roc(response = trainData$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")

結果輸出：

以上是找到的相對最優參數組合，看看具體性能：

哈哈，又給調回去了，矯枉過正。思路就是這么個思路，大家自行食用了。

五、最后

看到這里，我覺得還是Python的sk-learn提供的調參簡單些，至少不用寫循環。

數據嘛：

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

提取碼：x8xm