import pandas as pd import numpy as np import matplotlib.pyplot as plt from sklearn.model_selection import train_test_split from sklearn.linear_model import LogisticRegression from sklearn.metrics import confusion_matrix, accuracy_score, precision_score, recall_score, f1_score, roc_curve, roc_auc_score # 1. 数据读取与处理 data = pd.read_csv('data.csv') X = data.drop('target', axis=1) y = data['target'] X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42) # 2. 模型训练 model = LogisticRegression() model.fit(X_train, y_train) # 3. 模型预测 y_pred = model.predict(X_test) y_prob = model.predict_proba(X_test)[:, 1] # 4. 绘制二分类混淆矩阵 confusion_mat = confusion_matrix(y_test, y_pred) plt.imshow(confusion_mat, cmap=plt.cm.Blues) plt.title('Confusion Matrix') plt.colorbar() tick_marks = np.arange(2) plt.xticks(tick_marks, ['0', '1']) plt.yticks(tick_marks, ['0', '1']) plt.xlabel('Predicted Label') plt.ylabel('True Label') for i in range(2): for j in range(2): plt.text(j, i, confusion_mat[i, j], ha='center', va='center', color='white' if confusion_mat[i, j] > confusion_mat.max() / 2 else 'black') plt.show() # 5. 计算精确率、召回率和F1-score precision = precision_score(y_test, y_pred) recall = recall_score(y_test, y_pred) f1 = f1_score(y_test, y_pred) # 6. 计算AUC指标和绘制ROC曲线 auc = roc_auc_score(y_test, y_prob) fpr, tpr, thresholds = roc_curve(y_test, y_prob) plt.plot(fpr, tpr, label='ROC curve (area = %0.2f)' % auc) plt.plot([0, 1], [0, 1], 'k--') plt.xlim([0.0, 1.0]) plt.ylim([0.0, 1.05]) plt.xlabel('False Positive Rate') plt.ylabel('True Positive Rate') plt.title('ROC Curve') plt.legend(loc="lower right") plt.show() # 7. 输出结果 print('Precision:', precision) print('Recall:', recall) print('F1-score:', f1) print('AUC:', auc)对每行代码进行注释
时间: 2024-03-19 10:41:07 浏览: 118
Sure, here are the comments for each line of code:
```
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LogisticRegression
from sklearn.metrics import confusion_matrix, accuracy_score, precision_score, recall_score, f1_score, roc_curve, roc_auc_score
```
- Import the necessary libraries.
```
data = pd.read_csv('data.csv')
X = data.drop('target', axis=1)
y = data['target']
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
```
- Load the dataset from a CSV file and split it into training and testing sets.
```
model = LogisticRegression()
model.fit(X_train, y_train)
```
- Create a logistic regression model and fit it to the training data.
```
y_pred = model.predict(X_test)
y_prob = model.predict_proba(X_test)[:, 1]
```
- Make predictions on the testing data and get the predicted probabilities for class 1.
```
confusion_mat = confusion_matrix(y_test, y_pred)
plt.imshow(confusion_mat, cmap=plt.cm.Blues)
plt.title('Confusion Matrix')
plt.colorbar()
tick_marks = np.arange(2)
plt.xticks(tick_marks, ['0', '1'])
plt.yticks(tick_marks, ['0', '1'])
plt.xlabel('Predicted Label')
plt.ylabel('True Label')
for i in range(2):
for j in range(2):
plt.text(j, i, confusion_mat[i, j], ha='center', va='center', color='white' if confusion_mat[i, j] > confusion_mat.max() / 2 else 'black')
plt.show()
```
- Calculate and display the confusion matrix as an image.
```
precision = precision_score(y_test, y_pred)
recall = recall_score(y_test, y_pred)
f1 = f1_score(y_test, y_pred)
```
- Calculate the precision, recall, and F1-score metrics.
```
auc = roc_auc_score(y_test, y_prob)
fpr, tpr, thresholds = roc_curve(y_test, y_prob)
plt.plot(fpr, tpr, label='ROC curve (area = %0.2f)' % auc)
plt.plot([0, 1], [0, 1], 'k--')
plt.xlim([0.0, 1.0])
plt.ylim([0.0, 1.05])
plt.xlabel('False Positive Rate')
plt.ylabel('True Positive Rate')
plt.title('ROC Curve')
plt.legend(loc="lower right")
plt.show()
```
- Calculate the AUC metric and plot the ROC curve.
```
print('Precision:', precision)
print('Recall:', recall)
print('F1-score:', f1)
print('AUC:', auc)
```
- Print the metrics.
阅读全文