邮件垃圾分类（逻辑回归/支持向量机） - 数学建模社区-数学中国

import numpy as np
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LogisticRegression
from sklearn.svm import SVC
from sklearn.metrics import accuracy_score
# 假设emails和labels是你的数据集和标签
# emails = ["your email data here"]
# labels = [0, 1, 0, 1, ...] # 0代表正常邮件，1代表垃圾邮件
# 分割数据集为训练集和测试集
X_train, X_test, y_train, y_test = train_test_split(emails, labels, test_size=0.2, random_state=42)
# 使用TF-IDF进行文本特征提取
vectorizer = TfidfVectorizer(stop_words='english', max_features=1000)
X_train_tfidf = vectorizer.fit_transform(X_train)
X_test_tfidf = vectorizer.transform(X_test)
# 逻辑回归分类器
logistic_clf = LogisticRegression()
logistic_clf.fit(X_train_tfidf, y_train)
y_pred_logistic = logistic_clf.predict(X_test_tfidf)
# 支持向量机分类器
svm_clf = SVC()
svm_clf.fit(X_train_tfidf, y_train)
y_pred_svm = svm_clf.predict(X_test_tfidf)
# 评估模型
accuracy_logistic = accuracy_score(y_test, y_pred_logistic)
accuracy_svm = accuracy_score(y_test, y_pred_svm)
print(f"Logistic Regression Accuracy: {accuracy_logistic}")
print(f"SVM Accuracy: {accuracy_svm}")

复制代码