不均衡なデータセットに対処するための分類方法は何ですか?

from imblearn.over_sampling import SMOTE
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LogisticRegression
from sklearn.metrics import accuracy_score, recall_score, f1_score

# 加载数据集并划分训练集和测试集
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

# 使用SMOTE算法进行数据重采样
smote = SMOTE(random_state=42)
X_train_resampled, y_train_resampled = smote.fit_resample(X_train, y_train)

# 训练逻辑回归模型
model = LogisticRegression(random_state=42)
model.fit(X_train_resampled, y_train_resampled)

# 在测试集上进行预测
y_pred = model.predict(X_test)

# 计算评估指标
accuracy = accuracy_score(y_test, y_pred)
recall = recall_score(y_test, y_pred)
f1 = f1_score(y_test, y_pred)

print("Accuracy: {:.2f}%, Recall: {:.2f}%, F1: {:.2f}%".format(accuracy*100, recall*100, f1*100))

# 训练逻辑回归模型并设置类别权重
model = LogisticRegression(random_state=42, class_weight="balanced")
model.fit(X_train, y_train)

# 在测试集上进行预测
y_pred = model.predict(X_test)

# 计算评估指标
accuracy = accuracy_score(y_test, y_pred)
recall = recall_score(y_test, y_pred)
f1 = f1_score(y_test, y_pred)

print("Accuracy: {:.2f}%, Recall: {:.2f}%, F1: {:.2f}%".format(accuracy*100, recall*100, f1*100))

from sklearn.ensemble import RandomForestClassifier

# 训练随机森林模型
model = RandomForestClassifier(random_state=42)
model.fit(X_train, y_train)

# 在测试集上进行预测
y_pred = model.predict(X_test)

# 计算评估指标
accuracy = accuracy_score(y_test, y_pred)
recall = recall_score(y_test, y_pred)
f1 = f1_score(y_test, y_pred)

print("Accuracy: {:.2f}%, Recall: {:.2f}%, F1: {:.2f}%".format(accuracy*100, recall*100, f1*100))