dga域名列表

import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import accuracy_score

# 假设我们有一个包含域名和标签（恶意或良性）的数据集
data = pd.read_csv('dga_domains.csv')

# 特征提取（例如，域名的长度、字符种类等）
data['length'] = data['domain'].apply(len)
data['entropy'] = data['domain'].apply(lambda x: -sum([p * math.log(p, 2) for p in char_freq(x)]))

# 划分训练集和测试集
X_train, X_test, y_train, y_test = train_test_split(data[['length', 'entropy']], data['label'], test_size=0.2)

# 训练模型
clf = RandomForestClassifier()
clf.fit(X_train, y_train)

# 预测
y_pred = clf.predict(X_test)
print(f'Accuracy: {accuracy_score(y_test, y_pred)}')