期刊图片复现|Python绘制多模型对比二分类任务ROC曲线

import pandas as pdimport matplotlib.pyplot as pltfrom sklearn.model_selection import train_test_split, GridSearchCVfrom sklearn.preprocessing import StandardScalerfrom sklearn.linear_model import LogisticRegressionfrom sklearn.svm import SVCfrom sklearn.ensemble import RandomForestClassifier, GradientBoostingClassifierfrom sklearn.metrics import roc_curve, aucimport sysplt.rcParams['font.family'] = 'serif'plt.rcParams['font.serif'] = ['Times New Roman']plt.rcParams['axes.unicode_minus'] = Falseimport matplotlibmatplotlib.rcParams['pdf.fonttype'] = 42matplotlib.rcParams['ps.fonttype'] = 42

color_schemes= {    1: {        "Logistic Regression": '#1f77b4', "SVM (RBF Kernel)": '#d62728', "Random Forest": '#ff7f0e', "Gradient Boosting": '#2ca02c',        "diag_line": 'navy', "xy_label": '#8B0000', "bg_color": '#F5F5DC'    },}selected_scheme= 2  #选择颜色方案SELECTED_COLORS = color_schemes[selected_scheme]#获取颜色方案

def plot_roc_curves(y_true, all_scores, plot_title, colors_dict,filename=None):    fig, ax = plt.subplots(figsize=(8, 7)) #画布    ax.set_facecolor(colors_dict['bg_color']) # 设置的背景颜色    # 网格线    ax.grid(True,            which='both',            linestyle='--',            linewidth=2,            color='lightgrey',            dashes=(3, 5))    #存储每个模型AUC值的文本标注位置    auc_text_positions = {        "Logistic Regression": (0.65, 0.95),        "Random Forest": (0.6, 0.82),        "Gradient Boosting": (0.35, 0.68),        "SVM (RBF Kernel)": (0.5, 0.55)    }        #绘制对角虚线/参考线    ax.plot([0, 1], [0, 1], color=colors_dict['diag_line'], lw=2, linestyle='--')    ax.set_xlim([-0.02, 1.0]) #设置X轴的范围    ax.set_ylim([0, 1.05]) #设置Y轴的范围    ax.set_xlabel('Specificity', fontsize=18, color=colors_dict['xy_label']) #x轴标题    ax.set_ylabel('Sensitivity', fontsize=18, color=colors_dict['xy_label']) #Y轴标题    ax.set_title(plot_title, fontsize=20, loc='left', pad=10) #设置主图标题    ax.xaxis.set_major_locator(plt.MultipleLocator(0.25)) #设置X轴主刻度的间隔    ax.yaxis.set_major_locator(plt.MultipleLocator(0.25)) #设置Y轴主刻度的间隔    ax.tick_params(axis='both', which='major', labelsize=14) #主刻度标签的字体大小    # 添加图例    ax.legend(loc='lower right', fontsize=14, frameon=True, edgecolor='black')    #遍历图框    for spine in ax.spines.values():        spine.set_edgecolor('#6B8E23') #颜色        spine.set_linewidth(2) #图框的粗细设置    plt.tight_layout() # 自动调整子图参数，使其填充整个图窗区域，防止标签重叠

excel_filename = r'data.xlsx'#原始数据路径df = pd.read_excel(excel_filename, engine='openpyxl')#读取数据# 提取所有特征和标签y = df.iloc[:, 0].valuesX= df.iloc[:, 1:].values#划分数据集为训练集和验证集X_train, X_val, y_train, y_val = train_test_split(X, y,test_size=0.3,random_state=42,stratify=y)#标准化处理scaler = StandardScaler()X_train_scaled = scaler.fit_transform(X_train)X_val_scaled = scaler.transform(X_val)

print(f"正在为 'Logistic Regression' 进行网格搜索")#初始化逻辑回归模型model_lr = LogisticRegression(random_state=42, solver='liblinear')#逻辑回归的超参数搜索网格param_grid_lr = {    'C': [0.01, 0.1, 1, 10, 100],    'penalty': ['l1', 'l2']}#配置网格搜索grid_search_lr = GridSearchCV(estimator=model_lr, param_grid=param_grid_lr, cv=5, scoring='roc_auc', n_jobs=-1, verbose=0)#执行网格搜索grid_search_lr.fit(X_train_scaled, y_train)best_model_lr = grid_search_lr.best_estimator_ #最佳模型print(f"'Logistic Regression' 网格搜索完成！最佳超参数: {grid_search_lr.best_params_}")#最佳逻辑回归模型预测正类的概率scores_lr_train = best_model_lr.predict_proba(X_train_scaled)[:, 1]scores_lr_val = best_model_lr.predict_proba(X_val_scaled)[:, 1]print(f"\n--- 正在为 'SVM (RBF Kernel)' 进行网格搜索")#初始化SVC模型model_svm = SVC(random_state=42, probability=True)#超参数搜索网格param_grid_svm = {    'C': [0.1, 1, 10],    'gamma': [0.01, 0.1, 1]}#网格搜索grid_search_svm = GridSearchCV(estimator=model_svm, param_grid=param_grid_svm, cv=5, scoring='roc_auc', n_jobs=-1, verbose=0)grid_search_svm.fit(X_train_scaled, y_train)#最佳SVM模型best_model_svm = grid_search_svm.best_estimator_print(f"SVM最佳超参数: {grid_search_svm.best_params_}")#预测正类的概率scores_svm_train = best_model_svm.predict_proba(X_train_scaled)[:, 1]scores_svm_val = best_model_svm.predict_proba(X_val_scaled)[:, 1]print(f"\n--- 正在为 'Random Forest' 进行网格搜索")#初始化RF模型model_rf = RandomForestClassifier(random_state=42)#超参数搜索网格param_grid_rf = {    'n_estimators': [50, 100, 200],    'max_depth': [5, 10, None]}#执行网格搜索grid_search_rf = GridSearchCV(estimator=model_rf, param_grid=param_grid_rf, cv=5, scoring='roc_auc', n_jobs=-1, verbose=0)grid_search_rf.fit(X_train_scaled, y_train)#最佳RF模型best_model_rf = grid_search_rf.best_estimator_print(f"'RF最佳超参数: {grid_search_rf.best_params_}")#预测正类的概率scores_rf_train = best_model_rf.predict_proba(X_train_scaled)[:, 1]scores_rf_val = best_model_rf.predict_proba(X_val_scaled)[:, 1]print(f"\n--- 正在为 'Gradient Boosting' 进行网格搜索 ---")# 初始化GBT模型model_gbt = GradientBoostingClassifier(random_state=42)param_grid_gbt = {    'n_estimators': [50, 100],    'learning_rate': [0.05, 0.1],    'max_depth': [3, 5]}#执行网格搜索grid_search_gbt = GridSearchCV(estimator=model_gbt, param_grid=param_grid_gbt, cv=5, scoring='roc_auc', n_jobs=-1, verbose=0)grid_search_gbt.fit(X_train_scaled, y_train)#最佳GBT模型best_model_gbt = grid_search_gbt.best_estimator_print(f"GBT最佳超参数: {grid_search_gbt.best_params_}")#预测正类的概率scores_gbt_train = best_model_gbt.predict_proba(X_train_scaled)[:, 1]scores_gbt_val = best_model_gbt.predict_proba(X_val_scaled)[:, 1]

#存储训练集上所有模型的预测分数train_scores_dict = {    "Logistic Regression": scores_lr_train,    "SVM (RBF Kernel)": scores_svm_train,    "Random Forest": scores_rf_train,    "Gradient Boosting": scores_gbt_train}#存储验证集上所有模型的预测分数val_scores_dict = {    "Logistic Regression": scores_lr_val,    "SVM (RBF Kernel)": scores_svm_val,    "Random Forest": scores_rf_val,    "Gradient Boosting": scores_gbt_val}#绘制训练集的ROC曲线plot_roc_curves(y_train,                train_scores_dict,                "(C) ROC Curves on Training Set (Model Comparison)",                SELECTED_COLORS,                filename='train'                )#绘制验证集的ROC曲线plot_roc_curves(y_val,                val_scores_dict,                "(C) ROC Curves on Validation Set (Model Comparison)",                SELECTED_COLORS,                filename='test'                )

selected_scheme= 20  #选择颜色方案

2.修改图面的文本标注位置：

auc_text_positions = {    "Logistic Regression": (0.65, 0.95),    "Random Forest": (0.6, 0.82),     "Gradient Boosting": (0.35, 0.68),    "SVM (RBF Kernel)": (0.5, 0.55)}

fig.savefig(fr'{filename}_{selected_scheme}.png', dpi=300, bbox_inches='tight')fig.savefig(fr'{filename}_{selected_scheme}.pdf', bbox_inches='tight')

4.设置原始数据的输入路径位置：

excel_filename = r'simulated_senescence_data.xlsx'#原始数据路径

y = df.iloc[:, 0].valuesX= df.iloc[:, 1:].values

6.修改各个模型的超参数：

param_grid_lr = {    'C': [0.01, 0.1, 1, 10, 100],    'penalty': ['l1', 'l2']}