首页from sklearn.metrics import classification_report,confusion_matrix,plot_roc_curve,roc_auc_score,f1_score,roc_curve,auc

from sklearn.metrics import classification_report,confusion_matrix,plot_roc_curve,roc_auc_score,f1_score,roc_curve,auc

时间: 2024-01-01 16:06:52 浏览: 87

ROC曲线绘制以及AUC分数计算

该代码是用PYTHON编写的绘制ROC曲线和计算AUC分数的，对做异常检测，故障诊断等领域的朋友很有帮助

这是Python的一个常用机器学习库Scikit-learn中的一些评价指标和可视化函数。其中，classification_report和confusion_matrix可以用于分类问题的评价，plot_roc_curve和roc_auc_score可以用于二分类问题的评价，f1_score可以同时考虑模型的精确度和召回率，roc_curve和auc可以用于绘制ROC曲线和计算AUC值。这些评价指标和可视化函数能够帮助我们更好地了解模型的性能和优化方向。

阅读全文

相关推荐

RandomForest_sklearn.zip_sklearn_sklearn RF_southern9qq_随机森林

from sklearn.metrics import accuracy_score 2. 加载数据集：我们可以使用sklearn内置的数据集，如鸢尾花数据集（iris），或者自己准备的数据集。 python iris = load_iris() X = iris.data y = ...

ANN.zip_sklearn_sklearn ANN_skleran ann_神经网络分类

5. **评估**：可以使用score方法评估模型性能，常见的评估指标有准确率、精确率、召回率和F1分数。sklearn.metrics模块提供了这些评估指标的计算函数。 6. **调优**：为了找到最佳模型参数，可以使用网格搜索...

X_train,X_test,y_train,y_test=train_test_split(X ,y,test_size=0.2,random_state=1)；reg = 0.01 LogRegModel = LogisticRegression(C=1/reg, solver = 'liblinear').fit(X_train, y_train) preds = LogRegModel.predict(X_test) print('accuracy', metrics.accuracy_score(y_test, preds)) print('recall', metrics.recall_score(y_test, preds)) print('precision', metrics.precision_score(y_test, preds)) print('f1-score', metrics.f1_score(y_test, preds))；from sklearn. metrics import classification_report print(classification_report(y_test, preds))；from sklearn.metrics import roc_curve from sklearn.metrics import confusion_matrix import matplotlib import matplotlib.pyplot as plt %matplotlib inline y_scores = LogRegModel.predict_proba(X_test) print(y_scores) # calculate ROC curve fpr, tpr, thresholds = roc_curve(y_test, y_scores[:,1]) # plot ROC curve fig = plt.figure(figsize=(6, 6)) # Plot the diagonal 50% line plt.plot([0, 1], [0, 1], 'k--') # Plot the FPR and TPR achieved by our model plt.plot(fpr, tpr) plt.xlabel('False Positive Rate') plt.ylabel('True Positive Rate') plt.title('ROC Curve') plt.show()

其中使用了 train_test_split 进行数据集的划分，然后使用 LogisticRegression 进行模型的训练，并对测试集进行预测，使用了多个评价指标，如准确率、召回率、精确率、F1-score 和分类报告等；此外还使用了 ROC 曲线...

from sklearn.datasets import load_iris from sklearn. model_selection import train_test_split from sklearn.metrics import classification_report from sklearn. neighbors import KNeighborsClassifier from sklearn. metrics import roc_curve, auc import matplotlib.pyplot as plt from sklearn. metrics import confusion_matrix import seaborn as sns import scikitplot as skplt #加载数据集 iris = load_iris() data = iris['data'] label = iris['target'] #数据集的划分 x_train,x_test,y_train,y_test = train_test_split(data,label,test_size=0.3) print(x_train) #模型构建 model = KNeighborsClassifier(n_neighbors=5) model.fit(x_train,y_train) #模型评估 #(1)精确率，召回率，F1分数，准确率(宏平均和微平均) predict = model. predict(x_test) result = classification_report(y_test,predict) print(result) # (2) 混淆矩阵 confusion_matrix = confusion_matrix(y_test, predict) print('混淆矩阵:', confusion_matrix) sns.set(font_scale=1) sns.heatmap(confusion_matrix, annot=True, annot_kws={"size", 16}, cmap=plt.cm.Blues) plt.title('Confusion Matrix') plt.ylabel('True label' ) plt.xlabel('Predicted label') plt.savefig('Confusion matrix. pdf') plt.show() #(3)ROC曲线 Y_pred_prob = model. predict_proba(x_test) plt.figure(figsize= (7,7)) ax= plt. subplot() skplt.metrics.plot_roc_curve(y_test,Y_pred_prob,ax= ax) ax.set_xlabel('False Positive Rate', fontsize = 20) ax.set_ylabel('True Positive Rate ',fontsize = 20) ax.set_title('ROC Areas ',fontsize = 20) plt.xlim((0, 1)) plt.ylim((0, 1)) plt.xticks(fontsize = 18) plt.yticks(fontsize = 18) plt.legend(fontsize =18) plt.savefig(' ROC.pdf') plt.show( ) #（4）P_R曲线 from sklearn.metrics import precision_recall_curve precision, recall, _ =precision_recall_curve(y_test) plt.fill_between(recall, precision,color='b') plt.xlabel('Recall') plt.ylabel('Precision') plt.ylim([0.0, 1.0]) plt.xlim([0.0, 1.0]) plt.plot(recall, precision) plt.title("Precision-Recall") plt.show()

其中load_iris用于加载鸢尾花数据集，train_test_split用于将数据集分为训练集和测试集，classification_report用于评估分类器的性能，KNeighborsClassifier是K近邻分类器，roc_curve和auc用于评估二元分类器的性能...

import pandas as pd from sklearn.ensemble import RandomForestClassifier from sklearn.metrics import accuracy_score, confusion_matrix,classification_report import seaborn as sns import matplotlib.pyplot as plt # 读取数据 data = pd.read_excel('E:/桌面/预测脆弱性/20230523/预测样本/预测样本.xlsx') # 分割训练集和验证集 train_data = data.sample(frac=0.8, random_state=1) test_data = data.drop(train_data.index) # 定义特征变量和目标变量 features = ['高程', '起伏度', '桥梁长', '道路长', '平均坡度', '平均地温', 'T小于0', '相态'] target = '交通风险' # 训练随机森林模型 rf = RandomForestClassifier(n_estimators=100, random_state=1) rf.fit(train_data[features], train_data[target]) # 在验证集上进行预测并计算精度、召回率和F1值等指标 pred = rf.predict(test_data[features]) accuracy = accuracy_score(test_data[target], pred) confusion_mat = confusion_matrix(test_data[target], pred) classification_rep = classification_report(test_data[target], pred) print('Accuracy:', accuracy) print('Confusion matrix:') print(confusion_mat) print('Classification report:') print(classification_rep) # 输出混淆矩阵图片 sns.heatmap(confusion_mat, annot=True, cmap="Blues") plt.show() # 读取新数据文件并预测结果 new_data = pd.read_excel('E:/桌面/预测脆弱性/20230523/预测样本/预测结果/交通风险预测096.xlsx') new_pred = rf.predict(new_data[features]) new_data['交通风险预测结果'] = new_pred new_data.to_excel('E:/桌面/预测脆弱性/20230523/预测样本/预测结果/交通风险预测096结果.xlsx', index=False)制作混淆矩阵的热力图以及多分类的roc曲线和auc值

from sklearn.metrics import multiclass_roc_auc_score, roc_curve, auc # 预测验证集结果 pred_prob = rf.predict_proba(test_data[features]) fpr = dict() tpr = dict() roc_auc = dict() for i in range(3): ...

import pandas as pd from sklearn.ensemble import RandomForestClassifier from sklearn.metrics import accuracy_score, confusion_matrix,classification_report, roc_curve, auc import seaborn as sns import matplotlib.pyplot as plt # 读取数据 data = pd.read_excel('E:/桌面/预测脆弱性/20230523/预测样本/预测样本.xlsx') # 分割训练集和验证集 train_data = data.sample(frac=0.8, random_state=1) test_data = data.drop(train_data.index) # 定义特征变量和目标变量 features = ['高程', '起伏度', '桥梁长', '道路长', '平均坡度', '平均地温', 'T小于0', '相态'] target = '交通风险' # 训练随机森林模型 rf = RandomForestClassifier(n_estimators=100, random_state=1) rf.fit(train_data[features], train_data[target]) # 在验证集上进行预测并计算精度、召回率和F1值等指标 pred = rf.predict(test_data[features]) accuracy = accuracy_score(test_data[target], pred) confusion_mat = confusion_matrix(test_data[target], pred) classification_rep = classification_report(test_data[target], pred) print('Accuracy:', accuracy) print('Confusion matrix:') print(confusion_mat) print('Classification report:') print(classification_rep) # 输出混淆矩阵图片 sns.heatmap(confusion_mat, annot=True, cmap="Blues") plt.show() # 计算并绘制ROC曲线和AUC值 fpr, tpr, thresholds = roc_curve(test_data[target], pred) roc_auc = auc(fpr, tpr) print('AUC:', roc_auc) plt.figure() lw = 2 plt.plot(fpr, tpr, color='darkorange', lw=lw, label='ROC curve (area = %0.2f)' % roc_auc) plt.plot([0, 1], [0, 1], color='navy', lw=lw, linestyle='--') plt.xlim([0.0, 1.0]) plt.ylim([0.0, 1.05]) plt.xlabel('False Positive Rate') plt.ylabel('True Positive Rate') plt.title('Receiver operating characteristic') plt.legend(loc="lower right") plt.show() # 读取新数据文件并预测结果 new_data = pd.read_excel('E:/桌面/预测脆弱性/20230523/预测样本/预测结果/交通风险预测096.xlsx') new_pred = rf.predict(new_data[features]) new_data['交通风险预测结果'] = new_pred new_data.to_excel('E:/桌面/预测脆弱性/20230523/预测样本/预测结果/交通风险预测096结果.xlsx', index=False)改进代码使用多元roc曲线

from sklearn.metrics import accuracy_score, confusion_matrix, classification_report, multiclass_roc_auc_score import seaborn as sns import matplotlib.pyplot as plt # 读取数据 data = pd.read_excel('E:...

修改和补充下列代码得到十折交叉验证的平均auc值和平均aoc曲线，平均分类报告以及平均混淆矩阵 min_max_scaler = MinMaxScaler() X_train1, X_test1 = x[train_id], x[test_id] y_train1, y_test1 = y[train_id], y[test_id] # apply the same scaler to both sets of data X_train1 = min_max_scaler.fit_transform(X_train1) X_test1 = min_max_scaler.transform(X_test1) X_train1 = np.array(X_train1) X_test1 = np.array(X_test1) config = get_config() tree = gcForest(config) tree.fit(X_train1, y_train1) y_pred11 = tree.predict(X_test1) y_pred1.append(y_pred11 X_train.append(X_train1) X_test.append(X_test1) y_test.append(y_test1) y_train.append(y_train1) X_train_fuzzy1, X_test_fuzzy1 = X_fuzzy[train_id], X_fuzzy[test_id] y_train_fuzzy1, y_test_fuzzy1 = y_sampled[train_id], y_sampled[test_id] X_train_fuzzy1 = min_max_scaler.fit_transform(X_train_fuzzy1) X_test_fuzzy1 = min_max_scaler.transform(X_test_fuzzy1) X_train_fuzzy1 = np.array(X_train_fuzzy1) X_test_fuzzy1 = np.array(X_test_fuzzy1) config = get_config() tree = gcForest(config) tree.fit(X_train_fuzzy1, y_train_fuzzy1) y_predd = tree.predict(X_test_fuzzy1) y_pred.append(y_predd) X_test_fuzzy.append(X_test_fuzzy1) y_test_fuzzy.append(y_test_fuzzy1)y_pred = to_categorical(np.concatenate(y_pred), num_classes=3) y_pred1 = to_categorical(np.concatenate(y_pred1), num_classes=3) y_test = to_categorical(np.concatenate(y_test), num_classes=3) y_test_fuzzy = to_categorical(np.concatenate(y_test_fuzzy), num_classes=3) print(y_pred.shape) print(y_pred1.shape) print(y_test.shape) print(y_test_fuzzy.shape) # 深度森林 report1 = classification_report(y_test, y_prprint("DF",report1) report = classification_report(y_test_fuzzy, y_pred) print("DF-F",report) mse = mean_squared_error(y_test, y_pred1) rmse = math.sqrt(mse) print('深度森林RMSE:', rmse) print('深度森林Accuracy:', accuracy_score(y_test, y_pred1)) mse = mean_squared_error(y_test_fuzzy, y_pred) rmse = math.sqrt(mse) print('F深度森林RMSE:', rmse) print('F深度森林Accuracy:', accuracy_score(y_test_fuzzy, y_pred)) mse = mean_squared_error(y_test, y_pred) rmse = math.sqrt(mse) print('F?深度森林RMSE:', rmse) print('F?深度森林Accuracy:', accuracy_score(y_test, y_pred))

from sklearn.metrics import classification_report, confusion_matrix, roc_curve, auc from sklearn.model_selection import StratifiedKFold min_max_scaler = MinMaxScaler() X_train, X_test, y_train, y_...

修改完善下列代码，得到十折交叉验证三分类的平均每一折的分类报告，平均每一折的混淆矩阵，平均每一折的auc值和roc曲线。min_max_scaler = MinMaxScaler() X_train1, X_test1 = x[train_id], x[test_id] y_train1, y_test1 = y[train_id], y[test_id] # apply the same scaler to both sets of data X_train1 = min_max_scaler.fit_transform(X_train1) X_test1 = min_max_scaler.transform(X_test1) # convert to numpy arrays X_train1 = np.array(X_train1) X_test1 = np.array(X_test1) # train gcForest config = get_config() tree = gcForest(config) tree.fit(X_train1, y_train1)

from sklearn.metrics import classification_report, confusion_matrix, roc_auc_score, roc_curve from sklearn.model_selection import StratifiedKFold import numpy as np import matplotlib.pyplot as plt # ...

开通CSDN年卡参与万元壕礼抽奖

海量 VIP免费资源千本正版电子书商城会员专享价千门课程&专栏

全年可省5,000元立即开通全年可省5,000元立即开通

最新推荐

基于springboot大学生就业信息管理系统源码数据库文档.zip

from sklearn.metrics import classification_report,confusion_matrix,plot_roc_curve,roc_auc_score,f1_score,roc_curve,auc

相关推荐

RandomForest_sklearn.zip_sklearn_sklearn RF_southern9qq_随机森林

ANN.zip_sklearn_sklearn ANN_skleran ann_神经网络 分类

Beyond Precision and Recall: The Application of F1 Score and ROC Curve

Demystifying the Confusion Matrix: How to Evaluate the Actual Performance of Classification Models

ROC曲线与AUC值：揭秘分类模型性能的深度分析

From Evaluation Metrics to Model Optimization: How to Select the Optimal Threshold

pandas中fpr,tpr,thresholds=roc_curve(y_test.values,y_pred)出现错误：multiclass format is not supported怎么解决

用深度神经网络训练mnist，输出Accuracy (ACC), Precision, Recall, F1 Score (F1),AUC,并画 ROC曲线python代码

交叉验证 加载iris数据集，拟合SVM ，1)使用train_test_split 分割训练集和测试集（80% VS 20%）2) 使用cross_val_score做十折交叉验证 3）计算交叉验证所有指标4）画出ROC曲线

怎么评估多分类的决策树roc，auc，ks值代码实现一下

调用sklearn库实现对鸢尾花数据的分类，采用逻辑回归分类方法，并计算以下多分类性能评价指标（两种方式）：混淆矩阵、准确率、精确率、召回率、F1值、分类报告，并绘制PR曲线与ROC曲线。

使用python调用sklearn库实现对鸢尾花数据的分类，采用逻辑回归分类方法，并计算以下多分类性能评价指标（两种方式）：混淆矩阵、准确率、精确率、召回率、F1值、分类报告，并绘制PR曲线与ROC曲线。

k折交叉验证法验证一个模型，并对模型性能进行评估（错误率，精度，查准率，查全率，f1,pr,roc曲线）pytorch框架

最新推荐

基于springboot大学生就业信息管理系统源码数据库文档.zip

基于java的驾校收支管理可视化平台的开题报告.docx

全国江河水系图层shp文件包下载

管理建模和仿真的文件

Keras模型压缩与优化：减小模型尺寸与提升推理速度

MTK 6229 BB芯片在手机中有哪些核心功能，OTG支持、Wi-Fi支持和RTC晶振是如何实现的？

点云二值化测试数据集的详细解读

"互动学习：行动中的多样性与论文攻读经历"

Keras正则化技术应用：L1_L2与Dropout的深入理解

在Python中使用xarray和cfgrib库处理GRIB数据时，如何有效解决遇到的DatasetBuildError错误？

ANN.zip_sklearn_sklearn ANN_skleran ann_神经网络分类

交叉验证加载iris数据集，拟合SVM ，1)使用train_test_split 分割训练集和测试集（80% VS 20%）2) 使用cross_val_score做十折交叉验证 3）计算交叉验证所有指标4）画出ROC曲线