当前位置： 首页 > news >正文

用软件做的网站权限管理,太仓网站设计早晨设计,网站建设小程序,phpcms仿行业网站基于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#xff0c;不想学Python咯。 答曰#xff1a;可#xff01;用GPT或者Kimi转一下就得了呗。 加上最近也没啥内容写了#xff0c;就帮各位搬运一下吧。 二、R代码实现随机森林分类 #xff…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代码实现随机森林分类 1导入数据 我习惯用RStudio自带的导入功能 2建立随机森林模型默认参数

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\(X)# Define control method for training with cross-validation trainControl - trainControl(method cv, number 10)# Fit Random Forest model on the training set model - train(X ~ ., data trainData, method rf, trControl trainControl)# Print the best parameters found by the model best_params - model\)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 包训练随机森林模型时最常见的可调参数是 mtry但还有其他几个参数可以根据需要调整。这些参数通常是从 randomForest 包继承而来的因为 caret 包的随机森林方法默认使用的是这个包所以第一次要安装。下面是一些可以调整的关键参数 ①mtry: 在每个分割中考虑的变量数量。默认情况下对于分类问题mtry 默认值是总变量数的平方根对于回归问题是总变量数的三分之一。 ②ntree: 构建的树的数量。更多的树可以提高模型的稳定性和准确性但会增加计算时间和内存使用。默认值通常是 500。 ③nodesize: 每个叶节点最少包含的样本数。增加这个参数的值可以减少模型的过拟合但可能会导致欠拟合。对于分类问题默认值通常为 1而回归问题则较大。 ④maxnodes: 最大的节点数。这限制了树的最大大小可以用来控制模型复杂度。 ⑤importance: 是否计算变量重要性。这不会影响模型的预测能力但会影响变量重要性分数的计算。 ⑥replace: 是否进行有放回抽样。默认为 TRUE意味着进行有放回的抽样。 ⑦classwt: 类的权重用于分类问题中的不平衡数据。 ⑧cutoff: 分类问题中用于预测类别的概率阈值。这通常是一个类别数目的向量。 ⑨sampsize: 用于每棵树的样本大小如果使用有放回抽样replaceTRUE它决定了每个样本被抽样的次数。 结果输出默认参数 在默认参数中caret包只会默默帮我们找几个合适的mtry值进行测试其他默认值。 随机森林祖传的过拟合现象。 三、随机森林调参方法4个值 设置mtry值取值2、数据集列数的平方根、数据集列数的一半ntree取值100、500和1000nodesize取值1、5、10maxnodes取值30、50、100

Load necessary libraries

library(caret) library(pROC) library(ggplot2) library(randomForest) # Using randomForest for model fitting# 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\(X)# Define ranges for each parameter including mtry mtry_range - c(2, sqrt(ncol(trainData)), ncol(trainData)/2) ntree_range - c(100, 500, 1000) nodesize_range - c(1, 5, 10) maxnodes_range - c(30, 50, 100)# Initialize variables to store the best model, its AUC, and parameters best_auc - 0 best_model - NULL best_params - NULL # Initialize best_params to store parameter values# Nested loops to try different combinations of parameters including mtry for (mtry in mtry_range) {for (ntree in ntree_range) {for (nodesize in nodesize_range) {for (maxnodes in maxnodes_range) {# Train the Random Forest modelrf_model - randomForest(X ~ ., data trainData, mtrymtry, ntreentree, nodesizenodesize, maxnodesmaxnodes)# Predict on validation set using probabilities for ROCvalidProb - predict(rf_model, newdata validData, type prob)[,2]# Calculate AUCvalidRoc - roc(validData\)X, validProb)auc - auc(validRoc)# Update the best model if the current model is betterif (auc best_auc) {best_auc - aucbest_model - rf_modelbest_params - list(mtrymtry, ntreentree, nodesizenodesize, maxnodesmaxnodes) # Store parameters of the best model}}}} }# Check if a best model was found and output parameters if (!is.null(best_params)) {cat(The best model parameters are:\n)print(best_params) } else {cat(No model was found to exceed the baseline performance.\n) }# Use best model for predictions trainPredict - predict(best_model, trainData, type prob)[,2] validPredict - predict(best_model, validData, type prob)[,2]# Rest of the analysis, including ROC curves and plotting trainRoc - roc(response trainData\(X, predictor trainPredict) validRoc - roc(response validData\)X, predictor validPredict)# Plotting code continues unchanged 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)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) }# Function to plot confusion matrix and further analysis remains the same… 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 还不错至少过拟合调下来了。 五、最后 数据嘛 链接https://pan.baidu.com/s/1rEf6JZyzA1ia5exoq5OF7g?pwdx8xm
提取码x8xm