支持向量机分析乳腺癌数据

要求

（1）     得出相应的分类指标准确率accuracy，精确率precision，召回率recall，F1-score，并画出最终的ROC曲线，得出AUC值。

（2）     对比感知机算法（调包就行）也进行训练和测试，比较两个算法的结果。

代码

import pandas as pd
import matplotlib.pyplot as plt
from sklearn import svm
from sklearn.linear_model import Perceptron
from sklearn.metrics import roc_curve, auc, classification_report
from sklearn.model_selection import cross_val_score, cross_val_predict


def acu_curve(y, prob):
    fpr, tpr, threshold = roc_curve(y, prob)  ###计算真正率和假正率
    roc_auc = auc(fpr, tpr)  ###计算auc的值
    print("AUC:", roc_auc)
    plt.figure()
    lw = 2
    plt.figure(figsize=(6, 6))
    plt.plot(fpr, tpr, color='darkorange',
             lw=lw, label='ROC curve (area = %0.3f)' % roc_auc)  ###假正率为横坐标，真正率为纵坐标做曲线
    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()


# 加载数据
train = pd.read_csv(r".\breast-cancer-train.csv").iloc[:, 1:]
test = pd.read_csv(r".\breast-cancer-test.csv").iloc[:, 1:]

x_train, y_train = train.iloc[:, :-1], train.iloc[:, -1]
x_test, y_test = test.iloc[:, :-1], test.iloc[:, -1]

# 用线性核函数建立支持向量机模型
model = svm.SVC(kernel='linear', probability=True)
model.fit(x_train, y_train)
print('------------------------SVM------------------------')
print(classification_report(y_test,model.predict(x_test)))
# 画出ROC曲线
acu_curve(y_test, model.predict_proba(x_test)[:,1:])

print('------------------------感知机算法------------------------')
# 感知机算法
model2 = Perceptron()
model2.fit(x_train, y_train)
print(classification_report(y_test, model2.predict(x_test)))
acu_curve(y_test, model2.predict(x_test))

注意