用python在乳腺癌数据集上应用Logistic回归进行预测并分析绘图

好的，下面是具体步骤：

1.导入所需库和数据集

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
from sklearn.datasets import load_breast_cancer
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LogisticRegression
from sklearn.metrics import confusion_matrix, accuracy_score

data = load_breast_cancer()
X = pd.DataFrame(data.data, columns=data.feature_names)
y = pd.Series(data.target)

2.拆分数据集为训练集和测试集

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=42)

3.训练模型并预测

lr = LogisticRegression()
lr.fit(X_train, y_train)

y_pred = lr.predict(X_test)

4.评估模型性能

conf_mat = confusion_matrix(y_test, y_pred)
print("Confusion matrix:\n", conf_mat)

acc_score = accuracy_score(y_test, y_pred)
print("Accuracy score:", acc_score)

5.绘制混淆矩阵

plt.imshow(conf_mat, cmap="Blues")

for i in range(len(conf_mat)):
    for j in range(len(conf_mat)):
        plt.text(i, j, str(conf_mat[i][j]), ha="center", va="center")

plt.xlabel("Predicted label")
plt.ylabel("True label")
plt.xticks([0,1], ["Benign", "Malignant"])
plt.yticks([0,1], ["Benign", "Malignant"])
plt.title("Confusion matrix")
plt.colorbar()
plt.show()

6.绘制ROC曲线和AUC

from sklearn.metrics import roc_curve, roc_auc_score

y_pred_proba = lr.predict_proba(X_test)[:,1]
fpr, tpr, thresholds = roc_curve(y_test, y_pred_proba)

plt.plot(fpr, tpr, label="ROC curve")
plt.plot([0,1], [0,1], "k--", label="Random guess")
plt.xlabel("FPR")
plt.ylabel("TPR")
plt.title("ROC curve")
plt.legend()
plt.show()

auc_score = roc_auc_score(y_test, y_pred_proba)
print("AUC score:", auc_score)

这样就完成了在乳腺癌数据集上应用Logistic回归进行预测并分析绘图的过程。