机器学习-分类算法-精确率和召回率08
from sklearn.datasets import fetch_20newsgroups
from sklearn.model_selection import train_test_split
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.naive_bayes import MultinomialNB
from sklearn.metrics import classification_report
def naviebayes():
# 准备数据
news = fetch_20newsgroups(subset="all")
print(news.data)
print(news.target)
# 数据分割
x_train,x_test,y_train,y_test = train_test_split(news.data,news.target,test_size=0.25)
# 对数据集进行特征抽取
tf = TfidfVectorizer()
# 以训练集当中的词的列表进行每篇文章的重要性统计
x_train = tf.fit_transform(x_train)
print(tf.get_feature_names())
x_test = tf.transform(x_test)
# 进行朴素贝叶斯算法的预测
mlt = MultinomialNB(alpha=1.0)
print(x_train.toarray())
mlt.fit(x_train,y_train)
y_predict= mlt.predict(x_test)
print("预测的文章类别为:",y_predict)
# 得出准确率
print("准确率:",mlt.score(x_test,y_test))
print("每个类别的精确率和召回率:",classification_report(y_test,y_predict,target_names=news.target_names))
return None
if __name__=="__main__":
naviebayes()
【推荐】编程新体验,更懂你的AI,立即体验豆包MarsCode编程助手
【推荐】凌霞软件回馈社区,博客园 & 1Panel & Halo 联合会员上线
【推荐】抖音旗下AI助手豆包,你的智能百科全书,全免费不限次数
【推荐】博客园社区专享云产品让利特惠,阿里云新客6.5折上折
【推荐】轻量又高性能的 SSH 工具 IShell:AI 加持,快人一步