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Logistic分类
（1）导入数据
我习惯用RStudio自带的导入功能：
（2）建立LR模型
# 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$X, p = 0.8, list = FALSE)
trainData <- data[trainIndex, ]
validData <- data[-trainIndex, ]
# Fit logistic regression model on the training set
model <- glm(X ~ ., data = trainData, family = "binomial")
# Predict on the training and validation sets
trainPredict <- predict(model, trainData, type = "response")
validPredict <- predict(model, validData, type = "response")主要解读下R里面LR回归的参数吧，也就是这个glm()函数：
在R语言中，glm()函数用于拟合广义线性模型（Generalized Linear Models），包括LR回归。以下是glm()函数的参数：
①formula: 一个公式对象，表示模型的因变量（响应变量）和自变量（解释变量）。对于LR回归，因变量应该是二元的（0和1），表示分类结果。自变量可以包括一个或多个连续或分类变量。
②data: 包含模型所需变量的数据框（data frame）或矩阵。
③family: 指定误差分布和链接函数的家族。对于LR回归，应设置为binomial。这指定了二项分布和逻辑斯蒂（logit）链接函数。
④weights: 可选参数，用于指定观测的权重。在逻辑回归中，这通常用于处理不平衡的数据集，对少数类进行加权以提高其在模型训练过程中的影响力。
⑤subset: 可选参数，用于指定用于拟合模型的数据子集。
⑥start: 可选参数，用于指定模型参数的初始估计值。
⑦etastart: 可选参数，用于指定线性预测器的初始估计值。
⑧mustart: 可选参数，用于指定是否必须提供初始值。
⑨offset: 可选参数，用于指定一个先验估计的已知量，通常用于泊松回归。
⑩control: 可选参数，用于指定控制模型拟合过程的参数。
可选参数主要关注weights吧，毕竟很多现实的数据都是不平衡数据。
（3）模型评价：ROC曲线
# Convert true values to factor for ROC analysis
trainData$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$sensitivities), aes(x = 1 - fpr, y = tpr)) +
geom_line(color = "red") +
geom_area(alpha = 0.2, fill = "red") +
geom_abline(slope = 1, intercept = 0, linetype = "dashed", color = "black") +
ggtitle("Validation ROC Curve") +
xlab("False Positive Rate") +
ylab("True Positive Rate") +
annotate("text", x = 0.5, y = 0.2, label = paste("Validation AUC =", round(auc(validRoc), 2)), hjust = 0.5, color = "red")结果如下：
嗯，R作图很有自己的特色！
（4）模型评价：混淆矩阵和指标计算
# Function to plot confusion matrix using ggplot2
plot_confusion_matrix <- function(conf_mat, dataset_name) {
conf_mat_df <- as.data.frame(as.table(conf_mat))
colnames(conf_mat_df) <- c("Actual", "Predicted", "Freq")
ggplot(data = conf_mat_df, aes(x = Predicted, y = Actual, fill = Freq)) +
geom_tile(color = "white") +
geom_text(aes(label = Freq), vjust = 1.5, color = "black", size = 5) +
scale_fill_gradient(low = "white", high = "steelblue") +
labs(title = paste("Confusion Matrix -", dataset_name, "Set"), x = "Predicted Class", y = "Actual Class") +
theme_minimal() +
theme(axis.text.x = element_text(angle = 45, hjust = 1), plot.title = element_text(hjust = 0.5))
}
# Calculate confusion matrices
confMatTrain <- table(trainData$X, trainPredict >= 0.5)
confMatValid <- table(validData$X, validPredict >= 0.5)
# Now call the function to plot and display the confusion matrices
plot_confusion_matrix(confMatTrain, "Training")
plot_confusion_matrix(confMatValid, "Validation")
# Extract values for calculations
a_train <- confMatTrain[1, 1]
b_train <- confMatTrain[1, 2]
c_train <- confMatTrain[2, 1]
d_train <- confMatTrain[2, 2]
a_valid <- confMatValid[1, 1]
b_valid <- confMatValid[1, 2]
c_valid <- confMatValid[2, 1]
d_valid <- confMatValid[2, 2]
# Training Set Metrics
acc_train <- (a_train + d_train) / sum(confMatTrain)
error_rate_train <- 1 - acc_train
sen_train <- d_train / (d_train + c_train)
sep_train <- a_train / (a_train + b_train)
precision_train <- d_train / (b_train + d_train)
F1_train <- (2 * precision_train * sen_train) / (precision_train + sen_train)
MCC_train <- (d_train * a_train - b_train * c_train) / sqrt((d_train + b_train) * (d_train + c_train) * (a_train + b_train) * (a_train + c_train))
auc_train <- roc(response = trainData$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)$auc
# Print Metrics
cat("Training Metrics\n")
cat("Accuracy:", acc_train, "\n")
cat("Error Rate:", error_rate_train, "\n")
cat("Sensitivity:", sen_train, "\n")
cat("Specificity:", sep_train, "\n")
cat("Precision:", precision_train, "\n")
cat("F1 Score:", F1_train, "\n")
cat("MCC:", MCC_train, "\n")
cat("AUC:", auc_train, "\n\n")
cat("Validation Metrics\n")
cat("Accuracy:", acc_valid, "\n")
cat("Error Rate:", error_rate_valid, "\n")
cat("Sensitivity:", sen_valid, "\n")
cat("Specificity:", sep_valid, "\n")
cat("Precision:", precision_valid, "\n")
cat("F1 Score:", F1_valid, "\n")
cat("MCC:", MCC_valid, "\n")
cat("AUC:", auc_valid, "\n")结果如下：
各种指标：
三、全部代码整合
知道各位懒得自己整合：
# Load necessary libraries
library(caret)
library(pROC)
library(ggplot2)
# Assume 'data' is your dataframe containing the data
# Set seed to ensure reproducibility
set.seed(123)
# Split data into training and validation sets (80% training, 20% validation)
trainIndex <- createDataPartition(data$X, p = 0.8, list = FALSE)
trainData <- data[trainIndex, ]
validData <- data[-trainIndex, ]
# Fit logistic regression model on the training set
model <- glm(X ~ ., data = trainData, family = "binomial")
# Predict on the training and validation sets
trainPredict <- predict(model, trainData, type = "response")
validPredict <- predict(model, validData, type = "response")
# 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")
# Function to plot confusion matrix using ggplot2 and automatically display it
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")
# Create the plot
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))
# Display the plot
print(p)
}
# Calculate confusion matrices
confMatTrain <- table(trainData$X, trainPredict >= 0.5)
confMatValid <- table(validData$X, validPredict >= 0.5)
# 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")四、最后
亲测：代码调试还是的GPT-4，Kimi还是不太行。
数据嘛：
链接：https://pan.baidu.com/s/1rEf6JZyzA1ia5exoq5OF7g?pwd=x8xm
提取码：x8x